Abstract: A method including receiving image data including a plurality of CT scan images of at least a portion of a subject; segmenting the CT scan images to identify portions of each image corresponding to the subject's colon; analyze axial views of the segmented CT scan images to identify a candidate polyp using a first CNN; analyzing at least two of axial views, sagittal views, and coronal views CT scan images corresponding to the candidate polyp using a second model to classify the candidate polyp as a polyp or not a polyp; and generating a user interface that includes the classified candidate polyp.

Abstract: A method includes receiving image data including a plurality of CT scan images of a portion of a subject; identifying a seed feature within the plurality of CT scan images based on Hounsfield unit values within each image; applying region growing to iteratively generate a 3D model of the subject's colon starting with the seed feature; and applying a graph cut process to refine the 3D model to produce a finalized 3D model of the subject's colon.

Abstract: Described herein are methods, systems and computer program products for measuring student engagement using facial expression analysis by tracking, using a first plurality of video cameras, key facial points of one or more students and using the tracked key facial points extracting a head pose for each of the one or more students; track, using a second plurality of video cameras, eye gaze of each of the one or more students, wherein the head pose and the eye gaze of each of the one or more students is provided to the behavioral engagement module and the emotional engagement module, and wherein the behavioral engagement module classifies an average behavioral engagement of the one or more students and/or a behavioral engagement of each of the one or more students, and wherein the emotional engagement module classifies each students' emotional engagement into two categories, emotionally engaged or emotionally non-engaged.

Abstract: The three-dimensional (3D) reconstruction of visible part of the human jaw is becoming required for many diagnostic and treatment procedures. The present invention improves upon Statistical Shape from Shading (SSFS) framework by using a novel approach to automatically extract prior information. This two-step framework consists of interdental gingiva regions extraction for each individual tooth and detection of the centerline across the jaw span. These two steps help extract the anatomical landmark points and detect the status of the jaw. Experimental results highlight the accuracy of the extracted prior information and how this information boosts recovering 3D models of the human jaw.

Abstract: The present development is a method for the visualization and automatic examination of the inner surface of tubular objects. The method uses a virtual camera rig arranged in a specific pattern within the tubular objects inner surface. The rig can be physical or virtual or hypothetical; graphics-based, providing the same functionality of a sequence of virtual cameras. This “Fly-In” method is a more general visualization technique than techniques of the prior art, it is more flexible and does not create distortion, it does not require alternation to the surface for viewing and it can handle multi-branches with variable diameter. It can also provide a clear assessment of the inner surface for immediate examination of the object.

Abstract: The present invention is a method to stitch images of human teeth that are captured by an intraoral camera. Oral dental applications based on visual data pose various challenges such as low lighting conditions and saliva. Herein we describe a stitching algorithm of low-texture/low-resolution imaging. First, normals of tooth surface are extracted using shape from shading. An algorithm to rectify the imprecise values of the surface normal due to the oral environment is applied and normal maps generated. Second, the normal maps are used to detect, extract and match the corresponding features. Finally, to enhance the stitching process for these unidealized data, normal maps are used to estimate as-projective-as-possible warps. The proposed approach outperforms the state-of-the-art auto-stitching approach and shows a better performance in such cases of low-texture regions.