Academic Journal

Automated Lesion and Feature Extraction Pipeline for Brain MRIs with Interpretability

Bibliographic Details
Title: Automated Lesion and Feature Extraction Pipeline for Brain MRIs with Interpretability
Authors: Reza Eghbali, Pierre Nedelec, David Weiss, Radhika Bhalerao, Long Xie, Jeffrey D. Rudie, Chunlei Liu, Leo P. Sugrue, Andreas M. Rauschecker
Source: Neuroinformatics
Neuroinformatics, vol 23, iss 1
Publisher Information: Springer Science and Business Media LLC, 2025.
Publication Year: 2025
Subject Terms: Radiomics, Image Processing, Computer-Assisted/methods [MeSH], Neuroimaging/methods [MeSH], Brain/diagnostic imaging [MeSH], Research, Humans [MeSH], Software [MeSH], Image Interpretation, Computer-Assisted/methods [MeSH], Machine Learning [MeSH], Magnetic Resonance Imaging/methods [MeSH], Neuroradiology, MRI pipeline, Image Processing, Brain, Neuroimaging, Magnetic Resonance Imaging, Machine Learning, Computer-Assisted, Image Interpretation, Computer-Assisted, Image Processing, Computer-Assisted, Humans, Image Interpretation, Software
Description: This paper introduces the Automated Lesion and Feature Extraction (ALFE) pipeline, an open-source, Python-based pipeline that consumes MR images of the brain and produces anatomical segmentations, lesion segmentations, and human-interpretable imaging features describing the lesions in the brain. ALFE pipeline is modeled after the neuroradiology workflow and generates features that can be used by physicians for quantitative analysis of clinical brain MRIs and for machine learning applications. The pipeline uses a decoupled design which allows the user to customize the image processing, image registrations, and AI segmentation tools without the need to change the business logic of the pipeline. In this manuscript, we give an overview of ALFE, present the main aspects of ALFE pipeline design philosophy, and present case studies.
Document Type: Article
Other literature type
File Description: application/pdf
Language: English
ISSN: 1559-0089
DOI: 10.1007/s12021-024-09708-z
Access URL: https://pubmed.ncbi.nlm.nih.gov/39786657
https://repository.publisso.de/resource/frl:6492469
https://escholarship.org/content/qt9b68n6p4/qt9b68n6p4.pdf
https://escholarship.org/uc/item/9b68n6p4
Rights: CC BY
Accession Number: edsair.doi.dedup.....28ce845d8e244dc8da88239dd055dc5a
Database: OpenAIRE
Description
ISSN:15590089
DOI:10.1007/s12021-024-09708-z