Abstract
Gastric cancer can present itself as a gastric ulcer, which can mimic a benign gastric ulcer. In this paper, we introduce an objective and precise gastric ulcer differentiation system based on deep convolutional neural network (CNN) which can support the specialists by improving the diagnostic accuracy of the endoscopic examination of gastric ulcers. We first generated a new dataset consisting of endoscopic images of gastric ulcers and their corresponding type labels obtained by biopsy. We then design various ulcer differentiation models using classification or detection networks, and evaluate the performance of the models on the new dataset. Experimental results confirm that the classification network-based method shows performance comparable to doctors' diagnosis, and the detection network-based one, which first detects ulcer regions and then determines the type of ulcer based on the detection results, exhibits the best performance. The proposed method provides an unbiased diagnosis and it outperforms endoscopic diagnoses performed by the specialists in terms of total accuracy.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018 |
| Editors | Bridget Kane, Jaakko Hollmen, Carolyn McGregor, Paolo Soda |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 351-356 |
| Number of pages | 6 |
| Volume | 2018-June |
| ISBN (Electronic) | 9781538660607 |
| DOIs | |
| Publication status | Published - 2018 Jul 20 |
| Event | 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018 - Karlstad, Sweden Duration: 2018 Jun 18 → 2018 Jun 21 |
Other
| Other | 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018 |
|---|---|
| Country | Sweden |
| City | Karlstad |
| Period | 18/6/18 → 18/6/21 |
Fingerprint
Keywords
- convolutional neural network
- deep learning
- endoscopy
- gastric ulcer
- ulcer detection
ASJC Scopus subject areas
- Radiology Nuclear Medicine and imaging
- Computer Science Applications
Cite this
A Novel Gastric Ulcer Differentiation System Using Convolutional Neural Networks. / Sun, Jee Young; Lee, Sang Won; Kang, Mun Cheon; Kim, Seung Wook; Kim, Seung Young; Ko, Sung-Jea.
Proceedings - 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018. ed. / Bridget Kane; Jaakko Hollmen; Carolyn McGregor; Paolo Soda. Vol. 2018-June Institute of Electrical and Electronics Engineers Inc., 2018. p. 351-356.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A Novel Gastric Ulcer Differentiation System Using Convolutional Neural Networks
AU - Sun, Jee Young
AU - Lee, Sang Won
AU - Kang, Mun Cheon
AU - Kim, Seung Wook
AU - Kim, Seung Young
AU - Ko, Sung-Jea
PY - 2018/7/20
Y1 - 2018/7/20
N2 - Gastric cancer can present itself as a gastric ulcer, which can mimic a benign gastric ulcer. In this paper, we introduce an objective and precise gastric ulcer differentiation system based on deep convolutional neural network (CNN) which can support the specialists by improving the diagnostic accuracy of the endoscopic examination of gastric ulcers. We first generated a new dataset consisting of endoscopic images of gastric ulcers and their corresponding type labels obtained by biopsy. We then design various ulcer differentiation models using classification or detection networks, and evaluate the performance of the models on the new dataset. Experimental results confirm that the classification network-based method shows performance comparable to doctors' diagnosis, and the detection network-based one, which first detects ulcer regions and then determines the type of ulcer based on the detection results, exhibits the best performance. The proposed method provides an unbiased diagnosis and it outperforms endoscopic diagnoses performed by the specialists in terms of total accuracy.
AB - Gastric cancer can present itself as a gastric ulcer, which can mimic a benign gastric ulcer. In this paper, we introduce an objective and precise gastric ulcer differentiation system based on deep convolutional neural network (CNN) which can support the specialists by improving the diagnostic accuracy of the endoscopic examination of gastric ulcers. We first generated a new dataset consisting of endoscopic images of gastric ulcers and their corresponding type labels obtained by biopsy. We then design various ulcer differentiation models using classification or detection networks, and evaluate the performance of the models on the new dataset. Experimental results confirm that the classification network-based method shows performance comparable to doctors' diagnosis, and the detection network-based one, which first detects ulcer regions and then determines the type of ulcer based on the detection results, exhibits the best performance. The proposed method provides an unbiased diagnosis and it outperforms endoscopic diagnoses performed by the specialists in terms of total accuracy.
KW - convolutional neural network
KW - deep learning
KW - endoscopy
KW - gastric ulcer
KW - ulcer detection
UR - http://www.scopus.com/inward/record.url?scp=85050970848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050970848&partnerID=8YFLogxK
U2 - 10.1109/CBMS.2018.00068
DO - 10.1109/CBMS.2018.00068
M3 - Conference contribution
AN - SCOPUS:85050970848
VL - 2018-June
SP - 351
EP - 356
BT - Proceedings - 31st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2018
A2 - Kane, Bridget
A2 - Hollmen, Jaakko
A2 - McGregor, Carolyn
A2 - Soda, Paolo
PB - Institute of Electrical and Electronics Engineers Inc.
ER -