Scholarlink

<p>Timely clinical intervention relies on the early as well as precise identification of lung cancer from histopathological images. This research introduces an Enhanced Multilayer Perceptron optimized via Artificial Gorilla Troops Optimization (EMLP-AGTO), designed as a streamlined as well as computationally effective substitute for traditional deep CNN methods. The system combines Wiener filtering to reduce noise as well as Local Tetra-Pattern (LTrP) descriptors to extract distinctive texture signatures from H&amp;E-stained slides. AGTO dynamically adjusts MLP parameters to ensure stable convergence as well as improve classification dependability. Tests conducted on the LC25000 dataset show robust as well as reliable effectiveness, attaining 99.89% accuracy, 99.86% precision, 99.91% sensitivity, and a 99.88% F1-score through five-fold cross-validation. Benchmarking additionally indicates that EMLP-AGTO trains 6–7 times quicker as well as achieves an inference speed of 2.1 ms per image, surpassing VGG16 and ResNet50 in computational efficiency. These findings emphasize the practical applicability of the suggested method for quick initial assessment in digital pathology processes. In summary, EMLP-AGTO functions as an interpretable as well as resource-effective tool for decision support that can enhance diagnostic efficiency in clinical environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Utilising a New Improved Multi-Layer Perceptron-based Artificial Gorilla Troops Optimiser Algorithm for Biomedical Image Analysis to Detect Lung Cancer

  • 期刊论文

  • 发表日期：

    2026年6月3日

查看全文
  • D. Devarajan,
  • R. Radha,
  • S. Sivakumar,
  • S. Senthilkumar

摘要

Timely clinical intervention relies on the early as well as precise identification of lung cancer from histopathological images. This research introduces an Enhanced Multilayer Perceptron optimized via Artificial Gorilla Troops Optimization (EMLP-AGTO), designed as a streamlined as well as computationally effective substitute for traditional deep CNN methods. The system combines Wiener filtering to reduce noise as well as Local Tetra-Pattern (LTrP) descriptors to extract distinctive texture signatures from H&E-stained slides. AGTO dynamically adjusts MLP parameters to ensure stable convergence as well as improve classification dependability. Tests conducted on the LC25000 dataset show robust as well as reliable effectiveness, attaining 99.89% accuracy, 99.86% precision, 99.91% sensitivity, and a 99.88% F1-score through five-fold cross-validation. Benchmarking additionally indicates that EMLP-AGTO trains 6–7 times quicker as well as achieves an inference speed of 2.1 ms per image, surpassing VGG16 and ResNet50 in computational efficiency. These findings emphasize the practical applicability of the suggested method for quick initial assessment in digital pathology processes. In summary, EMLP-AGTO functions as an interpretable as well as resource-effective tool for decision support that can enhance diagnostic efficiency in clinical environments.