Partial 3D-reconstruction of the colon from monoscopic colonoscopy videos using shape-from-motion and deep learning

For the image-based documentation of a colonoscopy procedure, a 3D-reconstuction of the hollow colon structure from endoscopic video streams is desirable. To obtain this reconstruction, 3D information about the colon has to be extracted from monocular colonoscopy image sequences. This information can be provided by estimating depth through shape-from-motion approaches, using the image information from two successive image frames and the exact knowledge of their disparity. Nevertheless, during a standard colonoscopy the spatial offset between successive frames is continuously changing. Thus, in this work deep convolutional neural networks (DCNNs) are applied in order to obtain piecewise depth maps and point clouds of the colon. These pieces can then be fused for a partial 3D reconstruction.

Stitching and registering highly multiplexed whole slide images of tissues and tumors using ASHLAR software

ABSTRACTWidespread use of highly multiplexed microscopy to study normal and diseased tissues at a single-cell level is complicated by underdevelopment of the necessary software. This is particularly true of high resolution whole-slide imaging (WSI), which involves gigapixel datasets of specimens as large as 5 cm2. WSI is necessary for accurate spatial analysis and a diagnostic necessity. High resolution WSI requires collection of successive image tiles; multiplexing commonly involves successive data acquisition cycles, each with a subset of dyes, antibodies or oligonucleotides. We describe a new Python tool, ASHLAR (Alignment by Simultaneous Harmonization of Layer/Adjacency Registration), that coordinates stitching and registration and scales to 103 or more image tiles over many imaging cycles to generate accurate, high-plex image mosaics, the key type of data for downstream visualization and computational analysis. ASHLAR is more robust and accurate than existing methods and compatible with any scanner or microscope conforming to Open Microscopy Environment standards.

Design and Synthesis of Luminescent Lanthanide-Based Bimodal Nanoprobes for Dual Magnetic Resonance (MR) and Optical Imaging

Current biomedical imaging techniques are crucial for the diagnosis of various diseases. Each imaging technique uses specific probes that, although each one has its own merits, do not encompass all the functionalities required for comprehensive imaging (sensitivity, non-invasiveness, etc.). Bimodal imaging methods are therefore rapidly becoming an important topic in advanced healthcare. This bimodality can be achieved by successive image acquisitions involving different and independent probes, one for each mode, with the risk of artifacts. It can be also achieved simultaneously by using a single probe combining a complete set of physical and chemical characteristics, in order to record complementary views of the same biological object at the same time. In this scenario, and focusing on bimodal magnetic resonance imaging (MRI) and optical imaging (OI), probes can be engineered by the attachment, more or less covalently, of a contrast agent (CA) to an organic or inorganic dye, or by designing single objects containing both the optical emitter and MRI-active dipole. If in the first type of system, there is frequent concern that at some point the dye may dissociate from the magnetic dipole, it may not in the second type. This review aims to present a summary of current activity relating to this kind of dual probes, with a special emphasis on lanthanide-based luminescent nano-objects.

Successive Image Generation from a Single Sentence

Through various examples in history such as the early man’s carving on caves, dependence on diagrammatic representations, the immense popularity of comic books we have seen that vision has a higher reach in communication than written words. In this paper, we analyse and propose a new task of transfer of information from text to image synthesis. Through this paper we aim to generate a story from a single sentence and convert our generated story into a sequence of images. We plan to use state of the art technology to implement this task. With the advent of Generative Adversarial Networks text to image synthesis have found a new awakening. We plan to take this task a step further, in order to automate the entire process. Our system generates a multi-lined story given a single sentence using a deep neural network. This story is then fed into our networks of multiple stage GANs inorder to produce a photorealistic image sequence.

Applying Artificial Bee Colony Algorithm for feature optimization in UAV Navigation

In this paper, the bee colony algorithm is used for optimizing features which have been extracted from UAV’s digital camera by SURF algorithm. To do that, the local map is stored in UAV memory before flight. During flight, images will be captured by a digital camera and the features in successive image will be extracted using SURF algorithm because SURF algorithm is considered highly insensitive to environmental light, scale changes and noise. Then, the extracted features will be optimized using the bee colony algorithm and will be compared with the original map features to find the location and direction of UAV. Simulations show that proposed algorithm has good precision and is robust to scale changes, light intensity variations, and noise.

Cars Tracking and Counting at Night

This work proposes a robust scheme to automatically tracking and counting cars in the traffic surveillance. In the proposed method, pixels at a specific position of successive image frames are first processed by the modified iterative threshold selection technique to establish the background model. Second, an original image is subtracted by this background to obtain a difference image that is performed with the differential image between an original image and its precedent neighboring image to yield an image with initial contour points of moving objects. Third, the robust edge-following scheme manipulates these contour points to produce closed-form objects. Particularly, two headlights of a car are merged with their corresponding reflective lights on the ground to yield two light objects for a car extraction at night. As compared to the conventional methods, the proposed method is demonstrated to have the best accuracy of moving object extraction. Finally, object motion connection is effectively employed to track object paths and compute the number of moving cars. The practical implementation reveals that the proposed method can precisely and reliably estimate a traffic amount.