Behnaz Pirzamanbin
Associate senior lecturer
Deep Learning for Resolving 3D Microstructural Changes in the Fibrotic Liver
Author
Editor
- Shandong Wu
- Behrouz Shabestari
- Lei Xing
Summary, in English
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
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
Department/s
- eSSENCE: The e-Science Collaboration
- Department of Statistics
- Muscle Biology
- EXODIAB: Excellence of Diabetes Research in Sweden
- Autoimmunity
- Diabetic Complications
Publishing year
2025-02-08
Language
English
Pages
74-84
Publication/Series
Lecture Notes in Computer Science
Volume
15384
Document type
Conference paper
Publisher
Springer
Topic
- Other Mathematics
Conference name
International Conference on Medical Image Computing and Computer-Assisted Intervention - Applications of Medical Artificial Intelligence
Conference date
2024-10-06 - 2024-10-10
Conference place
Marrakesh, Morocco
Status
Published
Research group
- Muscle Biology
- Autoimmunity
- Diabetic Complications
ISBN/ISSN/Other
- ISSN: 1611-3349
- ISBN: 978-3-031-82007-6
- ISBN: 978-3-031-82006-9