arXiv subjects

Mert R. Sabuncu

Publications and source records attributed to Mert R. Sabuncu.

96 records · Page 6Linked to original sources

arXiv2018

Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

Traditional deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task, and provide an empirical analysis of the algorithm. Our approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees and uncertainty estimates. Our implementation is available online at http://voxelmorph.csail.mit.edu .

cs.CV↗

arXiv2018

Joint Cell Nuclei Detection and Segmentation in Microscopy Images Using 3D Convolutional Networks

We propose a 3D convolutional neural network to simultaneously segment and detect cell nuclei in confocal microscopy images. Mirroring the co-dependency of these tasks, our proposed model consists of two serial components: the first part computes a segmentation of cell bodies, while the second module identifies the centers of these cells. Our model is trained end-to-end from scratch on a mouse parotid salivary gland stem cell nuclei dataset comprising 107 image stacks from three independent cell preparations, each containing several hundred individual cell nuclei in 3D. In our experiments, we conduct a thorough evaluation of both detection accuracy and segmentation quality, on two different datasets. The results show that the proposed method provides significantly improved detection and segmentation accuracy compared to state-of-the-art and benchmark algorithms. Finally, we use a previously described test-time drop-out strategy to obtain uncertainty estimates on our predictions and validate these estimates by demonstrating that they are strongly correlated with accuracy.

eess.IV↗

arXiv2018

Conditional Entropy as a Supervised Primitive Segmentation Loss Function

Supervised image segmentation assigns image voxels to a set of labels, as defined by a specific labeling protocol. In this paper, we decompose segmentation into two steps. The first step is what we call "primitive segmentation", where voxels that form sub-parts (primitives) of the various segmentation labels available in the training data, are grouped together. The second step involves computing a protocol-specific label map based on the primitive segmentation. Our core contribution is a novel loss function for the first step, where a primitive segmentation model is trained. The proposed loss function is the entropy of the (protocol-specific) "ground truth" label map conditioned on the primitive segmentation. The conditional entropy loss enables combining training datasets that have been manually labeled with different protocols. Furthermore, as we show empirically, it facilitates an efficient strategy for transfer learning via a lightweight protocol adaptation model that can be trained with little manually labeled data. We apply the proposed approach to the volumetric segmentation of brain MRI scans, where we achieve promising results.

eess.IV↗

arXiv2018

Medical Image Imputation from Image Collections

We present an algorithm for creating high resolution anatomically plausible images consistent with acquired clinical brain MRI scans with large inter-slice spacing. Although large data sets of clinical images contain a wealth of information, time constraints during acquisition result in sparse scans that fail to capture much of the anatomy. These characteristics often render computational analysis impractical as many image analysis algorithms tend to fail when applied to such images. Highly specialized algorithms that explicitly handle sparse slice spacing do not generalize well across problem domains. In contrast, we aim to enable application of existing algorithms that were originally developed for high resolution research scans to significantly undersampled scans. We introduce a generative model that captures fine-scale anatomical structure across subjects in clinical image collections and derive an algorithm for filling in the missing data in scans with large inter-slice spacing. Our experimental results demonstrate that the resulting method outperforms state-of-the-art upsampling super-resolution techniques, and promises to facilitate subsequent analysis not previously possible with scans of this quality. Our implementation is freely available at https://github.com/adalca/papago .

cs.CV↗

arXiv2018

An Unsupervised Learning Model for Deformable Medical Image Registration

We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. Current registration methods optimize an objective function independently for each pair of images, which can be time-consuming for large data. We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest. Given a new pair of scans, we can quickly compute a registration field by directly evaluating the function using the learned parameters. We model this function using a convolutional neural network (CNN), and use a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field. The proposed method does not require supervised information such as ground truth registration fields or anatomical landmarks. We demonstrate registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Our method promises to significantly speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is available at https://github.com/balakg/voxelmorph .

cs.CV↗

arXiv2018

A Probabilistic Disease Progression Model for Predicting Future Clinical Outcome

In this work, we consider the problem of predicting the course of a progressive disease, such as cancer or Alzheimer's. Progressive diseases often start with mild symptoms that might precede a diagnosis, and each patient follows their own trajectory. Patient trajectories exhibit wild variability, which can be associated with many factors such as genotype, age, or sex. An additional layer of complexity is that, in real life, the amount and type of data available for each patient can differ significantly. For example, for one patient we might have no prior history, whereas for another patient we might have detailed clinical assessments obtained at multiple prior time-points. This paper presents a probabilistic model that can handle multiple modalities (including images and clinical assessments) and variable patient histories with irregular timings and missing entries, to predict clinical scores at future time-points. We use a sigmoidal function to model latent disease progression, which gives rise to clinical observations in our generative model. We implemented an approximate Bayesian inference strategy on the proposed model to estimate the parameters on data from a large population of subjects. Furthermore, the Bayesian framework enables the model to automatically fine-tune its predictions based on historical observations that might be available on the test subject. We applied our method to a longitudinal Alzheimer's disease dataset with more than 3000 subjects [23] and present a detailed empirical analysis of prediction performance under different scenarios, with comparisons against several benchmarks. We also demonstrate how the proposed model can be interrogated to glean insights about temporal dynamics in Alzheimer's disease.

cs.LG↗