The Role of Artificial Intelligence in Enhancing Diagnostic Imaging

Research Gap

Artificial intelligence (AI) has significantly impacted diagnostic imaging by enhancing diagnostic accuracy, efficiency, and patient outcomes across various medical specialties such as cardiovascular magnetic resonance imaging (CMR), nuclear cardiology, musculoskeletal imaging, and oncology. The integration of AI into diagnostic imaging has shown promise in improving patient safety, diagnostic accuracy, and overall outcomes. Studies have highlighted the potential of AI in areas like radiology, pathology, and oncology, emphasizing the need for collaborative efforts, expanded datasets, and user-friendly AI tools to facilitate its integration into clinical practice. Furthermore, AI has been instrumental in areas like interventional pulmonology, gynecologic malignancies, and endoscopic ultrasonography, showcasing its versatility and potential in revolutionizing diagnostic imaging practices.

Research Questions:

1. How can artificial intelligence be further optimized to enhance diagnostic accuracy and efficiency in various medical imaging modalities?

2. What collaborative efforts are needed to expand datasets and develop user-friendly AI tools for seamless integration into clinical practice in diagnostic imaging?

3. In what ways can AI-driven frameworks be refined to improve precision and speed in medical image evaluation, ultimately enhancing clinical diagnostics and patient care?

4. How can deep learning models be effectively utilized to address data imbalances and enhance disease classification in diagnostic imaging, particularly in respiratory infections?

5. What are the key challenges and opportunities in leveraging artificial intelligence for the early detection and diagnosis of various medical conditions in diagnostic imaging?

6. How can AI be harnessed to advance the understanding and diagnosis of neurodegenerative diseases through state-of-the-art methods in diagnostic imaging?

7. What novel approaches and methodologies can be explored to integrate AI into digital pathology, thereby improving diagnostic efficiency and treatment outcomes?

8. How can artificial intelligence be applied in the early diagnosis of gastrointestinal cancers, such as gastric cancer and colorectal cancer, to improve patient outcomes and survival rates?

9. What are the current trends and future directions in the application of AI in enhancing diagnostic imaging during the COVID-19 pandemic, particularly in the context of medical imaging technologies and AI-enabled solutions?

10. How can the synergy between human expertise and AI technologies be optimized to maximize diagnostic accuracy and efficiency in clinical imaging, fostering a collaborative environment for improved patient care and outcomes?

Abstract:

The integration of artificial intelligence (AI) in diagnostic imaging has revolutionized healthcare practices, offering advanced tools for disease detection, treatment planning, and patient care. This research paper explores the role of AI in enhancing diagnostic accuracy across various medical specialties, including radiology, pathology, oncology, and specialized areas like interventional pulmonology, gynecologic malignancies, and endoscopic ultrasonography. By leveraging AI algorithms, healthcare providers can streamline diagnostic workflows, improve disease detection and classification, and optimize treatment strategies. The study highlights emerging trends in AI and diagnostic imaging, ethical and legal implications, and future research directions to address current challenges and advance healthcare practices. Collaborative efforts, user-friendly AI tools, and real-world applications demonstrate the transformative potential of AI in diagnostic imaging, emphasizing the need for responsible AI deployment, patient-centered care, and regulatory compliance in clinical practice. The findings underscore the profound implications of AI integration in healthcare and offer recommendations for future research to optimize diagnostic accuracy, improve patient outcomes, and advance the quality of healthcare delivery.

Introduction

Diagnostic imaging is a critical component of modern healthcare, allowing for the visualization of internal body structures to assist in diagnosing and treating various medical conditions. The advancement of diagnostic imaging techniques has significantly enhanced patient care and outcomes. However, the growing complexity of medical imaging data presents challenges in interpretation and diagnosis. In this context, artificial intelligence (AI) has emerged as a transformative technology with the potential to revolutionize diagnostic imaging practices. AI, particularly deep learning models, provides advanced capabilities in image analysis, pattern recognition, and decision-making, thereby improving diagnostic accuracy and efficiency (Aggarwal et al. 2021).

