FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease
In the past few years, the assessment of Parkinson’s disease (PD) has mainly been based on the clinician’s examination, the patient’s medical history, and self-report. Parkinson’s disease may be misdiagnosed due to a lack of clinical experience. Moreover, it is highly subjective and is not conducive...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/2/119 |
| _version_ | 1797620365231390720 |
|---|---|
| author | Ming Chen Tao Ren Pihai Sun Jianfei Wu Jinfeng Zhang Aite Zhao |
| author_facet | Ming Chen Tao Ren Pihai Sun Jianfei Wu Jinfeng Zhang Aite Zhao |
| author_sort | Ming Chen |
| collection | DOAJ |
| description | In the past few years, the assessment of Parkinson’s disease (PD) has mainly been based on the clinician’s examination, the patient’s medical history, and self-report. Parkinson’s disease may be misdiagnosed due to a lack of clinical experience. Moreover, it is highly subjective and is not conducive to reflecting a true result. Due to the high incidence rate and increasing trend of PD, it is significant to use objective monitoring and diagnostic tools for accurate and timely diagnosis. In this paper, we designed a low-level feature extractor that uses convolutional layers to extract local information about an image and a high-level feature extractor that extracts global information about an image through the autofocus mechanism. PD is detected by fusing local and global information. The model is trained and evaluated on two publicly available datasets. Experiments have shown that our model has a strong advantage in diagnosing whether people have PD; gait-based analysis and recognition can also provide effective evidence for the early diagnosis of PD. |
| first_indexed | 2024-03-11T08:40:14Z |
| format | Article |
| id | doaj.art-e7e82f589ea34a718ab97d6dab0650da |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T08:40:14Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-e7e82f589ea34a718ab97d6dab0650da2023-11-16T21:12:35ZengMDPI AGInformation2078-24892023-02-0114211910.3390/info14020119FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s DiseaseMing Chen0Tao Ren1Pihai Sun2Jianfei Wu3Jinfeng Zhang4Aite Zhao5College of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaIn the past few years, the assessment of Parkinson’s disease (PD) has mainly been based on the clinician’s examination, the patient’s medical history, and self-report. Parkinson’s disease may be misdiagnosed due to a lack of clinical experience. Moreover, it is highly subjective and is not conducive to reflecting a true result. Due to the high incidence rate and increasing trend of PD, it is significant to use objective monitoring and diagnostic tools for accurate and timely diagnosis. In this paper, we designed a low-level feature extractor that uses convolutional layers to extract local information about an image and a high-level feature extractor that extracts global information about an image through the autofocus mechanism. PD is detected by fusing local and global information. The model is trained and evaluated on two publicly available datasets. Experiments have shown that our model has a strong advantage in diagnosing whether people have PD; gait-based analysis and recognition can also provide effective evidence for the early diagnosis of PD.https://www.mdpi.com/2078-2489/14/2/119Parkinson’s diseasegait recognitionCNNTransformer |
| spellingShingle | Ming Chen Tao Ren Pihai Sun Jianfei Wu Jinfeng Zhang Aite Zhao FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease Information Parkinson’s disease gait recognition CNN Transformer |
| title | FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease |
| title_full | FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease |
| title_fullStr | FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease |
| title_full_unstemmed | FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease |
| title_short | FuseLGNet: Fusion of Local and Global Information for Detection of Parkinson’s Disease |
| title_sort | fuselgnet fusion of local and global information for detection of parkinson s disease |
| topic | Parkinson’s disease gait recognition CNN Transformer |
| url | https://www.mdpi.com/2078-2489/14/2/119 |
| work_keys_str_mv | AT mingchen fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease AT taoren fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease AT pihaisun fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease AT jianfeiwu fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease AT jinfengzhang fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease AT aitezhao fuselgnetfusionoflocalandglobalinformationfordetectionofparkinsonsdisease |