Breast Cancer Detection using Residual Convolutional Neural Network and Weighted Loss
| Main Authors: | Sena, Samuel Aji, Mudjirahardjo, Panca, Pramono, Sholeh Hadi |
|---|---|
| Format: | Article info application/pdf eJournal |
| Bahasa: | eng |
| Terbitan: |
LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO
, 2019
|
| Online Access: |
https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430 https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430/250 |
| ctrlnum |
article-430 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><title lang="en-US">Breast Cancer Detection using Residual Convolutional Neural Network and Weighted Loss</title><title lang="id-ID">Breast Cancer Detection using Residual Convolutional Neural Network and Weighted Loss</title><creator>Sena, Samuel Aji</creator><creator>Mudjirahardjo, Panca</creator><creator>Pramono, Sholeh Hadi</creator><description lang="en-US">This research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image is a hard task because it needs manual observation by a pathologist to find the malignant region. The deep learning model used in this research is made up of multiple layers of the residual convolutional neural network, and instead of using another type of classifier, a multilayer neural network was used as the classifier and stacked together and trained using end-to-end training approach. The system is trained using invasive ductal carcinoma dataset from the Hospital of the University of Pennsylvania and The Cancer Institute 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 is quite challenging. Weighted loss function was used as the objective function to tackle this problem. We achieve 78.26% and 78.03% for Recall and F1-Score metrics, respectively which are an improvement compared to the previous approach.</description><description lang="id-ID">This research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image is a hard task because it needs manual observation by a pathologist to find the malignant region. The deep learning model used in this research is made up of multiple layers of the residual convolutional neural network, and instead of using another type of classifier, a multilayer neural network was used as the classifier and stacked together and trained using end-to-end training approach. The system is trained using invasive ductal carcinoma dataset from the Hospital of the University of Pennsylvania and The Cancer Institute 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 is quite challenging. Weighted loss function was used as the objective function to tackle this problem. We achieve 78.26% and 78.03% for Recall and F1-Score metrics, respectively which are an improvement compared to the previous approach.</description><publisher lang="en-US">LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO</publisher><date>2019-06-30</date><type>Journal:Article</type><type>Other:info:eu-repo/semantics/publishedVersion</type><type>Journal:Article</type><type>File:application/pdf</type><identifier>https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430</identifier><identifier>10.20895/infotel.v11i2.430</identifier><source lang="en-US">JURNAL INFOTEL; Vol 11 No 2 (2019): May 2019; 43-47</source><source lang="id-ID">JURNAL INFOTEL; Vol 11 No 2 (2019): May 2019; 43-47</source><source>2460-0997</source><source>2085-3688</source><source>10.20895/infotel.v11i2</source><language>eng</language><relation>https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430/250</relation><rights lang="en-US">Copyright (c) 2019 JURNAL INFOTEL</rights><rights lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</rights><recordID>article-430</recordID></dc>
|
| language |
eng |
| format |
Journal:Article Journal Other:info:eu-repo/semantics/publishedVersion Other File:application/pdf File Journal:eJournal |
| author |
Sena, Samuel Aji Mudjirahardjo, Panca Pramono, Sholeh Hadi |
| title |
Breast Cancer Detection using Residual Convolutional Neural Network and Weighted Loss |
| publisher |
LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO |
| publishDate |
2019 |
| url |
https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430 https://ejournal.st3telkom.ac.id/index.php/infotel/article/view/430/250 |
| contents |
This research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image is a hard task because it needs manual observation by a pathologist to find the malignant region. The deep learning model used in this research is made up of multiple layers of the residual convolutional neural network, and instead of using another type of classifier, a multilayer neural network was used as the classifier and stacked together and trained using end-to-end training approach. The system is trained using invasive ductal carcinoma dataset from the Hospital of the University of Pennsylvania and The Cancer Institute 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 is quite challenging. Weighted loss function was used as the objective function to tackle this problem. We achieve 78.26% and 78.03% for Recall and F1-Score metrics, respectively which are an improvement compared to the previous approach. |
| id |
IOS3580.article-430 |
| institution |
STT Telematika Telkom Purwokerto |
| institution_id |
236 |
| institution_type |
library:university library |
| library |
Perpustakaan STT Telematika Telkom Purwokerto |
| library_id |
392 |
| collection |
Jurnal Infotel |
| repository_id |
3580 |
| subject_area |
Rekayasa |
| city |
PURWOKERTO |
| province |
JAWA TENGAH |
| repoId |
IOS3580 |
| first_indexed |
2019-07-03T16:20:09Z |
| last_indexed |
2020-04-13T09:54:22Z |
| recordtype |
dc |
| _version_ |
1685974450684559360 |
| score |
17.610468 |