Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for segmenting a medical image. In one aspect, a method comprises: receiving a medical image that is captured using a medical imaging modality and that depicts a region of tissue in a body; and processing the medical image using a segmentation neural network to generate a segmentation output. The segmentation neural network can include a sequence of multiple encoder blocks and a decoder subnetwork. Training the segmentation neural network can include determining a set of error values for a segmentation channel; identifying the highest error values from the set of error values for the segmentation channel; and determining a segmentation loss based on the highest error values identified for the segmentation channel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for segmenting a medical image. In one aspect, a method comprises: receiving a medical image that is captured using a medical imaging modality and that depicts a region of tissue in a body; and processing the medical image using a segmentation neural network to generate a segmentation output, wherein the segmentation neural network comprises a sequence of multiple encoder blocks, wherein: each encoder block is a residual neural network block comprising one or more two-dimensional convolutional neural network layers, one or more three-dimensional convolutional neural network layers, or both, and each encoder block is configured to process a respective encoder block input to generate a respective encoder block output wherein a spatial resolution of the encoder block output is lower than a spatial resolution of the encoder block input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for segmenting a medical image. In one aspect, a method comprises: receiving a medical image that is captured using a medical imaging modality and that depicts a region of tissue in a body; and processing the medical image using a segmentation neural network to generate a segmentation output, wherein the segmentation neural network comprises a sequence of multiple encoder blocks, wherein: each encoder block is a residual neural network block comprising one or more two-dimensional convolutional neural network layers, one or more three-dimensional convolutional neural network layers, or both, and each encoder block is configured to process a respective encoder block input to generate a respective encoder block output wherein a spatial resolution of the encoder block output is lower than a spatial resolution of the encoder block input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for segmenting a medical image. In one aspect, a method comprises: receiving a medical image that is captured using a medical imaging modality and that depicts a region of tissue in a body; and processing the medical image using a segmentation neural network to generate a segmentation output, wherein the segmentation neural network comprises a sequence of multiple encoder blocks, wherein: each encoder block is a residual neural network block comprising one or more two-dimensional convolutional neural network layers, one or more three-dimensional convolutional neural network layers, or both, and each encoder block is configured to process a respective encoder block input to generate a respective encoder block output wherein a spatial resolution of the encoder block output is lower than a spatial resolution of the encoder block input.

Abstract: A system and method suitable for monitoring user technique of an inhaler device configured for delivery of a medicament is provided. The system may include a microphone adapted for sensing sound made during operation of the inhaler device and processing circuitry operable to process a data signal obtained from the microphone, wherein the data signal includes acoustic information sensed. The processing circuitry is adapted to determine inhalation and exhalation breath characteristics that occur during use, by analyzing the temporal and spectral components of the acoustic information sensed and processed to differentiate between an inhalation and an exhalation, based on both the temporal and spectral components. This information can be processed to determine user technique adherence to inhaler or respiratory device protocol. The analysis of temporal and spectral components can determine the impact of user technique errors on the quantity and the deposition of medicament delivered into the user's airways.

Abstract: A system for rehabilitating patients affected by balance disorders with or without vestibular hypofunction and/or malfunction with or without an associated hearing loss, which includes sensors of sound and head movement, processing circuitry, a power source coupled to head phones, an air conduction hearing aid, bone conduction hearing aid, middle ear implant or an electrical stimulator implanted into the cochlea capable of stimulating areas within the cochlea with the potential for current spread to surrounding non-auditory areas including the vestibular system.

Abstract: A system and method suitable for monitoring user technique of an inhaler device configured for delivery of a medicament is provided. The system may include a microphone adapted for sensing sound made during operation of the inhaler device and processing circuitry operable to process a data signal obtained from the microphone, wherein the data signal includes acoustic information sensed. The processing circuitry is adapted to determine inhalation and exhalation breath characteristics that occur during use, by analysing the temporal and spectral components of the acoustic information sensed and processed to differentiate between an inhalation and an exhalation, based on both the temporal and spectral components. This information can be processed to determine user technique adherence to inhaler or respiratory device protocol. The analysis of temporal and spectral components can determine the impact of user technique errors on the quantity and the deposition of medicament delivered into the user's airways.

Abstract: A system for rehabilitating patients affected by balance disorders with or without vestibular hypofunction and/or malfunction with or without an associated hearing loss, which includes sensors of sound and head movement, processing circuitry, a power source coupled to head phones, an air conduction hearing aid, bone conduction hearing aid, middle ear implant or an electrical stimulator implanted into the cochlea capable of stimulating areas within the cochlea with the potential for current spread to surrounding non-auditory areas including the vestibular system.