Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning

Differences in iron accumulation patterns have been observed in susceptibility-weighted images across different classes of atypical parkinsonian syndromes (APS). Deep learning methods have shown great potential in automatically detecting these differences. However, the models typically require exten...

Full description

Saved in:
Bibliographic Details
Main Authors: Won June Choi, Jin HwangBo, Quan Anh Duong, Jae-Hyeok Lee, Jin Kyu Gahm
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:NeuroImage
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1053811924004373
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850124377351258112
author Won June Choi
Jin HwangBo
Quan Anh Duong
Jae-Hyeok Lee
Jin Kyu Gahm
author_facet Won June Choi
Jin HwangBo
Quan Anh Duong
Jae-Hyeok Lee
Jin Kyu Gahm
author_sort Won June Choi
collection DOAJ
description Differences in iron accumulation patterns have been observed in susceptibility-weighted images across different classes of atypical parkinsonian syndromes (APS). Deep learning methods have shown great potential in automatically detecting these differences. However, the models typically require extensively labeled training datasets, which are costly and pose patient privacy risks. To address the issue of limited training datasets, we propose a novel few-shot learning framework for classifying multiple system atrophy parkinsonian (MSA-P) and progressive supranuclear palsy (PSP) within the APS category using fewer data items. Our method identifies feature areas where iron accumulation patterns occur in classes other than the target classification (MSA-P vs. PSP) and enhances stability by leveraging a superior hyperbolic space embedding technique. Experimental results demonstrate significantly improved performance over conventional methods, as validated by ablation studies and visualizations.
format Article
id doaj-art-e5788e405f5c4f61b3964d3ce75c50db
institution OA Journals
issn 1095-9572
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series NeuroImage
spelling doaj-art-e5788e405f5c4f61b3964d3ce75c50db2025-08-20T02:34:19ZengElsevierNeuroImage1095-95722024-12-0130412094010.1016/j.neuroimage.2024.120940Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learningWon June Choi0Jin HwangBo1Quan Anh Duong2Jae-Hyeok Lee3Jin Kyu Gahm4Department of Information Convergence Engineering, Pusan National University, Busan 46241, South KoreaDepartment of Neurology, Pusan National University Yangsan Hospital, Pusan National University School of Medicine, Yangsan 50612, South KoreaDepartment of Information Convergence Engineering, Pusan National University, Busan 46241, South KoreaDepartment of Neurology, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan 50612, South Korea; Medical Research Institute, Pusan National University School of Medicine, Yangsan 50612, South Korea; Corresponding author.School of Computer Science and Engineering, Pusan National University, Busan 46241, South Korea; Center for Artificial Intelligence Research, Pusan National University, Busan 46241, South Korea; Corresponding author.Differences in iron accumulation patterns have been observed in susceptibility-weighted images across different classes of atypical parkinsonian syndromes (APS). Deep learning methods have shown great potential in automatically detecting these differences. However, the models typically require extensively labeled training datasets, which are costly and pose patient privacy risks. To address the issue of limited training datasets, we propose a novel few-shot learning framework for classifying multiple system atrophy parkinsonian (MSA-P) and progressive supranuclear palsy (PSP) within the APS category using fewer data items. Our method identifies feature areas where iron accumulation patterns occur in classes other than the target classification (MSA-P vs. PSP) and enhances stability by leveraging a superior hyperbolic space embedding technique. Experimental results demonstrate significantly improved performance over conventional methods, as validated by ablation studies and visualizations.http://www.sciencedirect.com/science/article/pii/S1053811924004373Atypical parkinsonian syndrome (APS)Contrastive learningFew-shot learningHyperbolic spaceSusceptibility-weighted imaging (SWI)
spellingShingle Won June Choi
Jin HwangBo
Quan Anh Duong
Jae-Hyeok Lee
Jin Kyu Gahm
Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
NeuroImage
Atypical parkinsonian syndrome (APS)
Contrastive learning
Few-shot learning
Hyperbolic space
Susceptibility-weighted imaging (SWI)
title Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
title_full Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
title_fullStr Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
title_full_unstemmed Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
title_short Differentiating atypical parkinsonian syndromes with hyperbolic few-shot contrastive learning
title_sort differentiating atypical parkinsonian syndromes with hyperbolic few shot contrastive learning
topic Atypical parkinsonian syndrome (APS)
Contrastive learning
Few-shot learning
Hyperbolic space
Susceptibility-weighted imaging (SWI)
url http://www.sciencedirect.com/science/article/pii/S1053811924004373
work_keys_str_mv AT wonjunechoi differentiatingatypicalparkinsoniansyndromeswithhyperbolicfewshotcontrastivelearning
AT jinhwangbo differentiatingatypicalparkinsoniansyndromeswithhyperbolicfewshotcontrastivelearning
AT quananhduong differentiatingatypicalparkinsoniansyndromeswithhyperbolicfewshotcontrastivelearning
AT jaehyeoklee differentiatingatypicalparkinsoniansyndromeswithhyperbolicfewshotcontrastivelearning
AT jinkyugahm differentiatingatypicalparkinsoniansyndromeswithhyperbolicfewshotcontrastivelearning