An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1-weighted images
© 2023 The Authors. Human Brain Mapping published by Wiley Periodicals LLC..
Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL-based pipeline for automatic PD diagnosis based on QSM and T1-weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE-ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient-weighted class activation mapping (Grad-CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:44 |
---|---|
Enthalten in: |
Human brain mapping - 44(2023), 12 vom: 15. Aug., Seite 4426-4438 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Wang, Yida [VerfasserIn] |
---|
Links: |
---|
Themen: |
Deep learning |
---|
Anmerkungen: |
Date Completed 25.07.2023 Date Revised 26.07.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1002/hbm.26399 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM358365880 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM358365880 | ||
003 | DE-627 | ||
005 | 20231226074604.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1002/hbm.26399 |2 doi | |
028 | 5 | 2 | |a pubmed24n1194.xml |
035 | |a (DE-627)NLM358365880 | ||
035 | |a (NLM)37335041 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Wang, Yida |e verfasserin |4 aut | |
245 | 1 | 3 | |a An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1-weighted images |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 25.07.2023 | ||
500 | |a Date Revised 26.07.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023 The Authors. Human Brain Mapping published by Wiley Periodicals LLC. | ||
520 | |a Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL-based pipeline for automatic PD diagnosis based on QSM and T1-weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE-ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient-weighted class activation mapping (Grad-CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Parkinson's disease | |
650 | 4 | |a deep learning | |
650 | 4 | |a quantitative susceptibility mapping | |
650 | 4 | |a segmentation | |
700 | 1 | |a He, Naying |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Chunyan |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Youmin |e verfasserin |4 aut | |
700 | 1 | |a Wang, Chenglong |e verfasserin |4 aut | |
700 | 1 | |a Huang, Pei |e verfasserin |4 aut | |
700 | 1 | |a Jin, Zhijia |e verfasserin |4 aut | |
700 | 1 | |a Li, Yan |e verfasserin |4 aut | |
700 | 1 | |a Cheng, Zenghui |e verfasserin |4 aut | |
700 | 1 | |a Liu, Yu |e verfasserin |4 aut | |
700 | 1 | |a Wang, Xinhui |e verfasserin |4 aut | |
700 | 1 | |a Chen, Chen |e verfasserin |4 aut | |
700 | 1 | |a Cheng, Jingliang |e verfasserin |4 aut | |
700 | 1 | |a Liu, Fangtao |e verfasserin |4 aut | |
700 | 1 | |a Haacke, Ewart Mark |e verfasserin |4 aut | |
700 | 1 | |a Chen, Shengdi |e verfasserin |4 aut | |
700 | 1 | |a Yang, Guang |e verfasserin |4 aut | |
700 | 1 | |a Yan, Fuhua |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Human brain mapping |d 1994 |g 44(2023), 12 vom: 15. Aug., Seite 4426-4438 |w (DE-627)NLM09362719X |x 1097-0193 |7 nnns |
773 | 1 | 8 | |g volume:44 |g year:2023 |g number:12 |g day:15 |g month:08 |g pages:4426-4438 |
856 | 4 | 0 | |u http://dx.doi.org/10.1002/hbm.26399 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 44 |j 2023 |e 12 |b 15 |c 08 |h 4426-4438 |