Region of Interest Identification in the Cervical Digital Histology Images

Abstract

The region of interest (RoI) identification has a significant potential for yielding information about relevant histological features and is imperative to improve the effectiveness of digital pathology in clinical practice. The typical RoI is the stratified squamous epithelium (SSE) that appears on relatively small image areas. Hence, taking the entire image for classification adds noise caused by irrelevant background, making classification networks biased towards the background fragments. This paper proposes a novel approach for epithelium RoI identification based on automatic bounding boxes (bb) construction and SSE extraction and compares it with state-of-the-art histology RoI localization and detection techniques. Further classification of the extracted epithelial fragments based on DenseNet made it possible to effectively identify the SSE RoI in cervical histology images (CHI). The design brings significant improvement to the identification of diagnostically significant regions. For this research, we created two CHI datasets, the CHI-I containing 171 color images of the cervical histology microscopy and CHI-II containing 1049 extracted fragments of microscopy, which are the most considerable publicly available SSE datasets.

An Integrated Approach to Automated Diagnosis of Cervical Intraepithelial Neoplasia in Digital Histology Images

“…For this study, we used 1715 images from two datasets, own the CHI dataset [3] and samples obtained from the MTCHI dataset [4], to augment the CHI. MTCHI samples were derived from 80 digital images of histology whole slide images (WHI).…”

Cervical Intraepithelial Neoplasia Grading from Prepared Digital Histology Images

“…Resulting patches were evaluated and checked for any inconsistencies. Phase I has been comprehensively detailed in [6]. In Phase II, the focus of this paper, the research protocol necessitated the inclusion of supplementary patches to increase sample variety.…”

“…The CHI dataset [6] includes SSE patches obtained from glass slides images, 357 patch images from 38 CIN 1 and 443 patch images from 58 CIN 2 grade. The MTCHI samples were derived from 80 digital whole slide images (WHI).…”