Advances and Prospect of Artificial Intelligence in Theranostics of Lung Cancer

The Clinical Lung Cancer Advances And Prospect Of Artificial Intelligence In Theranostics Of Lung Cancer. *Corresponding Author: Daxiang Cui, Institute of Nano Biomedicine and Engineering, School of Sensing Science and Engineering, School of Electronic Informa- tion and Electrical Engineering, Shanghai JiaoTong university, Shanghai 200240, China. Email: [email protected] Received: 22-Feb-2025, Manuscript No. TCLC- 4508 ; Editor Assigned: 23-Feb-2025 ; Reviewed: 11-Mar-2025, QC No. TCLC- 4508 ; Published: 26-Mar-2025, DOI: 10.52338/tclc.2025.4508 Citation: Daxiang Cui. Advances and Prospect of Artificial Intelligence in Theranostics of Lung Cancer. The Clinical Lung Cancer. 2025 March; 10(1). doi: 10.52338/tclc.2025.4508. Copyright © 2025 Daxiang Cui. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ISSN 3064-6693 Review Article Xinyuan Cui 1 , Wanting Hao 1 , Shenshen Cui 2 , Yanlei Liu 2 , Ruokun Li 1,4 , Daxiang Cui 2,3 *, Fuhua Yan 1,4 *. 1 Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China. 2 Institute of Nano Biomedicine and Engineering, School of Sensing Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai JiaoTong university, Shanghai 200240, China. 3 Medical and Engineering Cross Research Institute, The First Affiliated Hospital, School of Medicine of Henan University, Kaifeng 475001, China. 4 Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, PR China; Faculty of Medical Imaging Technology, College of Health Science and Technology, Shanghai Jiao Tong University School of M edicine, Shanghai200025, China. www.directivepublications.org Abstract Lung cancer is the first cause of cancer death worldwide. How to realize precise theranostics and management of Lung cancer has huge clinical demand. In past decade, artificial intelligence (AI), especially machine learning (ML) and deep learning (DL) are broadly used in medicine. Herein we focus on reviewing the main advances of ML and DL in diagnosis, treatment and prognosis of lung cancer. Besides, we summarize AI’s advantages, explore how AI assists theranostics of lung cancer by innovative AI algorithms, then we discussed the opportunities and challenges as well as the future directions in the clinical implementation of AI in lung cancer. Overall, AI integrated with multidisciplinary technology and data is a new development trend, its application in theranostics of lung cancer owns excellent clinical transformation value and prospect in near future. Keywords : Artificial intelligence; Deep learning; algorithms; Lung cancer; Theranostics. INTRODUCTION Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems used to simulate, extend and expand human intelligence[1], It is an important driving force for the new round of scientific and technological revolution and industrial transformation. Its application exploration has become frontier hot spot since AI was proposed by mathematician john mccarthy in 1956 [2]. In the past decade, AI has been widely used in medicine[3], great advances have made in those directions such as nanoparticles-labeled tomography chip for biomarker detection[4], immunochromatographic assay and microfludic chip[5,6], medical biosensor for Healthcare System[7,8], cancer diagnosis and tumor nanomedicine[9-11], molecular image diagnosis[12], surgical interventions[13], drug discovery and overcoming multidrug-resistance[14], surgical skills training and assessment[15,16], hospital-wide big data analysis[17], and personalized therapy [18-20]. Machine learning is one kind of implementation pathway of AI, mainly study learning algorithms. Machine learning algorithms mainly include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, deep learning, transfer learning, etc[21]. Deep learning (DL) is a new mean of machine learning, uses machines to treat various training data and to extract specific features by using backpropagation algorithms. DL mainly used multi- layered artificial neural networks to analyze data to establish DL models by using Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Deep Reinforcement Learning(DRL) and Generative Adversarial Network(GAN) [22]. DL models mainly adopt logic to treat data, recognize patterns, make conclusions, and make decisions[23]. In short, AI is based on the computer algorithm which is trained to realize the special functions including identifying and characterizing defined lesions. The computer algorithm is trained by exposing a large number of training elements using the previously described Machine Learning. Clinical decision support systems based on AI has made great advances[24]. Different types of AI computer systems are aimed to achieve different functions. Two main categories of AI systems are computer-aided detection (CADe) for lesion detection and

Directive Publications Daxiang Cui computer-aided diagnosis (CADx) for optical biopsy and lesion characterization[25,26]. Other AI systems provide assisted treatments, such as lesion description for complete endoscopic resection[27], magnetically programmed diffractive robotics was developed[28], magnetically controlled wireless power supply capsule endoscopy with intelligent software was used for NIR imaging and treatment of gastrointestinal diseases[29]. AI owns three outstanding advantages. Firstly, AI can optimize and realize efficient and flexible nonlinear modeling for large data sets. Secondly, these models can provide explanations that make knowledge dissemination easier. Thirdly, the human brain performance can be influenced by fatigue, stress or limited experiences, AI can make up for the limited capabilities of humans, prevent human errors, provide machines some reliable autonomy, and enhance work productivity and efficiency. Therefore, in order to service the increasing patients, AI should be best choice to assist theranostics and management of patients. Medical and industrial cross integration is the indispensable way of innovation and development[30]. The concept of medical and industrial integration development is that: based on the cross integration of medicine and engineering, it continues to track hot areas such as molecular biology, genomics, artificial intelligence technology, big data, cloud computing, mobile healthcare, and the internet of things, using quantum computing, 5G/6G communication, block chain, nanotechnology, Internet of Things, AI, AR, VR, MR technologies, to achieve prevention and diagnosis of diseases, treatment and rehabilitation, drug research and development, Traditional Chinese Medicine technology innovation. In short, with clinical needs as the goal, nanotechnology etc as the tools, information processing as the method, multidisciplinary cross to break through the bottlenecks and challenges of disease diagnosis and treatment[31-37]. For example, integrated nano-oncology has made great progress[38]. Gold nanoprism-assisted human PD-L1 siRNA realized gene therapy and photothermal therapy on lung cancer[39]. The quantity of medical robots with embedded AI software have become more and more, and rapidly enter into clinical application[27,40]. Lung cancer is first commonest malignancy among men and the third commonest cancer in women worldwide[41]. The overall 5-year survival rate of lung cancer patients is approximately 20%, however varies markedly depending on cancer stage and molecular typing. Stage I lung cancer patient has a 5-year overall survival rate of greater than 75%, stage III lung cancer patient drops to 25% of 5-year survival rate [42]. Discovering early lung cancer is the only pathway for its cure. Up to date, biomarker diagnosis, imaging diagnosis, cell and pathological diagnosis are the primary diagnostic techniques of lung cancer[43]. Imaging diagnosis includes nuclear magnetic resonance image(MRI), isotope image, ultrasound, positron emission tomography and Computer Tomography(PET/CT). X-ray chest radiography and CT are the two common anatomical imaging modalities that are regularly used to to recognize different lung diseases[44]. Herein we review the main advances of application of AI in diagnosis, treatment and prognosis of lung cancer. We outlook application prospect of AI in theranostics of lung cancer, and discuss about the opportunities and challenges brought by artificial intelligence ( Figure 1). Page - 2Open Access, Volume 10 , 2025 Figure 1. Overview of application of AI in theranostics of lung cancer. ADVANCES OF AI IN THERANOSTICS OF LUNG CANCER It is well known that lung cancer is the first commonest cancer worldwide. How to realize precise theranostics of lung cancer owns great clinical demand. Up to date, as shown in Figure 2, CT-based imaging diagnosis is the primary tool to detect lung cancer at early stage[45], AI in lung cancer bright the chance to integrate computational power and clinical decision- making[46].

