利用深度递归神经网络进行鸟类松鼠优化以检测前列腺癌

IF 1.4 4区工程技术 Q2 ENGINEERING, MULTIDISCIPLINARY

International Journal for Multiscale Computational Engineering Pub Date : 2024-07-01 DOI:10.1615/intjmultcompeng.2024050495

Goddumarri Vijay Kumar, Mohammed Ismail B, Bhaskara Reddy T, Mansour Tahernezhadi, Mansoor Alam

{"title":"利用深度递归神经网络进行鸟类松鼠优化以检测前列腺癌","authors":"Goddumarri Vijay Kumar, Mohammed Ismail B, Bhaskara Reddy T, Mansour Tahernezhadi, Mansoor Alam","doi":"10.1615/intjmultcompeng.2024050495","DOIUrl":null,"url":null,"abstract":"Prostate cancer is solid organ melanoma which increases mortality amongst humans. Automatic techniques for determining prostate cancer from magnetic resonance images (MRI) are highly recommended. Conventional techniques adapt different steps, which may result in huge computational costs. In order to perform automated prostate cancer classification with MRI, a deep model is developed in this research. Here, the MRI noise is removed using a Non-local Means (NLM) filter. Convolution neural networks (CNN) are also widely used to create segments in order to extract notable features, and they are used in deep recurrent neural networks (Deep RNN) for detecting prostate cancer. To train the classifier, the proposed Bird Squirrel (BS) algorithm is used. By combining the Bird search algorithm (BSA) and Squirrel search algorithm(SSA), the created BS is produced. With a higher accuracy of 0.937, a sensitivity of 0.958, and a specificity of 0.916, the proposed BS-DeepRNN enhanced efficiency.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Bird Squirrel Optimization with Deep Recurrent Neural Network forProstate Cancer Detection\",\"authors\":\"Goddumarri Vijay Kumar, Mohammed Ismail B, Bhaskara Reddy T, Mansour Tahernezhadi, Mansoor Alam\",\"doi\":\"10.1615/intjmultcompeng.2024050495\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Prostate cancer is solid organ melanoma which increases mortality amongst humans. Automatic techniques for determining prostate cancer from magnetic resonance images (MRI) are highly recommended. Conventional techniques adapt different steps, which may result in huge computational costs. In order to perform automated prostate cancer classification with MRI, a deep model is developed in this research. Here, the MRI noise is removed using a Non-local Means (NLM) filter. Convolution neural networks (CNN) are also widely used to create segments in order to extract notable features, and they are used in deep recurrent neural networks (Deep RNN) for detecting prostate cancer. To train the classifier, the proposed Bird Squirrel (BS) algorithm is used. By combining the Bird search algorithm (BSA) and Squirrel search algorithm(SSA), the created BS is produced. With a higher accuracy of 0.937, a sensitivity of 0.958, and a specificity of 0.916, the proposed BS-DeepRNN enhanced efficiency.\",\"PeriodicalId\":50350,\"journal\":{\"name\":\"International Journal for Multiscale Computational Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal for Multiscale Computational Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1615/intjmultcompeng.2024050495\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal for Multiscale Computational Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1615/intjmultcompeng.2024050495","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

摘要

前列腺癌是一种实体器官黑色素瘤，会增加人类的死亡率。通过磁共振图像（MRI）确定前列腺癌的自动技术备受推崇。传统技术采用不同的步骤，这可能会导致巨大的计算成本。为了利用核磁共振成像进行前列腺癌自动分类，本研究开发了一种深度模型。在此，使用非局部均值（NLM）滤波器去除 MRI 噪声。卷积神经网络（CNN）也被广泛用于创建片段以提取显著特征，并被用于检测前列腺癌的深度递归神经网络（Deep RNN）。为了训练分类器，使用了所提出的鸟松鼠（BS）算法。通过结合鸟搜索算法（BSA）和松鼠搜索算法（SSA），创建了 BS。所提出的 BS-DeepRNN 具有更高的准确度（0.937）、灵敏度（0.958）和特异度（0.916），提高了效率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Bird Squirrel Optimization with Deep Recurrent Neural Network forProstate Cancer Detection

Prostate cancer is solid organ melanoma which increases mortality amongst humans. Automatic techniques for determining prostate cancer from magnetic resonance images (MRI) are highly recommended. Conventional techniques adapt different steps, which may result in huge computational costs. In order to perform automated prostate cancer classification with MRI, a deep model is developed in this research. Here, the MRI noise is removed using a Non-local Means (NLM) filter. Convolution neural networks (CNN) are also widely used to create segments in order to extract notable features, and they are used in deep recurrent neural networks (Deep RNN) for detecting prostate cancer. To train the classifier, the proposed Bird Squirrel (BS) algorithm is used. By combining the Bird search algorithm (BSA) and Squirrel search algorithm(SSA), the created BS is produced. With a higher accuracy of 0.937, a sensitivity of 0.958, and a specificity of 0.916, the proposed BS-DeepRNN enhanced efficiency.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

International Journal for Multiscale Computational Engineering 工程技术-工程：综合

CiteScore

3.40

自引率

14.30%

发文量

审稿时长

>12 weeks

期刊介绍： The aim of the journal is to advance the research and practice in diverse areas of Multiscale Computational Science and Engineering. The journal will publish original papers and educational articles of general value to the field that will bridge the gap between modeling, simulation and design of products based on multiscale principles. The scope of the journal includes papers concerned with bridging of physical scales, ranging from the atomic level to full scale products and problems involving multiple physical processes interacting at multiple spatial and temporal scales. The emerging areas of computational nanotechnology and computational biotechnology and computational energy sciences are of particular interest to the journal. The journal is intended to be of interest and use to researchers and practitioners in academic, governmental and industrial communities.