Breast Cancer Prognostic Factors in the Digital Era: Comparison of Nottingham Grade using Whole Slide Images and Glass Slides

Comparative Evaluation of Breast Ductal Carcinoma Grading: A Deep-Learning Model and General Pathologists' Assessment Approach

Breast cancer is the most prevalent neoplasia among women, with early and accurate diagnosis critical for effective treatment. In clinical practice, however, the subjective nature of histological grading of infiltrating ductal adenocarcinoma of the breast (DAC-NOS) often leads to inconsistencies among pathologists, posing a significant challenge to achieving optimal patient outcomes. Our study aimed to address this reproducibility problem by leveraging artificial intelligence (AI). We trained a deep-learning model using a convolutional neural network-based algorithm (CNN-bA) on 100 whole slide images (WSIs) of DAC-NOS from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) dataset. Our model demonstrated high precision, sensitivity, and F1 score across different grading components in about 17.5 h with 19,000 iterations. However, the agreement between the model's grading and that of general pathologists varied, showing the highest agreement for the mitotic count score. These findings suggest that AI has the potential to enhance the accuracy and reproducibility of breast cancer grading, warranting further refinement and validation of this approach.

Development and validation of an AI-enabled digital breast cancer assay to predict early-stage breast cancer recurrence within 6 years

BACKGROUND

Breast cancer (BC) grading plays a critical role in patient management despite the considerable inter- and intra-observer variability, highlighting the need for decision support tools to improve reproducibility and prognostic accuracy for use in clinical practice. The objective was to evaluate the ability of a digital artificial intelligence (AI) assay (PDxBr) to enrich BC grading and improve risk categorization for predicting recurrence.

METHODS

In our population-based longitudinal clinical development and validation study, we enrolled 2075 patients from Mount Sinai Hospital with infiltrating ductal carcinoma of the breast. With 3:1 balanced training and validation cohorts, patients were retrospectively followed for a median of 6 years. The main outcome was to validate an automated BC phenotyping system combined with clinical features to produce a binomial risk score predicting BC recurrence at diagnosis.

RESULTS

The PDxBr training model (n = 1559 patients) had a C-index of 0.78 (95% CI, 0.76-0.81) versus clinical 0.71 (95% CI, 0.67-0.74) and image feature models 0.72 (95% CI, 0.70-0.74). A risk score of 58 (scale 0-100) stratified patients as low or high risk, hazard ratio (HR) 5.5 (95% CI 4.19-7.2, p < 0.001), with a sensitivity 0.71, specificity 0.77, NPV 0.95, and PPV 0.32 for predicting BC recurrence within 6 years. In the validation cohort (n = 516), the C-index was 0.75 (95% CI, 0.72-0.79) versus clinical 0.71 (95% CI 0.66-0.75) versus image feature models 0.67 (95% CI, 0.63-071). The validation cohort had an HR of 4.4 (95% CI 2.7-7.1, p < 0.001), sensitivity of 0.60, specificity 0.77, NPV 0.94, and PPV 0.24 for predicting BC recurrence within 6 years. PDxBr also improved Oncotype Recurrence Score (RS) performance: RS 31 cutoff, C-index of 0.36 (95% CI 0.26-0.45), sensitivity 37%, specificity 48%, HR 0.48, p = 0.04 versus Oncotype RS plus AI-grade C-index 0.72 (95% CI 0.67-0.79), sensitivity 78%, specificity 49%, HR 4.6, p < 0.001 versus Oncotype RS plus PDxBr, C-index 0.76 (95% CI 0.70-0.82), sensitivity 67%, specificity 80%, HR 6.1, p < 0.001.

CONCLUSIONS

PDxBr is a digital BC test combining automated AI-BC prognostic grade with clinical-pathologic features to predict the risk of early-stage BC recurrence. With future validation studies, we anticipate the PDxBr model will enrich current gene expression assays and enhance treatment decision-making.

Technical and Diagnostic Issues in Whole Slide Imaging Published Validation Studies

Objective

Digital pathology with whole-slide imaging (WSI) has many potential clinical and non-clinical applications. In the past two decades, despite significant advances in WSI technology adoption remains slow for primary diagnosis. The aim of this study was to identify common pitfalls of WSI reported in validation studies and offer measures to overcome these challenges.

Methods

A systematic search was conducted in the electronic databases Pubmed-MEDLINE and Embase. Inclusion criteria were all validation studies designed to evaluate the feasibility of WSI for diagnostic clinical use in pathology. Technical and diagnostic problems encountered with WSI in these studies were recorded.

Results

A total of 45 studies were identified in which technical issues were reported in 15 (33%), diagnostic issues in 8 (18%), and 22 (49%) reported both. Key technical problems encompassed slide scan failure, prolonged time for pathologists to review cases, and a need for higher image resolution. Diagnostic challenges encountered were concerned with grading dysplasia, reliable assessment of mitoses, identification of microorganisms, and clearly defining the invasive front of tumors.

