Potential quality pitfalls of digitalized whole slide image of breast pathology in routine practice

Abstract

Using digitalized whole slide images (WSI) in routine histopathology practice is a revolutionary technology. This study aims to assess the clinical impacts of WSI quality and representation of the corresponding glass slides. 40,160 breast WSIs were examined and compared with their corresponding glass slides. The presence, frequency, location, tissue type, and the clinical impacts of missing tissue were assessed. Scanning time, type of the specimens, time to WSIs implementation, and quality control (QC) measures were also considered. The frequency of missing tissue ranged from 2% to 19%. The area size of the missed tissue ranged from 1–70%. In most cases (>75%), the missing tissue area size was <10% and peripherally located. In all cases the missed tissue was fat with or without small entrapped normal breast parenchyma. No missing tissue was identified in WSIs of the core biopsy specimens. QC measures improved images quality and reduced WSI failure rates by seven-fold. A negative linear correlation between the frequency of missing tissue and both the scanning time and the image file size was observed (p < 0.05). None of the WSI with missing tissues resulted in a change in the final diagnosis. Missing tissue on breast WSI is observed but with variable frequency and little diagnostic consequence. Balancing between WSI quality and scanning time/image file size should be considered and pathology laboratories should undertake their own assessments of risk and provide the relevant mitigations with the appropriate level of caution.

Artificial Intelligence-Based Quality Assessment of Histopathology Whole-Slide Images within a Clinical Workflow: Assessment of ‘PathProfiler’ in a Diagnostic Pathology Setting

“…The observations of this feasibility study are significant given that QC of WSI remains a crucial part of the transition to clinical utilisation of DP, and is increasingly recognised as such in commentaries from early adopters of DP [11,14,25,26]. Furthermore, evidence continues to emerge to support intuition that quality WSI are important during both the development of AI tools and in assuring their performance [5,6,26].…”

Types and frequency of whole slide imaging scan failures in a clinical high throughput digital pathology scanning laboratory

“… 1 Despite substantial documentation of WSI employment for a variety of use cases within a diversity of departments, clinical deployment still straggles behind that of digital imaging for radiology, stymied primarily from concerns including WSI quality and its potential impact upon pathology image analysis. 24 , 25 , 26 …”

Automatic breast carcinoma detection in histopathological micrographs based on Single Shot Multibox Detector

“…For example, while some scanners with high specifications scan 1 slide in 0.5–1.5 min, some WSI scanners take 7–9 min for scanning 1 slide. 31 Although WSI technology is becoming widespread in clinical practice, actually, using WSI is sometimes difficult in some hospitals. 32 Thus, proposing the significance of the AI model, which is easy to introduce and simpler to use using micrographs, could be important.…”