Klasifikasi Jenis Tumor Otak Meningioma, Glioma, Dan Pituitari Berbasis Hybrid Vgg-16 Dan Svm Untuk Diagnosis Praoperasi

Hajjanto, Ariq Dreiki (2024) Klasifikasi Jenis Tumor Otak Meningioma, Glioma, Dan Pituitari Berbasis Hybrid Vgg-16 Dan Svm Untuk Diagnosis Praoperasi. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5023201057_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (2MB) | Request a copy

Abstract

Berdasarkan Global Cancer Statistic pada tahun 2020, kasus baru tumor otak dan CNS mencapai 308.102 dengan kematian mencapai 251.329 di seluruh dunia. Di Indonesia sendiri, estimasi kejadian dan kematian pada tahun 2016 mencapai 6.337 dan 5.405 kasus. Banyak jenis tumor otak dengan variasi lokasi, ukuran, dan tingkat keganasan membuat melokalisasi dan klasifikasi tumor kompleks bagi ahli medis secara konvensional, menyebabkan kesalahan dalam penentuan jenis tumor otak karena perlu membaca hasil citra dalam jumlah yang sangat banyak. Keakuratan klasifikasi konvensional dapat dipengaruhi oleh beberapa faktor, seperti perbedaan subjektivitas individu dalam mengenali lokasi tumor, waktu, ketelitian, kelelahan, dan faktor manusia lainnya. Maka dari itu, dibutuhkan suatu metode dalam menghasilkan diagnosis tumor yang akurat dengan machine learning. Akan tetapi, penelitian yang menggunakan pendekatan machine learning sangat rentan akan overfitting disebabkan kurangnya dataset ataupun model arsitektur yang digunakan dan juga lamanya proses komputasi yang dibutuhkan. Oleh sebab itu, Pada penelitian ini diusulkan sistem klasifikasi hibrida dengan bantuan machine learning, yaitu menggunakan arsitektur/model VGG-16 dan Support Vector Machine (SVM). VGG-16 memiliki keunggulan dalam ekstraksi fitur hierarkis dan invariansi spasial yang memungkinkan identifikasi tumor dengan akurasi lebih tinggi. Output fitur jenis tumor otak dari VGG-16 direduksi menggunakan Principal Component Analysis (PCA), lalu diklasifikasi dengan bantuan SVM serta dioptimalkan dengan pengujian kombinasi kernel dan hyperparameter. Performa arsitektur dievaluasi menggunakan performance metrics dan komparasi model sebelumnya, yang memungkinkan penilaian objektif terhadap hasil yang dicapai. Hasil penelitian memberikan hasil untuk masing-masing metrik akurasi, presisi, recall¸f1-score, dan spesifisitas secara berturut-turut sebesar 96.9%, 97.3%, 96.67%, 96.67%, dan 99.97% dengan menggunakan kernel polynomial dengan hyperparameter C, degree, dan coef0 sebesar 10, 3, dan 0.5.
============================================================
According to the 2020 Global Cancer Statistics, there were 308,102 new cases of brain and CNS tumors, resulting in 251,329 deaths worldwide. In Indonesia alone, the estimated incidence and mortality in 2016 were 6,337 and 5,405 cases, respectively. The various types of brain tumors, with variations in location, size, and malignancy levels, make localization and classification complex for conventional medical professionals, leading to errors in brain tumor determination due to the need to analyze a vast amount of imaging results. Conventional classification accuracy can be influenced by factors such as individual subjectivity in recognizing tumor locations, timing, precision, fatigue, and other human factors. Therefore, a method is needed to produce accurate tumor diagnoses using machine learning. However, research using machine learning approaches is highly susceptible to overfitting due to the lack of datasets or the architectural models used and the lengthy computational processes required. Hence, this study proposes a hybrid classification system with the assistance of machine learning, utilizing the VGG-16 architecture/model and Support Vector Machine (SVM). VGG-16 excels in hierarchical feature extraction and spatial invariance, enabling higher accuracy in tumor identification. The output features of brain tumor types from VGG-16 are reduced using Principal Component Analysis (PCA) and then classified with the help of SVM, optimized by testing combinations of kernels and hyperparameters. The architecture performance is evaluated using performance metrics and comparison with previous models, allowing for an objective assessment of the achieved results. The study results for each metric of accuracy, precision, recall, f1-score, and specificity were 96.9%, 97.3%, 96.67%, 96.67%, and 99.97%, respectively, using the polynomial kernel with hyperparameters C, degree, and coef0 of 10, 3, and 0.5.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	VGG-16, Support Vector Machine, Principal Component Analysis, Brain Tumor, Disease
Subjects:	T Technology > T Technology (General) > T57.74 Linear programming T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis
Depositing User:	Ariq Dreiki Hajjanto
Date Deposited:	02 Aug 2024 05:18
Last Modified:	02 Aug 2024 05:18
URI:	http://repository.its.ac.id/id/eprint/110912

Actions (login required)

View Item