Tumor-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], 0.693–0.805) in comparison to the pathologists’ 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 < 0.001). 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 ± 19.6 vs. 19.0 ± 16.4, p = 0.003). Furthermore, the DL-assistant revision disclosed the correlation of sTIL-high tumors (sTIL ≥ 50) with the chemotherapeutic response (odd ratio 1.28 [95% confidence interval, 1.01–1.63], p = 0.039). 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.

The prevalence of CT interstitial lung abnormalities (ILAs) in an Asian health screening cohort was approximately 3%, and fibrotic ILA was independently associated with imaging progression, lung ca... Background The association between interstitial lung abnormalities (ILAs) and long-term outcomes has not been reported in Asian health screening populations. Purpose To investigate ILA prevalence i...

Purpose: Recently, anti-programmed cell death-1/anti-programmed cell death ligand-1 (anti-PD1/L1) immunotherapy has been demonstrated for its efficacy when combined with cytotoxic chemotherapy in randomized phase 3 trials for advanced biliary tract cancer (BTC). However, no biomarker predictive of benefit has been established for anti-PD1/L1 in BTC. Here, we evaluated tumor-infiltrating lymphocytes (TIL) using artificial intelligence-powered immune phenotype (AI-IP) analysis in advanced BTC treated with anti-PD1. Experimental Design: Pretreatment hematoxylin and eosin (H&E)–stained whole-slide images from 339 patients with advanced BTC who received anti-PD1 as second-line treatment or beyond, were employed for AI-IP analysis and correlative analysis between AI-IP and efficacy outcomes with anti-PD1. Next, data and images of the BTC cohort from The Cancer Genome Atlas (TCGA) were additionally analyzed to evaluate the transcriptomic and mutational characteristics of various AI-IP in BTC. Results: Overall, AI-IP were classified as inflamed [high intratumoral TIL (iTIL)] in 40 patients (11.8%), immune-excluded (low iTIL and high stromal TIL) in 167 patients (49.3%), and immune-desert (low TIL overall) in 132 patients (38.9%). The inflamed IP group showed a substantially higher overall response rate compared with the noninflamed IP groups (27.5% vs. 7.7%, P < 0.001). Median overall survival and progression-free survival were significantly longer in the inflamed IP group than in the noninflamed IP group (OS, 12.6 vs. 5.1 months; P = 0.002; PFS, 4.5 vs. 1.9 months; P < 0.001). In the TCGA cohort analysis, the inflamed IP showed increased cytolytic activity scores and IFNγ signature compared with the noninflamed IP. Conclusions: AI-IP based on spatial TIL analysis was effective in predicting the efficacy outcomes in patients with BTC treated with anti-PD1 therapy. Further validation is necessary in the context of anti-PD1/L1 plus gemcitabine–cisplatin.

Cytologic diagnosis of nuclear protein in testis (NUT) midline carcinoma (NMC) is important due to its aggressive behavior and miserable prognosis. Early diagnosis of NMC can facilitate proper management, and here we report two rare cases of thoracic NMC with cytohistologic correlation. In aspiration cytology, the tumor presented with mixed cohesive clusters and dispersed single cells, diffuse background necrosis and many neutrophils. Most of the tumor cells had scanty cytoplasm and medium-sized irregular nuclei, which had fine to granular nuclear chromatin. Interestingly, a few dyskeratotic cells or squamoid cell clusters were present in each case. Biopsy specimen histology revealed more frequent squamous differentiation, and additional immunohistochemistry tests showed nuclear expression of NUT. Because this tumor has a notorious progression and has been previously underestimated in terms of its prevalence, awareness of characteristic findings and proper ancillary tests should be considered in all suspicious cases.

Background/Objectives: The tumor microenvironment (TME) has emerged as a significant prognostic factor. This study aimed to identify prognostic factors by combining clinicopathologic parameters and the TME biomarkers in patients who underwent surgery following neoadjuvant chemoradiotherapy (nCRT) for locally advanced rectal cancer (LARC). Methods: CD8⁺ T cells, CXCR3, CXCL10, and α-smooth muscle actin (α-SMA) were analyzed via immunohistochemical staining. We also incorporated AI-powered digital pathology to assess the spatial TME. The associations between these biomarkers, clinicopathologic parameters, and survival outcomes were evaluated. Results: CD8⁺ T cell expression, CXCR3 expression in tumor-infiltrating lymphocytes (TILs), and immune phenotypes were correlated. LARC patients with a high expression of CD8⁺ T cells, CXCR3 in TILs, and an inflamed phenotype had a significantly better prognosis than their counterparts did. In the multivariate analysis, the expression of CD8⁺ T cells and the inflamed/immune-excluded phenotype were significant tumor immune microenvironment (TiME) biomarkers for recurrence-free survival (RFS) but not for overall survival (OS). Notably, patients with the immune-desert phenotype had a poor prognosis regardless of pathologic stage, even if postoperative chemotherapy was administered (p < 0.001). Conclusions: CD8⁺ T cells and AI-powered immune phenotypes, alongside clinical factors, can guide personalized treatment in LARC patients receiving nCRT. A therapeutic strategy to modify the TiME after nCRT could help reduce recurrence after surgery.