Classification of cervical cancer from Pap smear images: a convolutional neural network approach

Q3 Computer Science

International Journal of Intelligent Systems Technologies and Applications Pub Date : 2023-01-01 DOI:10.1504/ijista.2023.133702

Siti Noraini Sulaiman, Ajmal Hadi Ahmad Hishamuddin, Iza Sazanita Isa, Muhammad Khusairi Osman, Zainal Hisham Che Soh

{"title":"Classification of cervical cancer from Pap smear images: a convolutional neural network approach","authors":"Siti Noraini Sulaiman, Ajmal Hadi Ahmad Hishamuddin, Iza Sazanita Isa, Muhammad Khusairi Osman, Zainal Hisham Che Soh","doi":"10.1504/ijista.2023.133702","DOIUrl":null,"url":null,"abstract":"Cervical cancer is a significant global issue, with Pap smear tests being a common screening tool for precancerous stages. This study aims to develop a computer-aided diagnostics system that can classify precancerous cells from Pap smear images. The project employs convolutional neural networks (CNNs) trained using pre-processed images, adaptive fuzzy K-means (AFKM), and fuzzy C-means (FCM) to classify cervical cancer cell data as normal or abnormal. The datasets used in the project include normal, low-grade squamous intraepithelial lesion (LSIL), and high-grade squamous intraepithelial lesion (HSIL) categories. CNN1, CNN2, and CNN3 have been developed and CNN2 was chosen due to its highest accuracy of 87.71%. The CNN2 trained with AFKM outperformed other networks with an accuracy of 89.53%, precision of 0.870, recall of 0.870, specificity of 0.935, and F1-score of 0.870. This study demonstrates the potential of deep learning-based approaches for identifying and classifying cervical cell pre-cancerous stages.","PeriodicalId":38712,"journal":{"name":"International Journal of Intelligent Systems Technologies and Applications","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Intelligent Systems Technologies and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/ijista.2023.133702","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 0

Abstract

Cervical cancer is a significant global issue, with Pap smear tests being a common screening tool for precancerous stages. This study aims to develop a computer-aided diagnostics system that can classify precancerous cells from Pap smear images. The project employs convolutional neural networks (CNNs) trained using pre-processed images, adaptive fuzzy K-means (AFKM), and fuzzy C-means (FCM) to classify cervical cancer cell data as normal or abnormal. The datasets used in the project include normal, low-grade squamous intraepithelial lesion (LSIL), and high-grade squamous intraepithelial lesion (HSIL) categories. CNN1, CNN2, and CNN3 have been developed and CNN2 was chosen due to its highest accuracy of 87.71%. The CNN2 trained with AFKM outperformed other networks with an accuracy of 89.53%, precision of 0.870, recall of 0.870, specificity of 0.935, and F1-score of 0.870. This study demonstrates the potential of deep learning-based approaches for identifying and classifying cervical cell pre-cancerous stages.

查看原文本刊更多论文

从子宫颈抹片图像中分类宫颈癌:卷积神经网络方法

宫颈癌是一个重大的全球性问题，巴氏涂片检查是癌前阶段的常见筛查工具。本研究旨在开发一种计算机辅助诊断系统，可以从巴氏涂片图像中分类癌前细胞。该项目采用预处理图像、自适应模糊k均值(AFKM)和模糊c均值(FCM)训练的卷积神经网络(cnn)对宫颈癌细胞数据进行正常或异常分类。项目中使用的数据集包括正常、低级别鳞状上皮内病变(LSIL)和高级别鳞状上皮内病变(HSIL)类别。先后开发了CNN1、CNN2、CNN3，最终选择了准确率最高的CNN2，达到87.71%。使用AFKM训练的CNN2网络的准确率为89.53%，精密度为0.870，召回率为0.870，特异性为0.935,f1评分为0.870，优于其他网络。这项研究证明了基于深度学习的方法在识别和分类宫颈细胞癌前阶段方面的潜力。

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

International Journal of Intelligent Systems Technologies and Applications Computer Science-Computer Science (all)

CiteScore

1.30

自引率

0.00%

发文量

期刊介绍： Intelligent systems refer broadly to computer embedded or controlled systems, machines and devices that possess a certain degree of intelligence. IJISTA, a peer-reviewed double-blind refereed journal, publishes original papers featuring innovative and practical technologies related to the design and development of intelligent systems. Its coverage also includes papers on intelligent systems applications in areas such as manufacturing, bioengineering, agriculture, services, home automation and appliances, medical robots and robotic rehabilitations, space exploration, etc. Topics covered include: -Robotics and mechatronics technologies- Artificial intelligence and knowledge based systems technologies- Real-time computing and its algorithms- Embedded systems technologies- Actuators and sensors- Mico/nano technologies- Sensing and multiple sensor fusion- Machine vision, image processing, pattern recognition and speech recognition and synthesis- Motion/force sensing and control- Intelligent product design, configuration and evaluation- Real time learning and machine behaviours- Fault detection, fault analysis and diagnostics- Digital communications and mobile computing- CAD and object oriented simulations.