Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research.

In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: 1) the sharing of a rich data set; 2) collaboration and comparison of the various avenues of research being pursued in the community; and 3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website 1 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Abstract. Magnetic Resonance Imaging (MRI) is widely used in routine clinical diagnosis and treatment. However, variations in MRI acquisition protocols result in different appearances of normal and diseased tissue in the images. Convolutional neural networks (CNNs), which have shown to be successful in many medical image analysis tasks, are typically sensitive to the variations in imaging protocols. Therefore, in many cases, networks trained on data acquired with one MRI protocol, do not perform satisfactorily on data acquired with different protocols. This limits the use of models trained with large annotated legacy datasets on a new dataset with a different domain which is often a recurring situation in clinical settings. In this study, we aim to answer the following central questions regarding domain adaptation in medical image analysis: Given a fitted legacy model, 1) How much data from the new domain is required for a decent adaptation of the original network?; and, 2) What portion of the pre-trained model parameters should be retrained given a certain number of the new domain training samples? To address these questions, we conducted extensive experiments in white matter hyperintensity segmentation task. We trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain. We then compared the performance of the model to the surrogate scenarios where either the same trained network is used or a new network is trained from scratch on the new dataset. The domain-adapted network tuned only by two training examples achieved a Dice score of 0.63 substantially outperforming a similar network trained on the same set of examples from scratch.⋆ Mohsen Ghafoorian and Alireza Mehrtash contributed equally to this work.

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://wmh.isi.uu.nl/). Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner robustness.Twenty participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen scanners.The challenge remains open for future submissions and provides a public platform for method evaluation.

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

Objective:To investigate the temporal dynamics of cerebral small vessel disease (SVD) by 3 consecutive assessments over a period of 9 years, distinguishing progression from regression.Methods:Changes in SVD markers of 276 participants of the Radboud University Nijmegen Diffusion Tensor and Magnetic Resonance Imaging Cohort (RUN DMC) cohort were assessed at 3 time points over 9 years. We assessed white matter hyperintensities (WMH) volume by semiautomatic segmentation and rated lacunes and microbleeds manually. We categorized baseline WMH severity as mild, moderate, or severe according to the modified Fazekas scale. We performed mixed-effects regression analysis including a quadratic term for increasing age.Results:Mean WMH progression over 9 years was 4.7 mL (0.54 mL/y; interquartile range 0.95–5.5 mL), 20.3% of patients had incident lacunes (2.3%/y), and 18.9% had incident microbleeds (2.2%/y). WMH volume declined in 9.4% of the participants during the first follow-up interval, but only for 1 participant (0.4%) throughout the whole follow-up. Lacunes disappeared in 3.6% and microbleeds in 5.7% of the participants. WMH progression accelerated over time: including a quadratic term for increasing age during follow-up significantly improved the model (p < 0.001). SVD progression was predominantly seen in participants with moderate to severe WMH at baseline compared to those with mild WMH (odds ratio [OR] 35.5, 95% confidence interval [CI] 15.8–80.0, p < 0.001 for WMH progression; OR 5.7, 95% CI 2.8–11.2, p < 0.001 for incident lacunes; and OR 2.9, 95% CI 1.4–5.9, p = 0.003 for incident microbleeds).Conclusions:SVD progression is nonlinear, accelerating over time, and a highly dynamic process, with progression interrupted by reduction in some, in a population that on average shows progression.

Convolutional neural networks have been successfully applied to semantic segmentation problems. However, there are many problems that are inherently not pixel-wise classification problems but are nevertheless frequently formulated as semantic segmentation. This ill-posed formulation consequently necessitates hand-crafted scenario-specific and computationally expensive post-processing methods to convert the per pixel probability maps to final desired outputs. Generative adversarial networks (GANs) can be used to make the semantic segmentation network output to be more realistic or better structure-preserving, decreasing the dependency on potentially complex post-processing. In this work, we propose EL-GAN: a GAN framework to mitigate the discussed problem using an embedding loss. With EL-GAN, we discriminate based on learned embeddings of both the labels and the prediction at the same time. This results in much more stable training due to having better discriminative information, benefiting from seeing both 'fake' and 'real' predictions at the same time. This substantially stabilizes the adversarial training process. We use the TuSimple lane marking challenge to demonstrate that with our proposed framework it is viable to overcome the inherent anomalies of posing it as a semantic segmentation problem. Not only is the output considerably more similar to the labels when compared to conventional methods, the subsequent post-processing is also simpler and crosses the competitive 96% accuracy threshold.

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines.In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.