Histological grading of breast carcinomas: a study of interobserver agreement

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.

STARD3: A New Biomarker in HER2-Positive Breast Cancer

Pathological complete response (pCR) after neoadjuvant systemic treatment (NST) is an important prognostic factor in HER2-positive breast cancer. The majority of HER2-positive breast cancers are amplified at the HER2 gene locus, several genes are co-amplified with HER2, and a subset of them are co-expressed. The STARD3 gene belongs to the HER2 amplicon, and its role as a predictive marker was never addressed. The objective of this study was to investigate the predictive value of STARD3 protein expression on NST pathological response in HER2-positive breast cancer. In addition, we studied the prognostic value of this marker.

METHODS

We conducted a retrospective study between 2007 and 2020 on 112 patients with non-metastatic HER2-positive breast cancer treated by NST and then by surgery. We developed an immunohistochemistry assay for STARD3 expression and subcellular localization and determined a score for STARD3-positivity. As STARD3 is an endosomal protein, its expression was considered positive if the intracellular signal pattern was granular.

RESULTS

In this series, pCR was achieved in half of the patients. STARD3 was positive in 86.6% of cases and was significantly associated with pCR in univariate analysis (p = 0.013) and after adjustment on other known pathological parameters (p = 0.044). Performances on pCR prediction showed high sensitivity (96%) and negative predictive value (87%), while specificity was 23% and positive predictive value was 56%. Overall, specific, relapse-free, and distant metastasis-free survivals were similar among STARD3 positive and negative groups, independently of other prognosis factors.

CONCLUSION

NST is an opportunity for HER2-positive cancers. In this series of over a hundred HER2-positive and non-metastatic patients, a STARD3-negative score was associated with the absence of pathological complete response. This study suggests that determining STARD3 overexpression status on initial biopsies of HER2-positive tumors is an added value for the management of a subset of patients with high probability of no pathological response.

Predicting the Likelihood of Colorectal Cancer with Artificial Intelligence Tools Using Fourier Transform Infrared Signals Obtained from Tumor Samples

The early and accurate detection of colorectal cancer (CRC) significantly affects its prognosis and clinical management. However, current standard diagnostic procedures for CRC often lack sensitivity and specificity since most rely on visual examination. Hence, there is a need to develop more accurate methods for its diagnosis. Support vector machine (SVM) and feedforward neural network (FNN) models were designed using the Fourier transform infrared (FT-IR) spectral data of several colorectal tissues that were unanimously identified as either benign or malignant by different unrelated pathologists. The set of samples in which the pathologists had discordant readings were then analyzed using the AI models described above. Between the SVM and NN models, the NN model was able to outperform the SVM model based on their prediction confidence scores. Using the spectral data of the concordant samples as training set, the FNN was able to predict the histologically diagnosed malignant tissues (n = 118) at 59.9-99.9% confidence (average = 93.5%). Of the 118 samples, 84 (71.18%) were classified with an above average confidence score, 34 (28.81%) classified below the average confidence score, and none was misclassified. Moreover, it was able to correctly identify the histologically confirmed benign samples (n = 83) at 51.5-99.7% confidence (average = 91.64%). Of the 83 samples, 60 (72.29%) were classified with an above average confidence score, 22 (26.51%) classified below the average confidence score, and only 1 sample (1.20%) was misclassified. The study provides additional proof of the ability of attenuated total reflection (ATR) FT-IR enhanced by AI tools to predict the likelihood of CRC without dependence on morphological changes in tissues.

Clinical role of MiRNA 29a and MiRNA 335 on breast cancer management: their relevance to MMP2 protein level

BACKGROUND

Circulating miRNAs are novel biomarkers, authors aimed to investigate the expression level of miR-29a and miR-335 and their relevance to CEA, CA15.3, and matrix metalloproteinase-2 (MMP2).

MATERIALS AND METHODS

Breast cancer (BC) patients (n = 44), benign breast lesion patients (n = 25), and healthy individuals (n = 19) were enrolled for detection of miRNA expression levels, MMP2 and biochemical markers using quantitative polymerase chain reaction (PCR) and ELISA, respectively.

RESULTS

Expression of miR-29a and miR-335 were significantly decreased in breast patients as compared to healthy individuals, while biochemical markers were high in BC patients as compared to the other two groups. The diagnostic efficacy for miR-29a, miR-335, and MMP2 were superior to both CEA and CA 15.3 for early detection of BC patients.

CONCLUSIONS

Detection of the miR-29a and miR335 expression levels in serum samples are significant promising biomarkers for BC diagnosis.

Quantitative Evaluation of Inflammatory Markers in Peri-Implantitis and Periodontitis Tissues: Digital vs. Manual Analysis—A Proof of Concept Study

Background and Objectives: In dentistry, the assessment of the histomorphometric features of periodontal (PD) and peri-implant (PI) lesions is important to evaluate their underlying pathogenic mechanism. The present study aimed to compare manual and digital methods of analysis in the evaluation of the inflammatory biomarkers in PI and PD lesions. Materials and Methods: PD and PI inflamed soft tissues were excised and processed for histological and immunohistochemical analyses for CD3+, CD4+, CD8+, CD15+, CD20+, CD68+, and CD138+. The obtained slides were acquired using a digital scanner. For each marker, 4 pictures per sample were extracted and the area fraction of the stained tissue was computed both manually using a 594-point counting grid (MC) and digitally using a dedicated image analysis software (DC). To assess the concordance between MC and DC, two blinded observers analysed a total of 200 pictures either with good quality of staining or with non-specific background noise. The inter and intraobserver concordance was evaluated using the intraclass coefficient and the agreement between MC and DC was assessed using the Bland–Altman plot. The time spent analysing each picture using the two methodologies by both observers was recorded. Further, the amount of each marker was compared between PI and PD with both methodologies. Results: The inter- and intraobserver concordance was excellent, except for images with background noise analysed using DC. MC and DC showed a satisfying concordance. DC was performed in half the time compared to MC. The morphological analysis showed a larger inflammatory infiltrate in PI than PD lesions. The comparison between PI and PD showed differences for CD68+ and CD138+ expression. Conclusions: DC could be used as a reliable and time-saving procedure for the immunohistochemical analysis of PD and PI soft tissues. When non-specific background noise is present, the experience of the pathologist may be still required.

