Breast cancer histologic grading using digital microscopy: concordance and outcome association

Assessment of Ki-67 and mitoses in pituitary neuroendocrine tumours-Consistency counts

Pituitary neuroendocrine tumour Ki-67 proliferation index varies according to the number of tumour cells assessed. Consistent Ki-67 scoring approaches and re-evaluation of the recommended Ki-67 3% cut-off are required to clarify controversies in pituitary neuroendocrine tumour Ki-67 proliferation index assessment.

Digital pathology for reporting histopathology samples, including cancer screening samples - definitive evidence from a multisite study

AIMS

To conduct a definitive multicentre comparison of digital pathology (DP) with light microscopy (LM) for reporting histopathology slides including breast and bowel cancer screening samples.

METHODS

A total of 2024 cases (608 breast, 607 GI, 609 skin, 200 renal) were studied, including 207 breast and 250 bowel cancer screening samples. Cases were examined by four pathologists (16 study pathologists across the four speciality groups), using both LM and DP, with the order randomly assigned and 6 weeks between viewings. Reports were compared for clinical management concordance (CMC), meaning identical diagnoses plus differences which do not affect patient management. Percentage CMCs were computed using logistic regression models with crossed random-effects terms for case and pathologist. The obtained percentage CMCs were referenced to 98.3% calculated from previous studies.

RESULTS

For all cases LM versus DP comparisons showed the CMC rates were 99.95% [95% confidence interval (CI) = 99.90-99.97] and 98.96 (95% CI = 98.42-99.32) for cancer screening samples. In speciality groups CMC for LM versus DP showed: breast 99.40% (99.06-99.62) overall and 96.27% (94.63-97.43) for cancer screening samples; [gastrointestinal (GI) = 99.96% (99.89-99.99)] overall and 99.93% (99.68-99.98) for bowel cancer screening samples; skin 99.99% (99.92-100.0); renal 99.99% (99.57-100.0). Analysis of clinically significant differences revealed discrepancies in areas where interobserver variability is known to be high, in reads performed with both modalities and without apparent trends to either.

CONCLUSIONS

Comparing LM and DP CMC, overall rates exceed the reference 98.3%, providing compelling evidence that pathologists provide equivalent results for both routine and cancer screening samples irrespective of the modality used.

Exploration of the relationship between tumor-infiltrating lymphocyte score and histological grade in breast cancer

BACKGROUND

The histological grade is an important factor in the prognosis of invasive breast cancer and is vital to accurately identify the histological grade and reclassify of Grade2 status in breast cancer patients.

METHODS

In this study, data were collected from 556 invasive breast cancer patients, and then randomly divided into training cohort (n = 335) and validation cohort (n = 221). All patients were divided into actual low risk group (Grade1) and high risk group (Grade2/3) based on traditional histological grade, and tumor-infiltrating lymphocyte score (TILs-score) obtained from multiphoton images, and the TILs assessment method proposed by International Immuno-Oncology Biomarker Working Group (TILs-WG) were also used to differentiate between high risk group and low risk group of histological grade in patients with invasive breast cancer. Furthermore, TILs-score was used to reclassify Grade2 (G2) into G2 /Low risk and G2/High risk. The coefficients for each TILs in the training cohort were retrieved using ridge regression and TILs-score was created based on the coefficients of the three kinds of TILs.

RESULTS

Statistical analysis shows that TILs-score is significantly correlated with histological grade, and is an independent predictor of histological grade (odds ratio [OR], 2.548; 95%CI, 1.648-3.941; P < 0.0001), but TILs-WG is not an independent predictive factor for grade (P > 0.05 in the univariate analysis). Moreover, the risk of G2/High risk group is higher than that of G2/Low risk group, and the survival rate of patients with G2/Low risk is similar to that of Grade1, while the survival rate of patients with G2/High risk is even worse than that of patients with G3.

CONCLUSION

Our results suggest that TILs-score can be used to predict the histological grade of breast cancer and potentially to guide the therapeutic management of breast cancer patients.

Analytical Validation of the PreciseDx Digital Prognostic Breast Cancer Test in Early-Stage Breast Cancer

BACKGROUND

PreciseDx Breast (PDxBr) is a digital test that predicts early-stage breast cancer recurrence within 6-years of diagnosis.

