General Electric Company

Ge Precision Healthcare LLC

Xiao Jin

Geng Fu

Hua Qian

Jianjun Guo

Jiahua Fan

Scott David Wollenweber

Floribertus P M Heukensfeldt Jansen

Adrian Ivan

Hao Lai

Xue Rui

Systems, apparatus, methods, and computer-readable storage media to estimate scatter in an image are disclosed. An example apparatus includes a network generator to generate and train an inception neural network using first and second input to deploy an inception neural network model to process image data when first and second outputs of the inception neural network converge, the first input based on a raw sinogram of a first image and the second input based on an attenuation-corrected sinogram of the first image, the inception neural network including a first filter of a first size and a second filter of a second size in a layer to process the first input and/or the second input to generate an estimate of scatter in the first image. The example apparatus also includes an image processor to apply the estimate of scatter to a second image to generate a processed image.

Deep learning-based PET scatter estimation systems and methods using an inception neural network model

A method is provided that includes acquiring initial PET imaging data. The method also includes acquiring CT imaging data. Further, the method includes training a deep learning model for PET image reconstruction using the initial PET imaging data and the CT imaging data.

Systems and methods for improved PET imaging

A SiPM readout circuit includes a front-end circuit having amplifiers coupled to SiPM analog outputs, pixel readout channels coupled to amplifiers provide a timing signal representing gamma ray photon detection in individual SiPM, a block timing channel that creates a summed signal from all SiPMs, and generates a block timing signal and a validation signal, an energy channel that generates a summed energy signal and a two-dimensional position of the gamma ray photon detection in the block, and a control logic/processing circuit that performs a time stamp estimation method. Methods of determining the radiation event timing and a non-transitory computer-readable medium containing computer-readable instructions to implement the methods are disclosed.

Universal readout for silicon photomultiplier based detectors

Methods and systems are provided for medical imaging systems. In one embodiment, a method comprises estimating an external scatter contamination in emission data based on an estimated emission activity originating from anatomies outside a field-of-view (FOV) of a scanner, the anatomies identified based on an image segmentation analysis performed on an image generated in the imaging system, the image generated prior to acquiring the emission data. In this way, a scatter correction applied to the emission data may include both scatter originating within the FOV and outside the FOV, and hence may be more accurate.

Methods and systems for scatter correction in positron emission tomography

Embodiments of the invention are utilized to improve the timing performance of SiPM based PET detectors with light-sharing configuration. The universal readout design utilizes adaptive group readout to process noisy and slow signals generated by SiPM devices, and provides enhanced timing capabilities with simplified readout electronics.

Growing community of inventors

Brookfield, WI, United States of America

Xiao Jin