Google Inc.

Deepmind Technologies Limited

Olaf Ronneberger

Bernardino Romera-Paredes

Jeffrey De Fauw

Trevor Back

Samuel Blackwell

Harry Askham

Stanislav Nikolov

Joseph R Ledsam

Mustafa Suleyman

Julien Robert Michel Cornebise

Xavier Glorot

Pearse A Keane

Nenad Tomasev

Seyed Mohammadali Eslami

Balaji Lakshminarayanan

Clemens Ludwig Meyer

Simon Kohl

Cian Hughes

Danilo Jimenez Rezende

Andrew Zisserman

Pushmeet Kohli

Rudy Bunel

Jim Huibrecht Winkens

Ali Taylan Cemgil

Abhijit Guha Roy

Clemens Meyer

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network to (i) generate accurate network outputs for a machine learning task and (ii) generate intermediate outputs that can be used to reliably classify out-of-distribution inputs. In one aspect, a method comprises: training the neural network using supervised and contrastive losses, comprising repeatedly performing operations including: obtaining first and second network inputs; processing each network input using the neural network to generate its respective network input embedding; processing the first network input using the neural network to generate a network output; and adjusting the network parameter values using supervised and contrastive loss gradients, wherein: the supervised loss is based on: (i) the network output, and (ii) a corresponding target network output; and the contrastive loss is based on at least: (i) the first network input embedding, and (ii) the second network input embedding.

Classifying out-of-distribution data using a contrastive loss

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a final classification output for an image of eye tissue. The image is provided as input to each of one or more segmentation neural networks to obtain one or more segmentation maps of the eye tissue in the image. A respective classification input is generated from each of the segmentation maps. For each of the segmentation maps, the classification input for the segmentation map is provided as input to each of one or more classification neural networks to obtain, for each segmentation map, a respective classification output from each classification neural network. A final classification output for the image is generated from the respective classification outputs for each of the segmentation maps.

Generalizable medical image analysis using segmentation and classification neural networks

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.

3-D convolutional neural networks for organ segmentation in medical images for radiotherapy planning

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.

Sampling latent variables to generate multiple segmentations of an image

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.

Growing community of inventors

London, United Kingdom

Olaf Ronneberger