• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

Ȩ Ȩ > ¿¬±¸¹®Çå >

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Ãʱ¤°¢ ¾ÈÀú»çÁøÀ» ÀÌ¿ëÇÑ ´«º´ ŽÁö ÀΰøÁö´É ¸ðµ¨ÀÇ ¼º´É Æò°¡
¿µ¹®Á¦¸ñ(English Title) Performance Evaluation of Artificial Intelligence on Detecting Eyes Diseases Using Ultra-wide-field Images
ÀúÀÚ(Author) NGUYEN DUC TOAN   Á¤°æÈñ   º¯±Ô¸°   ÃßÇö½ÂNGUYEN DUC TOAN   Á¤°æÈñ   º¯±Ô¸°   ÃßÇö½Â   Kyung-hee Jung   Gyu-rin Byun   Hyun-seung Choo  
¿ø¹®¼ö·Ïó(Citation) VOL 49 NO. 01 PP. 1100 ~ 1102 (2022. 06)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(English Abstract)
With the development of deep learning, medical image analysis has been widely adopted with the combination with neural networks to achieve competitive results. As stated in World Health Organisation (WHO) website, vision impairment could affect young children in such a way that they would experience delayed motor, language, emotional, social and cognitive development and lifelong consequences. However, most of the cases related to visual impairment could be prevented by early diagnosis and treatment by a doctor with the help of the patients eyes¡¯ scans. In this work, we investigate and make comparison of the most recent deep learning methods that perform in retinal fundus images. Our implementation shows promising results of 95% AUC on ResNet152. Moreover, we provide a generated heatmap and a sample output that could help doctors in this crucial task.
Å°¿öµå(Keyword)
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå