Tissue Slide Digitization via Serial Section Map Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The digitization of tissue slides is hindered by issues such as debris, bubbles, annotations, and uneven staining, leading to increased scan time and storage requirements, as well as potential missed tissue content due to faint staining, which decreases analysis efficiency and accuracy.
Innovation Solution
A system and method that utilize a computing device and scanner to align and regenerate tissue maps, selecting optimal scan parameters to instruct the scanner, thereby avoiding unwanted areas and improving the accuracy of tissue content acquisition by processing serial sections as a group, using registration modules and machine learning techniques to correct for defects and enhance scanning efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the scanner scans the entire slide at high magnification to ensure complete tissue content acquisition, then the accuracy of tissue content acquisition is improved, but the scan time increases significantly
Solution Approach 1:
The slide is divided into multiple fields of view (FOVs) that are scanned sequentially at high magnification. The low magnification scan first identifies tissue regions and generates a map, which then guides the high magnification scanning of only those specific regions. This segmentation approach allows complete tissue content acquisition without scanning the entire slide at high magnification, thus reducing scan time while maintaining accuracy.
2Quantity of substance
If the scanner scans all areas of the slide including unwanted areas with debris and bubbles, then the completeness of data collection is improved, but the file storage size increases
Solution Approach 1:
Different regions of the slide are treated differently based on their content. The system generates a map that identifies tissue-containing regions versus unwanted areas (debris, bubbles, annotations). High magnification scanning is applied only to tissue regions where complete data collection is necessary, while unwanted areas are either scanned at low magnification or excluded from high magnification scanning entirely. This local quality approach ensures completeness of tissue data collection while minimizing file storage requirements by avoiding unnecessary high-resolution scanning of non-tissue areas.
3Productivity
If the scanner scans only the identified tissue regions to reduce scan time and storage, then the efficiency is improved, but the accuracy of tissue content acquisition deteriorates due to missed faintly stained tissue
Solution Approach 1:
A low magnification scan is performed first to generate a preliminary map of tissue regions. This preliminary action identifies potential tissue areas including those with faint staining that might be missed in targeted scanning. The map generated from this preliminary scan then guides the high magnification scanning process, ensuring that even faintly stained tissue regions are included in the detailed scan. This two-stage approach maintains scanning efficiency while preserving accuracy by using the preliminary low magnification scan as a comprehensive guide.
4Adaptability or versatility
If multiple serial sections are processed individually, then the flexibility in processing each section is improved, but the overall analysis time increases
Solution Approach 1:
Multiple serial sections are processed together as a group rather than individually. The system generates maps for multiple sections and aligns them using a registration module to create a composite map. This merged approach allows the system to identify tissue regions across all sections simultaneously and scan them collectively at high magnification. The flexibility to process sections as a group maintains adaptability in handling different section configurations while significantly reducing overall analysis time compared to individual processing.
Data Source
AI summary
The present disclosure describes an exemplary system and method for the digitization of tissue slides based on associations among serial sections. The system includes at least a computing device, wherein the computing device includes a memory and processor communicatively connected to one another, and a scanner, configured to scan a slide and send a digitized image of the slide to the computing device. A method for the digitization of tissue slides based on associations among serial sections may include receiving a candidate tissue map associated with a candidate tissue section, receiving a reference tissue map associated with a reference tissue section, aligning the candidate tissue map to the reference tissue map, comparing the aligned candidate tissue map to the reference tissue map, and generating a regenerated candidate tissue map as a function of the reference tissue map.