Back to results
US 12,597,128 B2Granted
Assessment of skin toxicity in an in vitro tissue samples using deep learning
AssigneeGenentech, Inc.
InventorsFang-Yao Hu, Sara Francesca Santagostino
Life of this patent
Estimating the term…
Abstract
In one embodiment, a method includes receiving a querying image associated with a tissue sample after a treatment by a drug compound, identifying a target layer of the tissue sample based on a machine-learning model trained to identify layers of tissue samples, calculating a normalized thickness of the identified target layer, and determining a toxicity indication of the treatment by the drug compound based on the normalized thickness of the identified target layer.
Claims20
A method comprising, by a digital pathology image processing system:
- receiving a querying image associated with a tissue sample after a treatment by a drug compound;
- identifying, based on a machine-learning model trained to identify layers of tissue samples, a target layer of the tissue sample;
- calculating a normalized thickness of the identified target layer, wherein calculating the normalized thickness comprises using an average thickness value for the identified target layer and an average thickness value of tissue samples from a control group;
- and
- determining a toxicity indication of the treatment by the drug compound based on the normalized thickness of the identified target layer.
2 more elements
A system comprising:
- one or more processors;
- and
- a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
- receive a querying image associated with a reconstructed human epidermis (RHE) sample after a treatment by a drug compound;
- identify, based on a machine-learning model trained to identify layers of RHE samples, an epidermal layer of the RHE sample;
- calculate a normalized thickness of the identified epidermal layer, wherein calculating the normalized thickness comprises using an average thickness value for the identified epidermal layer and an average thickness value of RHE samples from a control group;
- and
- determine a toxicity indication of the treatment by the drug compound based on the normalized thickness of the identified epidermal layer.
5 more elements
A system comprising:
- one or more processors;
- and
- a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
- receive a querying image associated with a reconstructed human epidermis (RHE) sample after a treatment by a drug compound;
- identify, based on a machine-learning model trained to identify layers of RHE samples, an epidermal layer of the RHE sample;
- calculate a normalized thickness of the identified epidermal layer, wherein calculating the normalized thickness comprises using an average thickness value for the identified epidermal layer and an average thickness value of RHE samples from a control group;
- and
- determine an efficacy indication of the treatment by the drug compound based on the normalized thickness of the identified epidermal layer.
5 more elements
Dependencies are inferred from the claim text.