Suman Pokhrel, Laxmi Kanta Dahal, N. Gupta, Rijesh Shrestha, Anshul Srivastava, Akash Bhasney
{"title":"基于卷积神经网络的脑肿瘤检测应用","authors":"Suman Pokhrel, Laxmi Kanta Dahal, N. Gupta, Rijesh Shrestha, Anshul Srivastava, Akash Bhasney","doi":"10.1109/CONIT55038.2022.9848177","DOIUrl":null,"url":null,"abstract":"A brain tumor is a collection, or mass, of abnormal cells in your brain. Your skull, which encloses your brain, is very rigid. Any growth inside such a restricted space can cause problems. Magnetic resonance imaging (MRI) is a non-invasive method for producing three-dimensional (3D) tomographic images of the human body. MRI is most often used for the detection of tumors, lesions, and other abnormalities in soft tissues, such as the brain. Clinically, radiologists qualitatively analyze films produced by MRI scanners. Brain Tumor segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual classification can result in inaccurate prediction and diagnosis. Moreover, it is an aggravating task when there is a large amount of data present to be assisted. Brain tumors have high diversity in appearance and there is a similarity between tumor and normal tissues and thus the extraction of tumor regions from images becomes unyielding. We implemented various state of the art Neural Networks like MobileN etV2, MobileNetV3 small, MobileNetV3 large, VGG16, VGG19 and our Custom CNN model. Among these models CNN was able to get the Highest amount of accuracy. Our proposed method consists of a Convolutional Neural Network (CNN) (which is implemented using Keras and Tensor flow) that is integrated to a full featured cross-platform desktop application(which is implemented using PyQt5 and MariaDB) that can be easily used in hospitals as well as local clinics. The main aim of this project is to distinguish between normal and abnormal pixels, and classify a tumor affected brain using real-world datasets.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Brain Tumor Detection Application Based On Convolutional Neural Network\",\"authors\":\"Suman Pokhrel, Laxmi Kanta Dahal, N. Gupta, Rijesh Shrestha, Anshul Srivastava, Akash Bhasney\",\"doi\":\"10.1109/CONIT55038.2022.9848177\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A brain tumor is a collection, or mass, of abnormal cells in your brain. Your skull, which encloses your brain, is very rigid. Any growth inside such a restricted space can cause problems. Magnetic resonance imaging (MRI) is a non-invasive method for producing three-dimensional (3D) tomographic images of the human body. MRI is most often used for the detection of tumors, lesions, and other abnormalities in soft tissues, such as the brain. Clinically, radiologists qualitatively analyze films produced by MRI scanners. Brain Tumor segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual classification can result in inaccurate prediction and diagnosis. Moreover, it is an aggravating task when there is a large amount of data present to be assisted. Brain tumors have high diversity in appearance and there is a similarity between tumor and normal tissues and thus the extraction of tumor regions from images becomes unyielding. We implemented various state of the art Neural Networks like MobileN etV2, MobileNetV3 small, MobileNetV3 large, VGG16, VGG19 and our Custom CNN model. Among these models CNN was able to get the Highest amount of accuracy. Our proposed method consists of a Convolutional Neural Network (CNN) (which is implemented using Keras and Tensor flow) that is integrated to a full featured cross-platform desktop application(which is implemented using PyQt5 and MariaDB) that can be easily used in hospitals as well as local clinics. The main aim of this project is to distinguish between normal and abnormal pixels, and classify a tumor affected brain using real-world datasets.\",\"PeriodicalId\":270445,\"journal\":{\"name\":\"2022 2nd International Conference on Intelligent Technologies (CONIT)\",\"volume\":\"242 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-06-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 2nd International Conference on Intelligent Technologies (CONIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CONIT55038.2022.9848177\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 2nd International Conference on Intelligent Technologies (CONIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CONIT55038.2022.9848177","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Brain Tumor Detection Application Based On Convolutional Neural Network
A brain tumor is a collection, or mass, of abnormal cells in your brain. Your skull, which encloses your brain, is very rigid. Any growth inside such a restricted space can cause problems. Magnetic resonance imaging (MRI) is a non-invasive method for producing three-dimensional (3D) tomographic images of the human body. MRI is most often used for the detection of tumors, lesions, and other abnormalities in soft tissues, such as the brain. Clinically, radiologists qualitatively analyze films produced by MRI scanners. Brain Tumor segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual classification can result in inaccurate prediction and diagnosis. Moreover, it is an aggravating task when there is a large amount of data present to be assisted. Brain tumors have high diversity in appearance and there is a similarity between tumor and normal tissues and thus the extraction of tumor regions from images becomes unyielding. We implemented various state of the art Neural Networks like MobileN etV2, MobileNetV3 small, MobileNetV3 large, VGG16, VGG19 and our Custom CNN model. Among these models CNN was able to get the Highest amount of accuracy. Our proposed method consists of a Convolutional Neural Network (CNN) (which is implemented using Keras and Tensor flow) that is integrated to a full featured cross-platform desktop application(which is implemented using PyQt5 and MariaDB) that can be easily used in hospitals as well as local clinics. The main aim of this project is to distinguish between normal and abnormal pixels, and classify a tumor affected brain using real-world datasets.