Abstract: Embodiments disclosed herein generally relate to connected machine learning models with joint training for lesion detection. Particularly, aspects of the present disclosure are directed to accessing a three-dimensional magnetic resonance imaging (MRI) image, wherein the three-dimensional MRI image depicts a region of a brain of a subject, wherein the region of the brain includes at least a first type of lesions and a second type of lesions; inputting the three-dimensional MRI image into a machine-learning model comprising a first convolutional neural network and a second convolutional neural network; generating a first segmentation mask for the first type of lesions using the first convolutional neural network that takes as input the three-dimensional MRI image; generating a second segmentation mask for the second type of lesions using the second convolutional neural network that takes as input the three-dimensional MRI image; and outputting the first segmentation mask and the second segmentation mask.

Abstract: Embodiments disclosed herein generally relate to multi-arm machine learning models for lesion detection. Particularly, aspects of the present disclosure are directed to accessing a three-dimensional magnetic resonance imaging (MRI) images. Each of the three-dimensional MRI images depict a same volume of a brain of a subject. The volume of the brain includes at least part of one or more lesions. Each three-dimensional MRI image of the three-dimensional MRI images is processed using one or more corresponding encoder arms of a machine-learning model to generate an encoding of the three-dimensional MRI image. The encodings of the three-dimensional MRI images are concatenated to generate a concatenated representation. The concatenated representation is processed using a decoder arm of the machine-learning model to generate a prediction that identifies one or more portions of the volume of the brain predicted to depict at least part of a lesion.

Abstract: Methods and systems disclosed herein relate generally to processing images to estimate whether at least part of a tumor is represented in the images. A computer-implemented method includes accessing an image of at least part of a biological structure of a particular subject, processing the image using a segmentation algorithm to extract a plurality of image objects depicted in the image, determining one or more structural characteristics associated with an image object of the plurality of image objects, processing the one or more structural characteristics using a trained machine-learning model to generate estimation data corresponding to an estimation of whether the image object corresponds to a lesion or tumor associated with the biological structure, and outputting the estimation data for the particular subject.

Abstract: Techniques disclosed herein facilitate tracking the degree to which a size of a biological structure changes over time. In some instances, an initial biological image (collected at a first time) can be segmented to characterized a boundary and size. A subsequent biological image can be processed to identify a deformation and/or transformation variable (e.g., one or more Jacobian matrices and/or one or more Jacobian determinants). The deformation and/or transformation variable(s) and initial segmentation can be used to predict a size of the biological structure at a subsequent time. The predicted size may inform a treatment recommendation.

Abstract: A Generative Adversarial Network (GAN) can be trained, where the GAN includes an anomaly-removing Generator network configured to modify a medical image to remove a depiction of a biological anomaly and one or more Discriminator networks (each configured to discriminate between real and fake images). The anomaly-removing Generator network can then receive a medical image that depicts a particular biological anomaly (or pre-processed version thereof) and generate a modified image predicted to lack any depiction of the particular biological anomaly. The size of the particular biological anomaly may be estimated based on the modified image and the received image (or pre-processed version thereof).

Abstract: Medical image(s) are input into a detection network to generate mask(s) identifying a set of regions within the medical image(s), where the detection network predicts that each region identified in the mask(s) includes a depiction of a tumor of one or more tumors within the subject. For each region, the region of the medical image(s) is processed using a tumor segmentation network to generate one or more tumor segmentation boundaries for the tumor present within the subject. For each tumor and by using a plurality of organ-specific segmentation networks, an organ is determined within which at least part of the tumor is located. An output is generated based on the one or more tumor segmentation boundaries and locations of the organs within which at least part of the one or more tumors are located.

Abstract: The present disclosure relates to techniques for segmenting tumors with positron emission tomography (PET) using deep convolutional neural networks for image and lesion metabolism analysis.