Multidimensional Deep Learning Reduces False-Positives in the Automated Detection of Cerebral Aneurysms on Time-Of-Flight Magnetic Resonance Angiography: A Multi-Center Study

Yuki Terasaki; Hajime Yokota; Kohei Tashiro; Takuma Maejima; Takashi Takeuchi; Ryuna Kurosawa; Shoma Yamauchi; Akiyo Takada; Hiroki Mukai; Kenji Ohira; Joji Ota; Takuro Horikoshi; Yasukuni Mori; Takashi Uno; Hiroki Suyari

doi:10.3389/fneur.2021.742126

Multidimensional Deep Learning Reduces False-Positives in the Automated Detection of Cerebral Aneurysms on Time-Of-Flight Magnetic Resonance Angiography: A Multi-Center Study

Front Neurol. 2022 Jan 18:12:742126. doi: 10.3389/fneur.2021.742126. eCollection 2021.

Authors

Yuki Terasaki^{1

2}, Hajime Yokota³, Kohei Tashiro¹, Takuma Maejima⁴, Takashi Takeuchi⁴, Ryuna Kurosawa⁴, Shoma Yamauchi⁴, Akiyo Takada⁴, Hiroki Mukai⁴, Kenji Ohira⁴, Joji Ota⁴, Takuro Horikoshi⁴, Yasukuni Mori⁵, Takashi Uno³, Hiroki Suyari⁵

Affiliations

¹ Graduate School of Science and Engineering, Chiba University, Chiba, Japan.
² Department of EC Platform, ZOZO Technologies, Inc., Tokyo, Japan.
³ Department of Diagnostic Radiology and Radiation Oncology, Graduate School of Medicine, Chiba University, Chiba, Japan.
⁴ Department of Radiology, Chiba University Hospital, Chiba, Japan.
⁵ Graduate School of Engineering, Chiba University, Chiba, Japan.

Abstract

Current deep learning-based cerebral aneurysm detection demonstrates high sensitivity, but produces numerous false-positives (FPs), which hampers clinical application of automated detection systems for time-of-flight magnetic resonance angiography. To reduce FPs while maintaining high sensitivity, we developed a multidimensional convolutional neural network (MD-CNN) designed to unite planar and stereoscopic information about aneurysms. This retrospective study enrolled time-of-flight magnetic resonance angiography images of cerebral aneurysms from three institutions from June 2006 to April 2019. In the internal test, 80% of the entire data set was used for model training and 20% for the test, while for the external tests, data from different pairs of the three institutions were used for training and the remaining one for testing. Images containing aneurysms > 15 mm and images without aneurysms were excluded. Three deep learning models [planar information-only (2D-CNN), stereoscopic information-only (3D-CNN), and multidimensional information (MD-CNN)] were trained to classify whether the voxels contained aneurysms, and they were evaluated on each test. The performance of each model was assessed using free-response operating characteristic curves. In total, 732 aneurysms (5.9 ± 2.5 mm) of 559 cases (327, 120, and 112 from institutes A, B, and C; 469 and 263 for 1.5T and 3.0T MRI) were included in this study. In the internal test, the highest sensitivities were 80.4, 87.4, and 82.5%, and the FPs were 6.1, 7.1, and 5.0 FPs/case at a fixed sensitivity of 80% for the 2D-CNN, 3D-CNN, and MD-CNN, respectively. In the external test, the highest sensitivities were 82.1, 86.5, and 89.1%, and 5.9, 7.4, and 4.2 FPs/cases for them, respectively. MD-CNN was a new approach to maintain sensitivity and reduce the FPs simultaneously.

Keywords: autodetection; cerebral aneurysm; deep learning; false positive; magnetic resonance angiography; multidimensional convolutional neural network.