Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network
Multi-contrast magnetic resonance imaging (MRI) is wildly applied to identify tuberous sclerosis complex (TSC) children in a clinic. In this work, a deep convolutional neural network with multi-contrast MRI is proposed to diagnose pediatric TSC. Firstly, by combining T2W and FLAIR images, a new synt...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/7/870 |
| _version_ | 1827367723492966400 |
|---|---|
| author | Dian Jiang Jianxiang Liao Cailei Zhao Xia Zhao Rongbo Lin Jun Yang Zhi-Cheng Li Yihang Zhou Yanjie Zhu Dong Liang Zhanqi Hu Haifeng Wang |
| author_facet | Dian Jiang Jianxiang Liao Cailei Zhao Xia Zhao Rongbo Lin Jun Yang Zhi-Cheng Li Yihang Zhou Yanjie Zhu Dong Liang Zhanqi Hu Haifeng Wang |
| author_sort | Dian Jiang |
| collection | DOAJ |
| description | Multi-contrast magnetic resonance imaging (MRI) is wildly applied to identify tuberous sclerosis complex (TSC) children in a clinic. In this work, a deep convolutional neural network with multi-contrast MRI is proposed to diagnose pediatric TSC. Firstly, by combining T2W and FLAIR images, a new synthesis modality named FLAIR<sub>3</sub> was created to enhance the contrast between TSC lesions and normal brain tissues. After that, a deep weighted fusion network (DWF-net) using a late fusion strategy is proposed to diagnose TSC children. In experiments, a total of 680 children were enrolled, including 331 healthy children and 349 TSC children. The experimental results indicate that FLAIR<sub>3</sub> successfully enhances the visibility of TSC lesions and improves the classification performance. Additionally, the proposed DWF-net delivers a superior classification performance compared to previous methods, achieving an AUC of 0.998 and an accuracy of 0.985. The proposed method has the potential to be a reliable computer-aided diagnostic tool for assisting radiologists in diagnosing TSC children. |
| first_indexed | 2024-03-08T09:16:14Z |
| format | Article |
| id | doaj.art-7e15b73a957e407e9d0333f46f40ea2b |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-08T09:16:14Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-7e15b73a957e407e9d0333f46f40ea2b2024-01-31T15:04:49ZengMDPI AGBioengineering2306-53542023-07-0110787010.3390/bioengineering10070870Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion NetworkDian Jiang0Jianxiang Liao1Cailei Zhao2Xia Zhao3Rongbo Lin4Jun Yang5Zhi-Cheng Li6Yihang Zhou7Yanjie Zhu8Dong Liang9Zhanqi Hu10Haifeng Wang11Research Centre for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen 518000, ChinaDepartment of Radiology, Shenzhen Children’s Hospital, Shenzhen 518000, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen 518000, ChinaDepartment of Emergency, Shenzhen Children’s Hospital, Shenzhen 518000, ChinaResearch Centre for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaResearch Centre for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaResearch Centre for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaResearch Centre for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaDepartment of Neurology, Shenzhen Children’s Hospital, Shenzhen 518000, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaMulti-contrast magnetic resonance imaging (MRI) is wildly applied to identify tuberous sclerosis complex (TSC) children in a clinic. In this work, a deep convolutional neural network with multi-contrast MRI is proposed to diagnose pediatric TSC. Firstly, by combining T2W and FLAIR images, a new synthesis modality named FLAIR<sub>3</sub> was created to enhance the contrast between TSC lesions and normal brain tissues. After that, a deep weighted fusion network (DWF-net) using a late fusion strategy is proposed to diagnose TSC children. In experiments, a total of 680 children were enrolled, including 331 healthy children and 349 TSC children. The experimental results indicate that FLAIR<sub>3</sub> successfully enhances the visibility of TSC lesions and improves the classification performance. Additionally, the proposed DWF-net delivers a superior classification performance compared to previous methods, achieving an AUC of 0.998 and an accuracy of 0.985. The proposed method has the potential to be a reliable computer-aided diagnostic tool for assisting radiologists in diagnosing TSC children.https://www.mdpi.com/2306-5354/10/7/870tuberous sclerosis complexchildrenconvolutional neural networkmulti-contrast MRIrare neurodevelopmental disorder |
| spellingShingle | Dian Jiang Jianxiang Liao Cailei Zhao Xia Zhao Rongbo Lin Jun Yang Zhi-Cheng Li Yihang Zhou Yanjie Zhu Dong Liang Zhanqi Hu Haifeng Wang Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network Bioengineering tuberous sclerosis complex children convolutional neural network multi-contrast MRI rare neurodevelopmental disorder |
| title | Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network |
| title_full | Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network |
| title_fullStr | Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network |
| title_full_unstemmed | Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network |
| title_short | Recognizing Pediatric Tuberous Sclerosis Complex Based on Multi-Contrast MRI and Deep Weighted Fusion Network |
| title_sort | recognizing pediatric tuberous sclerosis complex based on multi contrast mri and deep weighted fusion network |
| topic | tuberous sclerosis complex children convolutional neural network multi-contrast MRI rare neurodevelopmental disorder |
| url | https://www.mdpi.com/2306-5354/10/7/870 |
| work_keys_str_mv | AT dianjiang recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT jianxiangliao recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT caileizhao recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT xiazhao recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT rongbolin recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT junyang recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT zhichengli recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT yihangzhou recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT yanjiezhu recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT dongliang recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT zhanqihu recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork AT haifengwang recognizingpediatrictuberoussclerosiscomplexbasedonmulticontrastmrianddeepweightedfusionnetwork |