Sandra E. Black

Owen Crystal, Pejman J. Maralani, Sandra Black et al.

Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks were generated from the target domain using a novel conventional image processing ventricular segmentation algorithm and used to supplement the gold standard (GS) data from the source domain, Canadian Atherosclerosis Imaging Network (CAIN). Four models were tested on held-out test sets from four datasets: 1) SS+GS: trained on target SS masks and fine-tuned on source GS masks, 2) GS+SS: trained on source GS masks and fine-tuned on target SS masks, 3) trained on source GS (GS CAIN Only) and 4) trained on target SS masks (SS Only). The SS+GS model had the best and most consistent performance (mean DSC = 0.89, CoV = 0.05) and showed significantly (p < 0.05) higher DSC compared to the GS-only model on three target domains. Results suggest pre-training with noisy labels from the target domain allows the model to adapt to the dataset-specific characteristics and provides robust parameter initialization while fine-tuning with GS masks allows the model to learn detailed features. This method has wide application to other medical imaging problems where labeled data is scarce, and can be used as a per-dataset calibration method to accelerate wide-scale adoption.

Lyndon Boone, Mahdi Biparva, Parisa Mojiri Forooshani et al.

Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new and existing models to specific distribution shifts in MRI, and accessible multi-site benchmarking datasets are still scarce or task-specific. To address these limitations, we propose ROOD-MRI: a platform for benchmarking the Robustness of DNNs to Out-Of-Distribution (OOD) data, corruptions, and artifacts in MRI. The platform provides modules for generating benchmarking datasets using transforms that model distribution shifts in MRI, implementations of newly derived benchmarking metrics for image segmentation, and examples for using the methodology with new models and tasks. We apply our methodology to hippocampus, ventricle, and white matter hyperintensity segmentation in several large studies, providing the hippocampus dataset as a publicly available benchmark. By evaluating modern DNNs on these datasets, we demonstrate that they are highly susceptible to distribution shifts and corruptions in MRI. We show that while data augmentation strategies can substantially improve robustness to OOD data for anatomical segmentation tasks, modern DNNs using augmentation still lack robustness in more challenging lesion-based segmentation tasks. We finally benchmark U-Nets and transformer-based models, finding consistent differences in robustness to particular classes of transforms across architectures.

Lucia Ballerini, Ruggiero Lovreglio, Maria del C. Valdes-Hernandez et al.

Perivascular Spaces (PVS) are a recently recognised feature of Small Vessel Disease (SVD), also indicating neuroinflammation, and are an important part of the brain's circulation and glymphatic drainage system. Quantitative analysis of PVS on Magnetic Resonance Images (MRI) is important for understanding their relationship with neurological diseases. In this work, we propose a segmentation technique based on the 3D Frangi filtering for extraction of PVS from MRI. Based on prior knowledge from neuroradiological ratings of PVS, we used ordered logit models to optimise Frangi filter parameters in response to the variability in the scanner's parameters and study protocols. We optimized and validated our proposed models on two independent cohorts, a dementia sample (N=20) and patients who previously had mild to moderate stroke (N=48). Results demonstrate the robustness and generalisability of our segmentation method. Segmentation-based PVS burden estimates correlated with neuroradiological assessments (Spearman's $ρ$ = 0.74, p $<$ 0.001), suggesting the great potential of our proposed method