MATERIALS AND METHODS

Using hematoxylin and eosin-stained whole slide images of invasive breast cancer (IBC) and artificial intelligence-enabled morphology feature array, microanatomic features are generated. Morphometric attributes in combination with patient's age, tumor size, stage, and lymph node status predict disease free survival using a proprietary algorithm. Here, analytical validation of the automated annotation process and extracted histologic digital features of the PDxBr test, including impact of methodologic variability on the composite risk score is presented. Studies of precision, repeatability, reproducibility and interference were performed on morphology feature array-derived features. The final risk score was assessed over 20-days with 2-operators, 2-runs/day, and 2-replicates across 8-patients, allowing for calculation of within-run repeatability, between-run and within-laboratory reproducibility.

RESULTS

Analytical validation of features derived from whole slide images demonstrated a high degree of precision for tumor segmentation (0.98, 0.98), lymphocyte detection (0.91, 0.93), and mitotic figures (0.85, 0.84). Correlation of variation of the assay risk score for both reproducibility and repeatability were less than 2%, and interference from variation in hematoxylin and eosin staining or tumor thickness was not observed demonstrating assay robustness across standard histopathology preparations.

CONCLUSION

In summary, the analytical validation of the digital IBC risk assessment test demonstrated a strong performance across all features in the model and complimented the clinical validation of the assay previously shown to accurately predict recurrence within 6-years in early-stage invasive breast cancer patients.

Revolutionizing Breast Healthcare: Harnessing the Role of Artificial Intelligence

Breast cancer has the highest incidence and second-highest mortality rate among all cancers. The management of breast cancer is being revolutionized by artificial intelligence (AI), which is improving early detection, pathological diagnosis, risk assessment, individualized treatment recommendations, and treatment response prediction. Nuclear medicine has used artificial intelligence (AI) for over 50 years, but more recent advances in machine learning (ML) and deep learning (DL) have given AI in nuclear medicine additional capabilities. AI accurately analyzes breast imaging scans for early detection, minimizing false negatives while offering radiologists reliable, swift image processing assistance. It smoothly fits into radiology workflows, which may result in early treatments and reduced expenditures. In pathological diagnosis, artificial intelligence improves the quality of diagnostic data by ensuring accurate diagnoses, lowering inter-observer variability, speeding up the review process, and identifying errors or poor slides. By taking into consideration nutritional, genetic, and environmental factors, providing individualized risk assessments, and recommending more regular tests for higher-risk patients, AI aids with the risk assessment of breast cancer. The integration of clinical and genetic data into individualized treatment recommendations by AI facilitates collaborative decision-making and resource allocation optimization while also enabling patient progress monitoring, drug interaction consideration, and alignment with clinical guidelines. AI is used to analyze patient data, imaging, genomic data, and pathology reports in order to forecast how a treatment would respond. These models anticipate treatment outcomes, make sure that clinical recommendations are followed, and learn from historical data. The implementation of AI in medicine is hampered by issues with data quality, integration with healthcare IT systems, data protection, bias reduction, and ethical considerations, necessitating transparency and constant surveillance. Protecting patient privacy, resolving biases, maintaining transparency, identifying fault for mistakes, and ensuring fair access are just a few examples of ethical considerations. To preserve patient trust and address the effect on the healthcare workforce, ethical frameworks must be developed. The amazing potential of AI in the treatment of breast cancer calls for careful examination of its ethical and practical implications. We aim to review the comprehensive role of artificial intelligence in breast cancer management.

Comparison of glass and digital slides for cervical cytopathology screening and interpretation

Cervical cancer is the second most common form of cancer and a leading cause of premature death among women aged 15 to 44 worldwide. In Brazil, there is a high prevalence of infection by the human papillomavirus - HPV. Digital pathology optimizes time and space for reading cervicovaginal cytology slides. We evaluated the feasibility of using whole slide images (WSI) for the routine interpretation of cytology exams. A total of 99 cases of vaginal cytology were selected from a reference laboratory in Northeastern Brazil. Three cytotechnicians participated in the study. Cellular atypia was the one that most presented concordance values. Two observers almost perfectly agreed (k = 0.86 and k = 0.84, respectively) on the negative diagnoses. The performance of the evaluators for NILM (negative for intraepithelial lesion and malignancy) showed high reproducibility and sensitivity in the digital slides, mainly between evaluators A and C. In contrast, the microbiology group showed disagreement between the diagnoses by digital slides and the standard- gold. The concordance between the digital diagnoses and the gold standard for ASCUS was 89%. In the inflammatory category, Spearman's test showed similar results between raters A, B, and C (rs = 0.47, rs = 0.41, and rs = 0.47, respectively). This study reports the diagnostic validation using digital slides in view of the need to optimize the cytology visualization process. Our experience shows good diagnostic agreement between digital and optical microscopy in several analyzed categories, but mainly in relation to cellular atypia and inflammatory processes.

