• Automated Lesion and Feature E...

Result: Automated Lesion and Feature Extraction Pipeline for Brain MRIs with Interpretability.

Title:
Automated Lesion and Feature Extraction Pipeline for Brain MRIs with Interpretability.
Authors:
Eghbali R; Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA. eghbali@berkeley.edu.; Berkeley Institute for Data Science, University of California, Berkeley, Berkeley, CA, USA. eghbali@berkeley.edu., Nedelec P; Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA., Weiss D; Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA., Bhalerao R; Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA., Xie L; Siemens Healthineers, Erlangen, Germany., Rudie JD; Department of Radiology, University of California, San Diego, San Diego, CA, USA., Liu C; Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA.; Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA., Sugrue LP; Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA., Rauschecker AM; Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA.
Source:
Neuroinformatics [Neuroinformatics] 2025 Jan 09; Vol. 23 (1), pp. 2. Date of Electronic Publication: 2025 Jan 09.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Humana Press, Inc Country of Publication: United States NLM ID: 101142069 Publication Model: Electronic Cited Medium: Internet ISSN: 1559-0089 (Electronic) Linking ISSN: 15392791 NLM ISO Abbreviation: Neuroinformatics Subsets: MEDLINE
Imprint Name(s):
Original Publication: Totowa, NJ : Humana Press, Inc., c2003-
MeSH Terms:
Magnetic Resonance Imaging*/methods , Brain*/diagnostic imaging , Image Processing, Computer-Assisted*/methods, Humans ; Machine Learning ; Image Interpretation, Computer-Assisted/methods ; Software ; Neuroimaging/methods
References:
Front Neuroinform. 2011 Aug 22;5:13. (PMID: 21897815)
Radiology. 2016 Feb;278(2):563-77. (PMID: 26579733)
Sci Stat Database Manag. 2023 Jul;2023:. (PMID: 38344216)
Cancer Res. 2017 Nov 1;77(21):e104-e107. (PMID: 29092951)
Neurooncol Adv. 2022 Apr 22;4(1):vdac060. (PMID: 35611269)
Sci Rep. 2022 May 24;12(1):8784. (PMID: 35610333)
Neuroimage. 2011 Feb 1;54(3):2033-44. (PMID: 20851191)
Neuroimage. 2006 Jul 1;31(3):1116-28. (PMID: 16545965)
Neuroimage. 2012 Aug 15;62(2):774-81. (PMID: 22248573)
Front Neuroinform. 2014 Feb 21;8:14. (PMID: 24600388)
Med Image Anal. 2023 May;86:102789. (PMID: 36857946)
Radiol Artif Intell. 2020 Sep 23;2(5):e190146. (PMID: 33937838)
Expert Rev Precis Med Drug Dev. 2016;1(2):207-226. (PMID: 28042608)
AJNR Am J Neuroradiol. 2010 Jan;31(1):60-6. (PMID: 19729544)
Neuroimage Clin. 2021;31:102769. (PMID: 34333270)
Sci Data. 2017 Sep 05;4:170117. (PMID: 28872634)
Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961)
Sci Data. 2016 Jun 21;3:160044. (PMID: 27326542)
IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024. (PMID: 25494501)
Sci Rep. 2021 Dec 1;11(1):23202. (PMID: 34853344)
Radiology. 2020 Jun;295(3):626-637. (PMID: 32255417)
Radiol Artif Intell. 2024 Mar;6(2):e230126. (PMID: 38381038)
Bioengineering (Basel). 2023 Feb 22;10(3):. (PMID: 36978676)
Contributed Indexing:
Keywords: MRI pipeline; Neuroradiology; Radiomics
Entry Date(s):
Date Created: 20250109 Date Completed: 20250109 Latest Revision: 20250324
Update Code:
20250324
PubMed Central ID:
PMC11717894
DOI:
10.1007/s12021-024-09708-z
PMID:
39786657
Database:
MEDLINE

Further Information

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.
(© 2025. The Author(s).)

Declarations. Competing interests: The authors declare no competing interests.