Daxiang Cui Directive Publications Figure 2. CT Imaging in lung cancer. Instruction of the imaging modalities used in lung cancer screening, diagnosis, radiation planning & delivery, and follow-up. Reproduced from ref. 45 with permission from W.B. Saunders Ltd, Copyright 2022. In the key National Lung Screening Trial (NLST) study, lung cancer screening with low-dose computed tomography (LDCT) showed a clear reduction in mortality[47]. Analogous results were also achieved in succeeding American and European studies[48,49]. Annual CT chest screening could reduce lung cancer mortality by at least 20% after 7 years compare with annual chest X-ray radiography[50]. While lung CT screening has the potential to dramatically reduce the number of lung cancer related deaths, the false positive rate of LDCT screening for lung cancer is reported to be as high as 96.4%[51], and the radiologists undertake high burden to make screening precise and efficient for large volumes of CT scans. On the one hand, it is very necessary to establish a new method that can effectively distinguish benign from malignant pulmonary nodules. At present, lot of scholars try to extract radiomic features of CT images of pulmonary nodules and establish theory models to realize the intelligent identification of benign and malignant pulmonary nodules[52-54]. On the other hand, there is an urgent requirement to seek an auxiliary mean, which can improve the diagnostic efficiency of lung cancer by integrating with CT imaging. AI based on deep learning owns the ability of efficient self-optimization, which can enhance not only the recognition ability of pulmonary nodules with different properties as shown in Figure 3, but also helps to improve the diagnostic efficiency of early- stage lung cancer[55]. Figure 3. Categories of lung nodules in a CT scan; benign, primary malignant, and metastatic malignant (from left to right). Reproduced from ref. 55with permission from MDPI, Copyright 2019. AI systems for Lung Nodule Detection and Classification Toğaçar et al. used three deep learning models such as LeNet, AlexNet and VGG-16 to detect lung cancer. In addition, the features obtained from the last fully connected layer of CNNs are used as input data for different machine learning models, including linear regression (LR), linear discriminant analysis (LDA), decision tree (DT), support vector machine (SVM), Nearest Page - 3Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications Neighbor (NN) and softmax. The combination of the AlexNet model and NN classifier achieves effective classification precise rate of 98.74%[56]. Du et al. established a three-layer diagnosis system for lung cancer, in which three machine learning models such as decision tree C5.0, artificial neural network (ANN) and support vector machine (SVM) were involved[57]. Zheng et al. has achieved better performance not only for small nodules but also for large lesions based on this data set. This proves the effectiveness of the CAD system they developed for the detection of lung nodules[58]. Wang et al. developed an innovative CNN-based nodule-size- adaptive model for fast and precise candidate detection[59]. Pradhan et al. used a 3D Convolutional Neural Network (CNN) to identify lung cancer, they obtained training accuracy of 83.33%, testing accuracy of 100% and precision, recall, kappa- Score, and F-score of 1[60]. Xie et al. proposed a new automatic lung nodule detection framework with 2D Convolutional Neural Network (CNN) to assist the CT reading process[61]. Setio et al. established the LUNA16 architecture, an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available chest CT scan reference database LIDC-IDRI data set[62]. Firmino et al. introduced a CAD system that contains two main components: 1) A computer-aided detection (CADe) module for detecting and segmenting suspicious lung nodules, 2) A computer- aided diagnosis (CADx) module, which realizes nodule level assessment and patient-level malignant tumor classification by analyzing suspicious lesions from CADe[63]. Sharma, et al. demonstrated and verified a new type of tuberculosis nodule detection system based on deep neural network[64]. Huang et al. proposed an Amalgamated - Convolutional Neural Network (A-CNN) and use it to screening pulmonary nodules[65]. Nasrullah et al. used two deep three-dimensional (3D) customized mixed link network (CMixNet) architectures for lung nodule detection and classification, respectively. Nodule detection were performed through faster R-CNN based on efficiently learned features from CMixNet and U-Net like encoder-decoder architecture. Classification of the nodules was performed through a gradient boosting machine (GBM) on the learned features from the designed 3D CMix Net structure. Better results were obtained compared to the existing methods[66]. Jung et al. used a three-dimensional deep convolutional neural network (3D DCNN) with shortcut connections and a 3D DCNN with dense connections for lung nodule classification. They used an ensemble method that aggregates the results of multiple trained models to boost performance[67]. Page - 4Open Access, Volume 10 , 2025 Figure 4. (A) CNN detection of pulmonary nodules. (B) Two different types of ensemble methods. The general ensemble method (left) and checkpoint ensemble method (right) . (C) The flowchart of the three deep learning models. Reproduced from ref. 67 with permission from Spring Nature, Copyright 2018. AI systems for lung Cancer Classification and TNM Staging Lung cancer were classified into two major categories such as small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). SCLC constitutes approximately 15%, NSCLC constitutes approximately 85% of lung cancers. The pulmonary adenocarcinoma (ADC) and pulmonary squamous cell carcinoma (SqCC) are two most common entities in the NSCLC category, which constitutes approximately 90% of all NSCLC[68]. Kriegsmann et al. confirmed that convolutional neuronal networks (CNNs) could classify the most common lung cancers into subtypes including pulmonary adenocarcinoma (ADC), pulmonary squamous cell carcinoma (SqCC), and small-cell lung cancer (SCLC)[69]. Coudray et al. developed a deep convolutional neural network (inception v3) based on whole-slide images obtained from the cancer genome atlas to realize accurately and automatically classifying them into LUAD, LUSC or normal lung tissue[70].