Deep learning supported mitoses counting on whole slide images: A pilot study for validating breast cancer grading in the clinical workflow

Introduction

Breast cancer (BC) prognosis is largely influenced by histopathological grade, assessed according to the Nottingham modification of Bloom-Richardson (BR). Mitotic count (MC) is a component of histopathological grading but is prone to subjectivity. This study investigated whether mitoses counting in BC using digital whole slide images (WSI) compares better to light microscopy (LM) when assisted by artificial intelligence (AI), and to which extent differences in digital MC (AI assisted or not) result in BR grade variations.

Methods

Fifty BC patients with paired core biopsies and resections were randomly selected. Component scores for BR grade were extracted from pathology reports. MC was assessed using LM, WSI, and AI. Different modalities (LM-MC, WSI-MC, and AI-MC) were analyzed for correlation with scatterplots and linear regression, and for agreement in final BR with Cohen's κ.

Results

MC modalities strongly correlated in both biopsies and resections: LM-MC and WSI-MC (R² 0.85 and 0.83, respectively), LM-MC and AI-MC (R² 0.85 and 0.95), and WSI-MC and AI-MC (R² 0.77 and 0.83). Agreement in BR between modalities was high in both biopsies and resections: LM-MC and WSI-MC (κ 0.93 and 0.83, respectively), LM-MC and AI-MC (κ 0.89 and 0.83), and WSI-MC and AI-MC (κ 0.96 and 0.73).

Conclusion

This first validation study shows that WSI-MC may compare better to LM-MC when using AI. Agreement between BR grade based on the different mitoses counting modalities was high. These results suggest that mitoses counting on WSI can well be done, and validate the presented AI algorithm for pathologist supervised use in daily practice. Further research is required to advance our knowledge of AI-MC, but it appears at least non-inferior to LM-MC.

Breast Cancer: Impact of New Treatments?

BACKGROUND

Breast cancer treatment has seen tremendous progress since the early 1980s, with the first findings of new chemotherapy and hormone therapies. Screening started in the same period.

METHODS

A review of population data (SEER and the literature) shows an increase in recurrence-free survival until 2000 and it stagnates afterwards.

RESULTS

Over the period 1980-2000, the 15% survival gain was presented by pharma as a contribution of new molecules. The contribution of screening during that same period was not implemented by them, although screening has been accepted as a routine procedure in the States since the 1980s and everywhere else since 2000.

CONCLUSIONS

Interpretation of breast cancer outcome has largely focused on drugs, whereas other factors, such as screening, prevention, biologics, and genetics, were largely neglected. More attention should now be paid to examining the strategy based on realistic global data.

BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images

Breast cancer is one of the most common types of cancer and is the leading cause of cancer-related death. Diagnosis of breast cancer is based on the evaluation of pathology slides. In the era of digital pathology, these slides can be converted into digital whole slide images (WSIs) for further analysis. However, due to their sheer size, digital WSIs diagnoses are time consuming and challenging. In this study, we present a lightweight architecture that consists of a bilinear structure and MobileNet-V3 network, bilinear MobileNet-V3 (BM-Net), to analyze breast cancer WSIs. We utilized the WSI dataset from the ICIAR2018 Grand Challenge on Breast Cancer Histology Images (BACH) competition, which contains four classes: normal, benign, in situ carcinoma, and invasive carcinoma. We adopted data augmentation techniques to increase diversity and utilized focal loss to remove class imbalance. We achieved high performance, with 0.88 accuracy in patch classification and an average 0.71 score, which surpassed state-of-the-art models. Our BM-Net shows great potential in detecting cancer in WSIs and is a promising clinical tool.

