Abstract: Systems/techniques that facilitate machine learning generation of low-noise and high structural conspicuity images are provided. In various embodiments, a system can access an image and can apply at least one of image denoising or image resolution enhancement to the image, thereby yielding a first intermediary image. In various instances, the system can generate, via execution of a plurality of machine learning models, a plurality of second intermediary images based on the first intermediary image, wherein a given machine learning model in the plurality of machine learning models receives as input the first intermediary image, wherein the given machine learning model produces as output a given second intermediary image in the plurality of second intermediary images, and wherein the given second intermediary image represents a kernel-transformed version of the first intermediary image. In various cases, the system can generate a blended image based on the plurality of second intermediary images.

Abstract: Techniques are described for enhancing the quality of three-dimensional (3D) anatomy scan images using deep learning. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a reception component that receives a scan image generated from 3D scan data relative to a first axis of a 3D volume, and an enhancement component that applies an enhancement model to the scan image to generate an enhanced scan image having a higher resolution relative to the scan image. The enhancement model comprises a deep learning neural network model trained on training image pairs respectively comprising a low-resolution scan image and a corresponding high-resolution scan image respectively generated relative to a second axis of the 3D volume.

Abstract: Systems/techniques that facilitate self-supervised deblurring are provided. In various embodiments, a system can access an input image generated by an imaging device. In various aspects, the system can train, in a self-supervised manner based on a point spread function of the imaging device, a machine learning model to deblur the input image. More specifically, the system can append to the model one or more non-trainable convolution layers having a blur kernel that is based on the point spread function of the imaging device. In various aspects, the system can feed the input image to the model, the model can generate a first output image based on the input image, the one or more non-trainable convolution layers can generate a second output image by convolving the first output image with the blur kernel, and the system can update parameters of the model based on a difference between the input image and the second output image.

Abstract: A multimode detection system for detecting one or more samples is provided. The detection system comprises an electromagnetic radiation source, a reference arm, and a sample arm comprising a sensing substrate having a plurality of sample fields, wherein the sample fields are configured to receive the one or more samples. The system further comprises a phase difference generator configured to introduce pathlength differences in the reference arm, sample arm, or both, a spatial light modulator operatively coupled to the reference arm, sample arm, or both, wherein the spatial light modulator is configured to modulate incident radiation, resultant radiation, or both in the reference arm, sample arm, or both, and an imaging spectrometer configured to discriminate between two or more spatially separated sample en two or more spatially separated sample fields.

Abstract: Transducer configurations and methods for transducer positioning in electrical impedance tomography are provided. A plurality of transducers for one electrical impedance tomography arrangement are configured for positioning proximate a surface of an object and spaced apart along the object, wherein the transducers are one or more conductive rings and have at least one non-conductive portion. The arrangement further includes one or more excitation drivers coupled to the plurality of transducers and configured to generate excitation signals for the plurality of transducers. The arrangement also includes one or more response detectors coupled to the plurality of transducers and configured to measure a response of the object at the plurality of transducers to the excitation applied by the plurality of transducers based on the excitation signals.

Abstract: A method for classifying a tissue sample of a biopsy specimen into one of a plurality of classes is presented. The method includes receiving a light from at least one location of the tissue sample including a plurality of chromophores, wherein the received light comprises at least one of an attenuated illumination light and a re-emitted light. The method further includes processing a spectrum of the received light to determine a feature for each of the chromophores in the at least one location of the tissue sample. In addition, the method includes estimating a Z-score for each of the chromophores based on the determined feature. Also, the method includes classifying the tissue sample into one of the plurality of classes based on the estimated Z-score for each of the chromophores.

Abstract: A method for classifying a tissue sample of a biopsy specimen into one of a plurality of classes is presented. The method includes receiving a light from at least one location of the tissue sample including a plurality of chromophores, wherein the received light comprises at least one of an attenuated illumination light and a re-emitted light. The method further includes processing a spectrum of the received light to determine a feature for each of the chromophores in the at least one location of the tissue sample. In addition, the method includes estimating a Z-score for each of the chromophores based on the determined feature. Also, the method includes classifying the tissue sample into one of the plurality of classes based on the estimated Z-score for each of the chromophores.

Abstract: An electrode array, a system and a method for reconstructing the distribution of electrical properties within a multi-material object. One embodiment includes electrodes arranged along a three-dimensional helical path to provide one or more helical arrays and circuitry to measure signals for calculating a conductivity or admittivity distribution representative of the interior of the structure. Image data may be obtained which is representative of the multi-material region.

Abstract: A multimode detection system for detecting one or more samples is provided. The detection system comprises an electromagnetic radiation source, a reference arm, and a sample arm comprising a sensing substrate having a plurality of sample fields, wherein the sample fields are configured to receive the one or more samples. The system further comprises a phase difference generator configured to introduce pathlength differences in the reference arm, sample arm, or both, a spatial light modulator operatively coupled to the reference arm, sample arm, or both, wherein the spatial light modulator is configured to modulate incident radiation, resultant radiation, or both in the reference arm, sample arm, or both, and an imaging spectrometer configured to discriminate between two or more spatially separated sample en two or more spatially separated sample fields.

Abstract: Transducer configurations and methods for transducer positioning in electrical impedance tomography are provided. A plurality of transducers for one electrical impedance tomography arrangement are configured for positioning proximate a surface of an object and spaced apart along the object, wherein the transducers are one or more conductive rings and have at least one non-conductive portion. The arrangement further includes one or more excitation drivers coupled to the plurality of transducers and configured to generate excitation signals for the plurality of transducers. The arrangement also includes one or more response detectors coupled to the plurality of transducers and configured to measure a response of the object at the plurality of transducers to the excitation applied by the plurality of transducers based on the excitation signals.

Abstract: An electrode array, a system and a method for reconstructing the distribution of electrical properties within a multi-material object. One embodiment includes electrodes arranged along a three-dimensional helical path to provide one or more helical arrays and circuitry to measure signals for calculating a conductivity or admittivity distribution representative of the interior of the structure. Image data may be obtained which is representative of the multi-material region.

Abstract: A method of providing an image of an interior of a structure containing regions having different conductivities or admittivities. In one embodiment a series of electrical signal sets is applied to a series of electrodes, each signal set generating a rotating electric field. A measured set of electrical signals obtained from the electrodes are used to calculate a conductivity or admittivity distribution representative of the interior of the structure in a region about which the electrodes are positioned. The process of calculating the distribution includes defining a cost function, e.g., the energy function based on the distribution, and a forward model expressing the measured set of electrical signals as a function of the change in voltage values with respect to conductivity or admittivity and requiring that the partial derivative of the difference between the energy function and a function based on the forward model equal zero.