Daxiang Cui Directive Publications In addition to early detection, appropriate staging and grading of tumors or lesions are also very necessary in order to formulate appropriate cancer treatment strategies[71]. The tumor-lymph node-metastasis (TNM) staging system is one of the popular cancer staging methods[72]. Moitra et al. developed a simple and fast CNN model integrated with Recurrent Neural Network (RNN) to realize automatic AJCC staging of NSCLC. The developed CNN-RNN model is obviously superior to other machine learning algorithms under consideration[73]. Moitra et al. established a 1D CNN model to realize automatic staging and histopathological grading of non-small cell lung cancer[74]. AI Systems for EGFR mutation screening of Lung Cancer Lung cancers were mainly classified into two types such as non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). The gene mutations in epidermal growth factor receptor (EGFR) tyrosine kinase domain such as exon 19 E746-A750 deletion and exon 21 L858R point mutation are the commonest mutation points. EGFR tyrosine kinase inhibitors (TKIs) such as erlotinib and gefitinib, can treat effectively lung cancer patients with gene mutation of EGFR[75]. How to identify quickly gene mutation of EGFR owns great clinical requirement. 1575 radiomics features were extracted from PET images of 75 lung cancer patients with EGFR mutation based on contrast agents such as 18F-MPG and 18F-FDG. The Mann-Whitney U test was used for single factor analysis, the Least Absolute Shrinkage and Selection Operator (Lasso) Regression was used for feature screening, then the radiomics classification models were established by using support vector machines and ten-fold cross-validation, and were used to identify EGFR mutation in primary lung cancers and metastasis lung cancers(Figure 5,6), accuracy based on 18F-MPG PET images are respectively 90% for primary lung cancers, and 89.66% for metastasis lung cancers, accuracy based on 18F-FDG PET images are respectively 76% for primary lung cancers and 82.75% for metastasis lung cancers. The area under the curves (AUC) based on 18 F-MPG PET images are respectively 0.94877 for primary lung cancers, and 0.91775 for metastasis lung cancers, AUC based on 18 F-FDG PET images are respectively 0.87374 for primary lung cancers, and 0.82251 for metastasis lung cancers. In short, both 18F-MPG PET images and 18F-FDG PET images combined with established AI classification models can identify EGFR mutation, then direct clinical doctors to select matched target drug to treat lung cancer patients[Table 1].The established AI model for screening EGFR mutation based on PET imaging of patients with lung cancer own clinical translational prospects[76]. Page - 5Open Access, Volume 10 , 2025 Figure 5. Experimental flowchart. Reproduced from ref. 76 with permission from American Scientific Publishers, Copyright 2021. Figure 6. Patients classification: (A) 18F-MPG PET images; (B)18F-FDG PET images Reproduced from ref. 76 with permission from American Scientific Publishers, Copyright 2021.

Daxiang Cui Directive Publications Table 1. Performances of the model. Reproduced from ref. 76 with permission from American Scientific Publishers, Copyright 2021. Training set Accuracy Precision Sensitivity Specificity F1 18 F-MPG Primary foci 0.9 0.96 0.8571 0.9545 0.9057 Metastasis 0.8966 0.875 0.9333 0.8571 0.9032 18 F-FDG Primary foci 0.76 0.8333 0.7143 0.8182 0.7692 Metastasis 0.8275 0.7778 0.9333 0.7143 0.8485 Validation set Accuracy Precision Sensitivity Specificity F1 18 F-MPG Primary foci 0.92 0.9286 0.9286 0.9091 0.9286 Metastasis 0.9285 1 0.8571 1 0.9230 18 F-FDG Primary foci 0.76 0.8333 0.7143 0.8182 0.7692 Metastasis 0.7857 0.75 0.8571 0.7143 0.8 Page - 6Open Access, Volume 10 , 2025 AI Systems for Lung Cancer surgery therapy Robotic-assisted pulmonary lobectomy is suitable for patients being able to tolerate conventional lobectomy. Robotic lobectomy owns those advantages such as decreased rates of blood loss, blood transfusion, air leak, chest tube duration, length of stay, and mortality. Especially the use of artificial intelligence (AI) and machine learning (ML) can help in surgical decision-making by improving the recognition of minute and complex anatomical structures. All these advancements have led to faster recovery and fewer complications in Surgical patients [27,77,78]. The use of robotic assistance for complex pulmonary resections such as segmentectomy and sleeve lobectomy has steadily increased in recent years. Robotic surgery is well- suited for complex pulmonary operation given its specific advantages related to superior optics and precise tissue manipulation and dissection[79,80]. Diego, et al. developed robotic-assisted complex pulmonary surgery with a specific focus on right upper sleeve lobectomy for lung cancer[81,82]. Liu, et al. developed puncture surgical robot for lung nodule biopsy. MRI and CT image of patient with lung nodule was obtained, established multimode molecular imaging data, established two models for image segmentation, Double-well NET I and Double-well Net II, which are based on the potts model, double -well potential, network approximation theory and operator-splitting methods. DN-I provides a data-driven way to learn the region force functional, and to enhance segmentation performance. The Double-well Nets introduce an innovative approach that leverages mathematical foundations to enhance segmentation performance. Under the directing of image models, puncture surgical robot realizes a needle precisely reach the lesion site, extract diseased tissue, reduce the occurrence of complications, ensure fast recovery of lesion site[83]. With future advancements such as AI-driven automation, nanorobots, microscopic incision surgeries, semi-automated telerobotic systems, and the impact of 5G connectivity on remote surgery, robotic-assisted pulmonary lobectomy will achieve great advances to improve precision and accuracy, own obvious advantages[84]. AI Systems for Lung Cancer prognosis Predicting survival rates helps providers to ensure the best treatment plan (involving life quality and medical expenses of patients). Accurately predicting