A hyperspectral dataset of precancerous lesions in gastric cancer and benchmarks for pathological diagnosis.

Abstract

Gastric cancer (GC) is one of the most common cancers worldwide. A lot of studies have found that early GC has good prognosis. Unfortunately, the diagnosis rate of early GC is suboptimal due to inadequate disease screening and the insidious nature of early lesions. Pathological diagnosis is usually regarded as the "gold standard" for the diagnosis of GC. However, traditional pathological diagnosis is tedious and time-consuming. With the development of deep learning, computer-aided diagnosis is widely used to assist pathologists for diagnosis. As conventional pathology, diagnosis is based on color images, it is not as informative as hyperspectral imaging, which introduces spectroscopy into imaging techniques. This article combines microscopic hyperspectral image (HSI) with deep learning networks to assist in the diagnosis of precancerous lesions in gastric cancer (PLGC). A large scale microscopic hyperspectral PLGC dataset with 924 effective scenes is built and self-supervised learning is adopted to provide pretrained models for HSI. These pretrained models effectively improve the performance of downstream classification tasks. Furthermore, a symmetrically deep connected network is proposed to train with images from different imaging modalities and improve the diagnostic accuracy to 96.59%.