Automatic Glands Segmentation in Histological Images Obtained by Endoscopic Biopsy From Various Parts of the Colon

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2

2020

Glands segmentation is a very important and yet challenging problem of histological images analysis. Accurate segmentation of mucous glands is a crucial step to obtain reliable morphological statistics and is necessary for the development of high-quality diagnostic algorithms, which are an integral part of timely medical care. In this paper we propose a two-stage segmentation method, which predicts the probability maps of glands boundaries in histological images based on a priori knowledge about the geometric shape of the mucous glands and uses a convolutional neural network (CNN) model to get the final segmentation result based on the predicted probability maps. The proposed method demonstrates good results in separating adjacent glands, which is one of the most challenging aspects in automatic segmentation of histological glands and one of the most complicated for algorithms based on applying convolutional neural networks. The evaluation of the proposed algorithm was performed with Warwick-QU dataset, which contains real histological images of colon tissue.

“…The continuation of this research will include enhancing the prediction of glands contours maps and evaluating the method on PATH-DT-MSU [16,17] dataset.…”

Section: Discussionmentioning

confidence: 99%

Adaptive Method of Glands Segmentation on Histological Images

Kosov

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2

2020

“…The testing and evaluation of the proposed interactive segmentation method was performed on a S1 subset of a histological medical imaging dataset PATH-DT-MSU [7,8]. S1 subset of PATH-DT-MSU dataset (http://imaging.cs.msu.ru/en/research/histology/path-dt-msu) consists of 60 images obtained from hematoxylin and eosin staining of paraffin sections of colon biopsy material.…”

Section: Used Dataset and User Interaction Detailsmentioning

confidence: 99%

Semi-automatic Algorithm for Lumen Segmentation in Histological Images

Pochernina

Proceedings of the 32nd International Conference on Computer Graphics and Vision

2022

In this paper we focus on a problem of lumen segmentation in histological images. A large number of annotated images are necessary for the development of diagnostic algorithms that can help to detect changes, such as lumen serration, indicating really serious health problems like cancer. We propose a semi-automatic interactive segmentation algorithm to accelerate the process of manual image annotation. The core of our annotation approach is a classical graph-cut algorithm that uses manually selected parameters. The user annotates an image with two types of scribbles corresponding to the gland lumen structure and the non-lumen area. After that, the model annotates all unlabeled pixels, providing the user with a fully annotated image based on the scribbled input data. The user can interact with the annotation algorithm and add new scribbles to adjust the result. The algorithm allows to reduce the annotation time of a typical histological image by 10 times for the PATH-DT-MSU dataset that can potentially seriously increase the number of fully annotated histological images.

“…The third dataset is the subset of PATH-DT-MSU dataset [6,7], containing 7 H&E whole slide histological images of digestive tract tumors. Each WSI image is a full-thickness fragment of the stomach wall, cut from the surgical material, and includes areas of adenocarcinoma, adjacent areas of visually unchanged lamina propria and the underlying layers of the stomach wall (muscularis mucosae, submucosa, own muscle layer, subserous areas).…”

Section: Used Datamentioning

confidence: 99%

Tissue Type Recognition in Whole Slide Histological Images

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

Михайлов

et al. 2021

Automatic layers recognition of the wall of the stomach and colon on whole slide images is an extremely urgent task in digital pathology as it can be used for automatic determining the depth of invasion of the digestive tract tumors. In this paper we propose a new CNN-based method of automatic tissue type recognition on whole slide histological images. We also describe an effective pipeline of training that uses 2 different training datasets. The proposed method of automatic tissue type recognition achieved 0.929 accuracy and 0.903 balanced accuracy on CRC-VAL-HE-7K dataset for 9-types classification and 0.98 accuracy and 0.926 balanced accuracy on the test subset of whole slide images from PATH-DT- MSU dataset for 5-types classification. The developed method makes it possible to classify the areas corresponding to the gastric own mucous glands in the lamina propria and also to distinguish the tubular structures of a highly differentiated gastric adenocarcinoma with normal glands.