Expression of MiR-335 and its target metalloproteinase genes: clinical significance in breast cancer

BACKGROUND

Early diagnosis of breast cancer decreases mortality rate; therefore, novel diagnostic methods are urgently required. In this study, authors aimed to investigate the role of serum-derived miR-335 in breast cancer, and the expression of matrix metalloproteinase-2 (MMP2) and matrix metalloproteinase-9 (MMP9) and evaluating their feasibility and clinical utility as biomarkers for the early detection of breast cancer.

MATERIALS AND METHODS

Blood samples were collected from a total of 210 individuals who were enrolled in this study. The participants were divided into newly diagnosed breast cancer patients (n = 115), patients with benign breast lesions (n =55) and healthy individuals as control group (n =40). The expression profile of miR-335, MMP2 and MMP9 were determined using quantitative polymerase chain reaction (qPCR).

RESULTS

MiR 335 expression level was down-regulated in primary breast cancer group as compared to benign breast group and healthy individuals with 98% and 94.9% sensitivity and specificity, respectively. MMP2 and MMP9 showed significantly higher expression levels in breast cancer group as compared to both benign and healthy group and reporting 92.7% and 93% sensitivity, respectively. The relations between investigated markers and pathologic types, staging, grading, and lymph node involvement were significant with these factors. Expression level of miR-335 was decreased with increased MMP2 and MMP9 at significant level.

CONCLUSION

MiR-335, MMP2, and MMP9 can be used as diagnostic markers in breast cancer.

Immunological profiles of the breast cancer microenvironment represented by tumor-infiltrating lymphocytes and PD-L1 expression

Tumor-infiltrating lymphocytes (TILs) and programmed cell death 1 ligand 1 (PD-L1) are established prognostic and predictive biomarkers for certain breast cancer subsets. However, their association with the immune response complexity is not fully understood. Therefore, we analyzed the association between the immune cell fractions in breast cancer tissues and histologically assessed TIL (hTIL) and PD-L1 (hPD-L1). Forty-five tumor and eighteen blood samples were collected from patients with breast cancer. Total leukocyte counts, frequency of 11 immune cell populations, and PD-L1 expression in each cell fraction were evaluated by flow cytometry. TILs and PD-L1 were assessed by hematoxylin and eosin staining and immunohistochemistry, respectively. A higher hTIL score showed association with increased leukocyte infiltration, higher CD4⁺ and CD8⁺ T cell proportions, and lower natural killer and natural killer T cell proportions. PD-L1 was highly expressed in nonclassical monocytes, monocyte/macrophages, myeloid-derived suppressor cells, myeloid dendritic cells, dendritic cells, and other lineages in tumors. hPD-L1 positivity reflected PD-L1 expression accurately in these fractions, as well as increased leukocyte infiltration in tumors. These results indicate that hTILs reflect differences in the immune responses in the tumor microenvironment, and certain immune cell fractions are favorably expressed in the PD-L1 pathway in breast cancer microenvironments.

IIB or not IIB, part 2: assessing inter-rater and intra-rater repeatability of the Kenney-Doig scale in equine endometrial biopsy evaluation

Inter- and intra-rater variability negatively affects the reliability of various histopathology grading scales used as prognostic aids in human and veterinary medicine. The Kenney-Doig categorization (grading) scale, which is used to associate equine endometrial histologic lesions with prognostic estimation of a broodmare's reproductive potential, has not been evaluated for inter- or intra-rater variability, to our knowledge. To assess whether the Kenney-Doig system produces reliable results among observers, 8 pathologists, all with American College of Veterinary Pathologists certification, were recruited to blindly categorize the same set of 63 digital equine endometrial biopsy slides as well as to re-evaluate anonymously 21 of 63 of these slides at a later time. Cohen kappa values for pairwise comparison of final Kenney-Doig categories were -0.05 to 0.46 (unweighted) and 0.08-0.64 (weighted), with an average Light kappa of 0.19 (unweighted) and 0.36 (weighted) across all 8 pathologists, 0.14 (unweighted) and 0.33 (weighted) for pathologists at different institutions, and 0.22 (unweighted) and 0.46 (weighted) for pathologists at the same institution. Intra-class correlations measuring intra-rater agreement were 0.12-0.77 with an average of 0.55 for all 8 pathologists. We found that only slight-to-moderate inter-rater agreement and poor-to-good intra-rater agreement was produced by 8 pathologists using the Kenney-Doig scale, suggesting that the system is subject to significant observer variability and care should be taken when communicating Kenney-Doig categories to submitting clinicians with emphasis on the quality of endometrial lesions present instead of the category and associated expected foaling rate.

Clinicopathological Features Related to the Efficacy of CDK4/6 Inhibitor-Based Treatments in Metastatic Breast Cancer

Background:

Resistance to endocrine therapy has been a major obstacle in the management of hormone receptor (HR)-positive metastatic breast cancer (MBC). Meanwhile, a number of treatments are available to such patients, and physicians often encounter difficulties in choosing the most appropriate treatments for individual patients. The combination of CDK 4/6 inhibitors (CDKi) and endocrine therapy has now become a standard treatment for HR-positive and human epidermal growth factor receptor 2 (HER2)-negative MBC. However, no predictive markers for CDKi-based treatments have been established. Considering their side effects and the financial burden on patients, identifying such markers is crucial.

