Computer-Aided Diagnosis of Low Grade Endometrial Stromal Sarcoma (LGESS)

TL;DR

This study explores machine learning and deep learning techniques to improve the diagnosis of low grade endometrial stromal sarcoma from uterine tissue images, achieving around 87% accuracy.

Contribution

It introduces a pipeline combining image preprocessing with classification models, demonstrating the effectiveness of deep learning in LGESS diagnosis.

Findings

Deep learning models outperform classic machine learning methods.

Best accuracy achieved is approximately 87%.

Preprocessing improves classification performance.

Abstract

Low grade endometrial stromal sarcoma (LGESS) is rare form of cancer, accounting for about 0.2% of all uterine cancer cases. Approximately 75% of LGESS patients are initially misdiagnosed with leiomyoma, which is a type of benign tumor, also known as fibroids. In this research, uterine tissue biopsy images of potential LGESS patients are preprocessed using segmentation and staining normalization algorithms. A variety of classic machine learning and leading deep learning models are then applied to classify tissue images as either benign or cancerous. For the classic techniques considered, the highest classification accuracy we attain is about 0.85, while our best deep learning model achieves an accuracy of approximately 0.87. These results indicate that properly trained learning algorithms can play a useful role in the diagnosis of LGESS.