To support probe-based confocal laser endomicroscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps.

Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients undergoing screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as the criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a content-based image retrieval technique followed by k-nearest neighbor classification. The performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists was compared with that of automated pCLE software classification. All evaluations were performed using leave-one-patient-out cross-validation to avoid bias.

Colorectal lesions (135) were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study found no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There was very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing were: -0.073 to 0.073 for accuracy, -0.068 to 0.089 for sensitivity and -0.18 to 0.13 for specificity. The classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist.

The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.

This paper introduces ongoing research on computer-aided ophthalmic surgery. In particular, a novel Content-Based Video Retrieval (CBVR) system is presented. Its purpose is the following: given a video stream captured by a digital camera monitoring the surgery, the system should retrieve, in real-time, similar video subsequences in video archives. In order to retrieve semantically-relevant videos, most existing CBVR systems rely on temporally flexible distance measures such as Dynamic Time Warping. These distance measures are slow and therefore do not allow real-time retrieval. In the proposed system, temporal flexibility is introduced in the way video subsequences are characterized, which allows the use of simple and fast distance measures. As a consequence, realtime retrieval of similar video subsequences, among hundreds of thousands of examples, is now possible. Besides, the proposed system is adaptive: a fast training procedure is presented. The system has been successfully applied to automated recognition of retinal surgery steps on a 69-video dataset: areas under the Receiver Operating Characteristic curves range from A(z)=0.809 to A(z)=0.989.

Content-based image retrieval (CBIR) is a valuable computer vision technique which is increasingly being applied in the medical community for diagnosis support. However, traditional CBIR systems only deliver visual outputs, i.e., images having a similar appearance to the query, which is not directly interpretable by the physicians. Our objective is to provide a system for endomicroscopy video retrieval which delivers both visual and semantic outputs that are consistent with each other. In a previous study, we developed an adapted bag-of-visual-words method for endomicroscopy retrieval, called "Dense-Sift," that computes a visual signature for each video. In this paper, we present a novel approach to complement visual similarity learning with semantic knowledge extraction, in the field of in vivo endomicroscopy. We first leverage a semantic ground truth based on eight binary concepts, in order to transform these visual signatures into semantic signatures that reflect how much the presence of each semantic concept is expressed by the visual words describing the videos. Using cross-validation, we demonstrate that, in terms of semantic detection, our intuitive Fisher-based method transforming visual-word histograms into semantic estimations outperforms support vector machine (SVM) methods with statistical significance. In a second step, we propose to improve retrieval relevance by learning an adjusted similarity distance from a perceived similarity ground truth. As a result, our distance learning method allows to statistically improve the correlation with the perceived similarity. We also demonstrate that, in terms of perceived similarity, the recall performance of the semantic signatures is close to that of visual signatures and significantly better than those of several state-of-the-art CBIR methods. The semantic signatures are thus able to communicate high-level medical knowledge while being consistent with the low-level visual signatures and much shorter than them. In our resulting retrieval system, we decide to use visual signatures for perceived similarity learning and retrieval, and semantic signatures for the output of an additional information, expressed in the endoscopist own language, which provides a relevant semantic translation of the visual retrieval outputs.

A novel approach to the design of a semantic, low-dimensional, encoding for endoscopic imagery is proposed. This encoding is based on recent advances in scene recognition, where semantic modeling of image content has gained considerable attention over the last decade. While the semantics of scenes are mainly comprised of environmental concepts such as vegetation, mountains or sky, the semantics of endoscopic imagery are medically relevant visual elements, such as polyps, special surface patterns, or vascular structures. The proposed semantic encoding differs from the representations commonly used in endoscopic image analysis (for medical decision support) in that it establishes a semantic space, where each coordinate axis has a clear human interpretation. It is also shown to establish a connection to Riemannian geometry, which enables principled solutions to a number of problems that arise in both physician training and clinical practice. This connection is exploited by leveraging results from information geometry to solve problems such as (1) recognition of important semantic concepts, (2) semantically-focused image browsing, and (3) estimation of the average-case semantic encoding for a collection of images that share a medically relevant visual detail. The approach can provide physicians with an easily interpretable, semantic encoding of visual content, upon which further decisions, or operations, can be naturally carried out. This is contrary to the prevalent practice in endoscopic image analysis for medical decision support, where image content is primarily captured by discriminative, high-dimensional, appearance features, which possess discriminative power but lack human interpretability.

Gastro-intestinal (GI) endoscopy is a widely used clinical procedure for screening and surveillance of digestive tract diseases ranging from Barrett's Oesophagus to oesophageal cancer. Current surveillance protocol consists of periodic endoscopic examinations performed in 3-4 month intervals including expert's visual assessment and biopsies taken from suspicious tissue regions. Recent development of a new imaging technology, called probe-based confocal laser endomicroscopy (pCLE), enabled the acquisition of in vivo optical biopsies without removing any tissue sample. Besides its several advantages, i.e., noninvasiveness, real-time and in vivo feedback, optical biopsies involve a new challenge for the endoscopic expert. Due to their noninvasive nature, optical biopsies do not leave any scar on the tissue and therefore recognition of the previous optical biopsy sites in surveillance endoscopy becomes very challenging. In this work, we introduce a clustering and classification framework to facilitate retargeting previous optical biopsy sites in surveillance upper GI-endoscopies. A new representation of endoscopic videos based on manifold learning, "endoscopic video manifolds" (EVMs), is proposed. The low dimensional EVM representation is adapted to facilitate two different clustering tasks; i.e., clustering of informative frames and patient specific endoscopic segments, only by changing the similarity measure. Each step of the proposed framework is validated on three in vivo patient datasets containing 1834, 3445, and 1546 frames, corresponding to endoscopic videos of 73.36, 137.80, and 61.84 s, respectively. Improvements achieved by the introduced EVM representation are demonstrated by quantitative analysis in comparison to the original image representation and principal component analysis. Final experiments evaluating the complete framework demonstrate the feasibility of the proposed method as a promising step for assisting the endoscopic expert in retargeting the optical biopsy sites.