Connected machine learning model with joint training for lesion detection

Embodiments disclosed herein generally relate to a connected machine learning model with joint training for lesion detection. In particular, aspects of the present disclosure relate to accessing a three-dimensional magnetic resonance imaging (MRI) image, where the three-dimensional MRI image depicts a region of a brain of a subject, where the region of the brain includes at least a first type of lesion and a second type of lesion; 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 lesion of the first type using the first convolutional neural network using the three-dimensional MRI image as an input; generating a second segmentation mask for the lesion of the second type using the second convolutional neural network using the three-dimensional MRI image as an input; and outputting the first split mask and the second split mask. 本文公开的实施例总体上涉及用于病灶检测的利用联合训练的连