Scholarlink

<p>Detecting prostate cancer at an early stage in improper way can lead to overdiagnosis and overtreatment, potentially causing unnecessary anxiety and reduced quality of life for patients with slow-growing tumors that may never become life-threatening. As a result, there is a growing need for more reliable and precise detection methods that can minimize diagnostic errors and ensure better clinical decision-making. In this work, an advanced model named Cavier Groupers and Moray Eels enabled Graph Based Adaptive Regularized Learning Network (CGME-based GARLNet) is devised for detecting prostate cancer. This model improves detection accuracy while reducing costs and minimizing invasive procedures. The input MRI image is pre-processed utilizing an arithmetic mean filter. Then, affected area is segmented using Density Peak Clustering (DPC). Moreover, SqueezeNet features are extracted and cancer is finally detected using GARLNet, which is trained by CGME. The CGME is the integration of GME and Conditional Autoregressive Value-at-Risk (CaViar). The efficacy of CGME-based GARLNet is examined by assuming the metrics, like accuracy, sensitivity as well as specificity that yielded maximum values of 96.55%, 95.50% as well as 97.84%.</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

Cavier groupers and Moray Eels optimization algorithm enabled graph based adaptive regularized learning deep network for prostate cancer detection

  • 期刊论文

  • 发表日期：

    2025年12月5日

查看全文
  • Gyoo-Soo Chae

摘要

Detecting prostate cancer at an early stage in improper way can lead to overdiagnosis and overtreatment, potentially causing unnecessary anxiety and reduced quality of life for patients with slow-growing tumors that may never become life-threatening. As a result, there is a growing need for more reliable and precise detection methods that can minimize diagnostic errors and ensure better clinical decision-making. In this work, an advanced model named Cavier Groupers and Moray Eels enabled Graph Based Adaptive Regularized Learning Network (CGME-based GARLNet) is devised for detecting prostate cancer. This model improves detection accuracy while reducing costs and minimizing invasive procedures. The input MRI image is pre-processed utilizing an arithmetic mean filter. Then, affected area is segmented using Density Peak Clustering (DPC). Moreover, SqueezeNet features are extracted and cancer is finally detected using GARLNet, which is trained by CGME. The CGME is the integration of GME and Conditional Autoregressive Value-at-Risk (CaViar). The efficacy of CGME-based GARLNet is examined by assuming the metrics, like accuracy, sensitivity as well as specificity that yielded maximum values of 96.55%, 95.50% as well as 97.84%.