Journal Article

Performance changes due to differences in training data for cerebral aneurysm detection in head MR angiography images

Hanaoka Shouhei, Watadani Takeyuki, Miki Soichiro, Abe, Osamu, Nomura Yukihiro, Hayashi Naoto, Nakao Takahiro, Yoshikawa Takeharu

2021

Overview

PurposeThe performance of computer-aided detection (CAD) software depends on the quality and quantity of the dataset used for machine learning. If the data characteristics in development and practical use are different, the performance of CAD software degrades. In this study, we investigated changes in detection performance due to differences in training data for cerebral aneurysm detection software in head magnetic resonance angiography images.Materials and methodsWe utilized three types of CAD software for cerebral aneurysm detection in MRA images, which were based on 3D local intensity structure analysis, graph-based features, and convolutional neural network. For each type of CAD software, we compared three types of training pattern, which were two types of training using single-site data and one type of training using multisite data. We also carried out internal and external evaluations.ResultsIn training using single-site data, the performance of CAD software largely and unpredictably fluctuated when the training dataset was changed. Training using multisite data did not show the lowest performance among the three training patterns for any CAD software and dataset.ConclusionThe training of cerebral aneurysm detection software using data collected from multiple sites is desirable to ensure the stable performance of the software.

• Publisher: Springer Nature B.V
• Subject: Aneurysm / Aneurysms / Angiography / Artificial neural networks / Computer programs / Datasets / Learning algorithms / Machine learning / Magnetic resonance / Magnetic resonance imaging / Medical imaging / Neural networks / Software / Structural analysis / Training