Methods:

Clinicopathological features of 107 patients with HR-positive HER2-negative MBC, who received CDKi-based treatments at our institution were retrospectively investigated. HR status in distant metastatic lesions and immunocompetent cells in peripheral blood were also studied.

Results:

Progression-free survival (PFS) was significantly shorter in patients whose primary tumour was high grade (P = 0.016) or high neutrophil-to-lymphocyte ratio (NLR) at baseline (P = 0.017). Meanwhile, there were no differences in other factors, such as expression levels of hormone receptors. Patients whose metastatic lesions were of low tumour grade or high Ki67 labelling index had longer PFS, and such trends were more obvious than primary lesions.

Conclusion:

Our data indicate that tumour grade in primary lesion and NLR are potential predictive factors for CDKi-based treatments. Moreover, pathological assessment of metastatic lesions might also be useful.

Whale Optimizer-Based Clustering for Breast Histopathology Image Segmentation

Breast histopathology image segmentation is a complex task due to indiscernibly correlated and noisy regions of interest. Breast histopathological images are composed of different types of cells. Some of these cells can be harmful for humans due to the presence of cancer. Under such circumstances, many segmentation techniques for automatic detection of cancer cells have been proposed considering clustering schemes. However, such clustering methodologies are sensitive to initial cluster centers, which promote false-positive solutions. This paper presents the use of the Whale Optimization Algorithm (WOA) for proper clustering segmentation of breast histopathological images to overcome clustering issues. Also, a rigorous comparative study is conducted among the proposed approach and several state-of-art Nature-Inspired Optimization Algorithms (NIOAs) and traditional clustering techniques. The numerical results indicate that the proposed approach outperforms the other utilized clustering methods in terms of precision, robustness, and quality of the segmented outputs.

IIB or not IIB, part 1: retrospective evaluation of Kenney-Doig categorization of equine endometrial biopsies at a veterinary diagnostic laboratory and comparison with published reports

The Kenney-Doig scale is a histopathology categorization (grading) system often used as the standard for assessing endometrial disease and communicating prognostic fertility information for equine breeding prospects. We investigated how Kenney-Doig categories compared within the same institution and across different institutions to determine if observer variability may contribute to category frequencies. We conducted a retrospective analysis of all equine endometrial submission records between 1998 and 2018 at the Western College of Veterinary Medicine (WCVM) and Prairie Diagnostic Services (PDS). Of 726 biopsies, we found the following category distribution: 46 of 726 (6.3%) I, 307 of 726 (42.3%) IIA, 326 of 726 (44.9%) IIB, and 47 of 726 (6.5%) III. We also conducted a review of the literature and included 6 studies reporting Kenney-Doig category distributions. Chi-square analysis showed significant differences between the category distribution found at WCVM and PDS and the category distribution reported in the 6 studies. To account for differences in mare populations, individual category distributions were generated for 5 pathologists at the WCVM and PDS. The Fisher exact test among these 5 Kenney-Doig categories revealed significant differences in category tendencies, suggesting that observer variation affects the use of the scale. Our results suggest that there is a need for prospective inter-rater and intra-rater agreement studies of the repeatability of the Kenney-Doig scale.

Deep Learning-Based Diagnosis Method of Emergency Colorectal Pathology

One of the most common malignant tumors of the digestive tract is emergency colorectal cancer. In recent years, both morbidity and mortality rates, particularly in our country, are getting higher and higher. At present, diagnosis of colorectal cancer, specifically in the emergency department of a hospital, is based on the doctor's pathological diagnosis, and it is heavily dependent on the doctor's clinical experience. The doctor's workload is heavy, and misdiagnosis events occur from time to time. Therefore, computer-aided diagnosis technology is desperately needed for colorectal pathological images to assist pathologists in reducing their workload, improve the efficiency of diagnosis, and eliminate misdiagnosis. To address these issues, a gland segmentation of emergency colorectal pathology images and diagnosis of benign and malignant pathology is presented in this paper. Initially, a multifeatured auxiliary diagnosis is designed to enable diagnosis of benign and malignant diagnosis of emergency colorectal pathology. The proposed algorithm constructs an SVM-enabled pathological diagnosis model which is based on contour, color, and texture features. Additionally, their combination is used for pathological benign and malignant pathological diagnosis of two types of data sets D1 (original pathological image dataset) and D2 (dataset that has undergone glandular segmentation) diagnosis. Experimental results show that the proposed pathological diagnosis model has higher diagnostic accuracy on D2. Among these datasets, SVM based on the multifeature fusion of contour and texture achieved the highest diagnostic accuracy rate, i.e., 83.75%, which confirms that traditional image processing methods have limitations. Diagnosing benign and malignant colorectal pathology in an emergency is more difficult and must be treated on a priority basis. Finally, an emergency colorectal pathology diagnosis method, which is based on deep convolutional neural networks such as CIFAR and VGG, is proposed. After configuring and training process of the two networks, trained CIFAR and VGG network models are applied to the diagnosis of both datasets, i.e., D1 and D2, respectively.

