Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms
Auto-detection of cerebral aneurysms via convolutional neural network (CNN) is being increasingly reported. However, few studies to date have accurately predicted the risk, but not the diagnosis itself. We developed a multi-view CNN for the prediction of rupture risk involving small unruptured intra...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/11/4/239 |
| _version_ | 1797540167971504128 |
|---|---|
| author | Jun Hyong Ahn Heung Cheol Kim Jong Kook Rhim Jeong Jin Park Dick Sigmund Min Chan Park Jae Hoon Jeong Jin Pyeong Jeon |
| author_facet | Jun Hyong Ahn Heung Cheol Kim Jong Kook Rhim Jeong Jin Park Dick Sigmund Min Chan Park Jae Hoon Jeong Jin Pyeong Jeon |
| author_sort | Jun Hyong Ahn |
| collection | DOAJ |
| description | Auto-detection of cerebral aneurysms via convolutional neural network (CNN) is being increasingly reported. However, few studies to date have accurately predicted the risk, but not the diagnosis itself. We developed a multi-view CNN for the prediction of rupture risk involving small unruptured intracranial aneurysms (UIAs) based on three-dimensional (3D) digital subtraction angiography (DSA). The performance of a multi-view CNN-ResNet50 in accurately predicting the rupture risk (high vs. non-high) of UIAs in the anterior circulation measuring less than 7 mm in size was compared with various CNN architectures (AlexNet and VGG16), with similar type but different layers (ResNet101 and ResNet152), and single image-based CNN (single-view ResNet50). The sensitivity, specificity, and overall accuracy of risk prediction were estimated and compared according to CNN architecture. The study included 364 UIAs in training and 93 in test datasets. A multi-view CNN-ResNet50 exhibited a sensitivity of 81.82 (66.76–91.29)%, a specificity of 81.63 (67.50–90.76)%, and an overall accuracy of 81.72 (66.98–90.92)% for risk prediction. AlexNet, VGG16, ResNet101, ResNet152, and single-view CNN-ResNet50 showed similar specificity. However, the sensitivity and overall accuracy were decreased (AlexNet, 63.64% and 76.34%; VGG16, 68.18% and 74.19%; ResNet101, 68.18% and 73.12%; ResNet152, 54.55% and 72.04%; and single-view CNN-ResNet50, 50.00% and 64.52%) compared with multi-view CNN-ResNet50. Regarding F1 score, it was the highest in multi-view CNN-ResNet50 (80.90 (67.29–91.81)%). Our study suggests that multi-view CNN-ResNet50 may be feasible to assess the rupture risk in small-sized UIAs. |
| first_indexed | 2024-03-10T12:56:15Z |
| format | Article |
| id | doaj.art-8a59f41cd16c47c5a8a1ae295f501742 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T12:56:15Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-8a59f41cd16c47c5a8a1ae295f5017422023-11-21T11:53:08ZengMDPI AGJournal of Personalized Medicine2075-44262021-03-0111423910.3390/jpm11040239Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial AneurysmsJun Hyong Ahn0Heung Cheol Kim1Jong Kook Rhim2Jeong Jin Park3Dick Sigmund4Min Chan Park5Jae Hoon Jeong6Jin Pyeong Jeon7Department of Neurosurgery, College of Medicine, Hallym University, Chuncheon 24252, KoreaDepartment of Radioilogy, College of Medicine, Hallym University, Chuncheon 24252, KoreaDepartment of Neurosurgery, College of Medicine, Jeju National University, Jeju 63243, KoreaDepartment of Neurology, Konkuk University Medical Center, Seoul 05030, KoreaAIDOT Inc., Seoul 05854, KoreaAIDOT Inc., Seoul 05854, KoreaAIDOT Inc., Seoul 05854, KoreaDepartment of Neurosurgery, College of Medicine, Hallym University, Chuncheon 24252, KoreaAuto-detection of cerebral aneurysms via convolutional neural network (CNN) is being increasingly reported. However, few studies to date have accurately predicted the risk, but not the diagnosis itself. We developed a multi-view CNN for the prediction of rupture risk involving small unruptured intracranial aneurysms (UIAs) based on three-dimensional (3D) digital subtraction angiography (DSA). The performance of a multi-view CNN-ResNet50 in accurately predicting the rupture risk (high vs. non-high) of UIAs in the anterior circulation measuring less than 7 mm in size was compared with various CNN architectures (AlexNet and VGG16), with similar type but different layers (ResNet101 and ResNet152), and single image-based CNN (single-view ResNet50). The sensitivity, specificity, and overall accuracy of risk prediction were estimated and compared according to CNN architecture. The study included 364 UIAs in training and 93 in test datasets. A multi-view CNN-ResNet50 exhibited a sensitivity of 81.82 (66.76–91.29)%, a specificity of 81.63 (67.50–90.76)%, and an overall accuracy of 81.72 (66.98–90.92)% for risk prediction. AlexNet, VGG16, ResNet101, ResNet152, and single-view CNN-ResNet50 showed similar specificity. However, the sensitivity and overall accuracy were decreased (AlexNet, 63.64% and 76.34%; VGG16, 68.18% and 74.19%; ResNet101, 68.18% and 73.12%; ResNet152, 54.55% and 72.04%; and single-view CNN-ResNet50, 50.00% and 64.52%) compared with multi-view CNN-ResNet50. Regarding F1 score, it was the highest in multi-view CNN-ResNet50 (80.90 (67.29–91.81)%). Our study suggests that multi-view CNN-ResNet50 may be feasible to assess the rupture risk in small-sized UIAs.https://www.mdpi.com/2075-4426/11/4/239intracranial aneurysmconvolutional neural networkangiography |
| spellingShingle | Jun Hyong Ahn Heung Cheol Kim Jong Kook Rhim Jeong Jin Park Dick Sigmund Min Chan Park Jae Hoon Jeong Jin Pyeong Jeon Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms Journal of Personalized Medicine intracranial aneurysm convolutional neural network angiography |
| title | Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms |
| title_full | Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms |
| title_fullStr | Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms |
| title_full_unstemmed | Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms |
| title_short | Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms |
| title_sort | multi view convolutional neural networks in rupture risk assessment of small unruptured intracranial aneurysms |
| topic | intracranial aneurysm convolutional neural network angiography |
| url | https://www.mdpi.com/2075-4426/11/4/239 |
| work_keys_str_mv | AT junhyongahn multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT heungcheolkim multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT jongkookrhim multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT jeongjinpark multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT dicksigmund multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT minchanpark multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT jaehoonjeong multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms AT jinpyeongjeon multiviewconvolutionalneuralnetworksinruptureriskassessmentofsmallunrupturedintracranialaneurysms |