Analysis of application of digital image analysis in histopathology quality control

Abstract

Introduction

A correct histopathological diagnosis is dependent on an array of technical variables. The quality and completeness of a histological section on a slide is extremely prudent for correct interpretation. However, this is mostly done manually and depends largely on the expertise of histotechnician. In this study, we analysed the application of digital image analysis for quality control of histological section as a proof-of-concept.

Material and methods

Images of 1000 histological sections and their corresponding blocks were captured. Area of the section was measured from these digital images of tissue block (Digiblock) and slide (Digislide). The data was analysed to calculate DigislideQC score, dividing the area of tissue on the slide by the tissue area on the block and it was compared with the number of recuts done for incomplete section.

Results

Digislide QC score ranged from 0.1 to 0.99. It showed an area under curve (AUC) of 98.8%. A cut-off value of 0.65 had a sensitivity of 99.6% and a specificity of 96.7%.

Conclusion

Digiblock and Digislide images can provide information about quality of sections. DigislideQC score can correctly identify the slides which require recuts before it is sent for reporting and potentially reduce histopathologists’ slide screening effort and ultimately turnaround time. These can be incorporated in routine histopathology workflows and lab information systems. This simple technology can also improve future digital pathology and telepathology workflows.