Fast Medical Image Auto-segmentation for Bleeding Gastric Tissue Detection based on Deep DuS-KFCM Clustering

BackgroundDetection and classification of gastric bleeding tissues are one of the challenging tasks in endoscopy image analysis. Lesion detection plays an important role in gastric cancer (GC) diagnosis and follow-up. Manual segmentation of endoscopy images is a very time-consuming task and subject to intra- and interrater variability. Accurate GB segmentation in abdominal sequences is an essential and crucial task for surgical planning and navigation in gastric lesion ablation. However, GB segmentation in endoscope is a substantially challenging work because the intensity values of gastric blood are similar to those of adjacent structures. ObjectiveIn this paper the idea is to combine two parts: Neural Network and Fuzzy Logic--Hybrid Neuro-Fuzzy system. The objective of this manuscript is to provide an efficient way to segment the gastric bleeding lesion area. This work focuses on design and development of an automated diagnostic system using gastric bleeding cancer endoscopy images. MethodsIn this paper, a coarse-to-fine method was applied to segment gastric bleeding lesion from endoscopy images, which consists of two stages including rough segmentation and refined segmentation. The rough segmentation is based on a kernel fuzzy C-means algorithm with spatial information (SKFCM) algorithm combined with spatial gray level co-occurrence matrix (GLCM) and the refined segmentation is implemented with deeplabv3+ (backbone with resnet50) algorithm to improve the overall accuracy. ResultsExperimental results for gastric bleeding segmentation show that the method provides an accuracy of 87.9476% with specificity of 96.3343% and performs better than other related methods. onclusionsThe performance of the method was evaluated using two benchmark datasets: The GB Segmentation and the healthy datasets. Then use the gastric red spots (GRS) dataset to do the final test to verify weak bleeding symptoms. Our method achieves high accuracy in gastric bleeding lesion segmentation. The work describes an innovative way of using GLCM based textural features to extract underlying information in gastric bleeding cancer imagery. Modified deep DuS-KFCM endoscopy image segmentation method based on GLCM feature, The experimental results shown to be effective in image segmentation and has good performance of resisting noise, segmentation effect more ideal.