Dense Depth Estimation from Stereo Endoscopy Videos Using Unsupervised Optical Flow Methods

Tracking and mapping in medical computer vision: A review

As computer vision algorithms increase in capability, their applications in clinical systems will become more pervasive. These applications include: diagnostics, such as colonoscopy and bronchoscopy; guiding biopsies, minimally invasive interventions, and surgery; automating instrument motion; and providing image guidance using pre-operative scans. Many of these applications depend on the specific visual nature of medical scenes and require designing algorithms to perform in this environment. In this review, we provide an update to the field of camera-based tracking and scene mapping in surgery and diagnostics in medical computer vision. We begin with describing our review process, which results in a final list of 515 papers that we cover. We then give a high-level summary of the state of the art and provide relevant background for those who need tracking and mapping for their clinical applications. After which, we review datasets provided in the field and the clinical needs that motivate their design. Then, we delve into the algorithmic side, and summarize recent developments. This summary should be especially useful for algorithm designers and to those looking to understand the capability of off-the-shelf methods. We maintain focus on algorithms for deformable environments while also reviewing the essential building blocks in rigid tracking and mapping since there is a large amount of crossover in methods. With the field summarized, we discuss the current state of the tracking and mapping methods along with needs for future algorithms, needs for quantification, and the viability of clinical applications. We then provide some research directions and questions. We conclude that new methods need to be designed or combined to support clinical applications in deformable environments, and more focus needs to be put into collecting datasets for training and evaluation.

Occlusion-robust scene flow-based tissue deformation recovery incorporating a mesh optimization model

PURPOSE

Tissue deformation recovery is to reconstruct the change in shape and surface strain caused by tool-tissue interaction or respiration, which is essential for providing motion and shape information that benefits the improvement of the safety of minimally invasive surgery. The binocular vision-based approach is a practical candidate for deformation recovery as no extra devices are required. However, previous methods suffer from limitations such as the reliance on biomechanical priors and the vulnerability to the occlusion caused by surgical instruments. To address the issues, we propose a deformation recovery method incorporating mesh structures and scene flow.

METHODS

The method can be divided into three modules. The first one is the implementation of the two-step scene flow generation module to extract the 3D motion from the binocular sequence. Second, we propose a strain-based filtering method to denoise the original scene flow. Third, a mesh optimization model is proposed that strengthens the robustness to occlusion by employing contextual connectivity.

RESULTS

In a phantom and an in vivo experiment, the feasibility of the method in recovering surface deformation in the presence of tool-induced occlusion was demonstrated. Surface reconstruction accuracy was quantitatively evaluated by comparing the recovered mesh surface with the 3D scanned model in the phantom experiment. Results show that the overall error is 0.70 ± 0.55 mm.

CONCLUSION

The method has been demonstrated to be capable of continuously recovering surface deformation using mesh representation with robustness to the occlusion caused by surgical forceps and promises to be suitable for the application in actual surgery.

MSDESIS: Multitask Stereo Disparity Estimation and Surgical Instrument Segmentation

Reconstructing the 3D geometry of the surgical site and detecting instruments within it are important tasks for surgical navigation systems and robotic surgery automation. Traditional approaches treat each problem in isolation and do not account for the intrinsic relationship between segmentation and stereo matching. In this paper, we present a learning-based framework that jointly estimates disparity and binary tool segmentation masks. The core component of our architecture is a shared feature encoder which allows strong interaction between the aforementioned tasks. Experimentally, we train two variants of our network with different capacities and explore different training schemes including both multi-task and single-task learning. Our results show that supervising the segmentation task improves our network's disparity estimation accuracy. We demonstrate a domain adaptation scheme where we supervise the segmentation task with monocular data and achieve domain adaptation of the adjacent disparity task, reducing disparity End-Point-Error and depth mean absolute error by 77.73% and 61.73% respectively compared to the pre-trained baseline model. Our best overall multi-task model, trained with both disparity and segmentation data in subsequent phases, achieves 89.15% mean Intersection-over-Union in RIS and 3.18 millimetre depth mean absolute error in SCARED test sets. Our proposed multi-task architecture is real-time, able to process ( 1280×1024 ) stereo input and simultaneously estimate disparity maps and segmentation masks at 22 frames per second. The model code and pre-trained models are made available: https://github.com/dimitrisPs/msdesis.

Endoscope Localization and Dense Surgical Scene Reconstruction for Stereo Endoscopy by Unsupervised Optical Flow and Kanade-Lucas-Tomasi Tracking

In image-guided surgery, endoscope tracking and surgical scene reconstruction are critical, yet equally challenging tasks. We present a hybrid visual odometry and reconstruction framework for stereo endoscopy that leverages unsupervised learning-based and traditional optical flow methods to enable concurrent endoscope tracking and dense scene reconstruction. More specifically, to reconstruct texture-less tissue surfaces, we use an unsupervised learning-based optical flow method to estimate dense depth maps from stereo images. Robust 3D landmarks are selected from the dense depth maps and tracked via the Kanade-Lucas-Tomasi tracking algorithm. The hybrid visual odometry also benefits from traditional visual odometry modules, such as keyframe insertion and local bundle adjustment. We evaluate the proposed framework on endoscopic video sequences openly available via the SCARED dataset against both ground truth data, as well as two other state-of-the-art methods - ORB-SLAM2 and Endo-depth. Our proposed method achieved comparable results in terms of both RMS Absolute Trajectory Error and Cloud-to-Mesh RMS Error, suggesting its potential to enable accurate endoscope tracking and scene reconstruction.