Validating Whole Slide Imaging Systems for Diagnostic Purposes in Pathology

CONTEXT.—

The original guideline, "Validating Whole Slide Imaging for Diagnostic Purposes in Pathology," was published in 2013 and included 12 guideline statements. The College of American Pathologists convened an expert panel to update the guideline following standards established by the National Academies of Medicine for developing trustworthy clinical practice guidelines.

OBJECTIVE.—

To assess evidence published since the release of the original guideline and provide updated recommendations for validating whole slide imaging (WSI) systems used for diagnostic purposes.

DESIGN.—

An expert panel performed a systematic review of the literature. Frozen sections, anatomic pathology specimens (biopsies, curettings, and resections), and hematopathology cases were included. Cytology cases were excluded. Using the Grading of Recommendations Assessment, Development, and Evaluation approach, the panel reassessed and updated the original guideline recommendations.

RESULTS.—

Three strong recommendations and 9 good practice statements are offered to assist laboratories with validating WSI digital pathology systems.

CONCLUSIONS.—

Systematic review of literature following release of the 2013 guideline reaffirms the use of a validation set of at least 60 cases, establishing intraobserver diagnostic concordance between WSI and glass slides and the use of a 2-week washout period between modalities. Although all discordances between WSI and glass slide diagnoses discovered during validation need to be reconciled, laboratories should be particularly concerned if their overall WSI-glass slide concordance is less than 95%.

Assessment of deep learning algorithms to predict histopathological diagnosis of breast cancer: first Moroccan prospective study on a private dataset

Objective

Breast cancer is a critical public health issue and a leading cause of cancer-related deaths among women worldwide. Its early diagnosis and detection can effectively help in increasing the chances of survival rate. For this reason, the diagnosis and classification of breast cancer using Deep learning algorithms have attracted a lot of attention. Therefore, our study aimed to design a computational approach based on deep convolutional neural networks for an efficient classification of breast cancer histopathological images by using our own created dataset. We collected overall 328 digital slides, from 116 of surgical breast specimens diagnosed with invasive breast carcinoma of non-specific type, and referred to the histopathology department of the National Institute of Oncology in Rabat, Morocco. We used two models of deep neural network architectures in order to accurately classify the images into one of three categories: normal tissue-benign lesions, in situ carcinoma or invasive carcinoma.

Results

Both Resnet50 and Xception models achieved comparable results, with a small advantage to Xception extracted features. We reported high degrees of overall correct classification accuracy (88%), and sensitivity (95%) for detection of carcinoma cases, which is important for diagnostic pathology workflow in order to assist pathologists for diagnosing breast cancer with precision. The results of the present study showed that the designed classification model has a good generalization performance in predicting diagnosis of breast cancer, in spite of the limited size of the data. To our knowledge, this approach can be highly compared with other common methods in the automated analysis of breast cancer images reported in literature.

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.

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

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.

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.

A Pyramid Architecture-Based Deep Learning Framework for Breast Cancer Detection

Breast cancer diagnosis is a critical step in clinical decision making, and this is achieved by making a pathological slide and gives a decision by the doctors, which is the method of final decision making for cancer diagnosis. Traditionally, the doctors usually check the pathological images by visual inspection under the microscope. Whole-slide images (WSIs) have supported the state-of-the-art diagnosis results and have been admitted as the gold standard clinically. However, this task is time-consuming and labour-intensive, and all of these limitations make low efficiency in decision making. Medical image processing protocols have been used for this task during the last decades and have obtained satisfactory results under some conditions; especially in the deep learning era, it has exhibited the advantages than those in the shallow learning period. In this paper, we proposed a novel breast cancer region mining framework based on deep pyramid architecture from multilevel and multiscale breast pathological WSIs. We incorporate the tissue- and cell-level information together and integrate these into a LSTM model for the final sequence modelling, which successfully keeps the WSIs' integration and is not mentioned by the prevalence frameworks. The experiment results demonstrated that our proposed framework greatly improved the detection accuracy than that only using tissue-level information.

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.

Diagnostic concordance and discordance in digital pathology: a systematic review and meta-analysis

BACKGROUND

Digital pathology (DP) has the potential to fundamentally change the way that histopathology is practised, by streamlining the workflow, increasing efficiency, improving diagnostic accuracy and facilitating the platform for implementation of artificial intelligence-based computer-assisted diagnostics. Although the barriers to wider adoption of DP have been multifactorial, limited evidence of reliability has been a significant contributor. A meta-analysis to demonstrate the combined accuracy and reliability of DP is still lacking in the literature.

