Heterogeneous Learning for Brain Lesion Segmentation, Detection, and Classification
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Heterogeneous Learning for Brain Lesion Segmentation, Detection, and Classification. / Llambias, Sebastian Nørgaard; Nielsen, Mads; Ghazi, Mostafa Mehdipour.
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}). PMLR, 2024. s. 138-144 (Proceedings of Machine Learning Research, Bind 233).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Heterogeneous Learning for Brain Lesion Segmentation, Detection, and Classification
AU - Llambias, Sebastian Nørgaard
AU - Nielsen, Mads
AU - Ghazi, Mostafa Mehdipour
N1 - Publisher Copyright: © NLDL 2024. All rights reserved.
PY - 2024
Y1 - 2024
N2 - Brain lesions detected in magnetic resonance images often vary in type and rarity across different cohorts, posing a challenge for deep learning techniques that are typically specialized in recognizing single lesion types from homogenous data. This limitation restricts their practicality in diverse clinical settings. In this study, we explore different deep-learning approaches to develop robust models handling both subject and imaging variability, while recognizing multiple lesion types. Our research focuses on segmentation and detection tasks across four distinct datasets, encompassing six cohorts of subjects with white matter hyperintensities, multiple sclerosis lesions, or stroke abnormalities. Our findings reveal that a cascade approach, comprising a fully convolutional network and a fully connected classifier, offers optimal accuracy for robust multiclass lesion segmentation and detection. Notably, our proposed model remains competitive with models trained solely on one dataset and applied to the same dataset while showing robustness against domain shifts. Additionally, in related tasks, our model consistently produces results comparable with the state-of-the-art methods. This study contributes to advancing clinically applicable deep learning techniques for brain lesion recognition, offering a promising solution for handling lesion diversity in uncontrolled clinical environments.
AB - Brain lesions detected in magnetic resonance images often vary in type and rarity across different cohorts, posing a challenge for deep learning techniques that are typically specialized in recognizing single lesion types from homogenous data. This limitation restricts their practicality in diverse clinical settings. In this study, we explore different deep-learning approaches to develop robust models handling both subject and imaging variability, while recognizing multiple lesion types. Our research focuses on segmentation and detection tasks across four distinct datasets, encompassing six cohorts of subjects with white matter hyperintensities, multiple sclerosis lesions, or stroke abnormalities. Our findings reveal that a cascade approach, comprising a fully convolutional network and a fully connected classifier, offers optimal accuracy for robust multiclass lesion segmentation and detection. Notably, our proposed model remains competitive with models trained solely on one dataset and applied to the same dataset while showing robustness against domain shifts. Additionally, in related tasks, our model consistently produces results comparable with the state-of-the-art methods. This study contributes to advancing clinically applicable deep learning techniques for brain lesion recognition, offering a promising solution for handling lesion diversity in uncontrolled clinical environments.
M3 - Article in proceedings
AN - SCOPUS:85189366130
T3 - Proceedings of Machine Learning Research
SP - 138
EP - 144
BT - Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})
PB - PMLR
T2 - 5th Northern Lights Deep Learning Conference, NLDL 2024
Y2 - 9 January 2024 through 11 January 2024
ER -
ID: 388683263