Quantitative Assessment of Tumor-Infiltrating Lymphocytes Using Machine Learning Predicts Survival in Muscle-Invasive Bladder Cancer

Abstract

(1) Purpose: Although assessment of tumor-infiltrating lymphocytes (TILs) has been acknowledged to have important predictive prognostic value in muscle-invasive bladder cancer (MIBC), it is limited by inter- and intra-observer variability, hampering widespread clinical application. We aimed to evaluate the prognostic value of quantitative TILs score based on a machine learning (ML) algorithm to identify MIBC patients who might benefit from immunotherapy or the de-escalation of therapy. (2) Methods: We constructed an artificial neural network classifier for tumor cells, lymphocytes, stromal cells, and “ignore” cells from hematoxylin-and-eosin-stained slide images using the QuPath open source software. We defined four unique TILs variables based on ML to analyze TILs measurements. Pathological slide images from 133 MIBC patients were retrospectively collected as the discovery set to determine the optimal association of ML-read TILs variables with patient survival outcomes. For validation, we evaluated an independent external validation set consisting of 247 MIBC patients. (3) Results: We found that all four TILs variables had significant prognostic associations with survival outcomes in MIBC patients (p < 0.001 for all comparisons), with higher TILs score being associated with better prognosis. Univariate and multivariate Cox regression analyses demonstrated that electronic TILs (eTILs) variables were independently associated with overall survival after adjustment for clinicopathological factors including age, sex, and pathological stage (p < 0.001 for all analyses). Results analyzed in different subgroups showed that the eTILs variable was a strong prognostic factor that was not redundant with pre-existing clinicopathological features (p < 0.05 for all analyses). (4) Conclusion: ML-driven cell classifier-defined TILs variables were robust and independent prognostic factors in two independent cohorts of MIBC patients. eTILs have the potential to identify a subset of high-risk stage II or stage III-IV MIBC patients who might benefit from adjuvant immunotherapy.

Recent Advancements in Deep Learning Using Whole Slide Imaging for Cancer Prognosis

“…A considerable number of investigations have also employed variations of CNN, often categorized under the umbrella term of general deep learning. This group includes diverse studies by Liang et al [ 55 ], Zheng et al [ 49 ], and Jiang et al [ 48 ]. Residual networks, a form of CNN, have been frequently implemented, as seen in works by Liu et al [ 69 ], Wu et al [ 72 ], and Knuutila et al [ 76 ], who utilized the ResNet model due to its ability to effectively train very deep neural networks.…”

“…Bladder cancer and liver cancer have also been areas of significant research, with eight and five studies, respectively. Zheng et al [ 49 ] utilized deep learning with WSIs for bladder cancer prognosis, demonstrating the potential for more personalized treatments. For liver cancer, Saillard et al [ 54 ] leveraged deep learning models to uncover intricate patterns in WSIs, contributing to improved understanding of the disease’s progression.…”

“…The role of cellular composition, particularly TILs, in predicting cancer prognosis has been another significant research theme. Xu et al [ 32 ] examined the prognostic impact of TIL spatial distribution in colorectal cancer, whereas Zheng et al [ 49 ] used an artificial neural network classifier to identify tumor cells, lymphocytes, and stromal cells, underlining the prognostic value of electronic TIL variables in bladder cancer. Furthermore, Balkenhol et al [ 40 ] utilized a convolutional neural network to investigate the role of TILs in the prognosis of triple-negative breast cancer.…”

Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study

“…Deep learning, a technique in the field of artificial intelligence (AI) that can identify subtle patterns in complex pathological images, has broad applications in computational pathology [17]. In bladder cancer, AI-based methods can be used to detect histological patterns such as malignant tumor potential [18], tumor stroma ratio [19], and tumorinfiltrating lymphocytes [20], and have been used to predict molecular subtypes [21] and overall survival [22,23]. In breast cancer [24], colorectal cancer [25][26][27], and prostate cancer [28], deep learning has successfully predicted the LNM status from primary tumor specimens.…”