OBJECTIVES

We aimed to review the published literature on the diagnostic use of DP and to synthesise a statistically pooled evidence on safety and reliability of DP for routine diagnosis (primary and secondary) in the context of validation process.

METHODS

A comprehensive literature search was conducted through PubMed, Medline, EMBASE, Cochrane Library and Google Scholar for studies published between 2013 and August 2019. The search protocol identified all studies comparing DP with light microscopy (LM) reporting for diagnostic purposes, predominantly including H&E-stained slides. Random-effects meta-analysis was used to pool evidence from the studies.

RESULTS

Twenty-five studies were deemed eligible to be included in the review which examined a total of 10 410 histology samples (average sample size 176). For overall concordance (clinical concordance), the agreement percentage was 98.3% (95% CI 97.4 to 98.9) across 24 studies. A total of 546 major discordances were reported across 25 studies. Over half (57%) of these were related to assessment of nuclear atypia, grading of dysplasia and malignancy. These were followed by challenging diagnoses (26%) and identification of small objects (16%).

CONCLUSION

The results of this meta-analysis indicate equivalent performance of DP in comparison with LM for routine diagnosis. Furthermore, the results provide valuable information concerning the areas of diagnostic discrepancy which may warrant particular attention in the transition to DP.

Artificial intelligence grading of breast cancer: a promising method to refine prognostic classification for management precision

AIM

Artificial intelligence (AI)-based breast cancer grading may help to overcome perceived limitations of human assessment. Here, the potential value of AI grade was evaluated at the molecular level and in predicting patient outcome.

METHODS AND RESULTS

A supervised convolutional neural network (CNN) model was trained on images of 612 breast cancers from The Cancer Genome Atlas (TCGA). The test set, obtained from the Cooperative Human Tissue Network (CHTN), comprised 1058 cancers with corresponding survival data. Upon reversal, a CNN was trained from images of 1537 CHTN cancers and tested on 397 TCGA cancers. In TCGA, mRNA models were trained using AI grade and Nottingham grade (NG) as labels. Performance of mRNA models in predicting patient outcome was evaluated using data from 1807 cancers from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) cohort. In selecting images for training, nucleolar prominence determined high- versus low-grade cancer cells. In CHTN, NG corresponded to significant survival stratification in stages 1, 2 and 3 cancers, while AI grade showed significance in stages 1 and 2 and borderline in stage 3 tumours. In METABRIC, the mRNA model trained from AI grade was not significantly different to the NG-based model. The gene which best described AI grade was TRIP13, a gene involved with mitotic spindle assembly.

CONCLUSION

An AI grade trained from the morphologically distinctive feature of nucleolar prominence could transmit significant patient outcome information across three independent patient cohorts. AI grade shows promise in gene discovery and for second opinions.

Histologic grading of breast carcinoma: a multi-institution study of interobserver variation using virtual microscopy

Breast carcinoma grading is an important prognostic feature recently incorporated into the AJCC Cancer Staging Manual. There is increased interest in applying virtual microscopy (VM) using digital whole slide imaging (WSI) more broadly. Little is known regarding concordance in grading using VM and how such variability might affect AJCC prognostic staging (PS). We evaluated interobserver variability amongst a multi-institutional group of breast pathologists using digital WSI and how discrepancies in grading would affect PS. A digitally scanned slide from 143 invasive carcinomas was independently reviewed by 6 pathologists and assigned grades based on established criteria for tubule formation (TF), nuclear pleomorphism (NP), and mitotic count (MC). Statistical analysis was performed. Interobserver agreement for grade was moderate (κ = 0.497). Agreement was fair (κ = 0.375), moderate (κ = 0.491), and good (κ = 0.705) for grades 2, 3, and 1, respectively. Observer pair concordance ranged from fair to good (κ = 0.354-0.684) Perfect agreement was observed in 43 cases (30%). Interobserver agreement for the individual components was best for TF (κ = 0.503) and worst for MC (κ = 0.281). Seventeen of 86 (19.8%) discrepant cases would have resulted in changes in PS and discrepancies most frequently resulted in a PS change from IA to IB (n = 9). For two of these nine cases, Oncotype DX results would have led to a PS of 1A regardless of grade. Using VM, a multi-institutional cohort of pathologists showed moderate concordance for breast cancer grading, similar to studies using light microscopy. Agreement was the best at the extremes of grade and for evaluation of TF. Whether the higher variability noted for MC is a consequence of VM grading warrants further investigation. Discordance in grading infrequently leads to clinically meaningful changes in the prognostic stage.

