Compound computer vision workflow for efficient and automated immunohistochemical analysis of whole slide images.

AIMS: Immunohistochemistry (IHC) assessment of tissue is a central component of the modern pathology workflow, but quantification is challenged by subjective estimates by pathologists or manual steps in semi-automated digital tools. This study integrates various computer vision tools to develop a fully automated workflow for quantifying Ki-67, a standard IHC test used to assess cell proliferation on digital whole slide images (WSIs). METHODS: We create an automated nuclear segmentation strategy by deploying a Mask R-CNN classifier to recognise and count 3,3'-diaminobenzidine positive and negative nuclei. To further improve automation, we replaced manual selection of regions of interest (ROIs) by aligning Ki-67 WSIs with corresponding H&E-stained sections, using scale-invariant feature transform (SIFT) and a conventional histomorphological convolutional neural networks to define tumour-rich areas for quantification. RESULTS: The Mask R-CNN was tested on 147 images generated from 34 brain tumour Ki-67 WSIs and showed a high concordance with aggregate pathologists' estimates ([Formula: see text] assessors; [Formula: see text] r=0.9750). Concordance of each assessor's Ki-67 estimates was higher when compared with the Mask R-CNN than between individual assessors (ravg=0.9322 vs 0.8703; p=0.0213). Coupling the Mask R-CNN with SIFT-CNN workflow demonstrated ROIs can be automatically chosen and partially sampled to improve automation and dramatically decrease computational time (average: 88.55-19.28 min; p<0.0001). CONCLUSIONS: We show how innovations in computer vision can be serially compounded to automate and improve implementation in clinical workflows. Generalisation of this approach to other ancillary studies has significant implications for computational pathology.

PD-L1 assessment in cytology samples predicts treatment response to checkpoint inhibitors in NSCLC.

BACKGROUND: Testing for tumor programmed death ligand-1 (PD-L1) expression was initially developed with histology specimens in non-small cell lung cancer (NSCLC). However, cytology specimens are widely used for primary diagnosis and biomarker studies in clinical practice. Limited clinical data exist on the predictiveness of cytology-derived PD-L1 scores for response to immune checkpoint inhibitor (ICI) therapy. METHODS: We reviewed all NSCLC specimens clinically tested at the University Health Network (UHN) for PD-L1 with 22C3pharmDx, from 01/2013 to 04/2021. Treatment outcomes in patients treated with single agent ICI therapy were reviewed and compared according to cytology- and histology-derived PD-L1 scores. RESULTS: We identified 494 and 1942 unique patients with cytology- and histology-derived tumor proportion scores, respectively, during the study period. Informative testing rates were 95 % vs 98 % for cytology and histology, respectively. Clinical data were available for 152 patients treated with single agent ICI: 61 cytology and 91 histology. Overall response rates (ORR) were similar for cytology and histology (36 % vs 34 %; p = 0.23), as well as median progression free survival (PFS) (4.9 vs 4.2 months; p = 0.99) and overall survival (23.4 vs 19.7 months; p = 0.99). The results remained similar even after adjusting for PD-L1 expression levels and line of ICI treatment (PFS HR 1.15; 95 %CI 0.78-1.70; p = 0.47). CONCLUSIONS: Treatment outcomes to single agent ICI based on cytology-derived PD-L1 scores were comparable to histology controls. Our results support PD-L1 biomarker testing on both cytology and histology specimens.

Integrating morphologic and molecular histopathological features through whole slide image registration and deep learning.

BACKGROUND: Modern molecular pathology workflows in neuro-oncology heavily rely on the integration of morphologic and immunohistochemical patterns for analysis, classification, and prognostication. However, despite the recent emergence of digital pathology platforms and artificial intelligence-driven computational image analysis tools, automating the integration of histomorphologic information found across these multiple studies is challenged by large files sizes of whole slide images (WSIs) and shifts/rotations in tissue sections introduced during slide preparation. METHODS: To address this, we develop a workflow that couples different computer vision tools including scale-invariant feature transform (SIFT) and deep learning to efficiently align and integrate histopathological information found across multiple independent studies. We highlight the utility and automation potential of this workflow in the molecular subclassification and discovery of previously unappreciated spatial patterns in diffuse gliomas. RESULTS: First, we show how a SIFT-driven computer vision workflow was effective at automated WSI alignment in a cohort of 107 randomly selected surgical neuropathology cases (97/107 (91%) showing appropriate matches, AUC = 0.96). This alignment allows our AI-driven diagnostic workflow to not only differentiate different brain tumor types, but also integrate and carry out molecular subclassification of diffuse gliomas using relevant immunohistochemical biomarkers (IDH1-R132H, ATRX). To highlight the discovery potential of this workflow, we also examined spatial distributions of tumors showing heterogenous expression of the proliferation marker MIB1 and Olig2. This analysis helped uncover an interesting and unappreciated association of Olig2 positive and proliferative areas in some gliomas (r = 0.62). CONCLUSION: This efficient neuropathologist-inspired workflow provides a generalizable approach to help automate a variety of advanced immunohistochemically compatible diagnostic and discovery exercises in surgical neuropathology and neuro-oncology.