Show simple item record

dc.contributor.advisorAlam, Dr. Md. Golam Rabiul
dc.contributor.advisorReza, Md Tanzim
dc.contributor.authorMehedi, Md Humaion Kabir
dc.contributor.authorHaque, Ehteshamul
dc.contributor.authorRadin, Sameen Yasir
dc.contributor.authorUr Rahman, Md. Abrar
dc.date.accessioned2022-08-24T09:15:19Z
dc.date.available2022-08-24T09:15:19Z
dc.date.copyright2022
dc.date.issued2022-01
dc.identifier.otherID: 17201061
dc.identifier.otherID: 18101481
dc.identifier.otherID: 17221003
dc.identifier.otherID: 18101276
dc.identifier.urihttp://hdl.handle.net/10361/17120
dc.descriptionThis thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022en_US
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 37-40).
dc.description.abstractKidney disease is one of many severe chronic disease that a person can have. Early detection of this disease can be pivotal for proper treatment. Different neural net works have proven to be useful in disease prediction in the progression of modern science. In this paper, we have proposed a segmentation based kidney tumor clas sification using Deep Neural Network (DNN). We have done our work in two Steps. Firstly, we have segmented kidneys using a manual segmentation technique and trained UNet along with SegNet for kidney segmentation. Then, for the classifica tion task, the modified MobileNetV2, VGG16 and InceptionV3 was trained on the segmented kidney data. CT KIDNEY DATASET: Normal-Cyst-Tumor and Stone dataset(published in Kaggle) was used to train our models. Finally, the classifica tion models MobileNetV2, VGG16, InceptionV3 scored with 95.29%, 99.21% and 97.38% accuracy on test set. We found that the modified VGG16 model has the best accuracy and the highest sensitivity and specificity.en_US
dc.description.statementofresponsibilityMd Humaion Kabir Mehedi
dc.description.statementofresponsibilityEhteshamul Haque
dc.description.statementofresponsibilitySameen Yasir Radin
dc.description.statementofresponsibilityMd. Abrar Ur Rahman
dc.format.extent40 Pages
dc.language.isoen_USen_US
dc.publisherBrac Universityen_US
dc.rightsBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.
dc.subjectKidney Tumoren_US
dc.subjectComputed Tomography (CT)en_US
dc.subjectVGG16en_US
dc.subjectSegmentationen_US
dc.subjectClassificationen_US
dc.subjectDeep Neural Network (DNN)en_US
dc.subject.lcshNeural network
dc.subject.lcshNeural networks (Computer science)
dc.titleSegmentation based Kidney Tumor Classification using Deep Neural Networken_US
dc.typeThesisen_US
dc.contributor.departmentDepartment of Computer Science and Engineering, Brac University
dc.description.degreeB. Computer Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record