Modelling Brain Lesion Volume in Patches with CNN-based Poisson Regression

Kevin Raina

2020

Abstract

Monitoring the progression of lesions is important for clinical response. Summary statistics such as lesion volume are objective and easy to interpret, which can help clinicians assess lesion growth or decay. CNNs are commonly used in medical image segmentation for their ability to produce useful features within large contexts and their associated efficient iterative patch-based training. Many CNN architectures require hundreds of thousands parameters to yield a good segmentation. In this work, an efficient, computationally inexpensive CNN is implemented to estimate the number of lesion voxels in a predefined patch size from magnetic resonance (MR) images. The output of the CNN is interpreted as the conditional Poisson parameter over the patch, allowing standard mini-batch gradient descent to be employed. The ISLES2015 (SISS) data is used to train and evaluate the model, which by estimating lesion volume from raw features, accurately identified the lesion image with the larger lesion volume for 86% of paired sample patches. An argument for the development and use of estimating lesion volumes to also aid in model selection for segmentation is made.

Paper Citation

in Harvard Style

Raina K. (2020). Modelling Brain Lesion Volume in Patches with CNN-based Poisson Regression. In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING; ISBN 978-989-758-398-8, SciTePress, pages 172-176. DOI: 10.5220/0009102701720176

in Bibtex Style

@conference{bioimaging20,
author={Kevin Raina},
title={Modelling Brain Lesion Volume in Patches with CNN-based Poisson Regression},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING},
year={2020},
pages={172-176},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009102701720176},
isbn={978-989-758-398-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 2: BIOIMAGING
TI - Modelling Brain Lesion Volume in Patches with CNN-based Poisson Regression
SN - 978-989-758-398-8
AU - Raina K.
PY - 2020
SP - 172
EP - 176
DO - 10.5220/0009102701720176
PB - SciTePress