Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images

BackgroundThe traditional procedure of intracranial aneurysm (IA) diagnosis and evaluation in MRA is manually operated, which is time-consuming and labor-intensive. In this study, a deep learning model was established to diagnose and measure IA automatically based on the original MR images.MethodsA...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingning Yang, Fengxi Chen, Li Li, Rong Zeng, Jiaqing Li, Jingxu Xu, Chencui Huang, Junbang Feng, Chuanming Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2025.1544571/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324175540355072
author Qingning Yang
Fengxi Chen
Li Li
Rong Zeng
Jiaqing Li
Jingxu Xu
Chencui Huang
Junbang Feng
Chuanming Li
author_facet Qingning Yang
Fengxi Chen
Li Li
Rong Zeng
Jiaqing Li
Jingxu Xu
Chencui Huang
Junbang Feng
Chuanming Li
author_sort Qingning Yang
collection DOAJ
description BackgroundThe traditional procedure of intracranial aneurysm (IA) diagnosis and evaluation in MRA is manually operated, which is time-consuming and labor-intensive. In this study, a deep learning model was established to diagnose and measure IA automatically based on the original MR images.MethodsA total of 1,014 IAs (from 852 patients) from hospital 1 were included and randomly divided into training, testing, and internal validation sets in a 7:2:1 ratio. Additionally, 315 patients (179 cases with IA and 136 cases without IA) from hospital 2 were used for independent validation. A deep learning model of MR 3DUnet was established for IA diagnosis and size measurement. The true positive (TP), false positive (FP), false negative (FN), recall, sensitivity, and specificity indices were used to evaluate the diagnosis performance of MR 3DUnet. The two-sample t-test was used to compare the size measurement results of MR 3DUnet and two radiologists. A p-value of < 0.05 was considered statistically significant.ResultsThe fully automatic model processed the original MRA data in 13.6 s and provided real-time results, including IA diagnosis and size measurement. For the IA diagnosis, in the training, testing, and internal validation sets, the recall rates were 0.80, 0.75, and 0.79, and the sensitivities were 0.82, 0.75, and 0.75, respectively. In the independent validation set, the recall rate, sensitivity, specificity, and AUC were 0.71, 0.74, 0.77, and 0.75, respectively. Subgroup analysis showed a recall rate of 0.74 for IA diagnosis based on DSA. For IA size measurement, no significant difference was found between our MR 3DUnet and the manual measurements of DSA or MRA.ConclusionIn this study, a one-click, fully automatic deep learning model was developed for automatic IA diagnosis and size measurement based on 2D original images. It has the potential to significantly improve doctors’ work efficiency and reduce patients’ examination time, making it highly valuable in clinical practice.
format Article
id doaj-art-b09c2358df1d4710a23df6f34f31aff5
institution Kabale University
issn 1664-2295
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj-art-b09c2358df1d4710a23df6f34f31aff52025-08-20T03:48:47ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-04-011610.3389/fneur.2025.15445711544571Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw imagesQingning Yang0Fengxi Chen1Li Li2Rong Zeng3Jiaqing Li4Jingxu Xu5Chencui Huang6Junbang Feng7Chuanming Li8Chongqing Key Laboratory of Emergency Medicine, Chongqing, China; Medical Imaging Department, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, ChinaDepartment of Radiology, 7T Magnetic Resonance Translational Medicine Research Center, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, ChinaPathology Department, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, ChinaDepartment of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Information, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, ChinaDepartment of Research Collaboration, R&D Center, Beijing Deepwise and League of PHD Technology Co., Ltd., Beijing, ChinaDepartment of Research Collaboration, R&D Center, Beijing Deepwise and League of PHD Technology Co., Ltd., Beijing, ChinaChongqing Key Laboratory of Emergency Medicine, Chongqing, China; Medical Imaging Department, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, ChinaChongqing Key Laboratory of Emergency Medicine, Chongqing, China; Medical Imaging Department, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, ChinaBackgroundThe traditional procedure of intracranial aneurysm (IA) diagnosis and evaluation in MRA is manually operated, which is time-consuming and labor-intensive. In this study, a deep learning model was established to diagnose and measure IA automatically based on the original MR images.MethodsA total of 1,014 IAs (from 852 patients) from hospital 1 were included and randomly divided into training, testing, and internal validation sets in a 7:2:1 ratio. Additionally, 315 patients (179 cases with IA and 136 cases without IA) from hospital 2 were used for independent validation. A deep learning model of MR 3DUnet was established for IA diagnosis and size measurement. The true positive (TP), false positive (FP), false negative (FN), recall, sensitivity, and specificity indices were used to evaluate the diagnosis performance of MR 3DUnet. The two-sample t-test was used to compare the size measurement results of MR 3DUnet and two radiologists. A p-value of < 0.05 was considered statistically significant.ResultsThe fully automatic model processed the original MRA data in 13.6 s and provided real-time results, including IA diagnosis and size measurement. For the IA diagnosis, in the training, testing, and internal validation sets, the recall rates were 0.80, 0.75, and 0.79, and the sensitivities were 0.82, 0.75, and 0.75, respectively. In the independent validation set, the recall rate, sensitivity, specificity, and AUC were 0.71, 0.74, 0.77, and 0.75, respectively. Subgroup analysis showed a recall rate of 0.74 for IA diagnosis based on DSA. For IA size measurement, no significant difference was found between our MR 3DUnet and the manual measurements of DSA or MRA.ConclusionIn this study, a one-click, fully automatic deep learning model was developed for automatic IA diagnosis and size measurement based on 2D original images. It has the potential to significantly improve doctors’ work efficiency and reduce patients’ examination time, making it highly valuable in clinical practice.https://www.frontiersin.org/articles/10.3389/fneur.2025.1544571/fullmagnetic resonance angiographyintracranial aneurysmdeep learningdiagnosismeasurement
spellingShingle Qingning Yang
Fengxi Chen
Li Li
Rong Zeng
Jiaqing Li
Jingxu Xu
Chencui Huang
Junbang Feng
Chuanming Li
Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
Frontiers in Neurology
magnetic resonance angiography
intracranial aneurysm
deep learning
diagnosis
measurement
title Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
title_full Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
title_fullStr Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
title_full_unstemmed Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
title_short Automatic diagnosis and measurement of intracranial aneurysms using deep learning in MRA raw images
title_sort automatic diagnosis and measurement of intracranial aneurysms using deep learning in mra raw images
topic magnetic resonance angiography
intracranial aneurysm
deep learning
diagnosis
measurement
url https://www.frontiersin.org/articles/10.3389/fneur.2025.1544571/full
work_keys_str_mv AT qingningyang automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT fengxichen automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT lili automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT rongzeng automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT jiaqingli automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT jingxuxu automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT chencuihuang automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT junbangfeng automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages
AT chuanmingli automaticdiagnosisandmeasurementofintracranialaneurysmsusingdeeplearninginmrarawimages