the survival rate of lung cancer patients is one very difficult work. Due to the increasing complexity of lung cancer, many time and biological characteristics, and differences in patient populations, it remains a challenge [85]. The application of AI in clinical decision-making such as especially predicting survival rates of lung cancer patients will improve healthcare operations. Xu et al. evaluated deep learning networks for predicting clinical results by analyzing time-series CT images of locally advanced NSCLC patients[86]. Histological subtype prediction is one main mission in grading NSCLC tumors. Moitra et al. developed a more accurate deep learning model by integrating convolutional and bidirectional cycle neural networks to achieve histological subtype prediction, the model can be used in the automated prognosis analysis of patients with non-small cell lung cancer (NSCLC)[87]. Wu et al. established a convolutional neural network (CNN) framework called Deep LRHE to predict the risk of lung cancer recurrence by analyzing the histopathological images of lung cancer patients [88]. Afshar et al. investigated the function of 3D CNNs to quantify radiographic tumor characteristics and predict overall survival possibility[89]. Wang et al. developed a deep convolutional neural network(CNN) model to identify automatically the tumor area of advanced lung cancer from H&E pathology images as shown in Figure 7. They found that many characteristics of tumor shape are significantly related

Daxiang Cui Directive Publications to tumor prognosis. So they established one prognostic risk prediction model for lung cancer[90]. Tau et al. proposed a deep machine learning model integrated with a convolutional neural network (CNN) to predict the potential of newly diagnosed non–small cell lung cancer (NSCLC) to metastasize to lymph nodes or distant sites[91]. Chamberlin et al. used AI to detect automatically lung nodules and coronary calcium in the course of low-dose CT scans, and realized lung cancer screening. The result is that the system has good accuracy and prognostic value[92]. Figure 7. (A) Use two data sets and other comparison models to describe the workflow based on deep learning. (B) Flow chart of analysis process that Wang et al. developed to automatically identify the tumor area of lung ADC from H&E pathology images. Reproduced from ref. 90 with permission from Springer Nature, Copyright 2018. Page - 7Open Access, Volume 10 , 2025 DISCUSS OPPORTUNITIES AND CHALLENGES AND FUTURE DIRECTION Artificial intelligence (AI) have realized to handle successfully complex nonlinear relationships, fault tolerance, parallel distributed processing and learning[93]. AI display unique advantages such as self-adaptation, simultaneous operation of quantitative and qualitative knowledge and validating model results from some clinical studies in multiple fields[94]. AI also exhibit multipurpose in the filed of clinical medicine[95]. AI not only can make full use of the various aspects data of clinical diversity, but also can help to address some problems such as current lack objectivity and universality in expert systems[96,97]. Especially DL techniques improve our ability to interpret imaging data[98, 99]. Those AI results can enhance sensitivity of data analysis and ensure much fewer false positives than radiologists. However, they also exist the risk of overfitting the training data, and cause a brittle degraded performance in certain settings[100]. AI also have to face some important challenges that must be resolved to ensure its practical application in theranostics of lung cancer[101]. Firstly, medical imaging data from the lungs can not be used as input data directly. Secondly, there is a more sad view to be put forward[102], which is referred to inherent uncertainties in medicine, and the possibility that the “black box” of neural networks/ML applications will reduce physician skills and transform rapidly some departments of healthcare in ways that appear to be practical and economic but with unintended negative consequences. Thirdly, there are several ethical and safety issues including using AI after obtaining patient consent and verifying who is responsible for the misdiagnosis or incorrect therapy[103]. Fourthly, AI cannot determine causal relationships. AI generated the predictions, doctors have to evaluate and interpret critically in clinically meaningful ways. In the era of precision medicine, the predictability of artificial intelligence in cancer management has great promise in the near future[95]. However, the authors believe that AI cannot replace doctors completely, AI achieves the best performance, which is realized by using the way of human and machine collaboration. In near future, experts can study in depth the application of AI in the whole process of lung cancer management, for example, important main areas are early screening based on sensor for examining

Daxiang Cui Directive Publications exhaled VOC biomarkers, pathology identification, risk assessment, therapy guidance and outcome prediction. Despite existing these various challenges[104], in the era of precision medicine, integrating Genomics, proteomics and metabolomics data with clinical information is very necessary for future clinical practice. Therefore, artificial intelligence have to integrate with multiple disciplines data in order to make a new breakthrough, it is a new development direction. In addition, it is very necessary to use large random events to test AI models. Nanomaterials own unique nano-effects, for example, up conversion Nanoparticles, nano enzymes, gold nanoparticles based nanoprobes, which were used for targeted imaging and photodynamic or photothermal therapy of lung cancer[105,106,107]. Al technology has also integrated with nanotechnology, which was used for nanotheranostics of lung cancer, enhanced precise image localization of in vivo lung cancer, and directed local operation therapy. Medical and industrial cross owns unique advantages to solve key problem existed in diagnosis and therapy of lung cancer. In 2022, USA Open AI company published Chat GPT, it blew up the novel world of artificial intelligence, it