An image retrieval framework for real-time endoscopic image retargeting.

PURPOSE: Serial endoscopic examinations of a patient are important for early diagnosis of malignancies in the gastrointestinal tract. However, retargeting for optical biopsy is challenging due to extensive tissue variations between examinations, requiring the method to be tolerant to these changes whilst enabling real-time retargeting. METHOD: This work presents an image retrieval framework for inter-examination retargeting. We propose both a novel image descriptor tolerant of long-term tissue changes and a novel descriptor matching method in real time. The descriptor is based on histograms generated from regional intensity comparisons over multiple scales, offering stability over long-term appearance changes at the higher levels, whilst remaining discriminative at the lower levels. The matching method then learns a hashing function using random forests, to compress the string and allow for fast image comparison by a simple Hamming distance metric. RESULTS: A dataset that contains 13 in vivo gastrointestinal videos was collected from six patients, representing serial examinations of each patient, which includes videos captured with significant time intervals. Precision-recall for retargeting shows that our new descriptor outperforms a number of alternative descriptors, whilst our hashing method outperforms a number of alternative hashing approaches. CONCLUSION: We have proposed a novel framework for optical biopsy in serial endoscopic examinations. A new descriptor, combined with a novel hashing method, achieves state-of-the-art retargeting, with validation on in vivo videos from six patients. Real-time performance also allows for practical integration without disturbing the existing clinical workflow.

Real-time surgical tool tracking and pose estimation using a hybrid cylindrical marker.

PURPOSE: To provide an integrated visualisation of intraoperative ultrasound and endoscopic images to facilitate intraoperative guidance, real-time tracking of the ultrasound probe is required. State-of-the-art methods are suitable for planar targets while most of the laparoscopic ultrasound probes are cylindrical objects. A tracking framework for cylindrical objects with a large work space will improve the usability of the intraoperative ultrasound guidance. METHODS: A hybrid marker design that combines circular dots and chessboard vertices is proposed for facilitating tracking cylindrical tools. The circular dots placed over the curved surface are used for pose estimation. The chessboard vertices are employed to provide additional information for resolving the ambiguous pose problem due to the use of planar model points under a monocular camera. Furthermore, temporal information between consecutive images is considered to minimise tracking failures with real-time computational performance. RESULTS: Detailed validation confirms that our hybrid marker provides a large working space for different tool sizes (6-14 mm in diameter). The tracking framework allows translational movements between 40 and 185 mm along the depth direction and rotational motion around three local orthogonal axes up to [Formula: see text]. Comparative studies with the current state of the art confirm that our approach outperforms existing methods by providing nearly 100% detection rates and accurate pose estimation with mean errors of 2.8 mm and 0.72[Formula: see text]. The tracking algorithm runs at 20 frames per second for [Formula: see text] image resolution videos. CONCLUSION: Experiments show that the proposed hybrid marker can be applied to a wide range of surgical tools with superior detection rates and pose estimation accuracies. Both the qualitative and quantitative results demonstrate that our framework can be used not only for assisting intraoperative ultrasound guidance but also for tracking general surgical tools in MIS.

Online tracking and retargeting with applications to optical biopsy in gastrointestinal endoscopic examinations.

With recent advances in biophotonics, techniques such as narrow band imaging, confocal laser endomicroscopy, fluorescence spectroscopy, and optical coherence tomography, can be combined with normal white-light endoscopes to provide in vivo microscopic tissue characterisation, potentially avoiding the need for offline histological analysis. Despite the advantages of these techniques to provide online optical biopsy in situ, it is challenging for gastroenterologists to retarget the optical biopsy sites during endoscopic examinations. This is because optical biopsy does not leave any mark on the tissue. Furthermore, typical endoscopic cameras only have a limited field-of-view and the biopsy sites often enter or exit the camera view as the endoscope moves. In this paper, a framework for online tracking and retargeting is proposed based on the concept of tracking-by-detection. An online detection cascade is proposed where a random binary descriptor using Haar-like features is included as a random forest classifier. For robust retargeting, we have also proposed a RANSAC-based location verification component that incorporates shape context. The proposed detection cascade can be readily integrated with other temporal trackers. Detailed performance evaluation on in vivo gastrointestinal video sequences demonstrates the performance advantage of the proposed method over the current state-of-the-art.

