Modelling brain lesion volume in patches with CNN-based Poisson Regression

TL;DR

This paper introduces an efficient CNN-based Poisson regression model to estimate brain lesion volume from MRI patches, aiding clinical assessment and potentially improving segmentation model selection.

Contribution

It presents a novel, computationally inexpensive CNN approach that models lesion volume as a Poisson parameter, enabling accurate volume estimation from raw MRI features.

Findings

Achieved 86% accuracy in identifying larger lesion volumes in paired patches.

Demonstrated the model's effectiveness using ISLES2015 data.

Proposed lesion volume estimation as a tool for segmentation model selection.

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.