A Simple Localization and Classification Framework based on Template Matching and Self-Attention for TAO treatment diagnosis

  • Lee, Sanghyuck; 
  • Song, Taekyung; 
  • Kim, Min-Gi; 
  • Song, Da-Hyun; 
  • Park, Sangkeun; 
  • ... Lee, Jaesung
Citations

SCOPUS

0

초록

Treatment decision of thyroid-Associated orbitopathy is crucial to alleviate different side effect of the disease. Moreover, recent studies show the possibility of neural network-based treatment prediction. However, existing neural networks are affected by regions with fewer disease symptoms. Moreover, fine-grained segmentation or cropping is time-consuming and requires a large resource of professionals. In this paper, a simple localization and classification framework is proposed based on template matching and self-Attention. Our experimental results show that the proposed method performs statistically better than the existing method with the simple effort of pre-defining eight orbit templates. © 2024 IEEE.

키워드

Convolutional neural network; Self-Attention; Template matching; Thyroid-Associated orbitopathy; Transformer
제목
A Simple Localization and Classification Framework based on Template Matching and Self-Attention for TAO treatment diagnosis
저자
Lee, Sanghyuck; Song, Taekyung; Kim, Min-Gi; Song, Da-Hyun; Park, Sangkeun; Lee, Jaesung
DOI
10.1109/ICCE59016.2024.10444295
발행일
2024-01
유형
Conference paper
저널명
Digest of Technical Papers - IEEE International Conference on Consumer Electronics
권
2024 IEEE