BriefGPT.xyz
Jul, 2018
使用时变LSTM长期检测放射学异常
Longitudinal detection of radiological abnormalities with time-modulated LSTM
HTML
PDF
Ruggiero Santeramo, Samuel Withey, Giovanni Montana
TL;DR
本研究探讨利用长短时记忆网络(LSTMs)对放射学检查图像序列,包括报告进行建模,以提高分类性能,并发现对LSTM的简单修改可以显著提高分类性能,从而更好地检测胸部X光片上的异常,如心脏增大,实变,胸腔积液和食管裂孔疝。
Abstract
convolutional neural networks
(CNNs) have been successfully employed in recent years for the detection of
radiological abnormalities
in medical images such as plain x-rays. To date, most studies use CNNs on indiv
→