Advancements in medical image segmentation: A review of transformer models DOI

S. S. Kumar

Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110099 - 110099

Published: Jan. 22, 2025

Language: Английский

Medical steganography: Enhanced security and image quality, and new S-Q assessment DOI
Yuxiang Peng,

Chong Fu,

Yu Zheng

et al.

Signal Processing, Journal Year: 2024, Volume and Issue: 223, P. 109546 - 109546

Published: May 19, 2024

Language: Английский

Citations

4

Automatic Segmentation of Cervical Cells Based on Star-Convex Polygons in Pap Smear Images DOI Creative Commons
Yanli Zhao, Chong Fu, Wenchao Zhang

et al.

Bioengineering, Journal Year: 2022, Volume and Issue: 10(1), P. 47 - 47

Published: Dec. 30, 2022

Cervical cancer is one of the most common cancers that threaten women's lives, and its early screening great significance for prevention treatment cervical diseases. Pathologically, accurate segmentation cells plays a crucial role in diagnosis cancer. However, frequent presence adherent or overlapping Pap smear images makes separating them individually difficult task. Currently, there are few studies on cells, existing methods commonly suffer from low accuracy complex design processes. To address above problems, we propose novel star-convex polygon-based convolutional neural network with an encoder-decoder structure, called SPCNet. The model accomplishes relying three steps: automatic feature extraction, polygon detection, non-maximal suppression (NMS). Concretely, new residual-based attentional embedding (RAE) block suggested image extraction. It fuses deep features attention-based layers shallow original through residual connection, enhancing network's ability to extract abundant features. And then, adaptive NMS (PA-NMS) algorithm adopted screen generated proposals further achieve detection thus allowing completely segment cell instances images. Finally, effectiveness our method evaluated independent datasets. Extensive experimental results demonstrate obtains superior performance compared other well-established algorithms.

Language: Английский

Citations

17

Effectiveness of encoder-decoder deep learning approach for colorectal polyp segmentation in colonoscopy images DOI Creative Commons
Ameer Hamza, Muhammad Bilal, Muhammad Ramzan

et al.

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(4)

Published: Jan. 10, 2025

Language: Английский

Citations

0

从U-Net到Transformer:混合模型在医学图像分割中的应用进展 DOI

尹艺晓 Yin Yixiao,

马金刚 Ma Jingang,

张文凯 Zhang Wenkai

et al.

Laser & Optoelectronics Progress, Journal Year: 2025, Volume and Issue: 62(2), P. 0200001 - 0200001

Published: Jan. 1, 2025

Citations

0

Advancements in medical image segmentation: A review of transformer models DOI

S. S. Kumar

Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110099 - 110099

Published: Jan. 22, 2025

Language: Английский

Citations

0