Medical image segmentation with UNet-based multi-scale context fusion

• Published in: Scientific reports 2024-10, Vol.14 (1), p.15687-9, Article 15687
• Main Authors: Yuan, Yongqi, Cheng, Yong
• Format: Article
• Language: English
• Subjects: 631/114; 639/705/117; 692/4028; Algorithms; Diagnostic Imaging - methods; Humanities and Social Sciences; Humans; Image Interpretation, Computer-Assisted - methods; Image processing; Image Processing, Computer-Assisted - methods; multidisciplinary; Neoplasms - diagnostic imaging; Neoplasms - pathology; Science; Science (multidisciplinary); Semantics
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-66585-x

Histopathological examination holds a crucial role in cancer grading and serves as a significant reference for devising individualized patient treatment plans in clinical practice. Nevertheless, the distinctive features of numerous histopathological image targets frequently contribute to suboptimal segmentation performance. In this paper, we propose a UNet-based multi-scale context fusion algorithm for medical image segmentation, which extracts rich contextual information by extracting semantic information at different encoding stages and assigns different weights to the semantic information at different scales through TBSFF module to improve the learning ability of the network for features. Through multi-scale context fusion and feature selection networks, richer semantic features and detailed information are extracted. The target can be more accurately segmented without significantly increasing the extra overhead. The results demonstrate that our algorithm achieves superior Dice and IoU scores with a relatively small parameter count. Specifically, on the GlaS dataset, the Dice score is 90.56, and IoU is 83.47. For the MoNuSeg dataset, the Dice score is 79.07, and IoU is 65.98.