TY - CONF
T1 - 2Sranking-cnn
T2 - 29th British Machine Vision Conference, BMVC 2018
AU - Jun, Tae Joon
AU - Kim, Dohyeun
AU - Nguyen, Hoang Minh
AU - Kim, Daeyoung
AU - Eom, Youngsub
N1 - Funding Information:
This research was supported by International Research & Development Program of the National Research Foundation of Korea(NRF) funded by the Ministry of Science, ICT&Future Planning of Korea (2016K1A3A7A03952054) and support of Korea University Ansan Hospital providing fundus images and clinical advices for this research are gratefully acknowledged.
Publisher Copyright:
© 2018. The copyright of this document resides with its authors.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Glaucoma is a disease in which the optic nerve is chronically damaged by the elevation of the intra-ocular pressure, resulting in visual field defect. Therefore, it is important to monitor and treat suspected patients before they are confirmed with glaucoma. In this paper, we propose a 2-stage ranking-CNN that classifies fundus images as normal, suspicious, and glaucoma. Furthermore, we propose a method of using the class activation map as a mask filter and combining it with the original fundus image as an intermediate input. Our results have improved the average accuracy by about 10% over the existing 3-class CNN and ranking-CNN, and especially improved the sensitivity of suspicious class by more than 20% over 3-class CNN. In addition, the extracted ROI was also found to overlap with the diagnostic criteria of the physician. The method we propose is expected to be efficiently applied to any medical data where there is a suspicious condition between normal and disease.
AB - Glaucoma is a disease in which the optic nerve is chronically damaged by the elevation of the intra-ocular pressure, resulting in visual field defect. Therefore, it is important to monitor and treat suspected patients before they are confirmed with glaucoma. In this paper, we propose a 2-stage ranking-CNN that classifies fundus images as normal, suspicious, and glaucoma. Furthermore, we propose a method of using the class activation map as a mask filter and combining it with the original fundus image as an intermediate input. Our results have improved the average accuracy by about 10% over the existing 3-class CNN and ranking-CNN, and especially improved the sensitivity of suspicious class by more than 20% over 3-class CNN. In addition, the extracted ROI was also found to overlap with the diagnostic criteria of the physician. The method we propose is expected to be efficiently applied to any medical data where there is a suspicious condition between normal and disease.
UR - http://www.scopus.com/inward/record.url?scp=85084017770&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084017770&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85084017770
Y2 - 3 September 2018 through 6 September 2018
ER -