Preoperative prediction of histologic grade in invasive breast cancer by using contrast-enhanced spectral mammography-based radiomics

OBJECTIVE

To develop and validate a radiomics model based on contrast-enhanced spectral mammography (CESM), and preoperatively discriminate low-grade (grade I/II) and high-grade (grade III) invasive breast cancer.

METHOD

A total of 205 patients with CESM examination and pathologically confirmed invasive breast cancer were retrospectively enrolled. We randomly divided patients into two independent sets namely, training set (164 patients) and test set (41 patients) with a ratio of 8:2. Radiomics features were extracted from the low-energy and subtracted images. The least absolute shrinkage and selection operator (LASSO) logistic regression were established for feature selection, which were then utilized to construct three classification models namely, low energy, subtracted images and their combined model to discriminate high- and low-grade invasive breast cancer. Receiver operator characteristic (ROC) curves were used to confirm performance of three models in training set. The clinical usefulness was evaluated by using decision curve analysis (DCA). An independent test set was used to confirm the discriminatory power of the models. To test robustness of the result, we used 100 times LGOCV (leave group out cross validation) to validate three models.

RESULTS

From initial radiomics feature pool, 17 and 11 features were selected for low-energy image and subtracted image, respectively. The combined model using 28 features showed the best performance for preoperatively evaluating the histologic grade of invasive breast cancer, with an area under the curve, AUC = 0.88, and 95%confidence interval [CI] 0.85 to 0.92 in the training set and AUC = 0.80 (95%CI 0.67 to 0.92) in the test set. The mean AUC of LGOCV is 0.82.

CONCLUSIONS

CESM-based radiomics model is a non-invasive predictive tool that demonstrates good application prospects in preoperatively predicting histological grade of invasive breast cancer.

Visual histological assessment of morphological features reflects the underlying molecular profile in invasive breast cancer: a morphomolecular study

AIMS

Tumour genotype and phenotype are related and can predict outcome. In this study, we hypothesised that the visual assessment of breast cancer (BC) morphological features can provide valuable insight into underlying molecular profiles.

METHODS AND RESULTS

The Cancer Genome Atlas (TCGA) BC cohort was used (n = 743) and morphological features, including Nottingham grade and its components and nucleolar prominence, were assessed utilising whole-slide images (WSIs). Two independent scores were assigned, and discordant cases were utilised to represent cases with intermediate morphological features. Differentially expressed genes (DEGs) were identified for each feature, compared among concordant/discordant cases and tested for specific pathways. Concordant grading was observed in 467 of 743 (63%) of cases. Among concordant case groups, eight common DEGs (UGT8, DDC, RGR, RLBP1, SPRR1B, CXorf49B, PSAPL1 and SPRR2G) were associated with overall tumour grade and its components. These genes are related mainly to cellular proliferation, differentiation and metabolism. The number of DEGs in cases with discordant grading was larger than those identified in concordant cases. The largest number of DEGs was observed in discordant grade 1:3 cases (n = 1185). DEGs were identified for each discordant component. Some DEGs were uniquely associated with well-defined specific morphological features, whereas expression/co-expression of other genes was identified across multiple features and underlined intermediate morphological features.

CONCLUSION

Morphological features are probably related to distinct underlying molecular profiles that drive both morphology and behaviour. This study provides further evidence to support the use of image-based analysis of WSIs, including artificial intelligence algorithms, to predict tumour molecular profiles and outcome.

