Abstract: Systems and methods for detecting placement of an object in a digital image are provided. The system receives a digital image and processes the digital image to generate one or more candidate regions within the digital image using a first neural network. The system then selects a proposed region from the one or more candidate regions using the first neural network and assigns a score to the proposed region using the first neural network. Lastly, the system processes the proposed region using a second neural network to detect an object in the proposed region.

Abstract: Computer vision systems and methods for time-aware needle tip localization in two-dimensional (2D) ultrasound images are provided. A consecutive fused image sequence, derived from fusion of the enhanced frames and the corresponding B-mode frames, is processed by a time-aware neural network which includes a unified convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network. The CNN acts as a feature extractor, with stacked convolutional layers which progressively create a hierarchy of more abstract features. The LSTM models temporal dependencies in time-series data. The system learns spatiotemporal features associated with needle tip movement, for example, needle tip appearance and trajectory information, and successfully localizes the needle tip in the presence of abrupt intensity changes and motion artifacts.

Abstract: Computer vision systems and methods for real-time localization of a needle in an ultrasound video are provided. The method includes a step of receiving at a processor a plurality of frames from the ultrasound video. The method also includes the step of identifying by the processor one of the plurality of frames as a background image and a frame adjacent to the background image as a current image. The method further includes the step of performing by the processor a bitwise complement operation on the background image to generate a complement image. Moreover, the method includes the step of performing by the processor a pointwise logical AND operation on the complement image and the current image to identify the location of the needle.

Abstract: Computer vision systems and methods for real-time localization of a needle in an ultrasound video are provided. The method includes a step of receiving at a processor a plurality of frames from the ultrasound video. The method also includes the step of identifying by the processor one of the plurality of frames as a background image and a frame adjacent to the background image as a current image. The method further includes the step of performing by the processor a bitwise complement operation on the background image to generate a complement image. Moreover, the method includes the step of performing by the processor a pointwise logical AND operation on the complement image and the current image to identify the location of the needle.

Abstract: Systems and methods for detecting placement of an object in a digital image are provided. The system receives a digital image and processes the digital image to generate one or more candidate regions within the digital image using a first neural network. The system then selects a proposed region from the one or more candidate regions using the first neural network and assigns a score to the proposed region using the first neural network. Lastly, the system processes the proposed region using a second neural network to detect an object in the proposed region.

Abstract: This invention relates to a novel technique for producing images of arteries that overcomes a significant limitation of conventional computed tomographic angiography (CTA). The technique is performed by the acquisition of pre-contrast computed tomography in addition to the conventional computed tomographic angiography and by the digital subtraction of the pre-contrast computed tomogram from the conventional CTA after alignment of the two images.

Abstract: This invention relates to a novel technique for producing images of arteries that overcomes a significant limitation of conventional computed tomographic angiography (CTA). The technique is performed by the acquisition of pre-contrast computed tomography in addition to the conventional computed tomographic angiography and by the digital subtraction of the pre-contrast computed tomogram from the conventional CTA after alignment of the two images.