The importance of AI in diagnostic imaging lies in its capacity to rapidly and accurately process large volumes of imaging data, leading to more precise and timely diagnoses. AI algorithms can aid healthcare professionals in detecting abnormalities, predicting disease progression, and customizing treatment plans based on individual patient data. Additionally, AI has demonstrated potential in enhancing access to medical imaging services, particularly in low- and middle-income countries, by streamlining workflows and optimizing resource utilization (Frija et al. 2021, 101034).

Research Questions and Objectives:

1. How can AI be further optimized to enhance diagnostic accuracy and efficiency across various medical imaging modalities?

2. What collaborative efforts are necessary to expand datasets and develop user-friendly AI tools for seamless integration into clinical practice in diagnostic imaging?

3. In what ways can AI-driven frameworks be improved to enhance precision and speed in medical image evaluation, ultimately improving clinical diagnostics and patient care?

4. How can deep learning models be effectively employed to address data imbalances and enhance disease classification in diagnostic imaging, particularly in respiratory infections?

5. What are the primary challenges and opportunities in utilizing AI for the early detection and diagnosis of various medical conditions in diagnostic imaging?

6. How can AI be leveraged to advance the understanding and diagnosis of neurodegenerative diseases through cutting-edge methods in diagnostic imaging?

7. What innovative approaches and methodologies can be explored to integrate AI into digital pathology, thereby enhancing diagnostic efficiency and treatment outcomes?

8. How can AI be utilized in the early diagnosis of gastrointestinal cancers, such as gastric cancer and colorectal cancer, to improve patient outcomes and survival rates?

This research paper aims to investigate the role of AI in enhancing diagnostic imaging, addressing the aforementioned research questions to offer insights into the current state, challenges, and future directions of AI integration in diagnostic imaging practices. By examining the latest advancements and applications of AI in various medical imaging modalities, this study aims to contribute to the ongoing efforts to optimize diagnostic processes, enhance patient care, and advance the field of diagnostic imaging through innovative AI-driven solutions.

2: Fundamentals of Artificial Intelligence in Diagnostic Imaging

I. Overview of Artificial Intelligence and Machine Learning

Artificial intelligence (AI) and machine learning (ML) have transformed diagnostic imaging by enabling computers to interpret medical images with a level of accuracy and efficiency that rivals or surpasses human capabilities. AI encompasses technologies that simulate human intelligence processes, such as learning, reasoning, and problem-solving. Machine learning, a subset of AI, focuses on developing algorithms that can learn from and make predictions or decisions based on data. In the context of diagnostic imaging, AI and ML algorithms can analyze complex medical images, detect patterns, and assist healthcare professionals in making accurate diagnoses (Hirasawa et al. 2018, 653-660).

II. Applications of AI in Medical Imaging

The applications of AI in medical imaging are extensive, covering various specialties such as radiology, pathology, cardiology, oncology, and neurology. AI algorithms can be utilized for image segmentation, feature extraction, disease classification, and treatment planning. In radiology, AI has demonstrated promise in detecting abnormalities in X-rays, CT scans, and MRIs, while in pathology, AI can aid in the analysis of tissue samples for cancer diagnosis. Additionally, AI has played a crucial role in cardiovascular imaging, where it can analyze cardiac MRI images to assess heart function and detect abnormalities (Argentiero et al. 2022, 2866). The versatility of AI in medical imaging extends to applications in respiratory infections, gastrointestinal malignancies, and musculoskeletal disorders, showcasing its potential to enhance diagnostic accuracy and patient care across a wide range of medical conditions (Alhasan and Hasaneen 2021, 101933).

III. Current Trends and Developments

The field of AI in diagnostic imaging is rapidly progressing, with continuous advancements in deep learning models, computer vision techniques, and data analytics. Current trends focus on improving the interpretability and explainability of AI algorithms, enhancing their integration into clinical workflows, and addressing ethical and regulatory considerations. Collaborative efforts between healthcare providers, researchers, and technology developers are propelling innovation in AI applications for diagnostic imaging, with a focus on developing user-friendly tools that can be seamlessly integrated into existing healthcare systems. Moreover, the COVID-19 pandemic has expedited the adoption of AI in medical imaging, with AI-enabled solutions being utilized for the early detection and diagnosis of COVID-19-related complications (Tian 2024, 121-126). As AI continues to revolutionize diagnostic imaging practices, future developments are anticipated to further enhance the accuracy, efficiency, and accessibility of medical imaging services, ultimately improving patient outcomes and advancing the field of healthcare diagnostics.