established large predictive models based on big data, brings new opportunities for precise theranostics of lung cancer[108,109]. However, application of AI in robotic-assisted pulmonary lobectomy still pose major challenges, which are the high cost of intelligence robotic systems, how to keep maintenance of robotic systems, how to keep the size of the robot systems, have to train surgeon to master how to use robots system to perform lung cancer surgery. To solve those challenges will bring innovative developing opportunities, which is also new developing direction for theranostics of lung cancer in near future. CONCLUSION AND PROSPECTS In recent ten years, AI technology has integrated with chromatographic chip, microfludic chip, biosensors and PET/ CT, MRI imaging techniques, which were used for precise detection of lung cancer biomarkers and precise image localization of in vivo lung cancer, improved sensitivity and specificity of diagnosis, and realized automated diagnosis, staging, robotic-assisted treatment and prognosis of lung cancer with high efficiency. Artificial intelligence (AI) and machine learning, especially deep learning and deep seek are increasingly applied in theranostics of lung cancer. This article provides an overview of the application of AI in theranostics of lung cancer. The development and validation of AI algorithms requires large volumes of well-structured data, and and the algorithms are capable of treating variable levels of data. It is very important that clinicians understand how AI can be applied in theranostics of lung cancer where diagnostic criteria overlap, how AI use to fit into everyday clinical practice, and how AI use to address issues of patient safety. AI owns a clear role in providing support for clinical doctors, but its relatively recent introduction means that confidence in its application still must be fully established. AI robot-assisted surgical operation also need clinical test and transform. AI will play a key role in aiding clinicians in the theranostics and management of lung cancer in the future, AI will bring the benefits for patients and doctors from its application in everyday clinical practice. In conclusion, facing the requirement of clinical theranostics of lung cancer patients, AI integrating with multidisciplinary technology and data is a new development trend, application of AI in theranostics and and management of lung cancer owns excellent clinical transformation value and prospect in near future. Acknowledgments This work was supported from Project of International Cooperation and Exchanges of the National Natural Science Foundation of China ( No. 82020108017), Innovation Group Project of National Natural Science Foundation of China (No.81921002), National Key Research and Development Program of China (No. 2017FYA0205301), Projects of Shanghai Science and Technology Commission (21DZ2203200, and No. 20142201300), and Natural Science Foundation of Shanghai (No. 22ZR1467600). Conflicts of interest The authors declare no conflicts of interest. REFERENCES 1. Colom R, Karama S, Jung RE, Haier RJ. Human intelligence and brain networks. Dialogues Clin Neurosci 2010; 12: 489-501. 2. Adami C. A brief history of Artificial intelligence research. Artificial Life 2021;27:131-137. 3. Kaul V, Enslin S, Gross SA. History of Artificial Intelligence in Medicine. Gastrointest Endosc 2020;92:807-812 4. Yan WQ, Wang K, Xu H, Huo XY, Jin QH, Cui DX. Machine Learning Approach to Enhance the Performance of MNP-Labeled Lateral Flow Immunoassay. Nano-Micro Letters 2019; 11:7 5. Qin Q, Wang K, Yang JC, Xu H, Cao B, Wo Y, Jin QH, Cui DX. Algorithms for immunochromatographic assay: review and impact on future application. Analyst 2019;144:5659-5676 Page - 8Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications 6. Chen MR, Lin SJ, Zhou C, Cui DX, Haick H, Tang N. From Conventional to Microfluidic: Progress in Extracellular Vesicle Separation and Individual Characterization. Advanced Healthcare Materials 2023;12(8): DOI10.1002/ adhm.202202437 7. Chen MR, Cui DX, Haick H, Tang N. Artificial Intelligence- Based Medical Sensors for Healthcare System. Advanced Sensor Research 2024; 3:2300009 8. Chen MR, Zhang M, Yang ZY, Zhou C, Cui DX, Haick H, Tang N. AI-Driven Wearable Mask-Inspired Self-Healing Sensor Array for Detection and Identification of Volatile Organic Compounds. Advanced Functional Materials 2024;34:DOI10.1002/adfm.202309732 9. Wang JH, Liu G, Zhou C, Cui XY, Wang W, Wang JL, Huang YX, Jiang JL, Wang ZT, Tang ZY, Zhang AM, Cui DX. Application of artificial intelligence in cancer diagnosis and tumor nanomedicine. Nanoscale 2024;16:14213- 14246 10. Zha YQ, Xue CL, Liu YL, Ni J, De La Fuente JM, Cui DX. Artificial intelligence in theranostics of gastric cancer, a review. Medical review 2023; 3:214-229. 11. Zhu XY, Li Y, Gu N. Application of Artificial Intelligence in the Exploration and Optimization of Biomedical Nanomaterials. Nano Bieomedicine and Engineering 2023;15: 342-353 12. Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM.Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging 2016;35:1285-1298 13. Lisboa PJ. A review of evidence of health benefit from artificial neural networks in medical intervention. Neural Netw 2002;15:11-39 14. Sun JH, Wang BQ, Warden AR, Cui DX, Ding XT. Overcoming Multidrug-Resistance in Bacteria with a Two-Step Process to Repurpose and Recombine Established Drugs. Analytical Chemistry 2019; 91: 13562-13569 15. Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial Intelligence in Surgery: Promises and Perils. Annals of surgery, 2018; 268:70-76 16. Fard MJ, Ameri S, Darin Ellis R, Chinnam RB, Pandya AK, Klein MD. Automated robot-assisted surgical skill evaluation: Predictive analytics approach. Int J Med Robot 2018; 14: e1850 17. Gant V, Rodway S, Wyatt J. Artificial neural networks: practical considerations for clinical application. Clinical Applications of Artificial Neural Networks, R. Dybowski and V. Gant, Editors. Cambridge: Cambridge University Press, 2001; 329-356. 