Augmented interpretation of HER2, ER, and PR in breast cancer by artificial intelligence analyzer: enhancing interobserver agreement through a reader study of 201 cases.

"the models are implemented using pytorch v1 7 1 (available at https://github com/pytorch/pytorch ).; the cell detection model and the tissue segmentation model are based on a proprietary implementation of deeplabv3+ (open-source implementations available online e g at https://github com/vainf/deeplabv3plus-pytorch ) with a resnet-34 and resnet-101 backbone architectures (open-source implementation available at https://github com/pytorch/vision/blob/master/torchvision/models/resnet py )."

"Declarations Ethics approval and consent to participateThis study was approved by the Institutional Review Board (IRB) of Kyung Hee University Hospital (IRB no. KHUH 2022-01-035). Informed consent was waived by the IRB because of the retrospective design of the study and the anonymized clinical data used in the analysis. The study was performed in accordance with the Declaration of Helsinki. Consent for publicationNot applicable. Competing interestsSoo Ick Cho, Sangwon Shin, Taebum Lee, Wonkyung Jung, Hajin Lee, Jiyoung Park, Sanghoon Song, Gahee Park, Heon Song, Seonwook Park, Jinhee Lee, Mingu Kang, Jongchan Park, Sergio Pereira, Donggeun Yoo, Keunhyung Chung, and Siraj M. Ali are employees of Lunit and/or have stock/stock options in Lunit. Competing interests Soo Ick Cho, Sangwon Shin, Taebum Lee, Wonkyung Jung, Hajin Lee, Jiyoung Park, Sanghoon Song, Gahee Park, Heon Song, Seonwook Park, Jinhee Lee, Mingu Kang, Jongchan Park, Sergio Pereira, Donggeun Yoo, Keunhyung Chung, and Siraj M. Ali are employees of Lunit and/or have stock/stock options in Lunit."

"Funding This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2022R1A2C1010536)."