A Heuristic Strategy Assisted Deep Learning Models for Brain Tumor Classification and Abnormality Segmentation

Computational Intelligence, Journal Year: 2025, Volume and Issue: 41(1)

Published: Jan. 13, 2025

ABSTRACT Brain tumors are prevalent forms of malignant neoplasms that, depending on their type, location, and grade, can significantly reduce life expectancy due to invasive nature potential for rapid progression. Accordingly, brain classification is an essential step that allows doctors perform appropriate treatment. Many studies have been done in the sector medical image processing by employing computational methods effectively segment classify tumors. However, larger amount information collected healthcare images prohibits manual segmentation process a reasonable time frame, reducing error measures settings. Therefore, automated efficient techniques crucial. In addition, various visual information, noisy images, occlusion, uneven textures, confused objects, other features may impact process. implementation deep learning provides remarkable results medicinal processing, particularly conventional learning‐assisted struggle with complex structures dimensional issues. Thus, this paper develops effective technique diagnosing The main aspect proposed system tumor types segmenting affected regions raw images. This novel approach be applied applications like diagnostic centers, decision‐making tools, clinical trials, research institutes, disease prognosis, so on. Initially, requisite from standard datasets further, it subjected period. stage, Multi‐scale Dilated TransUNet++ (MDTUNet++) model employed abnormalities. Further, segmented given into Adaptive Dense Residual Attention Network (ADDRAN) types. Here, optimize ADDRAN technique's parameters, Improved Hermit Crab Optimizer (IHCO) supported, which increases accuracy rates overall network. Finally, numerical examination conducted guarantee robustness usefulness designed contrasting related techniques. For Dataset 1, value attains 93.71 work compared 87.86 CNN, 90.18 DenseNet, 89.56 90.96 RAN DRAN, respectively. supremacy has achieved recommended while detecting

Language: Английский

Boundary aware microscopic hyperspectral pathology image segmentation network guided by information entropy weight

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: March 27, 2025

Introduction Accurate segmentation of lesion tissues in medical microscopic hyperspectral pathological images is crucial for enhancing early tumor diagnosis and improving patient prognosis. However, the complex structure indistinct boundaries present significant challenges achieving precise segmentation. Methods To address these challenges, we propose a novel method named BE-Net. It employs multi-scale strategy edge operators to capture fine details, while incorporating information entropy construct attention mechanisms that further strengthen representation relevant features. Specifically, first Laplacian Gaussian operator convolution boundary feature extraction block, which encodes gradient through improved detection emphasizes channel weights based on weighting. We designed grouped module optimize fusion process between encoder decoder, with goal details emphasizing representations. Finally, spatial block guide model most important locations regions. Result evaluate BE-Net image datasets gastric intraepithelial neoplasia mucosal intestinal metaplasia. Experimental results demonstrate outperforms other state-of-the-art methods terms accuracy preservation. Discussion This advance has implications field MHSIs Our code freely available at https://github.com/sharycao/BE-NET .

Language: Английский

Boundary Aware Microscopic Hyperspectral Pathology Image Segmentation Network Guided by Information Entropy Weight

Published: Jan. 1, 2024

Language: Английский