(주) 뷰노

(주) 뷰노

문의사항 남기기
KR EN
VUNO MED INC.
Publications
BACK TO LIST
Journal of Magnetic Resonance Imaging

Deep Learning-based Brainstem Segmentation and Multi-class Classification for Parkinsonian Syndrome

  • Dec. 2025

ABSTRACT

Background

Brain segmentation using structural MRI is effective for identifying regional atrophy in Parkinsonian syndromes. However, clinical validation of the automated deep learning-based brainstem segmentation model has been limited.

Purpose

To develop and validate a two-step deep learning algorithm for automatic segmentation of brainstem substructures and classifying Parkinsonian syndromes using derived volumetric measurements.

Study Type

Retrospective.

Subjects

The internal dataset comprised 300 normal cognition (NC) subjects (171 females) for segmentation and 513 subjects (265 males) for classification (207 NC, 52 progressive supranuclear palsy [PSP], 65 multiple system atrophy-cerebellar variant [MSA-C], and 189 Parkinson's disease [PD]). The external dataset comprised 82 subjects (43 males; 24 PSP, 28 MSA-C, and 30 PD).

Field Strength/Sequence

3D gradient-echo T1-weighted sequence at 3 T.

Assessment

Segmentation performance was evaluated with the Dice Similarity Coefficient (DSC) by comparing model outputs against manual labels. For classification, regional brain volumes from the segmentations were used as input features for multi-class classification with support vector machine (SVM), random forest, and XGBoost models, evaluated by area under the receiver operating characteristic curve (AUROC). Five-fold cross-validation was used for internal validation and tested on an external dataset. Three radiologists analyzed an external dataset with and without the model, with a one-month washout period between sessions.

Statistical Tests

For the segmentation volume, differences between groups were assessed using Student's t-test or Mann–Whitney U test. Classification performance was evaluated using a one-vs-rest approach with macro-averaging across classes.

Results

Brainstem segmentation DSC scores were 0.969 (internal) and 0.996 (external) compared to the ground-truth masks. Using regional volumetrics, the SVM achieved the highest differentiation performance, with AUROCs of 0.937 (internal) and 0.914 (external). A radiology resident achieved improved performance with the model.

Data Conclusion

Our proposed two-step algorithm combining deep-learning-based brainstem segmentation and machine-learning classification enables automated differentiation of Parkinsonian syndromes using 3D T1-weighted brain MRI.

Link

https://onlinelibrary.wiley.com/doi/abs/10.1002/jmri.70215?casa_token=KwQB25OICjkAAAAA:_ZakXmpAonVjDxGsn7vW12h3M14kCIryOlhrzC7Zu8Qo7ULBRS9ylL7aLESmt05bFwuQxXw_3J0NaIO0

Author

Seongken Kim, Pae Sun Suh, Woo Hyun Shim, Hwon Heo, Changhyun Park, Eunpyeong Hong, Saehyun Kim, Seung Hyun Lee, Dongsoo Lee, Wooseok Jung, Jinyoung Kim, Sungyang Jo, Sun Ju Chung, Young Hee Sung, Ho Sung Kim, Sang Joon Kim, Eung Yeop Kim, Chong Hyun Suh

Tag in

#medical_image

#VUNO Med®-DeepBrain®

이전글
이전글이 없습니다.
다음글
Development and validation of a deep learning-based automatic segmentation and classification of cerebral white matter hyperintensities 2025. 12. 15
List

이 웹사이트는 원활한 서비스 제공을 위하여 당사 개인정보 처리방침에 명시된 쿠키를 사용합니다.

만일 당사의 쿠키 사용 정책에 대해 더 알고 싶으신 경우에는 개인정보 처리방침 을 참고하여 주시기 바랍니다.