Processing system for data stream of digital pathological images

Abstract

The invention discloses a processing system for a data stream of digital pathological images, which provides a data stream of a plurality of digital pathology images for a computing system, and comprises an acquisition unit, a first storage unit, a metadata unit and an analysis unit, wherein the acquisition unit is used for acquiring digital pathological images; the first storage unit is used for reading metadata of the digital pathological image, performing byte-level partitioning on the digital pathological image according to a byte sequence on the basis of the metadata so as to obtain a plurality of sub-blocks of a plurality of image sub-slices including adjacent areas, then storing the plurality of sub-blocks and generating sub-slice information of each image sub-slice; the metadata unit is used for recording metadata and sub-slice information; and the analysis unit is used for obtaining the data stream corresponding to at least one image sub-slice at one time in a way of sharing a handle opened by the sub-block based on the metadata, the byte offset of the image sub-slice and the byte size after receiving a data request for obtaining the data stream. Therefore, the digital pathological image can be quickly stored and shared based on the data stream at low cost.

Description

technical field [0001] The present disclosure generally relates to a system for processing data streams of digital pathology images. Background technique [0002] At present, the use of digital pathological image analysis is becoming more and more scene-oriented and professional. Based on ultra-high-resolution digital pathological images and deep learning technologies such as artificial intelligence technology, the pathological analysis system has gradually become a tool to assist clinical pathological analysis. Digital pathological images are obtained by scanning traditional pathological slides with a digital scanner, collecting high-resolution digital pathological images, and then splicing and integrating the obtained localized images. Compared with traditional pathological slides, digital pathological images have many advantages in storage management, teaching, remote diagnosis and image repeatability, which solves the problem that traditional pathological slides are easi...

AI Technical Summary

Problems solved by technology

[0004] However, digital pathology images have a lot of information and a single file has a large capacity. Storing digital pathology images in hospital storage or scanner control host workstations is often not conducive to data sharing and is inconvenient to expand. Another method is for tens of thousands to hundreds of thousands Storage of unequal image sub-slices in layers often consumes a lot of hardware resources and time, and the reading and writing of small files requires high performance of the hard disk, usually requiring more expensive solid-state drives

In addition, due to the randomness of online viewing of digital pathological images, and the artificial intelligence analysis of digital pathological images often needs to be analyzed based on the data of the entire digital pathological image, the hit rate of the cache is low

Therefore, there are still huge challenges in the storage and sharing of digital pathology images

Images