Amelia, Viola (2025) Klasifikasi Kanker Paru-Paru Berdasarkan Gambar CT-Scan Menggunakan Metode EfficientNet-B7 Dan Inception-V3. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003211017-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003211017-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy |
Abstract
Kanker paru-paru merupakan salah satu penyebab utama kematian di dunia yang menekankan pentingnya deteksi dini untuk meningkatkan peluang kesembuhan pasien. Pencitraan CT scan adalah metode yang umum digunakan dalam mendiagnosis kanker paru-paru, namun identifikasi manual terhadap citra ini memerlukan waktu dan keahlian tinggi. Untuk mengatasi tantangan tersebut, penelitian ini mengimplementasikan metode deep learning menggunakan arsitektur EfficientNet-B7 dan Inception V3 untuk klasifikasi kanker paru-paru. Penelitian ini menggunakan dataset IQ-OTH/NCCD yang mencakup 1097 gambar CT scan dengan tiga kategori: malignant, benign, dan normal. Data diproses melalui tahapan preprocessing seperti resizing, normalisasi, dan augmentasi. Model dilatih menggunakan arsitektur EfficientNet-B7 dan Inception V3, yang dirancang untuk efisiensi komputasi tinggi tanpa mengurangi akurasi prediksi. Hasil dari penelitian ini mencakup evaluasi kinerja model EfficientNet-B7 dan Inception V3 dalam klasifikasi kanker paru-paru. Nilai F-1 Score pada Confussion Matrix digunakan untuk mengukur kebaikan model dan mengevaluasi penerapan model dalam pengolahan citra medis. Model EfficientNet-B7 menunjukkan kinerja yang sangat baik dengan akurasi keseluruhan 98,64% dan F1-Score 0,98. Inception V3 memberikan hasil yang baik dengan akurasi keseluruhan 98,19% dan F1-Score 0,96. Model EfficientNet-B7 menunjukkan hasil yang lebih baik dalam akurasi, recall dan F1-Score dibanding Inception V3.
=========================================================================================================================================
Lung cancer is one of the leading causes of death worldwide, emphasizing the importance of early detection to improve patient survival rates. CT scans are a commonly used method for diagnosing lung cancer, but manual identification of these images requires time and high levels of expertise. To address this challenge, this study implements a deep learning method using the EfficientNet-B7 and Inception V3 architectures for lung cancer classification. The study uses the IQ-OTH/NCCD dataset, which includes 1,097 CT scan images categorized into three groups: malignant, benign, and normal. The data undergoes preprocessing steps such as resizing, normalization, and augmentation. The models were trained using the EfficientNet-B7 and Inception V3 architectures, which are designed for high computational efficiency without compromising prediction accuracy. The results of this study include an evaluation of the performance of the EfficientNet-B7 and Inception V3 models in lung cancer classification. The F-1 Score in the Confusion Matrix was used to measure the quality of the models and evaluate their application in medical image processing. The EfficientNet-B7 model demonstrated excellent performance with an overall accuracy of 98.64% and an F1-Score of 0.98. Inception V3 provided good results with an overall accuracy of 98.19% and an F1-Score of 0.96. The EfficientNet-B7 model showed better results in accuracy, recall, and F1-Score compared to Inception V3.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | CNN, Kanker Paru-Paru, Klasifikasi, EfficientNet, Inception, CNN, Lung Cancer, Classification, EfficientNet, Inception |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing. |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Viola Amelia |
| Date Deposited: | 01 Aug 2025 06:41 |
| Last Modified: | 01 Aug 2025 06:41 |
| URI: | http://repository.its.ac.id/id/eprint/125575 |
Actions (login required)
 |
View Item |