Clinical Validation of Artificial Intelligence-Powered PD-L1 Tumor Proportion Score Interpretation for Immune Checkpoint Inhibitor Response Prediction in Non-Small Cell Lung Cancer.

PURPOSE: Evaluation of PD-L1 tumor proportion score (TPS) by pathologists has been very impactful but is limited by factors such as intraobserver/interobserver bias and intratumor heterogeneity. We developed an artificial intelligence (AI)-powered analyzer to assess TPS for the prediction of immune checkpoint inhibitor (ICI) response in advanced non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: The AI analyzer was trained with 393,565 tumor cells annotated by board-certified pathologists for PD-L1 expression in 802 whole-slide images (WSIs) stained by 22C3 pharmDx immunohistochemistry. The clinical performance of the analyzer was validated in an external cohort of 430 WSIs from patients with NSCLC. Three pathologists performed annotations of this external cohort, and their consensus TPS was compared with AI-based TPS. RESULTS: In comparing PD-L1 TPS assessed by AI analyzer and by pathologists, a significant positive correlation was observed (Spearman coefficient = 0.925; P < .001). The concordance of TPS between AI analyzer and pathologists according to TPS ≥50%, 1%-49%, and <1% was 85.7%, 89.3%, and 52.4%, respectively. In median progression-free survival (PFS), AI-based TPS predicted prognosis in the TPS 1%-49% or TPS <1% group better than the pathologist's reading, with the TPS ≥50% group as a reference (hazard ratio [HR], 1.49 [95% CI, 1.19 to 1.86] v HR, 1.36 [95% CI, 1.08 to 1.71] for TPS 1%-49% group, and HR, 2.38 [95% CI, 1.69 to 3.35] v HR, 1.62 [95% CI, 1.23 to 2.13] for TPS <1% group). CONCLUSION: PD-L1 TPS assessed by AI analyzer correlates with that of pathologists, with clinical performance also being comparable when referenced to PFS. The AI model can accurately predict tumor response and PFS of ICI in advanced NSCLC via assessment of PD-L1 TPS.

An artificial intelligence-powered PD-L1 combined positive score (CPS) analyser in urothelial carcinoma alleviating interobserver and intersite variability.

AIMS: Immune checkpoint inhibitors targeting programmed death-ligand 1 (PD-L1) have shown promising clinical outcomes in urothelial carcinoma (UC). The combined positive score (CPS) quantifies PD-L1 22C3 expression in UC, but it can vary between pathologists due to the consideration of both immune and tumour cell positivity. METHODS AND RESULTS: An artificial intelligence (AI)-powered PD-L1 CPS analyser was developed using 1,275,907 cells and 6175.42 mm2 of tissue annotated by pathologists, extracted from 400 PD-L1 22C3-stained whole slide images of UC. We validated the AI model on 543 UC PD-L1 22C3 cases collected from three institutions. There were 446 cases (82.1%) where the CPS results (CPS ≥10 or <10) were in complete agreement between three pathologists, and 486 cases (89.5%) where the AI-powered CPS results matched the consensus of two or more pathologists. In the pathologist's assessment of the CPS, statistically significant differences were noted depending on the source hospital (P = 0.003). Three pathologists reevaluated discrepancy cases with AI-powered CPS results. After using the AI as a guide and revising, the complete agreement increased to 93.9%. The AI model contributed to improving the concordance between pathologists across various factors including hospital, specimen type, pathologic T stage, histologic subtypes, and dominant PD-L1-positive cell type. In the revised results, the evaluation discordance among slides from different hospitals was mitigated. CONCLUSION: This study suggests that AI models can help pathologists to reduce discrepancies between pathologists in quantifying immunohistochemistry including PD-L1 22C3 CPS, especially when evaluating data from different institutions, such as in a telepathology setting.

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

BACKGROUND: Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations. METHODS: AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment. RESULTS: Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance. CONCLUSIONS: This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer.

Tumor-infiltrating lymphocytes (TIL) have been suggested as an important prognostic marker in colorectal cancer, but assessment usually requires additional tissue processing and interpretational efforts. The aim of this study is to assess the clinical significance of artificial intelligence (AI)-powered spatial TIL analysis using only a hematoxylin and eosin (H&E)-stained whole-slide image (WSI) for the prediction of prognosis in stage II-III colon cancer treated with surgery and adjuvant therapy. In this retrospective study, we used Lunit SCOPE IO, an AI-powered H&E WSI analyzer, to assess intratumoral TIL (iTIL) and tumor-related stromal TIL (sTIL) densities from WSIs of 289 patients. The patients with confirmed recurrences had significantly lower sTIL densities (mean sTIL density 630.2/mm2 in cases with confirmed recurrence vs. 1021.3/mm2 in no recurrence, p < 0.001). Additionally, significantly higher recurrence rates were observed in patients having sTIL or iTIL in the lower quartile groups. Risk groups defined as high-risk (both iTIL and sTIL in the lowest quartile groups), low-risk (sTIL higher than the median), or intermediate-risk (not high- or low-risk) were predictive of recurrence and were independently associated with clinical outcomes after adjusting for other clinical factors. AI-powered TIL analysis can provide prognostic information in stage II/III colon cancer in a practical manner.

Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes as a predictive biomarker for axitinib in adenoid cystic carcinoma.

BACKGROUND: This study analyzed the predictive value of artificial intelligence (AI)-powered tumor-infiltrating lymphocyte (TIL) analysis in recurrent or metastatic (R/M) adenoid cystic carcinoma (ACC) treated with axitinib. METHODS: Patients from a multicenter, prospective phase II trial evaluating axitinib efficacy in R/M ACC were included in this study. H&E whole-side images of archival tumor tissues were analyzed by Lunit SCOPE IO, an AI-powered spatial TIL analyzer. RESULTS: Twenty-seven patients were included in the analysis. The best response was stable disease, and the median progression-free survival (PFS) was 11.1 months (95% CI, 9.2-13.7 months). Median TIL densities in the cancer and surrounding stroma were 25.8/mm2 (IQR, 8.3-73.0) and 180.4/mm2 (IQR, 69.6-342.8), respectively. Patients with stromal TIL density >342.5/mm2 exhibited longer PFS (p = 0.012). CONCLUSIONS: Cancer and stromal area TIL infiltration were generally low in R/M ACC. Higher stromal TIL infiltration was associated with a longer PFS with axitinib treatment.

Deep learning model improves tumor-infiltrating lymphocyte evaluation and therapeutic response prediction in breast cancer.

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.

Artificial intelligence-powered programmed death ligand 1 analyser reduces interobserver variation in tumour proportion score for non-small cell lung cancer with better prediction of immunotherapy response.

BACKGROUND: Manual evaluation of programmed death ligand 1 (PD-L1) tumour proportion score (TPS) by pathologists is associated with interobserver bias. OBJECTIVE: This study explored the role of artificial intelligence (AI)-powered TPS analyser in minimisation of interobserver variation and enhancement of therapeutic response prediction. METHODS: A prototype model of an AI-powered TPS analyser was developed with a total of 802 non-small cell lung cancer (NSCLC) whole-slide images. Three independent board-certified pathologists labelled PD-L1 TPS in an external cohort of 479 NSCLC slides. For cases of disagreement between each pathologist and the AI model, the pathologists were asked to revise the TPS grade (<1%, 1%-49% and ≥50%) with AI assistance. The concordance rates among the pathologists with or without AI assistance and the effect of the AI-assisted revision on clinical outcome upon immune checkpoint inhibitor (ICI) treatment were evaluated. RESULTS: Without AI assistance, pathologists concordantly classified TPS in 81.4% of the cases. They revised their initial interpretation by using the AI model for the disagreement cases between the pathologist and the AI model (N = 91, 93 and 107 for each pathologist). The overall concordance rate among the pathologists was increased to 90.2% after the AI assistance (P < 0.001). A reduction in hazard ratio for overall survival and progression-free survival upon ICI treatment was identified in the TPS subgroups after the AI-assisted TPS revision. CONCLUSION: The AI-powered TPS analyser assistance improves the pathologists' consensus of reading and prediction of the therapeutic response, raising a possibility of standardised approach for the accurate interpretation.

Artificial Intelligence-Powered Spatial Analysis of Tumor-Infiltrating Lymphocytes as Complementary Biomarker for Immune Checkpoint Inhibition in Non-Small-Cell Lung Cancer.

PURPOSE: Biomarkers on the basis of tumor-infiltrating lymphocytes (TIL) are potentially valuable in predicting the effectiveness of immune checkpoint inhibitors (ICI). However, clinical application remains challenging because of methodologic limitations and laborious process involved in spatial analysis of TIL distribution in whole-slide images (WSI). METHODS: We have developed an artificial intelligence (AI)-powered WSI analyzer of TIL in the tumor microenvironment that can define three immune phenotypes (IPs): inflamed, immune-excluded, and immune-desert. These IPs were correlated with tumor response to ICI and survival in two independent cohorts of patients with advanced non-small-cell lung cancer (NSCLC). RESULTS: Inflamed IP correlated with enrichment in local immune cytolytic activity, higher response rate, and prolonged progression-free survival compared with patients with immune-excluded or immune-desert phenotypes. At the WSI level, there was significant positive correlation between tumor proportion score (TPS) as determined by the AI model and control TPS analyzed by pathologists (P < .001). Overall, 44.0% of tumors were inflamed, 37.1% were immune-excluded, and 18.9% were immune-desert. Incidence of inflamed IP in patients with programmed death ligand-1 TPS at < 1%, 1%-49%, and ≥ 50% was 31.7%, 42.5%, and 56.8%, respectively. Median progression-free survival and overall survival were, respectively, 4.1 months and 24.8 months with inflamed IP, 2.2 months and 14.0 months with immune-excluded IP, and 2.4 months and 10.6 months with immune-desert IP. CONCLUSION: The AI-powered spatial analysis of TIL correlated with tumor response and progression-free survival of ICI in advanced NSCLC. This is potentially a supplementary biomarker to TPS as determined by a pathologist.