Automated detection and grading of Invasive Ductal Carcinoma breast cancer using ensemble of deep learning models

Invasive ductal carcinoma (IDC) breast cancer is a significant health concern for women all around the world and early detection of the disease may increase the survival rate in patients. Therefore, Computer-Aided Diagnosis (CAD) based systems can assist pathologists to detect the disease early. In this study, we present an ensemble model to detect IDC using DenseNet-121 and DenseNet-169 followed by test time augmentation (TTA). The model achieved a balanced accuracy of 92.70% and an F1-score of 95.70% outperforming the current state-of-the-art. Comparative analysis against various pre-trained deep learning models and preprocessing methods have been carried out. Qualitative analysis has also been conducted on the test dataset. After the detection of IDC breast cancer, it is important to grade it for further treatment. In our study, we also propose an ensemble model for the grading of IDC using the pre-trained DenseNet-121, DenseNet-201, ResNet-101v2, and ResNet-50 architectures. The model is inferred from two validation cohorts. For the patch-level classification, the model yielded an overall accuracy of 69.31%, 75.07%, 61.85%, and 60.50% on one validation cohort and 62.44%, 79.14%, 76.62%, and 71.05% on the second validation cohort for 4×, 10×, 20×, and 40× magnified images respectively. The same architecture is further validated using a different IDC dataset where it achieved an overall accuracy of 90.07%. The performance of the models on the detection and grading of IDC shows that they can be useful to help pathologists detect and grade the disease.

High Pregnane X Receptor (PXR) Expression Is Correlated with Poor Prognosis in Invasive Breast Carcinoma

Pregnane X Receptor (PXR) is involved in human cancer, either by directly affecting carcinogenesis or by inducing drug-drug interactions and chemotherapy resistance. The clinical significance of PXR expression in invasive breast carcinoma was evaluated in the present study. PXR protein expression was assessed immunohistochemically on formalin fixed paraffin-embedded breast invasive carcinoma tissue sections, obtained from 148 patients, and was correlated with clinicopathological parameters, molecular phenotypes, tumor cells' proliferative capacity, and overall disease-free patients' survival. Additionally, the expression of PXR was examined on human breast carcinoma cell lines of different histological grade, hormonal status, and metastatic potential. PXR positivity was noted in 79 (53.4%) and high PXR expression in 48 (32.4%), out of 148 breast carcinoma cases. High PXR expression was positively associated with nuclear grade (p = 0.0112) and histological grade of differentiation (p = 0.0305), as well as with tumor cells' proliferative capacity (p = 0.0051), and negatively with luminal A subtype (p = 0.0295). Associations between high PXR expression, estrogen, and progesterone receptor negative status were also recorded (p = 0.0314 and p = 0.0208, respectively). High PXR expression was associated with shorter overall patients' survival times (log-rank test, p = 0.0009). In multivariate analysis, high PXR expression was identified as an independent prognostic factor of overall patients' survival (Cox-regression analysis, p = 0.0082). PXR expression alterations were also noted in breast cancer cell lines of different hormonal status. The present data supported evidence that PXR was related to a more aggressive invasive breast carcinoma phenotype, being a strong and independent poor prognosticator.

Clinicopathological Examination of Metaplastic Spindle Cell Carcinoma of the Breast: Case Series

Background:

Spindle cell carcinoma (SpCC) of the breast is a rare histological type, a subtype of metaplastic carcinoma characterized by atypical spindle cell and epithelial carcinoma. The proportions of the spindle cell and epithelial components vary among tumours. Due to its rarity, biological characteristics of this disease have been poorly studied.

Methods:

In total, 10 patients with SpCC were surgically treated at our institution from January 2007 to December 2018. We retrospectively investigated these SpCC cases, focusing on the differences between spindle cell and epithelial components. Microsatellite status was also examined.

Results:

Nine cases were triple-negative breast cancer (TNBC). The rates of high tumour grade were 70% in spindle cell components and 56% in epithelial components (P = .65), while the mean Ki67 labelling index were 63% and 58%, respectively (P = .71). Mean programmed death ligand 1 (PD-L1) expression in these components was 11% and 1%, respectively (P = .20). All 10 tumours were microsatellite stable. Patient outcomes of triple-negative SpCC did not differ from those of propensity-matched patients with conventional TNBC.

Conclusions:

Spindle cell components showed higher values in factors examined, although there was no statistically significant difference. Our data reveal that these 2 components of SpCC may be of different biological nature.

Grading of invasive breast carcinoma: the way forward

Histologic grading has been a simple and inexpensive method to assess tumor behavior and prognosis of invasive breast cancer grading, thereby identifying patients at risk for adverse outcomes, who may be eligible for (neo)adjuvant therapies. Histologic grading needs to be performed accurately, on properly fixed specimens, and by adequately trained dedicated pathologists that take the time to diligently follow the protocol methodology. In this paper, we review the history of histologic grading, describe the basics of grading, review prognostic value and reproducibility issues, compare performance of grading to gene expression profiles, and discuss how to move forward to improve reproducibility of grading by training, feedback and artificial intelligence algorithms, and special stains to better recognize mitoses. We conclude that histologic grading, when adequately carried out, remains to be of important prognostic value in breast cancer patients.

Impact of circulating miRNA-373 on breast cancer diagnosis through targeting VEGF and cyclin D1 genes

Background

Breast cancer (BC) is the common primary tumor among females. Hence, there is an urgent need to improve the early prediction and diagnosis of BC. For that reason, the object of the current study is to analyze the expression levels of miRNA-373 and its target genes including vascular endothelial growth factor (VEGF) and cyclin D1 in women with BC.

Results

Upregulation of miRNA-373 and its target genes was observed in BC patients followed by patients with benign breast lesions compared to downregulation in controls. There was a significant association between the expression level of miRNA-373 and all clinical features. The same associations were observed between its target genes and all clinico-pathological features except hormonal status. The correlation between miRNA-373 and both genes was significant.