18. Yang YM, Han Y, Sun QY, Cheng J, Yue CX, Liu YL, Song J, Jin WL, Ding XT, de la Fuente JM, Ni J, Wang XQ, Cui DX. Au-siRNA@ aptamer nanocages as a high-efficiency drug and gene delivery system for targeted lung cancer therapy. Journal of Nanobiotechnology 2021;19:54 19. Han Y, Yang YM, Sun QY, Li B, Yue CX, Liu YL, de la Fuente JM, Cui DX. Dual-targeted lung cancer therapy via inhalation delivery of UCNP-siRNA-AS1411 nanocages. Cancer Biology & Medicine 2021;19:1047-1060 20. Ciaburro G. Machine fault detection methods based on machine learning algorithms: A review. Math Biosci Eng. 2022;19:11453-11490 21. Theodosiou AA, Read RC. Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. Journal of Infection. 2023;87:287-294. 22. Stahlschmidt SR, Ulfenborg B, Synnergren J. Multimodal deep learning for biomedical data fusion: a review. Brief Bioinform. 2022;23(2):bbab569 23. Binson VA, Thomas S, Subramoniam M, Arun J, Naveen S, Madhu S.A Review of Machine Learning Algorithms for Biomedical Applications.Ann Biomed Eng. 2024;52(5):1159-1183. 24. Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. NPJ Digital Medicine 2020;3:17 25. Clare R, Erika LC, Mari-lynn D, Allan JW. The impact of clinical decision-support systems on provider behavior in the inpatient setting:A systematic review and meta- analysis. J Hosp Med. 2022; 17:368-383 26. Aslam MA, Xue CL, Liu MH, Wang K, Cui DX. Classification and Prediction of Gastric Cancer from Saliva Diagnosis using Artificial Neural Network. Engineering Letters 2021;29:10-24 Page - 9Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications 27. Chatterjee S, Das S, Ganguly K, Mandal D.Advancements in robotic surgery: innovations, challenges and future prospects. J Robot Surg. 2024 ;18(1):28. 28. Smart CL, Pearson TG, Liang Z, Lim MX, Abdelrahman MI, Monticone F, Cohen I, McEuen PL. Magnetically programmed diffractive robotics. Science 2024;386: 1031–1037. 29. Zhou C, Jiang JL, Huang SW, Wang JH, Cui XY, Wang WC, Chen MR, Peng JW, Shi NQ, Wang BS, Zhang AM,Zhang Q, Li QC, Cui SS,Xue SH,Wang W, Tang N, Cui DX. An ingestible near-infrared fluorescence capsule endoscopy for specific gastrointestinal diagnoses. Biosensors & Bioelectronics 2024;257:116209 30. Iacovacci V, Diller E, Ahmed D, Menciassi A. Medical Microrobots. Annu Rev Biomed Eng. 2024;26(1):561-591. 31. Conde J, Tian FR, Hernandez YL, Bao CC, Cui DX, Janssen KP, Ricardo IM, Baptista PV, Stoeger T, de la Fuente JM. In vivo tumor targeting via nanoparticle-mediated therapeutic siRNA coupled to inflammatory response in lung cancer mouse models. Biomaterials 2013:34:7744- 7753 32. Yue CX, Zhang CL, Alfranca G, Yang Y, Jiang XQ, Yang YM, Pan F, de la Fuente JM, Cui DX. Near-Infrared Light Triggered ROS-activated Theranostic Platform based on Ce6-CPT-UCNPs for Simultaneous Fluorescence Imaging and Chemo-Photodynamic Combined Therapy. Theranostics 2016;6:456-469 33. Conde J, Bao CC, Tan YQ, Cui DX, Edelman ER, Azevedo HS, Byrne HJ, Artzi N, Tian FR. Dual Targeted Immunotherapy via In Vivo Delivery of Biohybrid RNAi-Peptide Nanoparticles to Tumor-Associated Macrophages and Cancer Cells. Advanced Functional Materials 2015;25:4183-4194 34. Liu B, Qiao GL, Han Y, Shen E, Alfranca G, Tan HS, Wang LR, Pan SJ, Ma LJ, Xiong WJ, Liu, Yanlei; Cui, Daxiang.Targeted theranostics of lung cancer: PD-L1- guided delivery of gold nanoprisms with chlorin e6 for enhanced imaging and photothermal/photodynamic therapy.Acta Biomaterialia 2020;117:361-373 35. Zhang AM, Gao A, Zhou C, Xue CL, Zhang Q, De La Fuente JM, Cui DX. Confining Prepared Ultrasmall Nanozymes Loading ATO for Lung Cancer Catalytic Therapy/ Immunotherapy. Advanced Materials 2023;35:DOI 10.1002/adma.202303722 36. Hou WX, Zhao X, Qian XQ, Pan F, Zhang CL, Yang YM, de la Fuente JM, Cui DX. pH-Sensitive self-assembling nanoparticles for tumor near-infrared fluorescence imaging and chemo-photodynamic combination therapy. Nanoscale 2016;8:104-116 37. Yang YM, Yue CX, Han Y, Zhang W, He A, Zhang CL, Yin T, Zhang Q, Zhang JJ, Yang Y, Ni J, Sun JL, Cui DX. Tumor-Responsive Small Molecule Self-Assembled Nanosystem for Simultaneous Fluorescence Imaging and Chemotherapy of Lung Cancer. Advanced Functional Materials 2016;26:8735-8745 38. Jiang JL , Cui XY, Huang YX, Yan DM, Wang BS, Yang ZY, Chen MR, Wang JH, Zhang YN, Liu G, Zhou C, Cui SS, Ni J, Yang FH, Cui DX. Advances and Prospects in Integrated Nano-oncology. Nano Biomedicine and Engineering 2024;16:152-187 39. Liu B, Cao W, Qiao GL, Yao SY, Pan SJ, Wang LR, Yue CX, Ma LJ, Liu YL, Cui DX. Effects of gold nanoprism- assisted human PD-L1 siRNA on both gene down- regulation and photothermal therapy on lung cancer. Acta Biomaterialia 2019;99:307-319 40. Gunning D, Stefik M, Choi J, Miller T, Stumf S, Yang GZ. XAI-explainable artificial intelligence. Science Robotics 2019;4:7120 41. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018; 68: 394- 424 42. Bade BC, Dela Cruz CS. Lung Cancer 2020: Epidemiology, Etiology, and Prevention. Clin Chest Med .2020;41:1-24. 43. Azar FE, Azami-Aghdash S, Pournaghi-Azar F, Mazdaki A, Rezapour A, Ebrahimi P, Yousefzadeh N. Cost- effectiveness of lung cancer screening and treatment methods: a systematic review of systematic reviews. BMC Health Services Research 2017;17:413. 44. Al-Sheikh MH, Al Dandan O, Al-Shamayleh AS, Jalab HA, Ibrahim RW.Multi-class deep learning architecture for classifying lung diseases from chest X-Ray and CT images. Sci Rep 2023;13(1):19373 45. Avasarala SK, Rickman OB. Endobronchial Therapies for Diagnosis, Staging, and Treatment of Lung Cancer. Surgical Clinics of North America 2022;102:393-412. Page - 10Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications 46. Christie JR, Lang P, Zelko LM, Palma DA, Abdelrazek M, Mattonen SA. Artificial Intelligence in Lung Cancer: Bridging the Gap Between Computational Power and Clinical Decision-Making. Can Assoc Radiol J. 2021;72(1):86-97. 47. Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, Gareen IF, Gatsonis C, Marcus PM, Sicks JD. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011; 365:395-409 48. Balata H, Evison M, Sharman A, Crosbie P, Booton R. CT screening for lung cancer: Are we ready to implement in Europe? Lung Cancer 2019; 134: 25-33. 