Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering

Abstract

Deep learning models are increasingly being used to interpret whole-slide images (WSIs) in digital pathology and to predict genetic mutations. Currently, it is commonly assumed that tumor regions have most of the predictive power. However, it is reasonable to assume that other tissues from the tumor microenvironment may also provide important predictive information. In this paper, we propose an unsupervised clustering-based multiple-instance deep learning model for the prediction of genetic mutations using WSIs of three cancer types obtained from The Cancer Genome Atlas. Our proposed model facilitates the identification of spatial regions related to specific gene mutations and exclusion of patches that lack predictive information through the use of unsupervised clustering. This results in a more accurate prediction of gene mutations when compared with models using all image patches on WSIs and two recently published algorithms for all three different cancer types evaluated in this study. In addition, our study validates the hypothesis that the prediction of gene mutations solely based on tumor regions on WSI slides may not always provide the best performance. Other tissue types in the tumor microenvironment could provide a better prediction ability than tumor tissues alone. These results highlight the heterogeneity in the tumor microenvironment and the importance of identification of predictive image patches in digital pathology prediction tasks.

Deep learning-empowered crop breeding: intelligent, efficient and promising

“…Furthermore, models trained in one species can be directly applied to closely related species ( Kelley, 2020 ), due to the conservation of molecular processes in closely related species. Chen et al. (2023) proposed an unsupervised clustering method and developed a deep learning model accordingly to predict gene mutations.…”

Application of Deep Learning in Histopathology Images of Breast Cancer: A Review

“…Although various unsupervised clustering applications have been developed in digital pathology, few studies have evaluated the use of unsupervised clustering to identify image patches related to gene mutation. Chen et al [192] proposed a multi-instance learning method based on unsupervised clustering and developed an in-depth learning model using WSIs of three common cancer types obtained from the Cancer Genome Map (TCGA) to optimize the prediction of genetic mutation.…”

“…Attention mechanism simulates human visual behavior by applying different weights to images. This method can highlight the key areas and non key areas in pathological images, thus improving the prediction results of the model [181] Based on ResNet and attention mechanism, a method for predicting pathological gene subtypes of breast cancer is proposed [183] KNN and K-means Use unsupervised clustering method to reduce the workload of manual labeling by pathologists Unsupervised [192]…”

Deep-GenMut: Automated genetic mutation classification in oncology: A deep learning comparative study

“…The identification and analysis of cancer-causing genes is crucial in the field of clinical trials [ 13 ]. Currently, physicians have to manually evaluate and categorize individual mutated genes by analyzing the information contained in the clinical literature in text format [ 14 , 15 ]. However, although the manual process of interpreting genomics for gene classification is critical to saving lives [ 16 , 17 ], it is challenging as it is both time-consuming and subjective.…”