Conclusions

Our results prove that miRNA-373, as an oncomir, would be a vital biomarker for BC diagnosis and prognosis by targeting both VEGF and cyclin D1.

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Automated grading systems using deep convolution neural networks (DCNNs) have proven their capability and potential to distinguish between different breast cancer grades using digitized histopathological images. In digital breast pathology, it is vital to measure how confident a DCNN is in grading using a machine-confidence metric, especially with the presence of major computer vision challenging problems such as the high visual variability of the images. Such a quantitative metric can be employed not only to improve the robustness of automated systems, but also to assist medical professionals in identifying complex cases. In this paper, we propose Entropy-based Elastic Ensemble of DCNN models (3E-Net) for grading invasive breast carcinoma microscopy images which provides an initial stage of explainability (using an uncertainty-aware mechanism adopting entropy). Our proposed model has been designed in a way to (1) exclude images that are less sensitive and highly uncertain to our ensemble model and (2) dynamically grade the non-excluded images using the certain models in the ensemble architecture. We evaluated two variations of 3E-Net on an invasive breast carcinoma dataset and we achieved grading accuracy of 96.15% and 99.50%.

Clinical impact of PTEN methylation status as a prognostic marker for breast cancer

Background

Aberrant DNA methylation of phosphatase and tensin homolog (PTEN) gene has been found in many cancers. The object of this study was to evaluate the clinical impact of PTEN methylation as a prognostic marker in breast cancer. The study includes 153 newly diagnosed females, and they were divided according to their clinical diagnosis into breast cancer patients (n = 112) and females with benign breast lesion (n = 41). A group of healthy individuals (n = 25) were recruited as control individuals. Breast cancer patients were categorized into early stage (0–I, n = 48) and late stage (II–III, n = 64), and graded into low grade (I–II, n = 42) and high grade (III, n = 70). Their pathological types were invasive duct carcinoma (IDC) (n = 66) and duct carcinoma in situ (DCI) (n = 46). Tumor markers (CEA and CA15.3) were detected using ELISA. DNA was taken away from the blood, and the PTEN promoter methylation level was evaluated using the EpiTect Methyl II PCR method.

Results

The findings revealed the superiority of PTEN methylation status as a good discriminator of the cancer group from the other two groups (benign and control) with its highest AUC and increased sensitivity (96.4%) and specificity (100%) over tumor markers (50% and 84% for CEA and 49.1% and 86.4% for CA15.3), respectively. The frequency of PTEN methylation was 96.4% of breast cancer patients and none of the benign and controls showed PTEN methylation and the means of PTEN methylation (87 ± 0.6) were significantly increased in blood samples of breast cancer group as compared to both benign and control groups (25 ± 0.7 and 12.6 ± 0.3), respectively.

Methylation levels of PTEN were higher in the blood of patients with ER-positive than in patients with ER-negative cancers (P = 0.007) and in HER2 positive vs. HER2 negative tumors (P = 0.001). The Kaplan-Meier analysis recognizes PTEN methylation status as a significant forecaster of bad progression-free survival (PFS) and overall survival (OS), after 40 months follow-up.

Conclusions

PETN methylation could be supposed as one of the epigenetic aspects influencing the breast cancer prognosis that might foretell more aggressive actions and worse results in breast cancer patients.

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.

FGFR1 copy number in breast cancer: associations with proliferation, histopathological grade and molecular subtypes

AIMS

FGFR1 is located on 8p11.23 and regulates cell proliferation and survival. Increased copy number of FGFR1 is found in several cancers including cancer of the breast. ZNF703 is located close to FGFR1 at 8p11-12 and is frequently expressed in the luminal B subtype of breast cancer. Using tissue samples from a well-described cohort of patients with breast cancer with long-term follow-up, we studied associations between FGFR1 copy number in primary breast cancer tumours and axillary lymph node metastases, and proliferation status, molecular subtype and prognosis. Furthermore, we studied associations between copy number increase of FGFR1 and copy number of ZNF703.

METHODS

We used fluorescence in situ hybridisation for FGFR1 and the chromosome 8 centromere applied to tissue microarray sections from a series of 534 breast cancer cases.

RESULTS

We found increased copy number (≥4) of FGFR1 in 74 (13.9%) of tumours. Only 6 of the 74 cases with increased copy number were non-luminal. Increased FGFR1 copy number was significantly associated with high Ki-67 status, high mitotic count and high histopathological grade, but not with prognosis. Forty-two (7.9%) cases had mean copy number ≥6. Thirty of these showed ZNF708 copy number ≥6.

CONCLUSIONS

Our results show that FGFR1 copy number increase is largely found among luminal subtypes of breast cancer, particularly luminal B (HER2^-). It is frequently accompanied by increased copy number of ZNF703. FGFR1 copy number increase is associated with high histopathological grade and high proliferation. However, we did not discover an association with prognosis.

Clinical impact of LncRNA XIST and LncRNA NEAT1 for diagnosis of high-risk group breast cancer patients

Long noncoding RNAs (lncRNAs) are evolving as contributing biomarkers for many diseases. Among these lncRNAs, X inactive-specific transcript (XIST), and nuclear paraspeckle assembly transcript 1 (NEAT1) were studied as undesirable upregulated nucleic acid markers for unfavorable prognosis of cancer. The authors aimed to investigate their role as diagnostic markers for breast cancer (BC) patients with high-risk factors. Serum samples were obtained from BC patients (n = 121), patients with benign breast lesions (n = 35), and healthy volunteers (n = 22). Assessment of lncRNA XIST, and lncRNA NEAT1 expression was performed using real time PCR. Expression levels of the investigated lncRNAs were significantly higher in BC patients as compared to the other groups. Both lncRNAs were significantly correlated with BC laterality, lymph node involvement, and clinical stages. LncRNA NEAT1 reported a significant aberrant expression with pathological types, histological grading and, hormonal status. The sensitivity of lncRNA NEAT1 was superior for detection of BC with high risk-factors as compared to lncRNA XIST. In conclusion, the detection of lncRNAs in body fluids has demonstrated a significant importance for detecting BC patients with high-risk factors, and was related to hormonal receptors, thus may be used for determining the direction of treatment strategy.

