A New Intelligent Model Based on Improved Inception-V3 for Oral Cancer and Cyst Classification

IF 0.8 4区医学 Q4 BIOPHYSICS

Journal of Mechanics in Medicine and Biology Pub Date : 2023-10-21 DOI:10.1142/s0219519423400985

Suxian Xiang, Yun He, Chenxi Huang, Ziyi Guo, Siming Lin, Jin Zhu

{"title":"A New Intelligent Model Based on Improved Inception-V3 for Oral Cancer and Cyst Classification","authors":"Suxian Xiang, Yun He, Chenxi Huang, Ziyi Guo, Siming Lin, Jin Zhu","doi":"10.1142/s0219519423400985","DOIUrl":null,"url":null,"abstract":"Oral cancer, which is also called mouth cancer, is cancer of the lining of the mouth, lips, or upper throat that has appeared in more than 355,000 people worldwide and caused more than 177,000 deaths, so it is essential to diagnose it as early as possible. Computed tomography (CT) scan is conducive to oral cancer diagnosis, but classifying oral CT images to cancer and cyst manually is difficult and time-consuming. A novel intelligent model based on improved Inception-v3 for classifying oral cancer and cyst CT images automatically is proposed in this paper. We replace the conventional convolution block in Inception-v3 with the Inverted Bottleneck Block and introduce Squeeze-and-Excitation Block (SEB) and Convolutional Block Attention Block (CBAB). The proposed model in this paper is trained on a dataset consisting of CT images of two classes (oral cancer and cyst), and the proposed model achieves 84.053% accuracy, 82.364% sensitivity, 84.508% specificity for oral cancer classification and outperforms other common models in classifying oral CT images.","PeriodicalId":50135,"journal":{"name":"Journal of Mechanics in Medicine and Biology","volume":"3 2","pages":"0"},"PeriodicalIF":0.8000,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Mechanics in Medicine and Biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/s0219519423400985","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOPHYSICS","Score":null,"Total":0}

引用次数: 0

Abstract

Oral cancer, which is also called mouth cancer, is cancer of the lining of the mouth, lips, or upper throat that has appeared in more than 355,000 people worldwide and caused more than 177,000 deaths, so it is essential to diagnose it as early as possible. Computed tomography (CT) scan is conducive to oral cancer diagnosis, but classifying oral CT images to cancer and cyst manually is difficult and time-consuming. A novel intelligent model based on improved Inception-v3 for classifying oral cancer and cyst CT images automatically is proposed in this paper. We replace the conventional convolution block in Inception-v3 with the Inverted Bottleneck Block and introduce Squeeze-and-Excitation Block (SEB) and Convolutional Block Attention Block (CBAB). The proposed model in this paper is trained on a dataset consisting of CT images of two classes (oral cancer and cyst), and the proposed model achieves 84.053% accuracy, 82.364% sensitivity, 84.508% specificity for oral cancer classification and outperforms other common models in classifying oral CT images.

查看原文本刊更多论文

基于改进Inception-V3的口腔癌和囊肿分类智能新模型

口腔癌，又称口腔癌，是一种发生在口腔、嘴唇或喉咙上部的癌症，全世界有超过35.5万人患有口腔癌，造成超过17.7万人死亡，因此尽早诊断是至关重要的。计算机断层扫描(CT)有助于口腔癌的诊断，但人工对口腔CT图像进行肿瘤和囊肿的分类困难且耗时。提出了一种基于改进Inception-v3的口腔癌和囊肿CT图像自动分类智能模型。我们用倒瓶颈块取代了Inception-v3中的传统卷积块，并引入了挤压和激励块(SEB)和卷积块注意块(CBAB)。本文提出的模型在由口腔癌和囊肿两类CT图像组成的数据集上进行训练，该模型对口腔癌的分类准确率为84.053%，灵敏度为82.364%，特异性为84.508%，在口腔CT图像分类方面优于其他常用模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Mechanics in Medicine and Biology 工程技术-工程：生物医学

CiteScore

1.20

自引率

12.50%

发文量

144

审稿时长

2.3 months

期刊介绍： This journal has as its objective the publication and dissemination of original research (even for "revolutionary concepts that contrast with existing theories" & "hypothesis") in all fields of engineering-mechanics that includes mechanisms, processes, bio-sensors and bio-devices in medicine, biology and healthcare. The journal publishes original papers in English which contribute to an understanding of biomedical engineering and science at a nano- to macro-scale or an improvement of the methods and techniques of medical, biological and clinical treatment by the application of advanced high technology. Journal''s Research Scopes/Topics Covered (but not limited to): Artificial Organs, Biomechanics of Organs. Biofluid Mechanics, Biorheology, Blood Flow Measurement Techniques, Microcirculation, Hemodynamics. Bioheat Transfer and Mass Transport, Nano Heat Transfer. Biomaterials. Biomechanics & Modeling of Cell and Molecular. Biomedical Instrumentation and BioSensors that implicate ''human mechanics'' in details. Biomedical Signal Processing Techniques that implicate ''human mechanics'' in details. Bio-Microelectromechanical Systems, Microfluidics. Bio-Nanotechnology and Clinical Application. Bird and Insect Aerodynamics. Cardiovascular/Cardiac mechanics. Cardiovascular Systems Physiology/Engineering. Cellular and Tissue Mechanics/Engineering. Computational Biomechanics/Physiological Modelling, Systems Physiology. Clinical Biomechanics. Hearing Mechanics. Human Movement and Animal Locomotion. Implant Design and Mechanics. Mathematical modeling. Mechanobiology of Diseases. Mechanics of Medical Robotics. Muscle/Neuromuscular/Musculoskeletal Mechanics and Engineering. Neural- & Neuro-Behavioral Engineering. Orthopedic Biomechanics. Reproductive and Urogynecological Mechanics. Respiratory System Engineering...