Background Patients with hereditary diffuse gastric cancer often undergo prophylactic gastrectomy to minimize cancer risk. Because intramucosal poorly cohesive carcinomas in this setting are typically not grossly visible, many pathologists assess the entire gastrectomy specimen microscopically. With 150 or more slides per case, this is a major time burden for pathologists. This study utilizes deep learning methods to analyze digitized slides and detect regions of carcinoma.
Methods Prophylactic gastrectomy specimens from seven patients with germline CDH1 mutations were analyzed (five for training/validation and two for testing, with a total of 133 tumor foci). All hematoxylin and eosin slides containing cancer foci were digitally scanned, and patches of size 256×256 pixels were randomly extracted from regions of cancer as well as from regions of normal background tissue, resulting in 15,851 images for training/validation and 970 images for testing. A model with DenseNet-169 architecture was trained for 150 epochs, then evaluated on images from the test set. External validation was conducted on 814 images scanned at an outside institution.
Results On individual patches, the trained model achieved a receiver operating characteristic (ROC) area under the curve (AUC) of 0.9986. This enabled it to maintain a sensitivity of 90% with a false-positive rate of less than 0.1%. On the external validation dataset, the model achieved a similar ROC AUC of 0.9984. On whole slide images, the network detected 100% of tumor foci and correctly eliminated an average of 99.9% of the non-cancer slide area from consideration.
Conclusions Overall, our model shows encouraging progress towards computer-assisted diagnosis of hereditary diffuse gastric cancer.
Citations
Citations to this article as recorded by
Artificial intelligence applicated in gastric cancer: A bibliometric and visual analysis via CiteSpace Guoyang Zhang, Jingjing Song, Zongfeng Feng, Wentao Zhao, Pan Huang, Li Liu, Yang Zhang, Xufeng Su, Yukang Wu, Yi Cao, Zhengrong Li, Zhigang Jie Frontiers in Oncology.2023;[Epub] CrossRef
Deep learning of endoscopic features for the assessment of neoadjuvant therapy response in locally advanced rectal cancer Anqi Wang, Jieli Zhou, Gang Wang, Beibei Zhang, Hongyi Xin, Haiyang Zhou Asian Journal of Surgery.2023; 46(9): 3568. CrossRef
Non-endoscopic Applications of Machine Learning in Gastric Cancer: A Systematic Review Marianne Linley L. Sy-Janairo, Jose Isagani B. Janairo Journal of Gastrointestinal Cancer.2023;[Epub] CrossRef
Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance Yuanqing Yang, Kai Sun, Yanhua Gao, Kuansong Wang, Gang Yu Diagnostics.2023; 13(19): 3115. CrossRef
Using Deep Learning to Predict Final HER2 Status in Invasive Breast Cancers That are Equivocal (2+) by Immunohistochemistry Sean A. Rasmussen, Valerie J. Taylor, Alexi P. Surette, Penny J. Barnes, Gillian C. Bethune Applied Immunohistochemistry & Molecular Morphology.2022; 30(10): 668. CrossRef
Background Immunohistochemistry (IHC) has played an essential role in the diagnosis of hematolymphoid neoplasms. However, IHC interpretations can be challenging in daily practice, and exponentially expanding volumes of IHC data are making the task increasingly difficult. We therefore developed a machine-learning expert-supporting system for diagnosing lymphoid neoplasms.
Methods A probabilistic decision-tree algorithm based on the Bayesian theorem was used to develop mobile application software for iOS and Android platforms. We tested the software with real data from 602 training and 392 validation cases of lymphoid neoplasms and compared the precision hit rates between the training and validation datasets.
Results IHC expression data for 150 lymphoid neoplasms and 584 antibodies was gathered. The precision hit rates of 94.7% in the training data and 95.7% in the validation data for lymphomas were not statistically significant. Results in most B-cell lymphomas were excellent, and generally equivalent performance was seen in T-cell lymphomas. The primary reasons for lack of precision were atypical IHC profiles for certain cases (e.g., CD15-negative Hodgkin lymphoma), a lack of disease-specific markers, and overlapping IHC profiles of similar diseases.
Conclusions Application of the machine-learning algorithm to diagnosis precision produced acceptable hit rates in training and validation datasets. Because of the lack of origin- or disease- specific markers in differential diagnosis, contextual information such as clinical and histological features should be taken into account to make proper use of this system in the pathologic decision-making process.
Citations
Citations to this article as recorded by
Real-Life Barriers to Diagnosis of Early Mycosis Fungoides: An International Expert Panel Discussion Emmilia Hodak, Larisa Geskin, Emmanuella Guenova, Pablo L. Ortiz-Romero, Rein Willemze, Jie Zheng, Richard Cowan, Francine Foss, Cristina Mangas, Christiane Querfeld American Journal of Clinical Dermatology.2023; 24(1): 5. CrossRef
Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms Jamshid Abdul-Ghafar, Kyung Jin Seo, Hye-Ra Jung, Gyeongsin Park, Seung-Sook Lee, Yosep Chong Diagnostics.2023; 13(7): 1308. CrossRef
Clinical approaches for integrating machine learning for patients with lymphoma: Current strategies and future perspectives Dai Chihara, Loretta J. Nastoupil, Christopher R. Flowers British Journal of Haematology.2023; 202(2): 219. CrossRef
Current Trend of Artificial Intelligence Patents in Digital Pathology: A Systematic Evaluation of the Patent Landscape Muhammad Joan Ailia, Nishant Thakur, Jamshid Abdul-Ghafar, Chan Kwon Jung, Kwangil Yim, Yosep Chong Cancers.2022; 14(10): 2400. CrossRef
Recent Application of Artificial Intelligence in Non-Gynecological Cancer Cytopathology: A Systematic Review Nishant Thakur, Mohammad Rizwan Alam, Jamshid Abdul-Ghafar, Yosep Chong Cancers.2022; 14(14): 3529. CrossRef
Diagnosis prediction of tumours of unknown origin using ImmunoGenius, a machine learning-based expert system for immunohistochemistry profile interpretation Yosep Chong, Nishant Thakur, Ji Young Lee, Gyoyeon Hwang, Myungjin Choi, Yejin Kim, Hwanjo Yu, Mee Yon Cho Diagnostic Pathology.2021;[Epub] CrossRef