Sena, Samuel Aji and Panca Mudjirahardjo and Sholeh Hadi Pramono (2019) Deteksi Kanker Payudara Jenis Invasive Ductal Carcinoma dengan Menggunakan Residual Convolutional Neural Network. Magister thesis, Universitas Brawijaya.
Abstract
-
English Abstract
This research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image are hard task because it needs manual observation by pathologist to find the malignant region. Deep learning model used in this research are made up of multiple layer of residual convolutional neural network and instead of using other type of classifier, multilayer neural network were used as the classifier and stacked together and trained using end-to- end training approach. The system are trained using invasive ductal carcinoma dataset from Hospital of the University of Pennsylvania and The Cancer Institue of New Jersey. From this dataset. 80% and 20% were randomly sampled and used as training and testing data respectively. Training a neural network on an imbalanced dataset are quite challenging. Weighted loss function were used as the objective function to tackle this problem. We achieve 78.26% dan 78.03% for Recall and F1-Score metric respectively which are an improvement compared to previous approach.
Other obstract
-
| Item Type: | Thesis (Magister) |
|---|---|
| Identification Number: | TES/006.32/SEN/d/2019/041904787 |
| Uncontrolled Keywords: | Keyword: IDC, breast cancer, deep learning, CNN, neural network, cross entropy |
| Subjects: | 000 Computer science, information and general works > 006 Special computer methods > 006.3 Artificial intelligence > 006.32 Neural nets (neural networks) |
| Divisions: | S2/S3 > Magister Teknik Elektro, Fakultas Teknik |
| Depositing User: | yulia Chasanah |
| Date Deposited: | 30 Aug 2022 02:42 |
| Last Modified: | 16 May 2023 07:54 |
| URI: | http://repository.ub.ac.id/id/eprint/193774 |
![[thumbnail of Ujian.pdf]](http://repository.ub.ac.id/style/images/fileicons/text.png) |
Text
Ujian.pdf Download (2MB) |
Actions (login required)
 |
View Item |