Abstract #1284

The neural network model that can consider the inhomogeneity of the judgements between different annotators: implementation for MRA diagnosis

Yasuhiko Tachibana¹, Masataka Nishimori², Masaaki Chiku³, Naoyuki Kitamura², Kensuke Umehara⁴, Junko Ota⁴, Takayuki Obata¹, and Tatsuya Higashi⁵

¹Applied MRI Research, Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, Chiba, Japan, ²MNES corporation, Tokyo, Japan, ³Medical Check Studio Ginza Clinic, Tokyo, Japan, ⁴Medical Informatics Section, QST Hospital, QST, Chiba, Japan, ⁵Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, Chiba, Japan

The neural network model was designed to judge the existence of aneurysms from brain MR angiography images. On the hypothesis that each radiologist (annotator) has a unique bias for decision, the network was designed so that it accepts input of who the annotator was as an additional information to compute the output. The hypothesis might be reasonable, and the model design might be useful because the accuracy of the trained model (area under the curve (AUC) in receiver operating characteristic (ROC) analysis) elevated significantly (P<.0001, DeLong test) by adding the information of who the annotator was.

This abstract and the presentation materials are available to members only; a login is required.

Join Here