Abstract: Systems/techniques that facilitate interpretable task-specific dimensionality-reduction are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can generate, via execution of a first deep learning neural network, a voxel-wise weight map corresponding to the three-dimensional medical image and a set of projection vectors corresponding to the three-dimensional medical image. In various instances, the system can generate a set of two-dimensional projection images of the three-dimensional medical image, based on the voxel-wise weight map and the set of projection vectors. In various cases, the first deep learning neural network can be trained in a serial pipeline with a second deep learning neural network that is configured to perform an inferencing task on two-dimensional inputs. This can cause the set of two-dimensional projection images to be tailored to the inferencing task.

Abstract: Systems are provided for perioperative care. In an example, a system includes one or more processors and memory storing instructions executable by the one or more processors to output a graphical user interface (GUI) including a first visual representation of a default or previously-determined phase of anesthesia delivery for a patient; receive a plurality of monitoring parameters of the patient over an observation window, at least a portion of the plurality of monitoring parameters obtained from an anesthesia delivery machine; identify, by applying a selected set of rules to the plurality of monitoring parameters, whether an event signaling a change to a new phase of anesthesia delivery for the patient is detected; based on the event being detected, update the GUI to display a second visual representation of the new phase; and based on the event not being detected, maintain the first visual representation on the GUI.

Abstract: Systems/techniques that facilitate interpretable task-specific dimensionality-reduction are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can generate, via execution of a first deep learning neural network, a voxel-wise weight map corresponding to the three-dimensional medical image and a set of projection vectors corresponding to the three-dimensional medical image. In various instances, the system can generate a set of two-dimensional projection images of the three-dimensional medical image, based on the voxel-wise weight map and the set of projection vectors. In various cases, the first deep learning neural network can be trained in a serial pipeline with a second deep learning neural network that is configured to perform an inferencing task on two-dimensional inputs. This can cause the set of two-dimensional projection images to be tailored to the inferencing task.