Bayesian workflow for the investigation of hierarchical classification models from tau-PET and structural MRI data across the Alzheimer's disease spectrum.

Background: Alzheimer's disease (AD) diagnosis in its early stages remains difficult with current diagnostic approaches. Though tau neurofibrillary tangles (NFTs) generally follow the stereotypical pattern described by the Braak staging scheme, the network degeneration hypothesis (NDH) has suggested that NFTs spread selectively along functional networks of the brain. To evaluate this, we implemented a Bayesian workflow to develop hierarchical multinomial logistic regression models with increasing levels of complexity of the brain from tau-PET and structural MRI data to investigate whether it is beneficial to incorporate network-level information into an ROI-based predictive model for the presence/absence of AD. Methods: This study included data from the Translational Biomarkers in Aging and Dementia (TRIAD) longitudinal cohort from McGill University's Research Centre for Studies in Aging (MCSA). Baseline and 1 year follow-up structural MRI and [18F]MK-6240 tau-PET scans were acquired for 72 cognitive normal (CN), 23 mild cognitive impairment (MCI), and 18 Alzheimer's disease dementia subjects. We constructed the four following hierarchical Bayesian models in order of increasing complexity: (Model 1) a complete-pooling model with observations, (Model 2) a partial-pooling model with observations clustered within ROIs, (Model 3) a partial-pooling model with observations clustered within functional networks, and (Model 4) a partial-pooling model with observations clustered within ROIs that are also clustered within functional brain networks. We then investigated which of the models had better predictive performance given tau-PET or structural MRI data as an input, in the form of a relative annualized rate of change. Results: The Bayesian leave-one-out cross-validation (LOO-CV) estimate of the expected log pointwise predictive density (ELPD) results indicated that models 3 and 4 were substantially better than other models for both tau-PET and structural MRI inputs. For tau-PET data, model 3 was slightly better than 4 with an absolute difference in ELPD of 3.10 ± 1.30. For structural MRI data, model 4 was considerably better than other models with an absolute difference in ELPD of 29.83 ± 7.55 relative to model 3, the second-best model. Conclusion: Our results suggest that representing the data generating process in terms of a hierarchical model that encompasses both ROI-level and network-level heterogeneity leads to better predictive ability for both tau-PET and structural MRI inputs over all other model iterations.

Multimodal 3D ultrasound and CT in image-guided spinal surgery: public database and new registration algorithms.

PURPOSE: Accurate multimodal registration of intraoperative ultrasound (US) and preoperative computed tomography (CT) is a challenging problem. Construction of public datasets of US and CT images can accelerate the development of such image registration techniques. This can help ensure the accuracy and safety of spinal surgeries using image-guided surgery systems where an image registration is employed. In addition, we present two algorithms to register US and CT images. METHODS: We present three different datasets of vertebrae with corresponding CT, US, and simulated US images. For each of the two latter datasets, we also provide 16 landmark pairs of matching structures between the CT and US images and performed fiducial registration to acquire a silver standard for assessing image registration. Besides, we proposed two patch-based rigid image registration algorithms, one based on normalized cross-correlation (NCC) and the other based on correlation ratio (CR) to register misaligned CT and US images. RESULTS: The CT and corresponding US images of the proposed database were pre-processed and misaligned with different error intervals, resulting in 6000 registration problems solved using both NCC and CR methods. Our results show that the methods were successful in aligning the pre-processed CT and US images by decreasing the warping index. CONCLUSIONS: The database provides a resource for evaluating image registration techniques. The simulated data have two applications. First, they provide the gold standard ground-truth which is difficult to obtain with ex vivo and in vivo data for validating US-CT registration methods. Second, the simulated US images can be used to validate real-time US simulation methods. Besides, the proposed image registration techniques can be useful for developing methods in clinical application.

LUMINOUS database: lumbar multifidus muscle segmentation from ultrasound images.

BACKGROUND: Among the paraspinal muscles, the structure and function of the lumbar multifidus (LM) has become of great interest to researchers and clinicians involved in lower back pain and muscle rehabilitation. Ultrasound (US) imaging of the LM muscle is a useful clinical tool which can be used in the assessment of muscle morphology and function. US is widely used due to its portability, cost-effectiveness, and ease-of-use. In order to assess muscle function, quantitative information of the LM must be extracted from the US image by means of manual segmentation. However, manual segmentation requires a higher level of training and experience and is characterized by a level of difficulty and subjectivity associated with image interpretation. Thus, the development of automated segmentation methods is warranted and would strongly benefit clinicians and researchers. The aim of this study is to provide a database which will contribute to the development of automated segmentation algorithms of the LM. CONSTRUCTION AND CONTENT: This database provides the US ground truth of the left and right LM muscles at the L5 level (in prone and standing positions) of 109 young athletic adults involved in Concordia University's varsity teams. The LUMINOUS database contains the US images with their corresponding manually segmented binary masks, serving as the ground truth. The purpose of the database is to enable development and validation of deep learning algorithms used for automatic segmentation tasks related to the assessment of the LM cross-sectional area (CSA) and echo intensity (EI). The LUMINOUS database is publicly available at http://data.sonography.ai . CONCLUSION: The development of automated segmentation algorithms based on this database will promote the standardization of LM measurements and facilitate comparison among studies. Moreover, it can accelerate the clinical implementation of quantitative muscle assessment in clinical and research settings.

Receptive Field Size as a Key Design Parameter for Ultrasound Image Segmentation with U-Net.

Automatic and accurate segmentation of medical images is an important task due to the direct impact of this procedure on both disease diagnosis and treatment. Segmentation of ultrasound (US) imaging is particularly challenging due to the presence of speckle noise. Recent deep learning approaches have demonstrated remarkable findings in image segmentation tasks, including segmentation of US images. However, many of the newly proposed structures are either task specific and suffer from poor generalization, or are computationally expensive. In this paper, we show that the receptive field plays a more significant role in the network's performance compared to the network's depth or the number of parameters. We further show that by controlling the size of the receptive field, a deep network can instead be replaced by a shallow network.