Abstract-Colonoscopy is the gold standard for colon cancer screening though still some polyps are missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection subchallenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks (CNNs) are the state of the art. Nevertheless it is also demonstrated that combining different methodologies can lead to an improved overall performance.

No abstract

International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical analysis of common practices related to the organization of challenges has not yet been performed. In this paper, we present a comprehensive analysis of biomedical image analysis challenges conducted up to now. We demonstrate the importance of challenges and show that the lack of quality control has critical consequences. First, reproducibility and interpretation of the results is often hampered as only a fraction of relevant information is typically provided. Second, the rank of an algorithm is generally not robust to a number of variables such as the test data used for validation, the ranking scheme applied and the observers that make the reference annotations. To overcome these problems, we recommend best practice guidelines and define open research questions to be addressed in the future.

Abstract. The recovery of 3D tissue structure and morphology during robotic assisted surgery is an important step towards accurate deployment of surgical guidance and control techniques in minimally invasive therapies. In this article, we present a novel stereo reconstruction algorithm that propagates disparity information around a set of candidate feature matches. This has the advantage of avoiding problems with specular highlights, occlusions from instruments and view dependent illumination bias. Furthermore, the algorithm can be used with any feature matching strategy allowing the propagation of depth in very disparate views. Validation is provided for a phantom model with known geometry and this data is available online in order to establish a structured validation scheme in the field. The practical value of the proposed method is further demonstrated by reconstructions on various in vivo images of robotic assisted procedures, which are also available to the community.

In recent years, tremendous progress has been made in surgical practice for example with Minimally Invasive Surgery (MIS). To overcome challenges coming from deported eye-to-hand manipulation, robotic and computer-assisted systems have been developed. Having real-time knowledge of the pose of surgical tools with respect to the surgical camera and underlying anatomy is a key ingredient for such systems. In this paper, we present a review of the literature dealing with vision-based and marker-less surgical tool detection. This paper includes three primary contributions: (1) identification and analysis of data-sets used for developing and testing detection algorithms, (2) in-depth comparison of surgical tool detection methods from the feature extraction process to the model learning strategy and highlight existing shortcomings, and (3) analysis of validation techniques employed to obtain detection performance results and establish comparison between surgical tool detectors. The papers included in the review were selected through PubMed and Google Scholar searches using the keywords: "surgical tool detection", "surgical tool tracking", "surgical instrument detection" and "surgical instrument tracking" limiting results to the year range 2000 2015. Our study shows that despite significant progress over the years, the lack of established surgical tool data-sets, and reference format for performance assessment and method ranking is preventing faster improvement.

One of the main challenges for computer-assisted surgery (CAS) is to determine the intra-operative morphology and motion of soft-tissues. This information is prerequisite to the registration of multi-modal patient-specific data for enhancing the surgeon's navigation capabilites by observing beyond exposed tissue surfaces and for providing intelligent control of robotic-assisted instruments. In minimally invasive surgery (MIS), optical techniques are an increasingly attractive approach for in vivo 3D reconstruction of the soft-tissue surface geometry. This paper reviews the state-of-the-art methods for optical intra-operative 3D reconstruction in laparoscopic surgery and discusses the technical challenges and future perspectives towards clinical translation. With the recent paradigm shift of surgical practice towards MIS and new developments in 3D optical imaging, this is a timely discussion about technologies that could facilitate complex CAS procedures in dynamic and deformable anatomical regions.

No abstract

Instrument detection, pose estimation, and tracking in surgical videos are an important vision component for computer-assisted interventions. While significant advances have been made in recent years, articulation detection is still a major challenge. In this paper, we propose a deep neural network for articulated multi-instrument 2-D pose estimation, which is trained on detailed annotations of endoscopic and microscopic data sets. Our model is formed by a fully convolutional detection-regression network. Joints and associations between joint pairs in our instrument model are located by the detection subnetwork and are subsequently refined through a regression subnetwork. Based on the output from the model, the poses of the instruments are inferred using maximum bipartite graph matching. Our estimation framework is powered by deep learning techniques without any direct kinematic information from a robot. Our framework is tested on single-instrument RMIT data, and also on multi-instrument EndoVis and in vivo data with promising results. In addition, the data set annotations are publicly released along with our code and model.