3: AI in Medical Imaging Modalities

I. AI in Radiology and Pathology

Artificial intelligence (AI) has revolutionized the fields of radiology and pathology by enhancing diagnostic accuracy, efficiency, and workflow optimization. In radiology, AI algorithms can analyze medical images such as X-rays, CT scans, and MRIs to detect abnormalities, assist in disease classification, and improve patient outcomes. AI-powered tools in pathology enable automated analysis of tissue samples, aiding in the diagnosis of various conditions, including cancer. The integration of AI in radiology and pathology has shown promising results in streamlining diagnostic processes, reducing interpretation errors, and facilitating timely interventions (Argentiero et al. 2022, 2866).

II. AI in Oncological Imaging

AI has significantly impacted oncological imaging by enabling early detection, precise tumor characterization, and treatment response assessment. AI algorithms can analyze complex imaging data from modalities like MRI, CT, and PET scans to identify subtle changes indicative of cancer. In oncology, AI plays a crucial role in tumor segmentation, radiomics analysis, and personalized treatment planning. By leveraging AI in oncological imaging, healthcare providers can make informed decisions, tailor treatment strategies, and monitor disease progression more effectively, ultimately improving patient care and outcomes (Davis et al. 2020, 1061-1066).

III. AI in Cardiac Imaging

The application of AI in cardiac imaging has transformed the field by enhancing diagnostic capabilities, risk prediction, and treatment planning for cardiovascular diseases. AI algorithms are utilized in various cardiac imaging modalities, including echocardiography, cardiac MRI, and nuclear imaging, to assess cardiac function, detect abnormalities, and predict adverse events. AI-driven solutions in cardiac imaging enable automated image analysis, accurate quantification of cardiac parameters, and personalized patient care. By harnessing the power of AI, clinicians can achieve faster and more precise diagnoses, leading to improved management of cardiac conditions and better patient outcomes (Jiang et al. 2020).

Hence, the integration of artificial intelligence in radiology, pathology, oncological imaging, and cardiac imaging has revolutionized diagnostic practices, offering advanced tools for accurate disease detection, characterization, and treatment planning. The utilization of AI in medical imaging modalities showcases the potential to enhance healthcare delivery, optimize clinical workflows, and improve patient outcomes in various medical specialties.

4: Enhancing Diagnostic Accuracy with AI

I. Role of AI in Disease Detection and Classification

Artificial intelligence (AI) plays a crucial role in disease detection and classification within the field of diagnostic imaging. By utilizing machine learning and deep learning algorithms, AI systems can analyze medical images accurately and efficiently, aiding in the early identification of abnormalities and diseases. AI algorithms can detect subtle patterns and variations in imaging data that may not be easily discernible to the human eye, thereby facilitating the timely diagnosis of conditions such as cancer, cardiovascular diseases, and respiratory infections. The ability of AI to automate disease detection and classification processes not only enhances diagnostic accuracy but also expedites treatment planning and improves patient outcomes Kim.

II. Impact of AI on Diagnostic Precision

The integration of AI in diagnostic imaging has significantly enhanced diagnostic precision by providing healthcare professionals with advanced tools for image analysis and interpretation. AI algorithms can assist in identifying minute details in medical images, reducing the risk of human error and improving the consistency of diagnoses. Moreover, AI-powered systems can analyze complex imaging data rapidly, leading to more accurate and reliable diagnostic results. By augmenting the capabilities of healthcare providers, AI contributes to increased diagnostic precision across various medical specialties, ultimately enhancing the quality of patient care and treatment outcomes (Mukherjee 2024).

III. Challenges and Opportunities

While AI has shown remarkable potential in enhancing diagnostic accuracy and precision, several challenges and opportunities exist in its implementation in diagnostic imaging. Challenges include the need for robust validation of AI algorithms, ensuring data privacy and security, addressing regulatory concerns, and integrating AI seamlessly into existing clinical workflows. Moreover, the interpretability and transparency of AI-driven diagnostic decisions remain critical areas of focus to foster trust and acceptance among healthcare professionals and patients. On the other hand, opportunities lie in leveraging AI for personalized medicine, optimizing treatment strategies, and advancing research in diagnostic imaging. Collaborative efforts between clinicians, researchers, and technology developers are essential to overcome challenges and harness the full potential of AI in enhancing diagnostic accuracy and precision in healthcare (Alsulimani 2024, 1051).