Conclusion

Despite technical advances with WSI technology, some critical concerns remain that need to be addressed to ensure trustworthy clinical diagnostic use. More focus on the quality of the pre-scanning phase and training of pathologists could help reduce the negative impact of WSI technical difficulties. WSI also seems to exacerbate specific diagnostic tasks that are already challenging among pathologists even when examining glass slides with conventional light microscopy.

Defining the area of mitoses counting in invasive breast cancer using whole slide image

Although counting mitoses is part of breast cancer grading, concordance studies showed low agreement. Refining the criteria for mitotic counting can improve concordance, particularly when using whole slide images (WSIs). This study aims to refine the methodology for optimal mitoses counting on WSI. Digital images of 595 hematoxylin and eosin stained sections were evaluated. Several morphological criteria were investigated and applied to define mitotic hotspots. Reproducibility, representativeness, time, and association with outcome were the criteria used to evaluate the best area size for mitoses counting. Three approaches for scoring mitoses on WSIs (single and multiple annotated rectangles and multiple digital high-power (×40) screen fields (HPSFs)) were evaluated. The relative increase in tumor cell density was the most significant and easiest parameter for identifying hotspots. Counting mitoses in 3 mm² area was the most representative regarding saturation and concordance levels. Counting in area <2 mm² resulted in a significant reduction in mitotic count (P = 0.02), whereas counting in area ≥4 mm² was time-consuming and did not add a significant rise in overall mitotic count (P = 0.08). Using multiple HPSF, following calibration, provided the most reliable, timesaving, and practical method for mitoses counting on WSI. This study provides evidence-based methodology for defining the area and methodology of visual mitoses counting using WSI. Visual mitoses scoring on WSI can be performed reliably by adjusting the number of monitor screens.

Digital validation of breast biomarkers (ER, PR, AR, and HER2) in cytology specimens using three different scanners

Progression in digital pathology has yielded new opportunities for a remote work environment. We evaluated the utility of digital review of breast cancer immunohistochemical prognostic markers (IHC) using whole slide images (WSI) from formalin fixed paraffin embedded (FFPE) cytology cell block specimens (CB) using three different scanners.CB from 20 patients with breast cancer diagnosis and available IHC were included. Glass slides including 20 Hematoxylin and eosin (H&E), 20 Estrogen Receptor (ER), 20 Progesterone Receptor (PR), 16 Androgen Receptor (AR), and 20 Human Epidermal Growth Factor Receptor 2 (HER2) were scanned on 3 different scanners. Four breast pathologists reviewed the WSI and recorded their semi-quantitative scoring for each marker. Kappa concordance was defined as complete agreement between glass/digital pairs. Discordances between microscopic and digital reads were classified as a major when a clinically relevant change was seen. Minor discordances were defined as differences in scoring percentages/staining pattern that would not have resulted in a clinical implication. Scanner precision was tabulated according to the success rate of each scan on all three scanners.In total, we had 228 paired glass/digital IHC reads on all 3 scanners. There was strong concordance kappa ≥0.85 for all pathologists when comparing paired microscopic/digital reads. Strong concordance (kappa ≥0.86) was also seen when comparing reads between scanners.Twenty-three percent of the WSI required rescanning due to barcode detection failures, 14% due to tissue detection failures, and 2% due to focus issues. Scanner 1 had the best average precision of 92%. HER2 IHC had the lowest intra-scanner precision (64%) among all stains.This study is the first to address the utility of WSI in breast cancer IHC in CB and to validate its reporting using 3 different scanners. Digital images are reliable for breast IHC assessment in CB and offer similar reproducibility to microscope reads.

Assessment of mitotic activity in breast cancer: revisited in the digital pathology era

The assessment of cell proliferation is a key morphological feature for diagnosing various pathological lesions and predicting their clinical behaviour. Visual assessment of mitotic figures in routine histological sections remains the gold-standard method to evaluate the proliferative activity and grading of cancer. Despite the apparent simplicity of such a well-established method, visual assessment of mitotic figures in breast cancer (BC) remains a challenging task with low concordance among pathologists which can lead to under or overestimation of tumour grade and hence affects management. Guideline recommendations for counting mitoses in BC have been published to standardise methodology and improve concordance; however, the results remain less satisfactory. Alternative approaches such as the use of the proliferation marker Ki67 have been recommended but these did not show better performance in terms of concordance or prognostic stratification. The advent of whole slide image technology has brought the issue of mitotic counting in BC into the light again with more challenges to develop objective criteria for identifying and scoring mitotic figures in digitalised images. Using reliable and reproducible morphological criteria can provide the highest degree of concordance among pathologists and could even benefit the further application of artificial intelligence (AI) in breast pathology, and this relies mainly on the explicit description of these figures. In this review, we highlight the morphology of mitotic figures and their mimickers, address the current caveats in counting mitoses in breast pathology and describe how to strictly apply the morphological criteria for accurate and reliable histological grade and AI models.

Visual assessment of mitotic figures in breast cancer: a comparative study between light microscopy and whole slide images

BACKGROUND AND AIMS

Visual assessment of mitotic figures in breast cancer (BC) remains a challenge. This is expected to be more pronounced in the digital pathology era. This study aims to refine the criteria of mitotic figure recognition, particularly in whole slide images (WSI).