Serum MiRNA-27a as potential diagnostic nucleic marker for breast cancer

BACKGROUND

Accumulating evidence reveals that microRNA 27a (miR 27a) is implicated in the pathogenesis of cancer. However, its diagnostic role in breast cancer (BC) still needs investigation.

MATERIALS AND METHODS

MiR 27a expression was assessed in serum samples from patients with primary BC (n = 100), benign breast lesions (n = 30) and control group served as healthy volunteers (n = 20) using quantitative real-time PCR.

RESULTS

Both expression and mean rank of miR 27a and tumor markers among BC patients as compared to the other two groups. Clinicopathological characteristics showed significant relation with miRN 27a expression for clinical stage, histological grading, ER receptor and HER-2/neu. The diagnostic efficacy for miR 27a was superior to both tumor markers for early detection of BC especially high-risk BC groups.

CONCLUSION

Detection of miR 27a expression may serve as a potential sensitive minimally invasive molecular marker for early detection of primary BC.

(Re) Defining the High-Power Field for Digital Pathology

BACKGROUND

The microscope high-power field (HPF) is the cornerstone for histopathology diagnostic evaluation such as the quantification of mitotic figures, lymphocytes, and tumor grading. With traditional light microscopy, HPFs are typically evaluated by quantifying histologic events in 10 fields of view at × 400 magnification. In the era of digital pathology, new variables are introduced that may affect HPF evaluation. The aim of this study was to determine the parameters that influence HPF in whole slide images (WSIs).

MATERIALS AND METHODS

Glass slides scanned on various devices (Leica's Aperio GT450, AT2, and ScanScope XT; Philips UltraFast Scanner; Hamamatsu's Nanozoomer 2.0HT; and 3DHistech's P1000) were compared to acquired digital slides reviewed on each vendor's respective WSI viewer software (e.g., Aperio ImageScope, ImageScope DX, Philips IMS, 3DHistech CaseViewer, and Hamamatsu NDP.view) and an in-house developed vendor-agnostic viewer. WSIs were reviewed at "×40" equivalent HPF on different sized monitors with varying display resolutions (1900 × 1080-4500 × 3000) and aspect ratios (e.g., Food and Drug Administration [FDA]-cleared 27" Philips PS27QHDCR, FDA-cleared 24" Dell MR2416, 24" Hewlett Packard Z24n G2, and 28" Microsoft Surface Studio). Digital and microscopic HPF areas were calculated and compared.

RESULTS

A significant variation of HPF area occurred between differing monitor size and display resolutions with minor differences between WSI viewers. No differences were identified by scanner or WSIs scanned at different resolutions (e.g., 0.5, 0.25, 0.24, and 0.12 μm/pixel).

CONCLUSION

Glass slide HPF at × 400 magnification with conventional light microscopy was not equivalent to "×40" digital HPF areas. Digital HPF quantification may vary due to differences in the tissue area displayed by monitor sizes, display resolutions, and WSI viewers but not by scanner or scanning resolution. These findings will need to be further clinically validated with potentially new digital metrics for evaluation.

The Evolution of Our Understanding of the Biology of Cancer Is the Key to Avoiding Overdiagnosis and Overtreatment

There has been a tremendous evolution in our thinking about cancer since the 1880s. Breast cancer is a particularly good example to evaluate the progress that has been made and the new challenges that have arisen due to screening that inadvertently identifies indolent lesions. The degree to which overdiagnosis is a problem depends on the reservoir of indolent disease, the disease heterogeneity, and the fraction of the tumors that have aggressive biology. Cancers span the spectrum of biological behavior, and population-wide screening increases the detection of tumors that may not cause harm within the patient's lifetime or may never metastasize or result in death. Our approach to early detection will be vastly improved if we understand, address, and adjust to tumor heterogeneity. In this article, we use breast cancer as a case study to demonstrate how the approach to biological characterization, diagnostics, and therapeutics can inform our approach to screening, early detection, and prevention. Overdiagnosis can be mitigated by developing diagnostics to identify indolent disease, incorporating biology and risk assessment in screening strategies, changing the pathology rules for tumor classification, and refining the way we classify precancerous lesions. The more the patterns of cancers can be seen across other cancers, the more it is clear that our approach should transcend organ of origin. This will be particularly helpful in advancing the field by changing both our terminology for what is cancer and also by helping us to learn how best to mitigate the risk of the most aggressive cancers.See all articles in this CEBP Focus section, "NCI Early Detection Research Network: Making Cancer Detection Possible."

Assessment of tumour proliferation by use of the mitotic activity index, and Ki67 and phosphohistone H3 expression, in early-stage luminal breast cancer

AIMS

Phosphohistone H3 (PhH3) has been proposed as a novel proliferation marker in breast cancer. This study compares the interobserver agreement for assessment of the mitotic activity index (MAI), Ki67 expression, and PhH3 in a cohort of oestrogen receptor (ER)-positive breast cancer patients.

