Release the Krakencoder: A unified brain connectome translation and fusion tool.

Brain connectivity can be estimated in many ways, depending on modality and processing strategy. Here we present the Krakencoder, a joint connectome mapping tool that simultaneously, bidirectionally translates between structural (SC) and functional connectivity (FC), and across different atlases and processing choices via a common latent representation. These mappings demonstrate unprecedented accuracy and individual-level identifiability; the mapping between SC and FC has identifiability 42-54% higher than existing models. The Krakencoder combines all connectome flavors via a shared low-dimensional latent space. This "fusion" representation i) better reflects familial relatedness, ii) preserves age- and sex-relevant information and iii) enhances cognition-relevant information. The Krakencoder can be applied without retraining to new, out-of-age-distribution data while still preserving inter-individual differences in the connectome predictions and familial relationships in the latent representations. The Krakencoder is a significant leap forward in capturing the relationship between multi-modal brain connectomes in an individualized, behaviorally- and demographically-relevant way.

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation.

In healthcare, machine learning (ML) shows significant potential to augment patient care, improve population health, and streamline healthcare workflows. Realizing its full potential is, however, often hampered by concerns about data privacy, diversity in data sources, and suboptimal utilization of different data modalities. This review studies the utility of cross-cohort cross-category (C4) integration in such contexts: the process of combining information from diverse datasets distributed across distinct, secure sites. We argue that C4 approaches could pave the way for ML models that are both holistic and widely applicable. This paper provides a comprehensive overview of C4 in health care, including its present stage, potential opportunities, and associated challenges.

Remote Associations Between Tau and Cortical Amyloid-ß Are Stage-Dependent.

Background: Histopathologic studies of Alzheimer's disease (AD) suggest that extracellular amyloid-ß (Aß) plaques promote the spread of neurofibrillary tau tangles. However, these two proteinopathies initiate in spatially distinct brain regions, so how they interact during AD progression is unclear. Objective: In this study, we utilized Aß and tau positron emission tomography (PET) scans from 572 older subjects (476 healthy controls (HC), 14 with mild cognitive impairment (MCI), 82 with mild AD), at varying stages of the disease, to investigate to what degree tau is associated with cortical Aß deposition. Methods: Using multiple linear regression models and a pseudo-longitudinal ordering technique, we investigated remote tau-Aß associations in four pathologic phases of AD progression based on tau spread: 1) no-tau, 2) pre-acceleration, 3) acceleration, and 4) post-acceleration. Results: No significant tau-Aß association was detected in the no-tau phase. In the pre-acceleration phase, the earliest stage of tau deposition, associations emerged between regional tau in medial temporal lobe (MTL) (i.e., entorhinal cortex, parahippocampal gyrus) and cortical Aß in lateral temporal lobe regions. The strongest tau-Aß associations were found in the acceleration phase, in which tau in MTL regions was strongly associated with cortical Aß (i.e., temporal and frontal lobes regions). Strikingly, in the post-acceleration phase, including 96% of symptomatic subjects, tau-Aß associations were no longer significant. Conclusions: The results indicate that associations between tau and Aß are stage-dependent, which could have important implications for understanding the interplay between these two proteinopathies during the progressive stages of AD.

Ensembling Low Precision Models for Binary Biomedical Image Segmentation.

Segmentation of anatomical regions of interest such as vessels or small lesions in medical images is still a difficult problem that is often tackled with manual input by an expert. One of the major challenges for this task is that the appearance of foreground (positive) regions can be similar to background (negative) regions. As a result, many automatic segmentation algorithms tend to exhibit asymmetric errors, typically producing more false positives than false negatives. In this paper, we aim to leverage this asymmetry and train a diverse ensemble of models with very high recall, while sacrificing their precision. Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent. Thus, in aggregate the false positive errors will cancel out, yielding high performance for the ensemble. Our strategy is general and can be applied with any segmentation model. In three different applications (carotid artery segmentation in a neck CT angiography, myocardium segmentation in a cardiovascular MRI and multiple sclerosis lesion segmentation in a brain MRI), we show how the proposed approach can significantly boost the performance of a baseline segmentation method.

VOLUMETRIC LANDMARK DETECTION WITH A MULTI-SCALE SHIFT EQUIVARIANT NEURAL NETWORK.

Deep neural networks yield promising results in a wide range of computer vision applications, including landmark detection. A major challenge for accurate anatomical landmark detection in volumetric images such as clinical CT scans is that large-scale data often constrain the capacity of the employed neural network architecture due to GPU memory limitations, which in turn can limit the precision of the output. We propose a multi-scale, end-to-end deep learning method that achieves fast and memory-efficient landmark detection in 3D images. Our architecture consists of blocks of shift-equivariant networks, each of which performs landmark detection at a different spatial scale. These blocks are connected from coarse to fine-scale, with differentiable resampling layers, so that all levels can be trained together. We also present a noise injection strategy that increases the robustness of the model and allows us to quantify uncertainty at test time. We evaluate our method for carotid artery bifurcations detection on 263 CT volumes and achieve a better than state-of-the-art accuracy with mean Euclidean distance error of 2.81mm.