49. Church TR, Black WC, Aberle DR, Berg CD, Clingan KL, Duan FH, Fagerstrom RM, Gareen IF, Gierada DS, Jones GC, Mahon I, Marcus PM, Sicks JD, Jain A, Baum S. Results of initial low-dose computed tomographic screening for lung cancer. N Engl J Med 2013; 368:1980-1991 50. Bach PB, Mirkin JN, Oliver TK, Azzoli CG, Berry DA, Brawley OW, Byers T, Colditz GA, Gould MK, Jett JR, Sabichi AL, Smith-Bindman R, Wood DE, Qaseem A, Detterbeck FC. Benefits and harms of CT screening for lung cancer: a systematic review. JAMA 2012; 307:2418-2429 . 51. Kumar KS, Venkatalakshmi K, Karthikeyan K. Lung Cancer Detection Using Image Segmentation by means of Various Evolutionary Algorithms. Comput Math Methods Med, 2019; 49: 09846 52. Park SC, Tan J, Wang XW, Lederman D, Leader JK, Kim SH, Zheng B. Computer-aided detection of early interstitial lung diseases using low-dose CT images. Physics in Medicine and Biology 2011; 56 4:1139-1153. 53. Mazzone PJ, Lam L. Evaluating the Patient With a Pulmonary Nodule: A Review .JAMA. 2022 ;327(3):264- 273. 54. Gheysens G, De Wever W, Cockmartin L, Bosmans H, Coudyzer W, De Vuysere S, Lefere M. Detection of pulmonary nodules with scoutless fixed-dose ultra-low-dose CT: a prospective study. Eur Radiol. 2022;32(7):4437-4445. 55. Nasrullah N, Sang J, Alam MS, Mateen M, Cai B, Hu H. Automated Lung Nodule Detection and Classification Using Deep Learning Combined with Multiple Strategies. Sensors (Basel). 2019;19(17):3722. 56. Toğaçar M, Ergen B, Cömert Z. Detection of lung cancer on chest CT images using minimum redundancy maximum relevance feature selection method with convolutional neural networks. Biocybernetics and Biomedical Engineering, 2020; 40: 23-39 57. Du YH, Zhao YR, Sidorenkov G, de Bock GH, Cui XN, Huang YB, Dorrius MD, Rook M, Groen HJM, Heuvelmans MA, Vliegenthart R, Chen KX, Xie XQ, Liu SY, Oudkerk M, Ye ZX. Methods of computed tomography screening and management of lung cancer in Tianjin: design of a population-based cohort study. Cancer Biol Med, 2019; 16: 181-188 58. Zheng SY, Cornelissen LJ, Cui XN, Jing XP, Veldhuis RNJ, Oudkerk M, van Ooijen PMA. Deep convolutional neural networks for multiplanar lung nodule detection: Improvement in small nodule identification. Medical Physics 2021; 48: 733-744. 59. Huang W, Xue Y, Wu YJPO. A CAD system for pulmonary nodule prediction based on deep three-dimensional convolutional neural networks and ensemble learning. Plos One 2019; 14: e0219369 60. Horry M, Chakraborty S, Pradhan B, Paul M, Gomes D, Ul-Haq A, Alamri A. Deep Mining Generation of Lung Cancer Malignancy Models from Chest X-ray Images .Sensors (Basel). 2021 ;21(19):6655. 61. Xie H, Yang D, Sun N, Chen Z, Zhang Y. Automated pulmonary nodule detection in CT images using deep convolutional neural networks. Pattern Recognition, 2019; 85:109-119 62. Setio AAA, Traverso A, de Bel T, Berens MSN, Bogaard CVD, Cerello P, Chen H, Dou Q, Fantacci ME, Geurts B, Gugten RV, Heng PA, Jansen B, de Kaste MMJ, Kotov V, Lin JY, Manders JTMC, Sóñora-Mengana A, García-Naranjo JC, Papavasileiou E, Prokop M, Saletta M, Schaefer- Prokop CM, Scholten ET, Scholten L, Snoeren MM, Torres EL, Vandemeulebroucke J, Walasek N, Zuidhof GCA, Ginneken BV, Jacobs C.Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Med Image Anal. 2017;42:1-13. 63. Firmino M, Angelo G, Morais H, Dantas MR, Valentim R.Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy. Biomed Eng Online 2016;15(1):2.

Page - 11Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications 64. Sharma AS, Sharma AR, Malhotra R, Singh PP, Chakrabortty RK, Mahajan SH, Pandit AK. An accurate artificial intelligence system for the detection of pulmonary and extra pulmonary Tuberculosis. Tuberculosis (Edinb) . 2021:131:102143.

65. Wang Y, Wu B, Zhang N, Liu J, Ren F, Zhao L. Research progress of computer aided diagnosis system for pulmonary nodules in CT images. J Xray Sci Technol. 2020;28(1):1-16. 66. Nasrullah N, Sang J, Alam MS, Mateen M, Cai B, Hu HB. Automated Lung Nodule Detection and Classification Using Deep Learning Combined with Multiple Strategies. Sensors (Basel)2019;19(17):3722. 67. Jung H, Kim B, Lee I, Lee J, Kang J. Classification of lung nodules in CT scans using three-dimensional deep convolutional neural networks with a checkpoint ensemble method. BMC Med Imaging. 2018;18(1):48.

68. Thakur SK, Singh DP, Choudhary J. Lung cancer identification: a review on detection and classification. Cancer Metastasis Rev. 2020;39(3):989-998. 69. Janßen C, Boskamp T, Le’Clerc Arrastia J, Otero Baguer D, Hauberg-Lotte L, Kriegsmann M, Kriegsmann K, Steinbuß G, Casadonte R, Kriegsmann J, Maaß P. Multimodal Lung Cancer Subtyping Using Deep Learning Neural Networks on Whole Slide Tissue Images and MALDI MSI. Cancers (Basel). 2022;14(24):6181. 70. Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, Moreira AL, Razavian N, Tsirigos A. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 2018;24(10):1559-1567. 71. Kriegsmann M, Haag C, Weis CA, Steinbuss G, Warth A, Zgorzelski C, Muley T, Winter H, Eichhorn ME, Eichhorn F, Kriegsmann J, Christopoulos P, Thomas M, Witzens- Harig M, Sinn P, Winterfeld MV, Heussel CP, Herth FJF, Klauschen F, Stenzinger A, Kriegsmann K. Deep Learning for the Classification of Small-Cell and Non-Small-Cell Lung Cancer. Cancers (Basel), 2020;12:1604 72. Rami-Porta R, Nishimura KK, Giroux DJ, et al. The International Association for the Study of Lung Cancer, Lung Cancer Staging Project: Proposals for Revision of the TNM Stage Groups in the Forthcoming (Ninth) Edition of the TNM Classification for Lung Cancer. J Thorac Oncol. 2024;19(7):1007-1027 73. Moitra D, Mandal RK. Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN). Health Information Science and Systems, 2019; 7: 14 74. Moitra D, Mandal RK. Classification of non-small cell lung cancer using one-dimensional convolutional neural network. Expert Systems with Applications, 2020; 159:113564 75. Voldborg BR, Damstrup L, Spang-Thomsen M, Poulsen HS. Epidermal growth factor receptor (EGFR) and EGFR mutations, function and possible role in clinical trials. Ann Oncol. 1997;8(12):1197-206. 76. Li H, Gao C, Sun YY, Li AJ , Lei W, Yang YM, Guo T, Sun XL, Wang K, Liu MH, Cui DX. Radiomics analysis to enhance precise identification of epidermal growth factor receptor mutation based on positron emission tomography images of lung cancer patients. J Biomed Nanotechnol. 