METHODS AND RESULTS

Tumour samples of 159 luminal breast cancer patients were collected. MAI and PhH3 scores were assessed by three breast cancer pathologists. Ki67 scores were assessed separately by two of the three pathologists. PhH3-positive cells were counted in an area of 2 mm2 , with a threshold of ≥13 positive cells being used to discriminate between low-proliferative and high-proliferative tumours. Ki67 expression was assessed with the global scoring method. Ki67 percentages of <20% were considered to be low. The intraclass correlation coefficient (ICC) and Cohen's κ statistics were used to evaluate interobserver agreement. The impact on histological grading of replacing the MAI with PhH3 was assessed. Counting PhH3-positive cells was highly reproducible among all three observers (ICC of 0.86). The κ scores for the categorical PhH3 count (κ = 0.78, κ = 0.68, and κ = 0.80) reflected substantial agreement among all observers, whereas agreement for the MAI (κ = 0.38, κ = 0.52, and κ = 0.26) and Ki67 (κ = 0.55) was fair to moderate. When PhH3 was used to determine the histological grade, agreement in grading increased (PhH3, κ = 0.52, κ = 0.48, and κ = 0.52; MAI, κ = 0.43, κ = 0.35, and κ = 0.32), and the proportion of grade III tumours increased (14%, 18%, and 27%).

CONCLUSION

PhH3 seems to outperform Ki67 and the MAI as a reproducible means to measure tumour proliferation in luminal-type breast cancer. Variation in the assessment of histological grade might be reduced by using PhH3, but would result in an increase in the proportion of high-grade cancers.

Mitotic count: A need for standardization

PURPOSE

The mitotic count (MC), number of mitosis per unit area, is a very important parameter frequently used for classification and grading of some tumors. Traditionally, the MC has been expressed in terms of number of mitoses per high power field. The size of the field of view can vary greatly among different microscopes. In order to avoid under or overestimation of mitotic count, a conversion needs to be made.

METHODS

A simple formula based on a simple rule of three has been devised to standardize the mitotic count to the reference area by multiplying the number of mitotic figures by a correction factor which has been calculated for the most frequently used microscopes and various common tumors.

RESULTS AND CONCLUSIONS

We propose this simple method, which involves only a single multiplication, to standardize the mitotic count to the reference area.

Prognostic Implication of Histopathologic Indicators in Salivary Duct Carcinoma: Proposal of a Novel Histologic Risk Stratification Model

Salivary duct carcinoma (SDC) is a rare, aggressive malignancy that histologically resembles high-grade mammary duct carcinoma. Because of the rarity of this entity, data verifying the association between histologic features and patient survival are limited. We conducted a comprehensive histologic review of 151 SDC cases and performed an analysis of the association between various histomorphologic parameters and the clinical outcome with the aim of developing a histologic risk stratification model that predicts the prognosis of SDC patients. A multivariate analysis revealed that prominent nuclear pleomorphism (overall survival [OS]: P=0.013; progression-free survival [PFS]: P=0.019), ≥30 mitoses/10 HPF (PFS: P=0.013), high tumor budding (OS: P=0.011; PFS: P<0.001), and high poorly differentiated clusters (OS: P<0.001; PFS: P<0.001) were independent prognostic factors. Patients with vascular invasion demonstrated a marginally significant association with shorter PFS (P=0.064) in a multivariate analysis. We proposed a 3-tier histologic risk stratification model based on the total number of positive factors among 4 prognostically relevant parameters (prominent nuclear pleomorphism, ≥30 mitoses/10 HPF, vascular invasion, and high poorly differentiated clusters). The OS and PFS of patients with low-risk (0 to 1 point) (23% of cases), intermediate-risk (2 to 3 points) (54% of cases), and high-risk (4 points) (23% of cases) tumors progressively deteriorated in this order (hazard ratio, 2.13 and 2.28, and 4.99 and 4.50, respectively; Ptrend<0.001). Our histologic risk stratification model could effectively predict patient survival and may be a useful aid to guide clinical decision-making in relation to the management of patients with SDC.

Abd El-bast S, A. Mohamed M, Swellam M. Clinical Impact of Oncomirs 221 and 222 on Breast Cancer Diagnosis

Background Dysregulation of miRNAs, non-coding RNAs of 18-25 ( ̴ 22nt), is a hallmark of malignancies among them is breast cancer. The present study aimed to investigate the expression levels of circulating oncomiRNAs (miRNA-221and miRNA-222) as a minimally non-invasive method for early detection of breast cancer as compared to tumor markers (CEA, CA15.3). Materials and methods MiRNA-221 and miRNA-222 expression levels were determined using quantitative real-time polymerase chain reaction (qPCR) in serum samples from three groups: primary breast cancer patients (n = 44), benign breast lesion patients (n = 25), and healthy individuals as control group (n = 19). Their diagnostic efficacy and relation with clinicopathological data were analyzed. Results MiRNA-221 and miRNA-222 expression and tumor markers reported significant increase in their mean levels in breast cancer group as compared to the benign breast lesions or control individuals. Among clinicopathological factors, miRs reported significant relation with pathological types, clinical staging, histological grading and hormonal status, while CEA and CA15.3 did not revealed significance with these factors. The diagnostic efficacy for investigated miRNAs was superior to tumor markers especially for detection of early stages and low grade tumors. Conclusion MiRNA-221 and miRNA-222 were superior over tumor markers for early detection of breast cancer especially those at high risk as primarybreast cancer patients with early stage or low grade tumors.

