Use of deep convolutional neural network-based features for detection of cardiac sarcoidosis from polar map
Conclusions: The classification performance of DCNN-based features outperformed the CoV-based classification performance. Experimental results suggested that DCNN-based high-dimensional features have a potential of semi-automated diagnosis of CS.
Source: Journal of Nuclear Medicine - Category: Nuclear Medicine Authors: Togo, R., Hirata, K., Manabe, O., Ohira, H., Tsujino, I., Ogawa, T., Haseyama, M., Shiga, T. Tags: Deep Learning In Molecular Imaging Studies Source Type: research
More News: Arrhythmia | Cardiology | Congestive Heart Failure | Heart | Heart Failure | Japan Health | Learning | Nuclear Medicine | Perfusion | PET Scan | Sarcoidosis | Study | Togo Health | Training | Universities & Medical Training