In conclusion, the role of AI in enhancing diagnostic accuracy is pivotal in transforming diagnostic imaging practices, offering advanced solutions for disease detection, classification, and precision. By addressing challenges and embracing opportunities, the integration of AI in diagnostic imaging holds immense promise for improving healthcare delivery, optimizing clinical workflows, and ultimately enhancing patient care and outcomes.

5: AI Integration in Clinical Practice

I. Collaborative Efforts and Expanded Datasets

The integration of artificial intelligence (AI) in clinical practice requires collaborative efforts between healthcare professionals, researchers, and technology developers to leverage the full potential of AI-driven solutions. Collaborations enable the pooling of expertise, resources, and data to enhance the development and validation of AI algorithms for diagnostic imaging. Expanded datasets play a crucial role in training AI models, ensuring their accuracy and generalizability across diverse patient populations and medical conditions. By fostering collaborative initiatives and sharing datasets, the healthcare community can accelerate the adoption of AI in clinical practice, leading to improved diagnostic accuracy and patient outcomes Melito and Rintell.

II. User-Friendly AI Tools for Clinical Integration

User-friendly AI tools are essential for seamless integration into clinical workflows and the effective utilization of AI in diagnostic imaging. Healthcare professionals require intuitive interfaces, clear visualization of AI-generated insights, and easy accessibility to AI-driven recommendations to incorporate AI into their daily practice. User-friendly AI tools enhance the usability and acceptance of AI solutions among clinicians, promoting their adoption and integration into routine clinical decision-making processes. By prioritizing the development of user-friendly AI tools, healthcare organizations can optimize the benefits of AI in diagnostic imaging and improve the efficiency of healthcare delivery (Lim et al. 2022, 1029-1034).

III. Real-world Applications and Case Studies

Real-world applications and case studies demonstrate the practical impact of AI integration in clinical practice, showcasing the effectiveness of AI-driven solutions in improving diagnostic accuracy and patient care. Case studies highlight successful implementations of AI in diagnostic imaging, such as the early detection of diseases, personalized treatment planning, and workflow optimization. By examining real-world applications of AI in clinical settings, healthcare professionals can gain insights into the benefits, challenges, and best practices associated with AI integration. These case studies serve as valuable examples of how AI can transform diagnostic imaging practices and enhance the quality of healthcare delivery (Pedro 2023, e0290613).

In conclusion, collaborative efforts, user-friendly AI tools, and real-world applications are essential components of successful AI integration in clinical practice. By fostering collaborations, developing user-friendly tools, and showcasing real-world applications, the healthcare community can harness the transformative power of AI in diagnostic imaging, ultimately improving diagnostic accuracy, patient outcomes, and the overall quality of healthcare delivery.

6: AI in Specialized Diagnostic Imaging Areas

I. AI in Interventional Pulmonology

Artificial intelligence (AI) is enhancing diagnostic accuracy, treatment planning, and patient outcomes in interventional pulmonology. AI algorithms can analyze imaging data from procedures such as bronchoscopy and thoracic imaging to assist in the detection and characterization of pulmonary nodules, lung cancers, and other respiratory conditions. By leveraging AI in interventional pulmonology, healthcare providers can optimize procedural guidance, improve lesion localization, and personalize treatment strategies for patients with pulmonary diseases. The integration of AI in interventional pulmonology showcases the potential to enhance procedural efficiency, diagnostic precision, and therapeutic outcomes in respiratory medicine Kuwahara et al..