Current and future applications of artificial intelligence in pathology: a clinical perspective

During the last decade, a dramatic rise in the development and application of artificial intelligence (AI) tools for use in pathology services has occurred. This trend is often expected to continue and reshape the field of pathology in the coming years. The deployment of computational pathology and applications of AI tools can be considered as a paradigm shift that will change pathology services, making them more efficient and capable of meeting the needs of this era of precision medicine. Despite the success of AI models, the translational process from discovery to clinical applications has been slow. The gap between self-contained research and clinical environment may be too wide and has been largely neglected. In this review, we cover the current and prospective applications of AI in pathology. We examine its applications in diagnosis and prognosis, and we offer insights for considerations that could improve clinical applicability of these tools. Then, we discuss its potential to improve workflow efficiency, and its benefits in pathologist education. Finally, we review the factors that could influence adoption in clinical practices and the associated regulatory processes.

Prognostic significance of nucleolar assessment in invasive breast cancer

AIMS

Nucleolar morphometric features have a potential role in the assessment of the aggressiveness of many cancers. However, the role of nucleoli in invasive breast cancer (BC) is still unclear. The aims of this study were to investigate the optimal method for scoring nucleoli in IBC and their prognostic significance, and to refine the grading of breast cancer (BC) by incorporating nucleolar score.

METHODS AND RESULTS

Digital images acquired from haematoxylin and eosin-stained sections from a large BC cohort were divided into training (n = 400) and validation (n = 1200) sets for use in this study. Four different assessment methods were evaluated in the training set to identify the optimal method associated with the best performance and significant prognostic value. These were: (i) a modified Helpap method; (ii) counting prominent nucleoli (size ≥2.5 µm) in 10 field views (FVs); (iii) counting prominent nucleoli in five FVs; and (iv) counting prominent nucleoli in one FV. The optimal method was applied to the validation set and to an external validation set, i.e. data from The Cancer Genome Atlas (n = 743). Scoring prominent nucleoli in five FVs showed the highest interobserver concordance rate (intraclass correlation coefficient of 0.8) and a significant association with BC-specific survival (P < 0.0001). A high nucleolar score was associated with younger age, larger tumour size, and higher grade. Incorporation of nucleolar score in the Nottingham grading system resulted in a higher significant association with survival than the conventional grade.

CONCLUSIONS

Quantification of nucleolar prominence in five FVs is a cost-efficient and reproducible morphological feature that can predict BC behaviour and can provide an alternative to pleomorphism to improve BC grading performance.

Artificial intelligence in digital breast pathology: Techniques and applications

Breast cancer is the most common cancer and second leading cause of cancer-related death worldwide. The mainstay of breast cancer workup is histopathological diagnosis - which guides therapy and prognosis. However, emerging knowledge about the complex nature of cancer and the availability of tailored therapies have exposed opportunities for improvements in diagnostic precision. In parallel, advances in artificial intelligence (AI) along with the growing digitization of pathology slides for the primary diagnosis are a promising approach to meet the demand for more accurate detection, classification and prediction of behaviour of breast tumours. In this article, we cover the current and prospective uses of AI in digital pathology for breast cancer, review the basics of digital pathology and AI, and outline outstanding challenges in the field.

Deep learning assisted mitotic counting for breast cancer

As part of routine histological grading, for every invasive breast cancer the mitotic count is assessed by counting mitoses in the (visually selected) region with the highest proliferative activity. Because this procedure is prone to subjectivity, the present study compares visual mitotic counting with deep learning based automated mitotic counting and fully automated hotspot selection. Two cohorts were used in this study. Cohort A comprised 90 prospectively included tumors which were selected based on the mitotic frequency scores given during routine glass slide diagnostics. This pathologist additionally assessed the mitotic count in these tumors in whole slide images (WSI) within a preselected hotspot. A second observer performed the same procedures on this cohort. The preselected hotspot was generated by a convolutional neural network (CNN) trained to detect all mitotic figures in digitized hematoxylin and eosin (H&E) sections. The second cohort comprised a multicenter, retrospective TNBC cohort (n = 298), of which the mitotic count was assessed by three independent observers on glass slides. The same CNN was applied on this cohort and the absolute number of mitotic figures in the hotspot was compared to the averaged mitotic count of the observers. Baseline interobserver agreement for glass slide assessment in cohort A was good (kappa 0.689; 95% CI 0.580-0.799). Using the CNN generated hotspot in WSI, the agreement score increased to 0.814 (95% CI 0.719-0.909). Automated counting by the CNN in comparison with observers counting in the predefined hotspot region yielded an average kappa of 0.724. We conclude that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible. Using a predefined hotspot area considerably improves reproducibility. Also, fully automated assessment of mitotic score appears to be feasible without introducing additional bias or variability.

