Inter-reader variability in follicular lymphoma grading: Conventional and digital reading

Abstract

Context:Pathologists grade follicular lymphoma (FL) cases by selecting 10, random high power fields (HPFs), counting the number of centroblasts (CBs) in these HPFs under the microscope and then calculating the average CB count for the whole slide. Previous studies have demonstrated that there is high inter-reader variability among pathologists using this methodology in grading.Aims:The objective of this study was to explore if newly available digital reading technologies can reduce inter-reader variability.Settings and Design:In this study, we considered three different reading conditions (RCs) in grading FL: (1) Conventional (glass-slide based) to establish the baseline, (2) digital whole slide viewing, (3) digital whole slide viewing with selected HPFs. Six board-certified pathologists from five different institutions read 17 FL slides in these three different RCs.Results:Although there was relative poor consensus in conventional reading, with lack of consensus in 41.2% of cases, which was similar to previously reported studies; we found that digital reading with pre-selected fields improved the inter-reader agreement, with only 5.9% lacking consensus among pathologists.Conclusions:Digital whole slide RC resulted in the worst concordance among pathologists while digital whole slide reading selected HPFs improved the concordance. Further studies are underway to determine if this performance can be sustained with a larger dataset and our automated HPF and CB detection algorithms can be employed to further improve the concordance.

Deep learning in cancer diagnosis, prognosis and treatment selection

“…Cancers are traditionally diagnosed by histopathology or cytopathology to confirm the presence of tumour cells within a patient sample, assess markers relevant to cancer and to characterise features such as tumour type, stage and grade. This microscopy-based assessment is crucial; however, the process is relatively labour-intensive and somewhat subjective [ 80 , 81 ]. A histology image viewed at high magnification (typically 20x or 40x) can reveal millions of subtle cellular features, and deep CNN models are exceptionally good at extracting features from high-resolution image data [ 82 ].…”

Informatics Approaches to Address New Challenges in the Classification of Lymphoid Malignancies

“…To explore the discrepancies in FL grading agreement at a more macroscopic level, Lozanski et al 20 compared the effect of three different reading conditions on achieving a consensus among pathologists. Six experienced hematopathologists were tested through traditional glass-slide readings, digitized whole-slide images, and evaluation of selected digital regions of interest.…”

“…Spatial heterogeneity within a sample makes the selection of representative fields difficult, so the authors proposed a computer-aided system that characterizes heterogeneity to aid field selection, reducing selection bias and improving accuracy. 20…”

Artificial Intelligence and Digital Microscopy Applications in Diagnostic Hematopathology

“…Since centroblast counts should be performed in neoplastic follicles, the generation of an automated system that accurately identifies the targeted follicles is a fundamental step toward standardization. It was reported that digital reading from WSI with preselected regions improved inter-reader agreement, with only 5.9% lacking consensus for centroblast enumeration [51]. However, fields were randomly selected by one of the pathologists, and hence might also be affected by subjectivity bias through including the zones that look histologically remarkable or of higher grade.…”