II. AI in Gynecologic Malignancies

The application of artificial intelligence (AI) has transformed the detection, characterization, and treatment of cervical, endometrial, and ovarian cancers in gynecologic malignancies. AI algorithms can analyze imaging modalities such as ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography-computed tomography (PET-CT) to aid in the early diagnosis, staging, and monitoring of gynecologic malignancies. By leveraging AI in gynecologic oncology, healthcare providers can make informed treatment decisions, predict patient outcomes, and tailor personalized treatment plans for individuals with gynecologic cancers. The integration of AI in gynecologic malignancies demonstrates the potential to improve diagnostic accuracy, treatment efficacy, and patient survival rates in women's health (Daoud et al. 2022, 5528).

III. AI in Endoscopic Ultrasonography

Artificial intelligence (AI) analysis in endoscopic ultrasonography is transforming the diagnosis and treatment of pancreaticobiliary diseases, gastrointestinal conditions, and other endoscopic procedures. AI algorithms can analyze endoscopic images and data to assist in the detection of abnormalities, characterization of lesions, and guidance for therapeutic interventions. By incorporating AI in endoscopic ultrasonography, healthcare providers can enhance procedural accuracy, optimize treatment planning, and improve patient outcomes in gastroenterology and hepatobiliary medicine. The utilization of AI in endoscopic ultrasonography highlights the potential to revolutionize endoscopic procedures, streamline diagnostic workflows, and advance the field of gastrointestinal imaging (Kuwahara et al. 2023).

In conclusion, the integration of artificial intelligence in specialized diagnostic imaging areas such as interventional pulmonology, gynecologic malignancies, and endoscopic ultrasonography offers advanced solutions for disease detection, treatment planning, and procedural guidance. By leveraging AI in these specialized fields, healthcare providers can enhance diagnostic accuracy, optimize treatment strategies, and improve patient outcomes, ultimately advancing the quality of care in respiratory medicine, women's health, and gastroenterology.

7: Future Directions and Challenges

I. Emerging Trends in AI and Diagnostic Imaging

The future of artificial intelligence (AI) in diagnostic imaging is marked by emerging trends that are poised to revolutionize healthcare practices. One prominent trend is the increasing integration of AI-driven solutions in routine clinical workflows, offering advanced tools for disease detection, treatment planning, and patient care. AI applications are expanding beyond traditional radiology and pathology to specialized areas such as interventional pulmonology, gynecologic malignancies, and endoscopic ultrasonography, showcasing the versatility and potential of AI in diverse medical specialties. Moreover, the development of AI models for personalized medicine, predictive analytics, and population health management represents a significant trend in leveraging AI to improve diagnostic accuracy and patient outcomes in diagnostic imaging Pedro.

II. Ethical and Legal Implications

As artificial intelligence (AI) continues to transform diagnostic imaging practices, ethical and legal implications arise that necessitate careful consideration and regulation. Key ethical considerations include transparency in AI algorithms, accountability for AI-generated diagnoses, patient privacy and data security, and the potential for bias in AI decision-making. Healthcare providers must ensure that AI systems are developed and deployed ethically, with a focus on patient safety, equity, and trust. From a legal standpoint, regulations governing the use of AI in healthcare, data protection laws, and liability issues in AI-assisted diagnostics require clear guidelines and frameworks to safeguard patient rights and ensure the responsible implementation of AI technologies in diagnostic imaging (Ueda et al. 2023, 3-15).

III. Future Research Directions

The future of artificial intelligence (AI) in diagnostic imaging presents exciting research directions that aim to address current challenges and propel innovation in healthcare practices. Future research efforts may focus on enhancing the interpretability and explainability of AI algorithms, improving the generalizability of AI models across diverse patient populations, and optimizing the integration of AI into clinical decision-making processes. Additionally, research on the impact of AI on healthcare disparities, patient outcomes, and clinician workflow will be crucial in shaping the future of AI in diagnostic imaging. Collaborative studies that involve multidisciplinary teams, real-world validation of AI models, and longitudinal assessments of AI-assisted interventions are essential for advancing the field of AI in diagnostic imaging and realizing its full potential in improving healthcare delivery (Lam et al. 2022, e37188).

Hence, the future of artificial intelligence in diagnostic imaging holds immense promise for transforming healthcare practices, enhancing diagnostic accuracy, and improving patient outcomes. By addressing emerging trends, ethical and legal implications, and future research directions, the healthcare community can harness the transformative power of AI to revolutionize diagnostic imaging practices and advance the quality of patient care.

