In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future.

No abstract

Active Learning methods create an optimized and labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results in this paper. Experiments on three medical image datasets show that our novel online active learning model requires significantly less labelings, is more accurate, and is more robust to class imbalances than existing methods. Our method is also more accurate and computationally efficient than the baseline model. Compared to random sampling and uncertainty sampling, the method uses 275 and 200 (out of 768) fewer labeled examples, respectively. For Diabetic Retinopathy detection, our method attains a 5.88% accuracy improvement over the baseline model when 80% of the dataset is labeled, and the model reaches baseline accuracy when only 40% is labeled. F I G U R E 1 Proposed Active Learning pipeline. To solve a supervised classification task, we will use a deep network (DN), an initial labeled dataset D t r ai n , an unlabeled dataset D or acl e , and an oracle who can label data. We desire to label as few examples as possible. Each active learning iteration, we use the DN to compute a feature embedding for all labeled examples in D t r ai n and the top M unlabeled examples from D or acl e with highest predictive entropy. We select and label oracle examples furthest in feature space from the centroid of all labeled examples. The oracle examples are selected one at a time, and the centroid updated after each labeling. We train the model on the expanded training set and repeat the process. In the online setting, the model weights are not reset between iterations and we use only the newly labeled examples and a subset of previously labeled examples.

Diabetic retinopathy (DR) detection is a critical retinal image analysis task in the context of early blindness prevention. Unfortunately, in order to train a model to accurately detect DR based on the presence of different retinal lesions, typically a dataset with medical expert's annotations at the pixel level is needed. In this paper, a new methodology based on the multiple instance learning (MIL) framework is developed in order to overcome this necessity by leveraging the implicit information present on annotations made at the image level. Contrary to previous MIL-based DR detection systems, the main contribution of the proposed technique is the joint optimization of the instance encoding and the image classification stages. In this way, more useful mid-level representations of pathological images can be obtained. The explainability of the model decisions is further enhanced by means of a new loss function enforcing appropriate instance and mid-level representations. The proposed technique achieves comparable or better results than other recently proposed methods, with 90% area under the receiver operating characteristic curve (AUC) on Messidor, 93% AUC on DR1, and 96% AUC on DR2, while improving the interpretability of the produced decisions.INDEX TERMS Multiple instance learning, diabetic retinopathy detection, bag of visual words, retinal image analysis.