EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning

Shikha Jain, Navin Rajpal, Pramod Kumar Soni

Frontiers in Computational Neuroscience · 29.01.2026 · 19

DOI: 10.3389/fncom.2025.1713766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computational Neuroscience, online erschienen am 29.01.2026. Verfasst von Shikha Jain und 2 weiteren Autor:innen. Beteiligte Einrichtung: University School of Information, Communication & Technology, Guru Gobind Singh Indraprastha University, New Delhi, India. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate detection and segmentation of multiple sclerosis (MS) lesions in brain Magnetic Resonance Imaging (MRI) is a challenging task due to their small size, irregular shape, and variability in different imaging modalities. Precise segmentation of MS lesions from brain MRI is vital for early diagnosis, disease progression monitoring, and treatment planning. We introduce MS-DASPNet, a Dual Attention Guided Deep Neural Network specifically designed to address the challenges of MS lesion detection, including small lesion sizes, low contrast, and heterogeneous appearance. MS-DASPNet employs a VGG-16-based encoder, an Atrous Spatial Pyramid Pooling (ASPP) bottleneck for multi-scale context learning, and dual attention modules in each skip connection to simultaneously refine spatial details and enhance channel-wise feature representation. Evaluations on four publicly available datasets, namely ISBI-2015, Mendeley, MICCAI-2016, and MICCAI-2021, demonstrate that MS-DASPNet achieves superior Precision, Dice, Sensitivity, and Jaccard scores compared to state-of-the-art methods. MS-DASPNet attains a Dice score of 0.8736 on the MICCAI-2016 dataset and 0.8706 on the MICCAI-2021 dataset, both outperforming existing segmentation techniques, highlighting its robustness and effectiveness in accurate MS lesion segmentation.

Schlagwörter

Stichwörter der Autor:innen

CNNatrous spatial pyramid poolingdeep learningdouble-headed attentionmultiple sclerosis

Autor:innen und Institutionen

  • University School of Information, Communication & Technology, Guru Gobind Singh Indraprastha University, New Delhi, India.
  • Department of Computer Applications, Manipal University Jaipur, Jaipur, India.

Zitieren

APA

Jain, S., Rajpal, N., & Soni, P. K. (2026). MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning. Frontiers in Computational Neuroscience, 19. https://doi.org/10.3389/fncom.2025.1713766

Vancouver

Jain S, Rajpal N, Soni PK. MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning. Frontiers in Computational Neuroscience. 2026;19. doi:10.3389/fncom.2025.1713766

BibTeX
@article{Jain2026,
  author = {Jain, Shikha and Rajpal, Navin and Soni, Pramod Kumar},
  title = {MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning},
  journal = {Frontiers in Computational Neuroscience},
  year = {2026},
  volume = {19},
  doi = {10.3389/fncom.2025.1713766}
}
Kostenlos starten →