Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated.

Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated.

Abstract: A system and method provides transcoding a video in parallel by multiple transcoders based on a measure of video coding complexity (VCC). The system has a video pre-processing module, a master transcoder, a transcoding controller and multiple transcoders. The video pre-processing module transcodes a source video into an intermediate video. The master transcoder partitions the intermediate video into multiple transcoding units, where a transcoding unit identifies a portion of data of the intermediate video for transcoding. The master transcoder further generates a transcoding request for each transcoding unit. The transcoding controller distributes the transcoding units to the multiple transcoders, which transcode the data of the transcoding units in parallel into transcoded data.

Abstract: An application sharing and collaboration (ASC) system comprising a first computer, where the first computer is configured to execute a graphics application. The graphics application is configured to: (a) call a set of OpenGL rendering functions to render an image into a local buffer, and (b) call a particular OpenGL function which has been modified to induce compression of the image from the local buffer and transfer of the compressed image to a set of one or more remote systems. Each of the one or more remote systems may be configured to: decompress the compressed image, and display the decompressed image.

Abstract: A method and apparatus are provided for MR based volumetric frameless 3-D interactive localization, virtual simulation, and dosimetric radiation therapy planning. Using an MR imaging device, a patient is scanned to generate a magnetic resonance image volume data set. Using the MR data set exclusively, parallel and divergent volume images of the patient is displayed for target tissue identification, localization, virtual simulation, and dosimetric radiation therapy planning. Preferably, the interactive localization, simulation, and dosimetric RTP is based exclusively on the 3-dimensional MR volume data set rendered in the form of at least one of a multi-planar reformatted image (MPR), an oblique multi-planar reformatted image (OMPR), a digitally reconstructed “radiograph” (DRR), and a digitally composited “radiograph” (DCR).