Automatic cerebral hemisphere segmentation in rat MRI with lesions via attention-based convolutional neural networks

TL;DR

This paper introduces MedicDeepLabv3+, an automatic CNN-based method for segmenting rat brain hemispheres in MRI scans with lesions, achieving high accuracy without preprocessing and outperforming existing methods.

Contribution

The paper presents MedicDeepLabv3+, a novel attention-based CNN architecture that improves segmentation accuracy and efficiency for rat brain MRI with lesions, requiring no preprocessing.

Findings

MedicDeepLabv3+ achieved Dice coefficients of 0.952 and 0.944.

It outperformed six state-of-the-art CNNs and traditional methods.

The method is fast, requiring less than a second per segmentation.

Abstract

We present MedicDeepLabv3+, a convolutional neural network that is the first completely automatic method to segment cerebral hemispheres in magnetic resonance (MR) volumes of rats with lesions. MedicDeepLabv3+ improves the state-of-the-art DeepLabv3+ with an advanced decoder, incorporating spatial attention layers and additional skip connections that, as we show in our experiments, lead to more precise segmentations. MedicDeepLabv3+ requires no MR image preprocessing, such as bias-field correction or registration to a template, produces segmentations in less than a second, and its GPU memory requirements can be adjusted based on the available resources. We optimized MedicDeepLabv3+ and six other state-of-the-art convolutional neural networks (DeepLabv3+, UNet, HighRes3DNet, V-Net, VoxResNet, Demon) on a heterogeneous training set comprised by MR volumes from 11 cohorts acquired at different lesion stages. Then, we evaluated the trained models and two approaches specifically designed for rodent MRI skull stripping (RATS and RBET) on a large dataset of 655 MR rat brain volumes. In our experiments, MedicDeepLabv3+ outperformed the other methods, yielding an average Dice coefficient of 0.952 and 0.944 in the brain and contralateral hemisphere regions. Additionally, we show that despite limiting the GPU memory and the training data, our MedicDeepLabv3+ also provided satisfactory segmentations. In conclusion, our method, publicly available at https://github.com/jmlipman/MedicDeepLabv3Plus, yielded excellent results in multiple scenarios, demonstrating its capability to reduce human workload in rat neuroimaging studies.