TY - JOUR
T1 - A narrative review of digital pathology and artificial intelligence
T2 - Focusing on lung cancer
AU - Sakamoto, Taro
AU - Furukawa, Tomoi
AU - Lami, Kris
AU - Pham, Hoa Hoang Ngoc
AU - Uegami, Wataru
AU - Kuroda, Kishio
AU - Kawai, Masataka
AU - Sakanashi, Hidenori
AU - Cooper, Lee Alex Donald
AU - Bychkov, Andrey
AU - Fukuoka, Junya
N1 - Funding Information:
Peer Review File: Available at http://dx.doi.org/10.21037/ tlcr-20-591 Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi. org/10.21037/tlcr-20-591). The series “New Developments in Lung Cancer Diagnosis and Pathological Patient Management Strategies” was commissioned by the editorial office without any funding or sponsorship. LADC reports grants from US National Cancer Institute, during the conduct of the study; grants from Roche Tissue Diagnostics, personal fees from Konica Minolta, outside the submitted work. JF reports grants from NEDO (New Energy and Industrial Technology Development Organization), other from PathPresenter, other from ContextVision, other from Sony, other from Future Corp, during the conduct of the study; other from Pathology Institute Corp, other from N Lab Corp, outside the submitted work; in addition, JF has a patent PCT/JP2020/000424 pending. The other authors
Funding Information:
Funding: This work was partly supported by the New Energy and Industrial Technology Development Organization (NEDO), the US National Institutes of Health National Cancer Institute grants U24CA19436201, U01CA220401 and National Institute of Biomedical Imaging and Bioengineering U01CA220401.
Publisher Copyright:
© Translational Lung Cancer Research. All rights reserved.
PY - 2020/10
Y1 - 2020/10
N2 - The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.
AB - The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.
KW - Artificial intelligence
KW - Deep learning
KW - Pathology
KW - Remote diagnosis
KW - Whole slide imaging
UR - http://www.scopus.com/inward/record.url?scp=85096288412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096288412&partnerID=8YFLogxK
U2 - 10.21037/tlcr-20-591
DO - 10.21037/tlcr-20-591
M3 - Review article
C2 - 33209648
AN - SCOPUS:85096288412
VL - 9
SP - 2255
EP - 2276
JO - Translational Lung Cancer Research
JF - Translational Lung Cancer Research
SN - 2226-4477
IS - 5
ER -