Method for object detection using hierarchical deep learning

Patent metadata

Field	Value
Publication number	US-12494071-B2
Application number	US-202318391820-A
Country	US
Kind code	B2
Filing date	Dec 21, 2023
Priority date	Oct 18, 2019
Publication date	Dec 9, 2025
Grant date	Dec 9, 2025

Abstract

A hierarchical deep-learning object detection framework provides a method for identifying objects of interest in high-resolution, high pixel count images, wherein the objects of interest comprise a relatively a small pixel count when compared to the overall image. The method uses first deep-learning model to analyze the high pixel count images, in whole or as a patchwork, at a lower resolution to identify objects, and a second deep-learning model to analyze the objects at a higher resolution to classify the objects.

First claim

The invention claimed is:

1 . A method comprising:
obtaining an image; analyzing the image, using a trained machine learning model to identify one or more objects of interest in the image, the analysis occurring at a lower resolution than the native resolution of the image; classifying the identified objects of interest at a higher resolution using a trained machine learning classifier, wherein the machine learning classifier outputs a latent vector for each classified object; aggregating the latent vectors for a predetermined number of classified objects; pooling the aggregated latent vectors by calculating a maximum or minimum of the data for each node of a feature map of the machine learning classifier; and performing a binary classification for each image based on the aggregated latent vectors, the binary classification indicating the presence or absence of an object of interest.

2 . The method of claim 1 further comprising:
producing a reduced dimension latent vector based on the pooled aggregated latent vectors.

3 . The method of claim 2 wherein reduced dimension latent vector is produced using principal component analysis on the pooled aggregated latent vectors.

4 . The method of claim 2 further comprising:
concatenating the reduced dimension latent vector with a vector representing metadata related to the image prior to performing binary classification.

5 . The method of claim 1 wherein the machine learning model places bounding boxes around the identified objects of interest.

6 . The method of claim 1 wherein the machine learning model outputs, with each identified object, a probability that the identified object is an object of interest.

7 . The method of claim 1 , further comprising:
separating the image into a plurality of smaller image patches; wherein analyzing the image comprises analyzing each of the plurality of smaller image patches separately.

8 . The method of claim 1 wherein the binary classification is performed using a random decision forest.

9 . The method of claim 1 :
wherein the image is a high-resolution whole slide image of organic tissue; and wherein the objects of interest are structures within the organic tissue.

10 . The method of claim 1 wherein the trained machine learning model uses a ResNet feature extractor.

11 . The method of claim 1 wherein trained machine learning model places a bounding box around each identified object of interest.

Assignees

• Univ Carnegie Mellon

Inventors

• Cagan Jonathan
• Leduc Philip
• Clymer Daniel

Classifications

• G06V40/14

  Vascular patterns · CPC title

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G06F18/2148

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06F18/2135

  based on approximation criteria, e.g. principal component analysis · CPC title

• G06F18/241

  relating to the classification model, e.g. parametric or non-parametric approaches · CPC title