Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep Learning for Resolving 3D Microstructural Changes in the Fibrotic Liver

Laprade, William M. ; Pirzamanbein, Behnaz LU orcid ; Mokso, Rajmund ; Nilsson, Julia LU ; Dahl, Vedrana A. ; Dahl, Anders Bjorholm ; Holmberg, Dan LU and Schmidt-Christensen, Anja LU orcid (2025) International Conference on Medical Image Computing and Computer-Assisted Intervention - Applications of Medical Artificial Intelligence In Lecture Notes in Computer Science 15384. p.74-84
Abstract
Portal hypertension, a life-threatening complication of cirrhosis,
is largely triggered by increased intrahepatic vascular resistance.
Fibrosis, regenerative nodule formation, intrahepatic angiogenisis and sinusoidal
remodelling are classical mechanisms that account for increased
intrahepatic vascular resistance in cirrhosis. Our study leverages highresolution
3D synchrotron radiation-based microtomography and a deep
learning-based segmentation approach to investigate these microstructural
changes in the liver. By employing a multi-planar U-Net model,
trained using annotated tomographic slices sourced from our developed
online learning tool, we effectively quantify critical vascular parameters
such... (More)
Portal hypertension, a life-threatening complication of cirrhosis,
is largely triggered by increased intrahepatic vascular resistance.
Fibrosis, regenerative nodule formation, intrahepatic angiogenisis and sinusoidal
remodelling are classical mechanisms that account for increased
intrahepatic vascular resistance in cirrhosis. Our study leverages highresolution
3D synchrotron radiation-based microtomography and a deep
learning-based segmentation approach to investigate these microstructural
changes in the liver. By employing a multi-planar U-Net model,
trained using annotated tomographic slices sourced from our developed
online learning tool, we effectively quantify critical vascular parameters
such as sinusoid proportions, local thickness, and connectivity. These
insights advance our understanding of liver microarchitecture and also
allows correlating vascular parameters to inflammation and fibrosis severity.
Understanding and quantifying these microstructural changes is essential
to be able to predict the transition from seemingly benign conditions
like steatosis or mild inflammation to severe fibrosis and cirrhosis (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Applications of Medical Artificial Intelligence : Third International Workshop, AMAI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings - Third International Workshop, AMAI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings
series title
Lecture Notes in Computer Science
editor
Wu, Shandong ; Shabestari, Behrouz and Xing, Lei
volume
15384
pages
74 - 84
publisher
Springer
conference name
International Conference on Medical Image Computing and Computer-Assisted Intervention - Applications of Medical Artificial Intelligence
conference location
Marrakesh, Morocco
conference dates
2024-10-06 - 2024-10-10
external identifiers
  • scopus:85219210884
ISSN
1611-3349
ISBN
978-3-031-82007-6
978-3-031-82006-9
DOI
10.1007/978-3-031-82007-6_8
language
English
LU publication?
yes
id
01d0671f-f357-4ba3-b77d-1bdd9e082237
date added to LUP
2025-02-05 15:20:39
date last changed
2025-07-14 12:32:32
@inproceedings{01d0671f-f357-4ba3-b77d-1bdd9e082237,
  abstract     = {{Portal hypertension, a life-threatening complication of cirrhosis,<br/>is largely triggered by increased intrahepatic vascular resistance.<br/>Fibrosis, regenerative nodule formation, intrahepatic angiogenisis and sinusoidal<br/>remodelling are classical mechanisms that account for increased<br/>intrahepatic vascular resistance in cirrhosis. Our study leverages highresolution<br/>3D synchrotron radiation-based microtomography and a deep<br/>learning-based segmentation approach to investigate these microstructural<br/>changes in the liver. By employing a multi-planar U-Net model,<br/>trained using annotated tomographic slices sourced from our developed<br/>online learning tool, we effectively quantify critical vascular parameters<br/>such as sinusoid proportions, local thickness, and connectivity. These<br/>insights advance our understanding of liver microarchitecture and also<br/>allows correlating vascular parameters to inflammation and fibrosis severity.<br/>Understanding and quantifying these microstructural changes is essential<br/>to be able to predict the transition from seemingly benign conditions<br/>like steatosis or mild inflammation to severe fibrosis and cirrhosis}},
  author       = {{Laprade, William M. and Pirzamanbein, Behnaz and Mokso, Rajmund and Nilsson, Julia and Dahl, Vedrana A. and Dahl, Anders Bjorholm and Holmberg, Dan and Schmidt-Christensen, Anja}},
  booktitle    = {{Applications of Medical Artificial Intelligence : Third International Workshop, AMAI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings}},
  editor       = {{Wu, Shandong and Shabestari, Behrouz and Xing, Lei}},
  isbn         = {{978-3-031-82007-6}},
  issn         = {{1611-3349}},
  language     = {{eng}},
  month        = {{02}},
  pages        = {{74--84}},
  publisher    = {{Springer}},
  series       = {{Lecture Notes in Computer Science}},
  title        = {{Deep Learning for Resolving 3D Microstructural Changes in the Fibrotic Liver}},
  url          = {{http://dx.doi.org/10.1007/978-3-031-82007-6_8}},
  doi          = {{10.1007/978-3-031-82007-6_8}},
  volume       = {{15384}},
  year         = {{2025}},
}