Interobserver variability in breast carcinoma grading results in prognostic stage differences

The AJCC Cancer Staging Manual 8th edition included tumor grade in the pathologic prognostic stage for breast carcinomas. Due to the known subjectivity of tumor grading, we aimed to assess the degree of interobserver agreement for invasive carcinoma grade among pathologists and determine its effect on pathologic prognostic stage. One hundred consecutive cases of invasive stage II carcinomas were independently graded twice, with an 4-week intervening wash-out period, by 6 breast pathologists utilizing established Nottingham grading criteria. Inter- and intra-observer variability was determined for overall grade and for each of the 3 scoring components. Interobserver variability was good to very good (κ range = 0.582-0.850) with even better intra-observer variability (mean κ = 0.766). Tubule score was the most reproducible element (κ = 0.588). Complete concordance was reached in 54 cases and 58 cases in rounds 1 and 2 respectively. In round 1 this resulted in different pathologic prognostic stage in only 25 of discordant cases, 18 of which were stage IA versus IB. In conclusion, grading agreement between pathologists was good to very good and discordant grades resulted in small changes to pathologic prognostic stage.

BioDog, biomarker detection for improving identification power of breast cancer histologic grade in methylomics

Aim: Breast cancer histologic grade (HG) is a well-established prognostic factor. This study aimed to select methylomic biomarkers to predict breast cancer HGs. Materials & methods: The proposed algorithm BioDog firstly used correlation bias reduction strategy to eliminate redundant features. Then incremental feature selection was applied to find the features with a high HG prediction accuracy. The sequential backward feature elimination strategy was employed to further refine the biomarkers. A comparison with existing algorithms were conducted. The HG-specific somatic mutations were investigated. Results & conclusions: BioDog achieved accuracy 0.9973 using 92 methylomic biomarkers for predicting breast cancer HGs. Many of these biomarkers were within the genes and lncRNAs associated with the HG development in breast cancer or other cancer types.

Deep learning and manual assessment show that the absolute mitotic count does not contain prognostic information in triple negative breast cancer

PURPOSE

The prognostic value of mitotic count for invasive breast cancer is firmly established. As yet, however, limited studies have been aimed at assessing mitotic counts as a prognostic factor for triple negative breast cancers (TNBC). Here, we assessed the prognostic value of absolute mitotic counts for TNBC, using both deep learning and manual procedures.

METHODS

A retrospective TNBC cohort (n = 298) was used. The absolute manual mitotic count was assessed by averaging counts from three independent observers. Deep learning was performed using a convolutional neural network on digitized H&E slides. Multivariable Cox regression models for relapse-free survival and overall survival served as baseline models. These were expanded with dichotomized mitotic counts, attempting every possible cut-off value, and evaluated by means of the c-statistic.

RESULTS

We found that per 2 mm2 averaged manual mitotic counts ranged from 1 to 187 (mean 37.6, SD 23.4), whereas automatic counts ranged from 1 to 269 (mean 57.6; SD 42.2). None of the cut-off values improved the models' baseline c-statistic, for both manual and automatic assessments.

CONCLUSIONS

Based on our results we conclude that the level of proliferation, as reflected by mitotic count, does not serve as a prognostic factor for TNBC. Therefore, TNBC patient management based on mitotic count should be discouraged.

Novel insights into breast cancer progression and metastasis: A multidisciplinary opportunity to transition from biology to clinical oncology

According to the most recent epidemiological studies, breast cancer shows the highest incidence and the second leading cause of death in women. Cancer progression and metastasis are the main events related to poor survival of breast cancer patients. This can be explained by the presence of highly resistant to chemo- and radiotherapy stem cells in many breast tumor tissues. In this context, numerous studies highlighted the possible involvement of epithelial to mesenchymal transition phenomenon as biological program to generate cancer stem cells, and thus participate to both metastatic and drug resistance process. Therefore, the comprehension of mechanisms (both cellular and molecular) involved in breast cancer occurrence and progression can lay the foundation for the development of new diagnostic and therapeutical protocols. In this review, we reported the most important findings in the field of breast cancer highlighting the most recent data concerning breast tumor biology, diagnosis and therapy.