Abstract
Solving the classification problem, unbalanced number of dataset among the classes often causes performance degradation. Especially when some classes dominate the other classes with its large number of datasets, trained model shows low performance in identifying the dominated classes. This is common case when it comes to medical dataset. Because the case with a serious degree is not quite usual, there are imbalance in number of dataset between severe case and normal cases of diseases. Also, there is difficulty in precisely identifying grade of medical data because of vagueness between them. To solve these problems, we propose new architecture of convolutional neural network named Tournament based Ranking CNN which shows remarkable performance gain in identifying dominated classes while trading off very small accuracy loss in dominating classes. Our Approach complemented problems that occur when method of Ranking CNN that aggregates outputs of multiple binary neural network models is applied to medical data. By having tournament structure in aggregating method and using very deep pretrained binary models, our proposed model recorded 68.36% of exact match accuracy, while Ranking CNN recorded 53.40%, pretrained Resnet recorded 56.12% and CNN with linear regression recorded 57.48%. As a result, our proposed method is applied efficiently to cataract grading which have ordinal labels with imbalanced number of data among classes, also can be applied further to medical problems which have similar features to cataract and similar dataset configuration.
| Original language | English |
|---|---|
| Title of host publication | 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1630-1636 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781538613115 |
| DOIs | |
| Publication status | Published - 2019 Jul |
| Event | 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, Germany Duration: 2019 Jul 23 → 2019 Jul 27 |
Publication series
| Name | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
|---|---|
| ISSN (Print) | 1557-170X |
Conference
| Conference | 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 |
|---|---|
| Country | Germany |
| City | Berlin |
| Period | 19/7/23 → 19/7/27 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics
Cite this
Tournament Based Ranking CNN for the Cataract grading. / Kim, Dohyeun; Jun, Tae Joon; Eom, Youngsub; Kim, Cherry; Kim, Daeyoung.
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1630-1636 8856636 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Tournament Based Ranking CNN for the Cataract grading
AU - Kim, Dohyeun
AU - Jun, Tae Joon
AU - Eom, Youngsub
AU - Kim, Cherry
AU - Kim, Daeyoung
PY - 2019/7
Y1 - 2019/7
N2 - Solving the classification problem, unbalanced number of dataset among the classes often causes performance degradation. Especially when some classes dominate the other classes with its large number of datasets, trained model shows low performance in identifying the dominated classes. This is common case when it comes to medical dataset. Because the case with a serious degree is not quite usual, there are imbalance in number of dataset between severe case and normal cases of diseases. Also, there is difficulty in precisely identifying grade of medical data because of vagueness between them. To solve these problems, we propose new architecture of convolutional neural network named Tournament based Ranking CNN which shows remarkable performance gain in identifying dominated classes while trading off very small accuracy loss in dominating classes. Our Approach complemented problems that occur when method of Ranking CNN that aggregates outputs of multiple binary neural network models is applied to medical data. By having tournament structure in aggregating method and using very deep pretrained binary models, our proposed model recorded 68.36% of exact match accuracy, while Ranking CNN recorded 53.40%, pretrained Resnet recorded 56.12% and CNN with linear regression recorded 57.48%. As a result, our proposed method is applied efficiently to cataract grading which have ordinal labels with imbalanced number of data among classes, also can be applied further to medical problems which have similar features to cataract and similar dataset configuration.
AB - Solving the classification problem, unbalanced number of dataset among the classes often causes performance degradation. Especially when some classes dominate the other classes with its large number of datasets, trained model shows low performance in identifying the dominated classes. This is common case when it comes to medical dataset. Because the case with a serious degree is not quite usual, there are imbalance in number of dataset between severe case and normal cases of diseases. Also, there is difficulty in precisely identifying grade of medical data because of vagueness between them. To solve these problems, we propose new architecture of convolutional neural network named Tournament based Ranking CNN which shows remarkable performance gain in identifying dominated classes while trading off very small accuracy loss in dominating classes. Our Approach complemented problems that occur when method of Ranking CNN that aggregates outputs of multiple binary neural network models is applied to medical data. By having tournament structure in aggregating method and using very deep pretrained binary models, our proposed model recorded 68.36% of exact match accuracy, while Ranking CNN recorded 53.40%, pretrained Resnet recorded 56.12% and CNN with linear regression recorded 57.48%. As a result, our proposed method is applied efficiently to cataract grading which have ordinal labels with imbalanced number of data among classes, also can be applied further to medical problems which have similar features to cataract and similar dataset configuration.
UR - http://www.scopus.com/inward/record.url?scp=85077905848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077905848&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2019.8856636
DO - 10.1109/EMBC.2019.8856636
M3 - Conference contribution
C2 - 31946209
AN - SCOPUS:85077905848
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 1630
EP - 1636
BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
ER -