Automated clustering of anomalous histopathology tissue samples
AssigneeDeciphex
InventorsMark Gregson, Hammad A. Qureshi
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for generating clusters of anomalous images. Histopathological samples are images at an associated imaging system to produce a plurality of images. A plurality of anomalous images are identified from the plurality of images at an anomaly detection system, having an associated latent space. The plurality of anomalous images are clustered to generate a plurality of clusters within a feature space defined by a set of classification features. The set of classification features include a feature derived from the latent space associated with the anomaly detection system.
Claims20
A method comprising:
- imaging histopathological samples at an associated imaging system to produce a plurality of images;
- identifying a plurality of anomalous images from the plurality of images at an anomaly detection system, the anomaly detection system having an associated latent space;
- and
- clustering the plurality of anomalous images to generate a plurality of clusters within a feature space defined by a set of classification features, the set of classification features comprising a feature derived from the latent space associated with the anomaly detection system.
A system comprising:
- a processor;
- and
- a non-transitory computer readable medium storing executable instructions comprising:
- an imager interface that receives histopathological samples from an associated imaging system to produce a plurality of images;
- an anomaly detection system, having an associated latent space, that identifies a plurality of anomalous images from the plurality of images;
- and
- a clustering system that clusters the plurality of anomalous images to generate a plurality of clusters within a feature space defined by a set of classification features that includes a feature derived from the latent space associated with the anomaly detection system.
A method comprising:
- imaging histopathological samples at an associated imaging system to produce a plurality of images;
- identifying a plurality of anomalous images from the plurality of images at an anomaly detection system comprising an autoencoder, the autoencoder having an associated latent space;
- clustering the plurality of anomalous images to generate a plurality of clusters within a feature space defined by a set of classification features, the set of classification features comprising a feature derived from the latent space associated with the autoencoder.
Dependencies are inferred from the claim text.