• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Computer Science
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Computer Science
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Deteksi Objek Abnormal Pada Paru-Paru Berdasarkan Citra X-Ray Toraks dengan Menggunakan Algoritma You Only Look Once (Yolo)

    View/Open
    Fulltext (2.808Mb)
    Date
    2021
    Author
    Adji, Wira Ardi Kesuma
    Advisor(s)
    Amalia
    Herriyance
    Metadata
    Show full item record
    Abstract
    In diagnosing pulmonary diseases, physicians usually perform a radiologic examination on pulmonary conditions by ensuring the presence of special findings or abnormal conditions. Detecting abnormal conditions may be conducted using a thorax x-ray. This study aimed to construct a model to detect abnormal objects using the Yolov5 algorithm on thorax x-ray images. Fourteen abnormal objects were detected, i.e., aortic enlargement, atelectasis, calcification, cardiomegaly, consolidation, ILD (interstitial lung disease), infiltration, lung opacity, nodule/mass, other lesions, pleural effusion, pleural thickening, pneumothorax, and pulmonary fibrosis. In building the training model, several methods are used to increase the accuracy of the model, namely weighted boxes fusion (WBF), image transformation using contrast limited adaptive histogram equalization (CLAHE), and data augmentation. The best accuracy results obtained from the model by doing 100 epochs training is 70%. In addition to building models, a web-based application was built which is expected to help doctors learn and simplify the process of diagnosing diseases of the lungs.
     
    Dalam mendiagnosis penyakit pada paru-paru biasanya dokter akan melakukan pemeriksaan radiologi terhadap kondisi paru-paru dengan memastikan adanya temuan khusus atau kondisi abnormal. Untuk mendeteksi kondisi abnormal yang terjadi dilakukan pemeriksaan melalui x-ray toraks. Penelitian ini bertujuan untuk membangun model untuk mendeteksi objek abnormal menggunakan algoritma Yolov5 pada citra x-ray toraks. Terdapat 14 objek abnormal yang akan dideteksi diantaranya aortic enlargement, atelectasis, calcification, cardiomegaly, consolidation, ILD (interstitial lung disease), infiltration, lung opacity, nodule/mass, other lesion, pleural effusion, pleural thickening, pneumothorax, dan pulmonary fibrosis. Dalam membangun model training digunakan beberapa metode untuk meningkatkan akurasi model yaitu weighted boxes fusion (WBF), transformasi citra menggunakan contrast limited adaptive histogram equalization (CLAHE), dan data augmentation. Hasil akurasi terbaik yang didapatkan dari model dengan melakukan training sebanyak 100 epoch adalah 70%. Selain membangun model, dibangun aplikasi berbasis web yang diharapkan dapat membantu dokter untuk belajar dan mempermudah dalam proses diagnosis penyakit pada paru-paru.

    URI
    https://repositori.usu.ac.id/handle/123456789/46446
    Collections
    • Undergraduate Theses [1180]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV