A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images
BackgroundParkinson’s disease (PD) is a prevalent long-term neurodegenerative disease. Though the criteria of PD diagnosis are relatively well defined, current diagnostic procedures using medical images are labor-intensive and expertise-demanding. Hence, highly integrated automatic diagnostic algori...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-08-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00874/full |
| _version_ | 1818608340732739584 |
|---|---|
| author | Jiahang Xu Jiahang Xu Fangyang Jiao Yechong Huang Xinzhe Luo Qian Xu Ling Li Xueling Liu Chuantao Zuo Ping Wu Xiahai Zhuang Xiahai Zhuang |
| author_facet | Jiahang Xu Jiahang Xu Fangyang Jiao Yechong Huang Xinzhe Luo Qian Xu Ling Li Xueling Liu Chuantao Zuo Ping Wu Xiahai Zhuang Xiahai Zhuang |
| author_sort | Jiahang Xu |
| collection | DOAJ |
| description | BackgroundParkinson’s disease (PD) is a prevalent long-term neurodegenerative disease. Though the criteria of PD diagnosis are relatively well defined, current diagnostic procedures using medical images are labor-intensive and expertise-demanding. Hence, highly integrated automatic diagnostic algorithms are desirable.MethodsIn this work, we propose an end-to-end multi-modality diagnostic framework, including segmentation, registration, feature extraction and machine learning, to analyze the features of striatum for PD diagnosis. Multi-modality images, including T1-weighted MRI and 11C-CFT PET, are integrated into the proposed framework. The reliability of this method is validated on a dataset with the paired images from 49 PD subjects and 18 Normal (NL) subjects.ResultsWe obtained a promising diagnostic accuracy in the PD/NL classification task. Meanwhile, several comparative experiments were conducted to validate the performance of the proposed framework.ConclusionWe demonstrated that (1) the automatic segmentation provides accurate results for the diagnostic framework, (2) the method combining multi-modality images generates a better prediction accuracy than the method with single-modality PET images, and (3) the volume of the striatum is proved to be irrelevant to PD diagnosis. |
| first_indexed | 2024-12-16T14:41:06Z |
| format | Article |
| id | doaj.art-20623a5188524dbe80b1b3e072e51e83 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-16T14:41:06Z |
| publishDate | 2019-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-20623a5188524dbe80b1b3e072e51e832022-12-21T22:27:55ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2019-08-011310.3389/fnins.2019.00874454296A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality ImagesJiahang Xu0Jiahang Xu1Fangyang Jiao2Yechong Huang3Xinzhe Luo4Qian Xu5Ling Li6Xueling Liu7Chuantao Zuo8Ping Wu9Xiahai Zhuang10Xiahai Zhuang11School of Data Science, Fudan University, Shanghai, ChinaFudan-Xinzailing Joint Research Center for Big Data, Fudan University, Shanghai, ChinaDepartment of Nuclear Medicine, Daping Hospital, Army Medical University, Chongqing, ChinaSchool of Data Science, Fudan University, Shanghai, ChinaSchool of Data Science, Fudan University, Shanghai, ChinaDepartment of Nuclear Medicine, North Huashan Hospital, Fudan University, Shanghai, ChinaPET Center, Huashan Hospital, Fudan University, Shanghai, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai, ChinaPET Center, Huashan Hospital, Fudan University, Shanghai, ChinaPET Center, Huashan Hospital, Fudan University, Shanghai, ChinaSchool of Data Science, Fudan University, Shanghai, ChinaFudan-Xinzailing Joint Research Center for Big Data, Fudan University, Shanghai, ChinaBackgroundParkinson’s disease (PD) is a prevalent long-term neurodegenerative disease. Though the criteria of PD diagnosis are relatively well defined, current diagnostic procedures using medical images are labor-intensive and expertise-demanding. Hence, highly integrated automatic diagnostic algorithms are desirable.MethodsIn this work, we propose an end-to-end multi-modality diagnostic framework, including segmentation, registration, feature extraction and machine learning, to analyze the features of striatum for PD diagnosis. Multi-modality images, including T1-weighted MRI and 11C-CFT PET, are integrated into the proposed framework. The reliability of this method is validated on a dataset with the paired images from 49 PD subjects and 18 Normal (NL) subjects.ResultsWe obtained a promising diagnostic accuracy in the PD/NL classification task. Meanwhile, several comparative experiments were conducted to validate the performance of the proposed framework.ConclusionWe demonstrated that (1) the automatic segmentation provides accurate results for the diagnostic framework, (2) the method combining multi-modality images generates a better prediction accuracy than the method with single-modality PET images, and (3) the volume of the striatum is proved to be irrelevant to PD diagnosis.https://www.frontiersin.org/article/10.3389/fnins.2019.00874/fullParkinson’s diseasemulti-modalityimage classificationU-Netstriatum |
| spellingShingle | Jiahang Xu Jiahang Xu Fangyang Jiao Yechong Huang Xinzhe Luo Qian Xu Ling Li Xueling Liu Chuantao Zuo Ping Wu Xiahai Zhuang Xiahai Zhuang A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images Frontiers in Neuroscience Parkinson’s disease multi-modality image classification U-Net striatum |
| title | A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images |
| title_full | A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images |
| title_fullStr | A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images |
| title_full_unstemmed | A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images |
| title_short | A Fully Automatic Framework for Parkinson’s Disease Diagnosis by Multi-Modality Images |
| title_sort | fully automatic framework for parkinson s disease diagnosis by multi modality images |
| topic | Parkinson’s disease multi-modality image classification U-Net striatum |
| url | https://www.frontiersin.org/article/10.3389/fnins.2019.00874/full |
| work_keys_str_mv | AT jiahangxu afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT jiahangxu afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT fangyangjiao afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT yechonghuang afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xinzheluo afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT qianxu afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT lingli afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xuelingliu afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT chuantaozuo afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT pingwu afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xiahaizhuang afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xiahaizhuang afullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT jiahangxu fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT jiahangxu fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT fangyangjiao fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT yechonghuang fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xinzheluo fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT qianxu fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT lingli fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xuelingliu fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT chuantaozuo fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT pingwu fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xiahaizhuang fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages AT xiahaizhuang fullyautomaticframeworkforparkinsonsdiseasediagnosisbymultimodalityimages |