No abstract

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.

This paper investigates the automatic monitoring of tool usage during a surgery, with potential applications in report generation, surgical training and real-time decision support. Two surgeries are considered: cataract surgery, the most common surgical procedure, and cholecystectomy, one of the most common digestive surgeries. Tool usage is monitored in videos recorded either through a microscope (cataract surgery) or an endoscope (cholecystectomy). Following state-of-the-art video analysis solutions, each frame of the video is analyzed by convolutional neural networks (CNNs) whose outputs are fed to recurrent neural networks (RNNs) in order to take temporal relationships between events into account. Novelty lies in the way those CNNs and RNNs are trained. Computational complexity prevents the end-to-end training of "CNN+RNN" systems. Therefore, CNNs are usually trained first, independently from the RNNs. This approach is clearly suboptimal for surgical tool analysis: many tools are very similar to one another, but they can generally be differentiated based on past events. CNNs should be trained to extract the most useful visual features in combination with the temporal context. A novel boosting strategy is proposed to achieve this goal: the CNN and RNN parts of the system are simultaneously enriched by progressively adding weak classifiers (either CNNs or RNNs) trained to improve the overall classification accuracy. Experiments were performed in a dataset of 50 cataract surgery videos, where the usage of 21 surgical tools was manually annotated, and a dataset of 80 cholecystectomy videos, where the usage of 7 tools was manually annotated. Very good classification performance are achieved in both datasets: tool usage could be labeled with an average area under the ROC curve of A=0.9961 and A=0.9939, respectively, in offline mode (using past, present and future information), and A=0.9957 and A=0.9936, respectively, in online mode (using past and present information only).

Dedicated but not limited only to HCC management, both contributions reach further steps toward more accurate multi-label tissue classification.

View synthesis brings geometric distortions which are not handled efficiently by existing image quality assessment metrics. Despite the widespread of 3-D technology and notably 3D television (3DTV) and free-viewpoints television (FTV), the field of view synthesis quality assessment has not yet been widely investigated and new quality metrics are required. In this study, we propose a new full-reference objective quality assessment metric: the View Synthesis Quality Assessment (VSQA) metric. Our method is dedicated to artifacts detection in synthesized viewpoints and aims to handle areas where disparity estimation may fail: thin objects, object borders, transparency, variations of illumination or color differences between left and right views, periodic objects… The key feature of the proposed method is the use of three visibility maps which characterize complexity in terms of textures, diversity of gradient orientations and presence of high contrast. Moreover, the VSQA metric can be defined as an extension of any existing 2D image quality assessment metric. Experimental tests have shown the effectiveness of the proposed method.

In the last decades, large datasets of fundus photographs have been collected in diabetic retinopathy (DR) screening networks. Through deep learning, these datasets were used to train automatic detectors for DR and a few other frequent pathologies, with the goal to automate screening. One challenge limits the adoption of such systems so far: automatic detectors ignore rare conditions that ophthalmologists currently detect. The reason is that standard deep learning requires too many examples of these conditions. To address this limitation, we propose a new machine learning (ML) framework, called spin-off learning, for the automatic detection of rare conditions, like papilledema or anterior ischemic optic neuropathy. This framework extends convolutional neural networks (CNNs), trained for frequent conditions, with an unsupervised probabilistic model for rare condition detection. Spin-off learning is based on the observation that CNNs often perceive photographs containing the same anomalies as similar, even though these CNNs were trained to detect unrelated conditions. This observation was based on the t-SNE visualization tool, which we decided to incorporate in our probabilistic model. Spin-off learning supports heatmap generation, so the detected anomalies can be highlighted in images for decision support. Experiments in a dataset of 164,660 screening examinations from the OPHDIAT screening network show that spin-off learning can detect 37 conditions, out of 41, with an area under the ROC curve (AUC) greater than 0.8 (average AUC: 0.938). In particular, spin-off learning significantly outperforms other candidate ML frameworks for detecting rare conditions, including multitask learning, transfer learning and one-shot learning. We expect these richer predictions to trigger the adoption of automated eye pathology screening, which will revolutionize clinical practice in ophthalmology.

No abstract

No abstract