Patent · US Active

Robust deep AUC/AUPRC maximization: a new surrogate loss and empirical studies on medical image classification

US12190505B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 2, 2021
Grant dateJan 7, 2025
Priority date
Expiry dateFeb 21, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V2201/03
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer-based automated method of performing classification includes learning a deep neural network by maximizing an area under a receiver operating characteristic curve (AUC) or precision-recall curve (AUPRC) score wherein a margin-based surrogate loss function is applied, receiving an input into a deep neural network, and processing the input to the deep neural network to generate a prediction, wherein the prediction comprises a classification of the input. The computer-based automated method may be performed by executing instructions in at least one processor, and wherein said instructions are stored on a non-transitory memory readable by the at least one processor.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.