METHOD AND RESULTS

Haematoxylin and eosin (H&E)-stained BC sections (n = 506) were examined using light microscopy (LM) and WSI. A set of features for identifying mitosis in WSI and to distinguish true figures from mimickers was developed. Changes in the mitotic count between the two platforms was explored. Morphological features of mitoses were recorded separately, including absence of nuclear membrane, chromatin hairy-like projections, shape, cytoplasmic features, mitotic cell size and relationship to surrounding cells. Each mitotic phase has its own mimickers. Fifty-eight per cent of mitoses showed absent hairy-like projection in WSI; however, 89% retained their ragged nuclear border, which distinguished them from mimickers including apoptotic cells, lymphocytes and dark elongated hyperchromatic structures. Mitosis in WSI showed loss of fine details, and there was a 20% average reduction rate of mitotic counts when compared to the same area on LM. Using refined mitosis recognition criteria in WSI resulted in a twofold improvement of interobserver concordance. However, when compared to LM, 19% of cases were underscored in WSIs.

CONCLUSIONS

All morphological features of mitosis should be considered to enable recognition and differentiation from their mimickers, particularly in WSI, to ensure reliable BC grading. Refining mitotic cut-offs per specific area when using WSI, based on the degree of reduction and association with outcome, is warranted.

Rapid Validation of Whole-Slide Imaging for Primary Histopathology Diagnosis

OBJECTIVES

The ongoing global severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic necessitates adaptations in the practice of surgical pathology at scale. Primary diagnosis by whole-slide imaging (WSI) is a key component that would aid departments in providing uninterrupted histopathology diagnosis and maintaining revenue streams from disruption. We sought to perform rapid validation of the use of WSI in primary diagnosis meeting recommendations of the College of American Pathologists guidelines.

METHODS

Glass slides from clinically reported cases from 5 participating pathologists with a preset washout period were digitally scanned and reviewed in settings identical to typical reporting. Cases were classified as concordant or with minor or major disagreement with the original diagnosis. Randomized subsampling was performed, and mean concordance rates were calculated.

RESULTS

In total, 171 cases were included and distributed equally among participants. For the group as a whole, the mean concordance rate in sampled cases (n = 90) was 83.6% counting all discrepancies and 94.6% counting only major disagreements. The mean pathologist concordance rate in sampled cases (n = 18) ranged from 90.49% to 97%.

CONCLUSIONS

We describe a novel double-blinded method for rapid validation of WSI for primary diagnosis. Our findings highlight the occurrence of a range of diagnostic reproducibility when deploying digital methods.

Accuracy and efficiency of an artificial intelligence tool when counting breast mitoses

BACKGROUND

The mitotic count in breast carcinoma is an important prognostic marker. Unfortunately substantial inter- and intra-laboratory variation exists when pathologists manually count mitotic figures. Artificial intelligence (AI) coupled with whole slide imaging offers a potential solution to this problem. The aim of this study was to accordingly critique an AI tool developed to quantify mitotic figures in whole slide images of invasive breast ductal carcinoma.

METHODS

A representative H&E slide from 320 breast invasive ductal carcinoma cases was scanned at 40x magnification. Ten expert pathologists from two academic medical centers labeled mitotic figures in whole slide images to train and validate an AI algorithm to detect and count mitoses. Thereafter, 24 readers of varying expertise were asked to count mitotic figures with and without AI support in 140 high-power fields derived from a separate dataset. Their accuracy and efficiency of performing these tasks were calculated and statistical comparisons performed.

RESULTS

For each experience level the accuracy, precision and sensitivity of counting mitoses by users improved with AI support. There were 21 readers (87.5%) that identified more mitoses using AI support and 13 reviewers (54.2%) that decreased the quantity of falsely flagged mitoses with AI. More time was spent on this task for most participants when not provided with AI support. AI assistance resulted in an overall time savings of 27.8%.

CONCLUSIONS

This study demonstrates that pathology end-users were more accurate and efficient at quantifying mitotic figures in digital images of invasive breast carcinoma with the aid of AI. Higher inter-pathologist agreement with AI assistance suggests that such algorithms can also help standardize practice. Not surprisingly, there is much enthusiasm in pathology regarding the prospect of using AI in routine practice to perform mundane tasks such as counting mitoses.

Review of the current state of digital image analysis in breast pathology

Advances in digital image analysis have the potential to transform the practice of breast pathology. In the near future, a move to a digital workflow offers improvements in efficiency. Coupled with artificial intelligence (AI), digital pathology can assist pathologist interpretation, automate time-consuming tasks, and discover novel morphologic patterns. Opportunities for digital enhancements abound in breast pathology, from increasing reproducibility in grading and biomarker interpretation, to discovering features that correlate with patient outcome and treatment. Our objective is to review the most recent developments in digital pathology with clear impact to breast pathology practice. Although breast pathologists currently undertake limited adoption of digital methods, the field is rapidly evolving. Care is needed to validate emerging technologies for effective patient care.