Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors.

Cher-Wei Liang,Hsuan-Ying Huang,Chung-Ming Lo,Pei-Wei Fang

doi:10.3390/cancers13225787

Abstract

Simple SummaryIn this study, we established four convolutional neural network (DCNN) models (AlexNet, ResNet101, DenseNet201, and InceptionV3) to predict drug-sensitive mutations from images of tissues with gastrointestinal stromal tumors. The treatment of these tumors depends on the mutational subtype of the KIT/PDGFRA genes. Previous studies rarely focused on mesenchymal tumors and mutational subtypes. More than 5000 images of 365 GISTs from three independent laboratories were used to generate the model. DenseNet201 achieved an accuracy of 87% while the accuracies of AlexNet, InceptionV3, and ResNet101 were 75%, 81%, and 86%, respectively. Cross-institutional inconsistency and the contributions of image color and subcellular components were studied and analyzed.Gastrointestinal stromal tumors (GIST) are common mesenchymal tumors, and their effective treatment depends upon the mutational subtype of the KIT/PDGFRA genes. We established deep convolutional neural network (DCNN) models to rapidly predict drug-sensitive mutation subtypes from images of pathological tissue. A total of 5153 pathological images of 365 different GISTs from three different laboratories were collected and divided into training and validation sets. A transfer learning mechanism based on DCNN was used with four different network architectures, to identify cases with drug-sensitive mutations. The accuracy ranged from 87% to 75%. Cross-institutional inconsistency, however, was observed. Using gray-scale images resulted in a 7% drop in accuracy (accuracy 80%, sensitivity 87%, specificity 73%). Using images containing only nuclei (accuracy 81%, sensitivity 87%, specificity 73%) or cytoplasm (accuracy 79%, sensitivity 88%, specificity 67%) produced 6% and 8% drops in accuracy rate, respectively, suggesting buffering effects across subcellular components in DCNN interpretation. The proposed DCNN model successfully inferred cases with drug-sensitive mutations with high accuracy. The contribution of image color and subcellular components was also revealed. These results will help to generate a cheaper and quicker screening method for tumor gene testing.

Highlights

Mutational analysis of cancer cells is a key, and usually rate-determining, step in targeted therapy
The aim of this study was to determine whether cases with drug-sensitive KIT exon 11 mutations could be predicted by the deep learning system directly from tumor cell morphology
Testing the best Lab 1 DenseNet model on the datasets from the Lab 2 and Lab 3 produced a testing accuracy ranging from 65% to 66%, and the model accuracy trained individually on datasets from the Lab 2 and Lab 3 ranged from 79% to 94% (Table 3)

Summary

Introduction

Mutational analysis of cancer cells is a key, and usually rate-determining, step in targeted therapy. While morphology is the basis for diagnosis, genes are usually the major determinant of treatment. Several studies have addressed this issue of morphology–genotype correlation in cancers [1,2,3,4,5,6]. In these studies, researchers primarily focused on identifying the presence of specific mutations within carcinomas, without taking into account the knowledge that, in some circumstances, the mutational subtype, not merely the presence or absence of a mutation, is the main determinant of effective treatment

Objectives

Methods

Results

Discussion

Conclusion