“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. 
Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of machine learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

An overview of deep learning in medical imaging focusing on MRI

We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network (CNN), and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this work, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model's accuracy is comparable to state-of-the-art methods, while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time, and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is freely available at this http URL.

/pdf/voxelmorph-a-learning-framework-for-deformable-medical-image-4slzlz3vmh.pdf

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

This paper presents a simple method for “do as I do” motion transfer: given a source video of a person dancing, we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard moves. We approach this problem as video-to-video translation using pose as an intermediate representation. To transfer the motion, we extract poses from the source subject and apply the learned pose-to-appearance mapping to generate the target subject. We predict two consecutive frames for temporally coherent video results and introduce a separate pipeline for realistic face synthesis. Although our method is quite simple, it produces surprisingly compelling results (see video). This motivates us to also provide a forensics tool for reliable synthetic content detection, which is able to distinguish videos synthesized by our system from real data. In addition, we release a first-of-its-kind open-source dataset of videos that can be legally used for training and motion transfer.

Everybody Dance Now

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

For many movement disorders, such as Parkinson's disease and ataxia, disease progression is visually assessed by a clinician using a numerical disease rating scale. These tests are subjective, time-consuming, and must be administered by a professional. This can be problematic where specialists are not available, or when a patient is not consistently evaluated by the same clinician. We present an automated method for quantifying the severity of motion impairment in patients with ataxia, using only video recordings. We consider videos of the finger-to-nose test, a common movement task used as part of the assessment of ataxia progression during the course of routine clinical checkups. 
Our method uses neural network-based pose estimation and optical flow techniques to track the motion of the patient's hand in a video recording. We extract features that describe qualities of the motion such as speed and variation in performance. Using labels provided by an expert clinician, we train a supervised learning model that predicts severity according to the Brief Ataxia Rating Scale (BARS). The performance of our system is comparable to that of a group of ataxia specialists in terms of mean error and correlation, and our system's predictions were consistently within the range of inter-rater variability. This work demonstrates the feasibility of using computer vision and machine learning to produce consistent and clinically useful measures of motor impairment.

A Video-Based Method for Objectively Rating Ataxia.

Video magnification techniques are useful for visualizing small changes in videos. For instance, Eulerian video magnification has been used to visualize the flow of blood in the human face. Such visualizations have possible applications in remote monitoring or screening for diseases. However, when visualizing blood flow, the signal of interest may be similar in amplitude to the noise in the video. This raises the question of what one is actually seeing in a magnified video: signal or noise? We seek to understand these signal and noise characteristics with the goal of producing informative and accurate visualizations. We present a preliminary algorithm for estimating the signal amplitude in the presence of relatively high noise. We demonstrate that the algorithm can be used to accurately estimate the signal amplitude in an uncompressed simulated video, but is susceptible to compression noise and motion.

/pdf/estimating-a-small-signal-in-the-presence-of-large-noise-34cie9nx58.pdf

Estimating a Small Signal in the Presence of Large Noise

We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, and colors. There are often many possible ways to create a given painting. Our goal is to learn to capture this rich range of possibilities. 
Creating distributions of long-term videos is a challenge for learning-based video synthesis methods. We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process. We implement this model as a convolutional neural network, and introduce a novel training scheme to enable learning from a limited dataset of painting time lapses. We demonstrate that this model can be used to sample many time steps, enabling long-term stochastic video synthesis. We evaluate our method on digital and watercolor paintings collected from video websites, and show that human raters find our synthetic videos to be similar to time lapse videos produced by real artists. Our code is available at this https URL.

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, and colors. There are often many possible ways to create a given painting. Our goal is to learn to capture this rich range of possibilities. Creating distributions of long-term videos is a challenge for learning-based video synthesis methods. We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process. We implement this model as a convolutional neural network, and introduce a novel training scheme to enable learning from a limited dataset of painting time lapses. We demonstrate that this model can be used to sample many time steps, enabling long-term stochastic video synthesis. We evaluate our method on digital and watercolor paintings collected from video websites, and show that human raters find our synthetic videos to be similar to time lapse videos produced by real artists.

/pdf/painting-many-pasts-synthesizing-time-lapse-videos-of-54mes3f014.pdf

Amy Zhao

Papers

A Video-Based Method for Objectively Rating Ataxia.

Estimating a Small Signal in the Presence of Large Noise

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

Applying video magnification techniques to the visualization of blood flow