Conclusion

I. Summary of Key Findings

The integration of artificial intelligence (AI) in diagnostic imaging has shown significant promise in enhancing diagnostic accuracy, improving patient outcomes, and revolutionizing healthcare practices. AI-driven solutions have demonstrated the ability to streamline diagnostic workflows, assist in disease detection and classification, and optimize treatment planning across various medical specialties. Emerging trends in AI and diagnostic imaging, such as personalized medicine, predictive analytics, and population health management, highlight the transformative potential of AI in advancing healthcare delivery. Ethical and legal implications surrounding AI integration underscore the importance of transparency, accountability, and patient privacy in the responsible deployment of AI technologies in clinical practice. Future research directions aim to address current challenges, enhance the interpretability of AI algorithms, and optimize the integration of AI into clinical decision-making processes to further improve healthcare outcomes.

II. Implications for Clinical Practice

The implications of AI integration in clinical practice are profound, offering healthcare providers advanced tools for disease diagnosis, treatment planning, and patient care. AI technologies have the potential to enhance diagnostic accuracy, reduce interpretation errors, and optimize clinical workflows, ultimately improving the quality and efficiency of healthcare delivery. By leveraging AI in specialized diagnostic imaging areas and routine clinical workflows, clinicians can enhance procedural guidance, personalize treatment strategies, and improve patient outcomes across diverse medical conditions. The ethical and legal considerations surrounding AI in healthcare underscore the importance of responsible AI deployment, patient-centered care, and regulatory compliance to ensure the safe and effective use of AI technologies in clinical practice.

III. Recommendations for Future Research

Future research in the field of artificial intelligence and diagnostic imaging should focus on addressing key challenges, advancing AI interpretability, and optimizing AI integration into clinical workflows. Collaborative efforts between healthcare professionals, researchers, and technology developers are essential to drive innovation, validate AI algorithms, and ensure the generalizability of AI models across diverse patient populations. Research on the impact of AI on healthcare disparities, patient outcomes, and clinician workflow will be crucial in shaping the future of AI in diagnostic imaging. Longitudinal studies, real-world validations, and multidisciplinary collaborations are recommended to further explore the potential of AI in transforming healthcare practices, improving diagnostic accuracy, and enhancing patient care outcomes.

In conclusion, the integration of artificial intelligence in diagnostic imaging holds immense potential to revolutionize healthcare practices, enhance patient care, and improve clinical outcomes. By addressing emerging trends, ethical considerations, and future research directions, the healthcare community can harness the transformative power of AI to advance diagnostic imaging practices and optimize healthcare delivery for the benefit of patients worldwide.

References:

Aggarwal, Ravi, Viknesh Sounderajah, Guy Martin, Daniel Shu Wei Ting, Alan Karthikesalingam, Dominic King, Hutan Ashrafian et al., 2021. "Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis", NPJ Digital Medicine(1), 4. https://doi.org/10.1038/s41746-021-00438-z

Alhasan, Mustafa and Mohamed Hasaneen, 2021. "Digital imaging, technologies and artificial intelligence applications during covid-19 pandemic", Computerized Medical Imaging and Graphics, 91:101933. https://doi.org/10.1016/j.compmedimag.2021.101933

Alsulimani, Ahmad, 2024. "The impact of artificial intelligence on microbial diagnosis", Microorganisms(6), 12:1051. https://doi.org/10.3390/microorganisms12061051

Argentiero, Adriana, Giuseppe Muscogiuri, Mark Rabbat, Chiara Martini, Nicolo’ Soldato, Paolo Basile, Andrea Baggiano et al., 2022. "The applications of artificial intelligence in cardiovascular magnetic resonance—a comprehensive review", Journal of Clinical Medicine(10), 11:2866. https://doi.org/10.3390/jcm11102866

Daoud, Taher, Sahil Sardana, Nir Stanietzky, Albert R. Klekers, Priya Bhosale, and Ajaykumar C. Morani, 2022. "Recent imaging updates and advances in gynecologic malignancies", Cancers(22), 14:5528. https://doi.org/10.3390/cancers14225528

