System and method for storage management of images

Patent metadata

Field	Value
Publication number	US-12373955-B2
Application number	US-202217872865-A
Country	US
Kind code	B2
Filing date	Jul 25, 2022
Priority date	Jul 25, 2022
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

Methods and systems for managing storage of data are disclosed. To manage storage of data, images may be stored across a number of storages that provide varying levels of storage performance and have correspondingly varying costs for storing data. To store the images across the storages, the images may be segmented into image segments and a likelihood of each of the image segments being used in the future may be identified. The image segments that are more likely to be used in the future may be stored in higher performance storages while the image segments that are less likely to be used in the future may be stored in lower performance storages. To identify the likelihood of each of the image segments being used in the future, the image segments may be classified based on their membership in one or more areas of interest within the images.

First claim

What is claimed is:

1. A method for managing storage of images in different storage tiers, the method comprising:
obtaining an image of the images;
identifying areas of interest in the image;
segmenting the image into segments to obtain image segments;
classifying the image segments based on the areas of interest in the image to obtain image segment classifications corresponding to the image segments comprises at least, for an image segment of the image segments:
determining a first quantity of the image segment that falls within the areas of interest in the image and classifying the first quantity as a first portion of the image segment;
determining a second quantity of the image segment that falls outside of the areas of interest in the image and classifying the second quantity as a second portion of the image segment; and
obtaining an access likelihood value for the image segment by at least multiplying a size of the first portion by a first weight associated with the areas of interest and treating the second portion as having no value, wherein an image segment classification of the image segment is based on the access likelihood value and the image segment classification being one of the image segment classifications;

obtaining a storage tier allocation for each of the image segments on a corresponding image segment classification of the image segment classifications to obtain storage tier allocations; and
for each of the image segments, storing the image segment in a storage of a storage tier of the storage tiers, the storage tier of the storage tiers being based on a storage tier allocation of the storage tier allocations associated with the image.

2. The method of claim 1 , wherein each of the areas of interest in the image define a group of pixels of the image that are diagnostically relevant to a medical condition.

3. The method of claim 2 , wherein each of the areas of interest in the image are identified as part of a medical investigation into the medical condition, the medical investigation being performed by a subject matter expert.

4. The method of claim 3 , wherein the subject matter expert is an inference model or a medical professional.

5. The method of claim 1 , wherein storing the image segment in the storage comprises:
identifying an image fidelity level associated with the storage tier of the storage tiers;
conforming the image segment to the image fidelity level to obtain a conformed image segment; and
storing the conformed image segment in the storage.

6. The method of claim 5 , wherein each of the storage tiers has an associated image fidelity level.

7. The method of claim 1 , wherein each of the areas of interest in the image are identified as part of a medical investigation into the medical condition, the medical investigation being performed by a subject matter expert.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for managing storage of images in different storage tiers, the operations comprising:
obtaining an image of the images;
identifying areas of interest in the image;
segmenting the image into segments to obtain image segments;
classifying the image segments based on the areas of interest in the image to obtain image segment classifications corresponding to the image segments comprises at least, for an image segment of the image segments:
determining a first quantity of the image segment that falls within the areas of interest in the image and classifying the first quantity as a first portion of the image segment;
determining a second quantity of the image segment that falls outside of the areas of interest in the image and classifying the second quantity as a second portion of the image segment; and
obtaining an access likelihood value for the image segment by at least multiplying a size of the first portion by a first weight associated with the areas of interest and treating the second portion as having no value, wherein an image segment classification of the image segment is based on the access likelihood value and the image segment classification being one of the image segment classifications;

obtaining a storage tier allocation for each of the image segments on a corresponding image segment classification of the image segment classifications to obtain storage tier allocations; and
for each of the image segments, storing the image segment in a storage of a storage tier of the storage tiers, the storage tier of the storage tiers being based on a storage tier allocation of the storage tier allocations associated with the image.

9. The non-transitory machine-readable medium of claim 8 , wherein each of the areas of interest in the image define a group of pixels of the image that are diagnostically relevant to a medical condition.

10. The non-transitory machine-readable medium of claim 9 , wherein each of the areas of interest in the image are identified as part of a medical investigation into the medical condition, the medical investigation being performed by a subject matter expert.

11. The non-transitory machine-readable medium of claim 10 , wherein the subject matter expert is an inference model or a medical professional.

12. The non-transitory machine-readable medium of claim 8 , wherein storing the image segment in the storage comprises:
identifying an image fidelity level associated with the storage tier of the storage tiers;
conforming the image segment to the image fidelity level to obtain a conformed image segment; and
storing the conformed image segment in the storage.

13. The non-transitory machine-readable medium of claim 8 , wherein each of the storage tiers has an associated image fidelity level.

14. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for managing storage of images in different storage tiers, the operations comprising:
obtaining an image of the images;
identifying areas of interest in the image;
segmenting the image into segments to obtain image segments;
classifying the image segments based on the areas of interest in the image to obtain image segment classifications corresponding to the image segments comprises at least, for an image segment of the image segments:
determining a first quantity of the image segment that falls within the areas of interest in the image and classifying the first quantity as a first portion of the image segment;
determining a second quantity of the image segment that falls outside of the areas of interest in the image and classifying the second quantity as a second portion of the image segment; and
obtaining an access likelihood value for the image segment by at least multiplying a size of the first portion by a first weight associated with the areas of interest and treating the second portion as having no value, wherein an image segment classification of the image segment is based on the access likelihood value and the image segment classification being one of the image segment classifications;

obtaining a storage tier allocation for each of the image segments on a corresponding image segment classification of the image segment classifications to obtain storage tier allocations; and
for each of the image segments, storing the image segment in a storage of a storage tier of the storage tiers, the storage tier of the storage tiers being based on a storage tier allocation of the storage tier allocations associated with the image.

15

Assignees

• Dell Products Lp

Inventors

• Ezrielev Ofir
• Savir Amihai
• Gefen Avitan
• Reineke Nicole

Classifications

• G06F16/185

  Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof (details of archiving G06F16/11) · CPC title

• G06F3/0685

  Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays · CPC title

• G06T3/40

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• G06F16/55 Primary

  Clustering; Classification · CPC title