Sangjoon Choi, Soo Ick Cho, Wonkyung Jung, Taebum Lee, Su Jin Choi, Sanghoon Song, Gahee Park, Seonwook Park, Minuk Ma, Sergio Pereira, Donggeun Yoo, Seunghwan Shin, Chan-Young Ock, Seokhwi Kim<\/p>\n
npj Breast Cancer, 2023<\/strong><\/p>\n Abstract<\/strong>
\nTumor-infiltrating lymphocytes (TILs) have been recognized as key players in the tumor microenvironment of breast cancer, but substantial interobserver variability among pathologists has impeded its utility as a biomarker. We developed a deep learning (DL)-based TIL analyzer to evaluate stromal TILs (sTILs) in breast cancer. Three pathologists evaluated 402 whole slide images of breast cancer and interpreted the sTIL scores. A standalone performance of the DL model was evaluated in the 210 cases (52.2%) exhibiting sTIL score differences of less than 10 percentage points, yielding a concordance correlation coefficient of 0.755 (95% confidence interval [CI], 0.693\u20130.805) in comparison to the pathologists\u2019 scores. For the 226 slides (56.2%) showing a 10 percentage points or greater variance between pathologists and the DL model, revisions were made. The number of discordant cases was reduced to 116 (28.9%) with the DL assistance (p\u2009<\u20090.001). The DL assistance also increased the concordance correlation coefficient of the sTIL score among every two pathologists. In triple-negative and human epidermal growth factor receptor 2 (HER2)-positive breast cancer patients who underwent the neoadjuvant chemotherapy, the DL-assisted revision notably accentuated higher sTIL scores in responders (26.8\u2009\u00b1\u200919.6 vs. 19.0\u2009\u00b1\u200916.4, p\u2009=\u20090.003). Furthermore, the DL-assistant revision disclosed the correlation of sTIL-high tumors (sTIL\u2009\u2265\u200950) with the chemotherapeutic response (odd ratio 1.28 [95% confidence interval, 1.01\u20131.63], p\u2009=\u20090.039). Through enhancing inter-pathologist concordance in sTIL interpretation and predicting neoadjuvant chemotherapy response, here we report the utility of the DL-based tool as a reference for sTIL scoring in breast cancer assessment.<\/p>\n