2021;17(4):691-702. 77. Wei B, Eldaif SM, Cerfolio RJ. Robotic Lung Resection for Non-Small Cell Lung Cancer. Surg Oncol Clin N Am. 2016;25(3):515-31. 78. Amirkhosravi F, Kim MP. Complex Robotic Lung Resection. Thorac Surg Clin. 2023 ;33(1):51-60. 79. Jacob A, Stamenkovic SA. Robotic-assisted thoracic surgery: left upper lobe sleeve lobectomy for an endobronchial tumour. Multimed Man Cardiothorac Surg. 2024:doi: 10.1510/mmcts.2023.079. 80. Merritt RE. Robotic Segmentectomy. Thorac Surg Clin. 2023 ;33(1):43-49. 81. Gonzalez-Rivas D, Bosinceanu M, Manolache V, Gallego- Poveda J, Garcia A, Paradela M, Dunning J, Bale MJ, Motas N. Uniportal fully robotic-assisted major pulmonary resections. Ann Cardiothorac Surg. 2023;12(1):52-61. 82. Watkins AA, Quadri SM, Servais EL. Robotic-Assisted Complex Pulmonary Resection: Sleeve Lobectomy for Cancer . Innovations (Phila) 2021;16(2):132-135. 83. Liu H, Liu J, Chan R, Tai XC. Double-well Net for Image Segmentation. Multiscale Modeling & Simulation 2024; 22:1449-1477 84. Gonzalez-Rivas D, Manolache V, Bosinceanu ML, Page - 12Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications Gallego-Poveda J, Garcia-Perez A, de la Torre M, Turna A, Motas N. Uniportal pure robotic-assisted thoracic surgery-technical aspects, tips and tricks. Ann Transl Med 2023;11(10):362. 85. Wang P, Luo Z, Luo C, Wang T. Application of a Comprehensive Model Based on CT Radiomics and Clinical Features for Postoperative Recurrence Risk Prediction in Non-small Cell Lung Cancer. Acad Radiol. 2024;31(6):2579-2590. 86. Xu YW, Hosny A, Zeleznik R, Parmar C, Coroller T, Franco I, Mak RH, Aerts HJWL. Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging. Clinical Cancer Research 2019; 25: 3266-3275 87. Moitra D, Mandal RK. Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN). Health Information Science and Systems, 2019; 7: 14 88. Wu ZJ, Wang L, Li CR, Cai YC, Liang YB, Mo XF, Lu QQ, Dong LX, Liu YG. Deep LRHE: A Deep Convolutional Neural Network Framework to Evaluate the Risk of Lung Cancer Recurrence and Metastasis From Histopathology Images. Frontiers in genetics, 2020; 11:768-768. 89. Afshar P, Oikonomou A, Naderkhani F, Tyrrell PN, Plataniotis KN, Farahani K, Mohammadi A.3D-MCN: A 3D Multi-scale Capsule Network for Lung Nodule Malignancy Prediction. Sci Rep. 2020;10(1):7948. 90. Wang S, Chen A, Yang L, Cai L, Xie Y, Fujimoto J, Gazdar A, Xiao GH. Comprehensive analysis of lung cancer pathology images to discover tumor shape and boundary features that predict survival outcome. Sci Rep. 2018;8(1):10393. 91. Tau N, Stundzia A, Yasufuku K, Hussey D, Metser U. Convolutional Neural Networks in Predicting Nodal and Distant Metastatic Potential of Newly Diagnosed Non– Small Cell Lung Cancer on FDG PET Images. American Journal of Roentgenology. 2020; 215: 192-197. 92. Chamberlin J, Kocher MR, Waltz J, Snoddy M, Stringer NFC, Stephenson J, Sahbaee P, Sharma P, Rapaka S, Schoepf UJ, Abadia AF, Sperl J, Hoelzer P, Mercer M, Somayaji N, Aquino G, Burt JR. Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value. BMC Med. 2021;19(1):55. 93. Dayarathna S, Islam KT, Uribe S, Yang G, Hayat M, Chen Z. Deep learning based synthesis of MRI, CT and PET: Review and analysis. Med Image Anal. 2024;92:103046. 94. Hosny A, Parmar C, Coroller TP, Grossmann P, Zeleznik R, Kumar A, Bussink J, Gillies RJ, Mak RH, Aerts HJWL. Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study. PLoS Med. 2018; 15: e1002711. 95. Chen ZH, Lin L, Wu CF, Li CF, Xu RH, Sun Y. Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine. Cancer Commun(Lond). 2021;41(11):1100-1115. 96. Kann BH, Hosny A, Aerts HJWL. Artificial intelligence for clinical oncology. Cancer Cell. 2021;39(7):916-927. 97. Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A.Artificial intelligence in digital pathology-new tools for diagnosis and precision oncology. Nat Rev Clin Oncol. 2019 ;16(11):703-715. 98. He J, Baxter SL, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nature Medicine 2019; 25:30-36. 99. Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, Kadoury S, Tang A. Deep Learning: A Primer for Radiologists. Radiographics 2017; 37: 2113- 2131. 100. Lan K, Wang DT, Fong S, Liu LS, Wong KKL, Dey N. A Survey of Data Mining and Deep Learning in Bioinformatics. Journal of Medical Systems, 2018; 42:139. 101. Chen JH, Asch SM. Machine Learning and Prediction in Medicine — Beyond the Peak of Inflated Expectations. New England Journal Of Medicine 2017; 376:2507-2509. 102. Cabitza F, Rasoini R, Gensini GF. Unintended Consequences of Machine Learning in Medicine. JAMA, 2017; 318: 517-518. 103. Clare R, Erika LC, Mari-lynn D, Allan JW. The impact of clinical decision-support systems on provider behavior in the inpatient setting:A systematic review and meta- analysis. J Hosp Med. 2022; 17:368-383 104. Dolmans D, Gijbels D. Research on problem-based learning: future challenges. Medical Education, 2013;47:214-218 Page - 13Open Access, Volume 10 , 2025

Daxiang Cui Directive Publications 105. Yue CX, Zhang CL, Alfranca G, Yang Y, Jiang XQ, Yang YM, Pan F, de la Fuente JM, Cui DX. Near-Infrared Light Triggered ROS-activated Theranostic Platform based on Ce6-CPT-UCNPs for Simultaneous Fluorescence Imaging and Chemo-Photodynamic Combined Therapy. Theranostics 2016;6:456-469 106. Zhang A, Gao A, Zhou C, Xue CL, Zhang Q, De La Fuente JM,Cui DX. Confining Prepared Ultrasmall Nanozymes Loading ATO for Lung Cancer Catalytic Therapy/ Immunotherapy.Advanced Materials 2023;35(45): 2303722 107. Liu B, Cao W, Qiao GL,Yao SY, Pan SJ, Wang LR, Yue CX, Ma LJ, Liu YL, Cui DX. Effects of gold nanoprism-assisted human PD-L1 siRNA on both gene down-regulation and photothermal therapy on lung cancer. Acta Biomaterialia 2019;99:307-319 108. Nazir F, Jawed SF, Tariq SM. Chat GPT and its potential role in medicine. J Pak Med Assoc. 2023;73(12):2509- 2510. 109. Biswas SS. Role of Chat GPT in Public Health. Ann Biomed Eng. 2023;51(5):868-869.

Page - 14Open Access, Volume 10 , 2025

This is an automatically generated text version. For the formatted version of record, download the PDF →