Davis, Ashlee M, Kristen Billick, Kenneth Horton, Madeline Jankowski, Peg Knoll, Jane E. Marshall, Alan Paloma et al., 2020. "Artificial intelligence and echocardiography: a primer for cardiac sonographers", Journal of the American Society of Echocardiography(9), 33:1061-1066. https://doi.org/10.1016/j.echo.2020.04.025

Frija, G., Ivana Blažić, Donald P. Frush, Monika Hierath, Michael Kawooya, Lluís Donoso-Bach, and Boris Brkljačić, 2021. "How to improve access to medical imaging in low- and middle-income countries ?", Eclinicalmedicine, 38:101034. https://doi.org/10.1016/j.eclinm.2021.101034

Hirasawa, Toshiaki, Kazuharu Aoyama, Tetsuya Tanimoto, Soichiro Ishihara, Satoki Shichijo, Tomohiro Ozawa, Tatsuya Ohnishi et al., 2018. "Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images", Gastric Cancer(4), 21:653-660. https://doi.org/10.1007/s10120-018-0793-2

Jiang, Beibei, Ning Guo, Yinghui Ge, Lu Zhang, Matthijs Oudkerk, and Xueqian Xie, 2020. "Development and application of artificial intelligence in cardiac imaging", British Journal of Radiology(1113), 93. https://doi.org/10.1259/bjr.20190812

Kim, Kyung Won, 2023. "Artificial intelligence in gastric cancer imaging with emphasis on diagnostic imaging and body morphometry", Journal of Gastric Cancer(3), 23:388. https://doi.org/10.5230/jgc.2023.23.e30

Kuwahara, Takamichi, Kazuo Hara, Nobumasa Mizuno, Shin Haba, Nozomi Okuno, Hiroki Koda, Akira Miyano et al., 2020. "Current status of artificial intelligence analysis for endoscopic ultrasonography", Digestive Endoscopy(2), 33:298-305. https://doi.org/10.1111/den.13880

Kuwahara, Takamichi, Kazuo Hara, Nobumasa Mizuno, Shin Haba, Nozomi Okuno, Toshitaka Fukui, Miyuki Urata et al., 2023. "Current status of artificial intelligence analysis for the treatment of pancreaticobiliary diseases using endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography", Den Open(1), 4. https://doi.org/10.1002/deo2.267

Lam, Thomas Y., Max FK Cheung, Yasmin Lynda Munro, Kong Meng Lim, Dennis Shung, and Joseph J.Y. Sung, 2022. "Randomized controlled trials of artificial intelligence in clinical practice: systematic review", Journal of Medical Internet Research(8), 24:e37188. https://doi.org/10.2196/37188

Lim, Sophie Soyeon, Tuan Phan, Meng Law, Gerard S Goh, Matthew Lukies, Tim Joseph, and Warren Clements, 2022. "Non‐radiologist perception of the use of artificial intelligence (ai) in diagnostic medical imaging reports", Journal of Medical Imaging and Radiation Oncology(8), 66:1029-1034. https://doi.org/10.1111/1754-9485.13388

Melito, Richard and David Rintell, 2013. "The process of collaboration: an expanded view", Journal of Systemic Therapies(1), 32:14-26. https://doi.org/10.1521/jsyt.2013.32.1.14

Mukherjee, Sreetama, 2024. "Navigating the future: a comprehensive review of artificial intelligence applications in gastrointestinal cancer", Cureus. https://doi.org/10.7759/cureus.54467

Pedro, Ana Rita, 2023. "Artificial intelligence in medicine: a comprehensive survey of medical doctor’s perspectives in portugal", Plos One(9), 18:e0290613. https://doi.org/10.1371/journal.pone.0290613

Tian, Jingxiao, 2024. "Intelligent medical detection and diagnosis assisted by deep learning", Applied and Computational Engineering(1), 64:121-126. https://doi.org/10.54254/2755-2721/64/20241356

Ueda, Daiju, Taro Kakinuma, Shohei Fujita, Koji Kamagata, Yasutaka Fushimi, Rintaro Ito, Yusuke Matsui et al., 2023. "Fairness of artificial intelligence in healthcare: review and recommendations", Japanese Journal of Radiology(1), 42:3-15. https://doi.org/10.1007/s11604-023-01474-3