Journal Article

Convolutional neural network-based segmentation can help in assessing the substantia nigra in neuromelanin MRI

Hori, Masaaki, Wada, Akihiko, Otsuka, Yujiro, Oyama, Genko, Kamagata, Koji, Ogawa, Takashi, Andica, Christina, Shimo, Yashushi, Suzuki, Michimasa, Aoki, Shigeki, Saccenti, Laetitia, Le Berre, Alice, Hattori, Nobutaka, Hagiwara, Akifumi, Irie, Ryusuke, Hatano, Taku, Takeshige-Amano, Haruka, Umemura, Atsushi

2019

Overview

Purpose This study aimed to evaluate the accuracy and diagnostic test performance of the U-net-based segmentation method in neuromelanin magnetic resonance imaging (NM-MRI) compared to the established manual segmentation method for Parkinson’s disease (PD) diagnosis. Methods NM-MRI datasets from two different 3T-scanners were used: a “principal dataset” with 122 participants and an “external validation dataset” with 24 participants, including 62 and 12 PD patients, respectively. Two radiologists performed SNpc manual segmentation. Inter-reader precision was determined using Dice coefficients. The U-net was trained with manual segmentation as ground truth and Dice coefficients used to measure accuracy. Training and validation steps were performed on the principal dataset using a 4-fold cross-validation method. We tested the U-net on the external validation dataset. SNpc hyperintense areas were estimated from U-net and manual segmentation masks, replicating a previously validated thresholding method, and their diagnostic test performances for PD determined. Results For SNpc segmentation, U-net accuracy was comparable to inter-reader precision in the principal dataset (Dice coefficient: U-net, 0.83 ± 0.04; inter-reader, 0.83 ± 0.04), but lower in external validation dataset (Dice coefficient: U-net, 079 ± 0.04; inter-reader, 0.85 ± 0.03). Diagnostic test performances for PD were comparable between U-net and manual segmentation methods in both principal (area under the receiver operating characteristic curve: U-net, 0.950; manual, 0.948) and external (U-net, 0.944; manual, 0.931) datasets. Conclusion U-net segmentation provided relatively high accuracy in the evaluation of the SNpc in NM-MRI and yielded diagnostic performance comparable to that of the established manual method.

• Publisher: Springer Berlin Heidelberg,Springer Nature B.V
• Subject: Accuracy / Aged / Artificial intelligence / Artificial neural networks / Case-Control Studies / Coefficients / Datasets / Diagnostic Neuroradiology / Diagnostic systems / Diagnostic tests / Female / Ground truth / Humans / Image Interpretation, Computer-Assisted - methods / Image processing / Image segmentation / Imaging / Magnetic resonance imaging / Magnetic Resonance Imaging - methods / Male / Masks / Medicine / Medicine & Public Health / Melanins - metabolism / Middle Aged / Movement disorders / Neural networks / Neural Networks, Computer / Neurodegenerative diseases / Neurology / Neuroradiology / Neurosciences / Neurosurgery / NMR / Nuclear magnetic resonance / Parkinson Disease - diagnostic imaging / Parkinson Disease - metabolism / Parkinson Disease - pathology / Parkinson's disease / Radiology / Replication / Retrospective Studies / Scanners / Substantia nigra / Substantia Nigra - diagnostic imaging / Substantia Nigra - metabolism / Substantia Nigra - pathology