Binocular endoscopy is gradually becoming the future of minimally invasive surgery (MIS) thanks to the development of stereo vision. However, some problems still exist, such as the low reconstruction accuracy, small surgical field, and low computational efficiency. To solve these problems, we designed a framework for real-time dense reconstruction in binocular endoscopy scenes. First, we obtained the initial disparity map using an SGBM algorithm and proposed the disparity confidence map as a dataset to provide StereoNet training. Then, based on the depth map predicted by StereoNet, the corresponding left image of each depth map was input into the Oriented Fast and Brief-Simultaneous Localization and Mapping (ORB-SLAM) framework using an RGB-D camera to realize the real-time dense reconstruction of the binocular endoscopy scene. The proposed algorithm was verified in the stomach phantom and a real pig stomach. Compared with the ground truth, the proposed algorithm’s RMSE is 1.620 mm, and the number of effective points in the point cloud is 834,650, which is a significant improvement in the mapping ability compared with binocular SLAM and ensures the real-time performance of the algorithm while performing dense reconstruction. The effectiveness of the proposed algorithm is verified.

In the practice of clinical endoscopy, the precise estimation of the lesion size is quite significant for diagnosis. In this paper, we propose a three-dime

There are shortcomings of binocular endoscope three-dimensional (3D) reconstruction in the conventional algorithm, such as low accuracy, small field of view, and loss of scale information. To address these problems, aiming at the specific scenes of stomach organs, a method of 3D endoscopic image stitching based on feature points is proposed. The left and right images are acquired by moving the endoscope and converting them into point clouds by binocular matching. They are then preprocessed to compensate for the errors caused by the scene characteristics such as uneven illumination and weak texture. The camera pose changes are estimated by detecting and matching the feature points of adjacent left images. Finally, based on the calculated transformation matrix, point cloud registration is carried out by the iterative closest point (ICP) algorithm, and the 3D dense reconstruction of the whole gastric organ is realized. The results show that the root mean square error is 2.07 mm, and the endoscopic field of view is expanded by 2.20 times, increasing the observation range. Compared with the conventional methods, it does not only preserve the organ scale information but also makes the scene much denser, which is convenient for doctors to measure the target areas, such as lesions, in 3D. These improvements will help improve the accuracy and efficiency of diagnosis.

Endoscopic image has complex backgrounds and spatially different noise, bringing mainstream denoising methods to the problem of incomplete noise removal and the loss of image detail. Thus, an endoscopic image denoising algorithm based on spatial attention UNet network is proposed in this paper. UNet based on residual learning is utilized as the backbone network. Spatial attention modules based on noise intensity estimation and edge feature extraction modules are used to remove noise better while preserving the image details and improving generalization ability. We take endoscopic images of real scenes using gastroscopy and compare our method with mainstream methods. Experimental results show that our approach improves PSNR by 3.51 or 2.93 and SSIM by 0.03 or 0.015 compared with CBDNet or EDCNN, respectively. Our method can effectively improve the impact of noise on the image quality of endoscopic images, thus better assisting doctors in diagnosis and treatment.