Vision-based deformation recovery for intraoperative force estimation of tool-tissue interaction for neurosurgery.

PURPOSE: In microsurgery, accurate recovery of the deformation of the surgical environment is important for mitigating the risk of inadvertent tissue damage and avoiding instrument maneuvers that may cause injury. The analysis of intraoperative microscopic data can allow the estimation of tissue deformation and provide to the surgeon useful feedback on the instrument forces exerted on the tissue. In practice, vision-based recovery of tissue deformation during tool-tissue interaction can be challenging due to tissue elasticity and unpredictable motion. METHODS: The aim of this work is to propose an approach for deformation recovery based on quasi-dense 3D stereo reconstruction. The proposed framework incorporates a new stereo correspondence method for estimating the underlying 3D structure. Probabilistic tracking and surface mapping are used to estimate 3D point correspondences across time and recover localized tissue deformations in the surgical site. RESULTS: We demonstrate the application of this method to estimating forces exerted on tissue surfaces. A clinically relevant experimental setup was used to validate the proposed framework on phantom data. The quantitative and qualitative performance evaluation results show that the proposed 3D stereo reconstruction and deformation recovery methods achieve submillimeter accuracy. The force-displacement model also provides accurate estimates of the exerted forces. CONCLUSIONS: A novel approach for tissue deformation recovery has been proposed based on reliable quasi-dense stereo correspondences. The proposed framework does not rely on additional equipment, allowing seamless integration with the existing surgical workflow. The performance evaluation analysis shows the potential clinical value of the technique.

Online scene association for endoscopic navigation.

Endoscopic surveillance is a widely used method for monitoring abnormal changes in the gastrointestinal tract such as Barrett's esophagus. Direct visual assessment, however, is both time consuming and error prone, as it involves manual labelling of abnormalities on a large set of images. To assist surveillance, this paper proposes an online scene association scheme to summarise an endoscopic video into scenes, on-the-fly. This provides scene clustering based on visual contents, and also facilitates topological localisation during navigation. The proposed method is based on tracking and detection of visual landmarks on the tissue surface. A generative model is proposed for online learning of pairwise geometrical relationships between landmarks. This enables robust detection of landmarks and scene association under tissue deformation. Detailed experimental comparison and validation have been conducted on in vivo endoscopic videos to demonstrate the practical value of our approach.

Narrow band 3 × 3 Mueller polarimetric endoscopy.

Mueller matrix polarimetric imaging has shown potential in tissue diagnosis but is challenging to implement endoscopically. In this work, a narrow band 3 × 3 Mueller matrix polarimetric endoscope was designed by rotating the endoscope to generate 0°, 45° and 90° linearly polarized illumination and positioning a rotating filter wheel in front of the camera containing three polarisers to permit polarization state analysis for backscattered light. The system was validated with a rotating linear polarizer and a diffuse reflection target. Initial measurements of 3 × 3 Mueller matrices on a rat are demonstrated, followed by matrix decomposition into the depolarization and retardance matrices for further analysis. Our work shows the feasibility of implementing polarimetric imaging in a rigid endoscope conveniently and economically in order to reveal diagnostic information.

Pathological site retargeting under tissue deformation using geometrical association and tracking.

Recent advances in microscopic detection techniques include fluorescence spectroscopy, fibred confocal microscopy and optical coherence tomography. These methods can be integrated with miniaturised probes to assist endoscopy, thus enabling diseases to be detected at an early and pre-invasive stage, forgoing the need for histopathological samples and off-line analysis. Since optical-based biopsy does not leave visible marks after sampling, it is important to track the biopsy sites to enable accurate retargeting and subsequent serial examination. In this paper, a novel approach is proposed for pathological site retargeting in gastroscopic examinations. The proposed method is based on affine deformation modelling with geometrical association combined with cascaded online learning and tracking. It provides online in vivo retargeting, and is able to track pathological sites in the presence of tissue deformation. It is also robust to partial occlusions and can be applied to a range of imaging probes including confocal laser endomicroscopy.