ETiSeg-Net: edge-aware self attention to enhance tissue segmentation in histopathological images DOI Creative Commons

R Rashmi,

S Girisha

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Дек. 23, 2024

Abstract Digital pathology employing Whole Slide Images (WSIs) plays a pivotal role in cancer detection. Nevertheless, the manual examination of WSIs for identification various tissue regions presents formidable challenges due to its labor-intensive nature and subjective interpretation. Convolutional Neural Network (CNN) based semantic segmentation algorithms have emerged as valuable tools assisting this task by automating ROI delineation. The incorporation attention modules carefully designed loss functions has shown promise further augmenting performance these algorithms. However, there exists notable gap research regarding utilization specifically segmentation, thereby constraining our comprehension application context. This study introduces ETiSeg-Net (Edge-aware self enhance Tissue Segmentation), CNN-based model that uses novel edge-based module achieve effective delineation class boundaries. In addition, an innovative iterative training strategy is devised efficiently optimize parameters. also conducts comprehensive investigation into impact on efficacy models. Qualitative quantitative evaluations models are conducted using publicly available datasets. findings underscore potential enhancing accuracy effectiveness segmentation.

Язык: Английский

Modified U-Net with attention gate for enhanced automated brain tumor segmentation DOI
Shoffan Saifullah, Rafał Dreżewski, Anton Yudhana

и другие.

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

Язык: Английский

Процитировано

1
Design of an Optimal Convolutional Neural Network Architecture for MRI Brain Tumor Classification by Exploiting Particle Swarm Optimization DOI Creative Commons

Sofia El Amoury,

Youssef Smili,

Youssef Fakhri

и другие.

Journal of Imaging, Год журнала: 2025, Номер 11(2), С. 31 - 31

Опубликована: Янв. 24, 2025

The classification of brain tumors using MRI scans is critical for accurate diagnosis and effective treatment planning, though it poses significant challenges due to the complex varied characteristics tumors, including irregular shapes, diverse sizes, subtle textural differences. Traditional convolutional neural network (CNN) models, whether handcrafted or pretrained, frequently fall short in capturing these intricate details comprehensively. To address this complexity, an automated approach employing Particle Swarm Optimization (PSO) has been applied create a CNN architecture specifically adapted MRI-based tumor classification. PSO systematically searches optimal configuration architectural parameters—such as types numbers layers, filter quantities neuron fully connected layers—with objective enhancing accuracy. This performance-driven method avoids inefficiencies manual design iterative trial error. Experimental results indicate that PSO-optimized achieves accuracy 99.19%, demonstrating potential improving diagnostic precision medical imaging applications underscoring value search advancing healthcare technology.

Язык: Английский

Процитировано

1
Automatic Glioma Segmentation Based on Efficient U-Net Model using MRI Images DOI Creative Commons
Yessine Amri, Amine Ben Slama, Zouhair Mbarki

и другие.

Intelligence-Based Medicine, Год журнала: 2025, Номер unknown, С. 100216 - 100216

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Advanced brain tumor segmentation using DeepLabV3Plus with Xception encoder on a multi-class MR image dataset DOI
Shoffan Saifullah, Rafał Dreżewski, Anton Yudhana

и другие.

Multimedia Tools and Applications, Год журнала: 2025, Номер unknown

Опубликована: Фев. 21, 2025

Язык: Английский

Процитировано

0
ETiSeg-Net: edge-aware self attention to enhance tissue segmentation in histopathological images DOI Creative Commons

R Rashmi,

S Girisha

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Дек. 23, 2024

Abstract Digital pathology employing Whole Slide Images (WSIs) plays a pivotal role in cancer detection. Nevertheless, the manual examination of WSIs for identification various tissue regions presents formidable challenges due to its labor-intensive nature and subjective interpretation. Convolutional Neural Network (CNN) based semantic segmentation algorithms have emerged as valuable tools assisting this task by automating ROI delineation. The incorporation attention modules carefully designed loss functions has shown promise further augmenting performance these algorithms. However, there exists notable gap research regarding utilization specifically segmentation, thereby constraining our comprehension application context. This study introduces ETiSeg-Net (Edge-aware self enhance Tissue Segmentation), CNN-based model that uses novel edge-based module achieve effective delineation class boundaries. In addition, an innovative iterative training strategy is devised efficiently optimize parameters. also conducts comprehensive investigation into impact on efficacy models. Qualitative quantitative evaluations models are conducted using publicly available datasets. findings underscore potential enhancing accuracy effectiveness segmentation.

Язык: Английский

Процитировано

0