Show simple item record

dc.contributor.advisorAlam, Md. Golam Rabiul
dc.contributor.authorBhuiyan, Mazedul Haque
dc.contributor.authorTabassum, Fariba
dc.contributor.authorBushra, Umme
dc.contributor.authorShwon, Md.Mahbub Rahman
dc.date.accessioned2021-06-02T04:28:19Z
dc.date.available2021-06-02T04:28:19Z
dc.date.copyright2020
dc.date.issued2020-04
dc.identifier.otherID: 15201035
dc.identifier.otherID: 15201038
dc.identifier.otherID: 15201034
dc.identifier.otherID: 15201044
dc.identifier.urihttp://hdl.handle.net/10361/14464
dc.descriptionThis thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.en_US
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 37-39).
dc.description.abstractUterine cervical cancer is the second most regular gynecological harm around the world. The appraisal of the degree of sickness is fundamental for arranging ideal treatment. Imaging procedures are progressively utilized in the pre-treatment workup of cervical malignancy[22]. Presently, MRI for the neighborhood degree of sickness assessment and PET-check for removed ailment appraisal is considered as firstline procedures. In any case, over the most recent couple of years, ultrasound has picked up consideration as an imaging system for assessing ladies with cervical cancer.In this paper, we will take a shot at the advancement of a profound conviction system to order ultrasound pictures of the cervical cells to recognize cervical malignant growth. This postulation talks about the depiction of examples of single pap-smear cells from a current database set up at Herlev University Hospital. Wellbeing, the apparatus ought to be utilized before disease improvement to distinguish pre-dangerous cells in the uterine cervix[16]. For the separation among ordinary and unusual cells, open cell qualities, for example, area, position, and splendor of the core and cytoplasm are utilized. The exhibition of the classifier is determined on the rate total blunder but on the other hand is tried on the recurrence of bogus negative and bogus positive mistakes. The point is to support the all out mistake instead of the outcomes acquired already. A detailed overview of Herlev University Hospital’s latest pap- data prepares a new comparison platform Papsmear for publishing on Twitter. The papsmear collection consists of 917 experiments on 7 separate types of normal and irregular cells spread unequally. Every sample is represented by 20 characteristics. The average performance of the tested classifiers indicates no substantial change in earlier tests, but similar results are obtained using very basic methods.en_US
dc.description.statementofresponsibilityMazedul Haque Bhuiyan
dc.description.statementofresponsibilityFaribaTabassum
dc.description.statementofresponsibilityUmme Bushra
dc.description.statementofresponsibilityMd.Mahbub Rahman Shwon
dc.format.extent39 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.subjectCervical Canceren_US
dc.subjectDeep Learningen_US
dc.subjectCervixen_US
dc.subjectPredictionen_US
dc.subjectPCAen_US
dc.subjectt-SNEen_US
dc.subjectAUC-ROC Curveen_US
dc.subjectXGBoosteren_US
dc.subjectSVMen_US
dc.subjectCNNen_US
dc.titleCervical Cancer Detection from Cervix Image Using Pap smear Imaging through CNNen_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