Deep learned tissue "fingerprints" classify breast cancers by ER/PR/Her2 status from H&E images

Because histologic types are subjective and difficult to reproduce between pathologists, tissue morphology often takes a back seat to molecular testing for the selection of breast cancer treatments. This work explores whether a deep-learning algorithm can learn objective histologic H&E features that predict the clinical subtypes of breast cancer, as assessed by immunostaining for estrogen, progesterone, and Her2 receptors (ER/PR/Her2). Translating deep learning to this and related problems in histopathology presents a challenge due to the lack of large, well-annotated data sets, which are typically required for the algorithms to learn statistically significant discriminatory patterns. To overcome this limitation, we introduce the concept of “tissue fingerprints,” which leverages large, unannotated datasets in a label-free manner to learn H&E features that can distinguish one patient from another. The hypothesis is that training the algorithm to learn the morphological differences between patients will implicitly teach it about the biologic variation between them. Following this training internship, we used the features the network learned, which we call “fingerprints,” to predict ER, PR, and Her2 status in two datasets. Despite the discovery dataset being relatively small by the standards of the machine learning community (n = 939), fingerprints enabled the determination of ER, PR, and Her2 status from whole slide H&E images with 0.89 AUC (ER), 0.81 AUC (PR), and 0.79 AUC (Her2) on a large, independent test set (n = 2531). Tissue fingerprints are concise but meaningful histopathologic image representations that capture biological information and may enable machine learning algorithms that go beyond the traditional ER/PR/Her2 clinical groupings by directly predicting theragnosis.

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.

A Novel Architecture to Classify Histopathology Images Using Convolutional Neural Networks

Histopathology is the study of tissue structure under the microscope to determine if the cells are normal or abnormal. Histopathology is a very important exam that is used to determine the patients’ treatment plan. The classification of histopathology images is very difficult to even an experienced pathologist, and a second opinion is often needed. Convolutional neural network (CNN), a particular type of deep learning architecture, obtained outstanding results in computer vision tasks like image classification. In this paper, we propose a novel CNN architecture to classify histopathology images. The proposed model consists of 15 convolution layers and two fully connected layers. A comparison between different activation functions was performed to detect the most efficient one, taking into account two different optimizers. To train and evaluate the proposed model, the publicly available PatchCamelyon dataset was used. The dataset consists of 220,000 annotated images for training and 57,000 unannotated images for testing. The proposed model achieved higher performance compared to the state-of-the-art architectures with an AUC of 95.46%.

Raman spectroscopy for rapid intra-operative margin analysis of surgically excised tumour specimens

Raman spectroscopy, a form of vibrational spectroscopy, has the ability to provide sensitive and specific biochemical analysis of tissue. This review article provides an in-depth analysis of the suitability of different Raman spectroscopy techniques in providing intra-operative margin analysis in a range of solid tumour pathologies. Surgical excision remains the primary treatment of a number of solid organ cancers. Incomplete excision of a tumour and positive margins on histopathological analysis is associated with a worse prognosis, the need for adjuvant therapies with significant side effects and a resulting financial burden. The provision of intra-operative margin analysis of surgically excised tumour specimens would be beneficial for a number of pathologies, as there are no widely adopted and accurate methods of margin analysis, beyond histopathology. The limitations of Raman spectroscopic studies to date are discussed and future work necessary to enable translation to clinical use is identified. We conclude that, although there remain a number of challenges in translating current techniques into a clinically effective tool, studies so far demonstrate that Raman Spectroscopy has the attributes to successfully perform highly accurate intra-operative margin analysis in a clinically relevant environment.

A qualitative transcriptional signature to reclassify histological grade of ER-positive breast cancer patients

Background

Histological grade (HG) is commonly adopted as a prognostic factor for ER-positive breast cancer patients. However, HG evaluation methods, such as the pathological Nottingham grading system, are highly subjective with only 50–85% inter-observer agreements. Specifically, the subjectivity in the pathological assignment of the intermediate grade (HG2) breast cancers, comprising of about half of breast cancer cases, results in uncertain disease outcomes prediction. Here, we developed a qualitative transcriptional signature, based on within-sample relative expression orderings (REOs) of gene pairs, to define HG1 and HG3 and reclassify pathologically-determined HG2 (denoted as pHG2) breast cancer patients.

Results

From the gene pairs with significantly stable REOs in pathologically-determined HG1 (denoted as pHG1) samples and reversely stable REOs in pathologically-determined HG3 (denoted as pHG3) samples, concordantly identified from seven datasets, we extracted a signature which could determine the HG state of samples through evaluating whether the within-sample REOs match with the patterns of the pHG1 REOs or pHG3 REOs. A sample was classified into the HG3 group if at least a half of the REOs of the 10 gene pairs signature within this sample voted for HG3; otherwise, HG1. Using four datasets including samples of early stage (I–II) ER-positive breast cancer patients who accepted surgery only, we validated that this signature was able to reclassify pHG2 patients into HG1 and HG3 groups with significantly different survival time. For the original pHG1 and pHG3 patients, the signature could also more accurately and objectively stratify them into distinct prognostic groups. And the up-regulated and down down-regulated genes in HG1 compared with HG3 involved in cell proliferation and extracellular signal transduction pathways respectively. By comparing with existing signatures, 10-GPS was with prognostic significance and was more aligned with survival of patients especially for pHG2 samples.

Conclusions

The transcriptional qualitative signature can provide an objective assessment of HG states of ER-positive breast cancer patients, especially for reclassifying patients with pHG2, to assist decision making on clinical therapy.

The Utility of Oncotype DX for Adjuvant Chemotherapy Treatment Decisions in Estrogen Receptor-positive, Human Epidermal Growth Factor Receptor 2-negative, Node-negative Breast Cancer

Introduction

Breast cancer is the most common cancer diagnosis in the UK. Recently, there has been a reduction in breast cancer-specific mortality and recurrence attributed, in part, to the delivery of adjuvant chemotherapy. The National Institute for Health and Care Excellence (NICE) recommends the use of genetic profiling with Oncotype DX (ODX) to guide decisions to offer adjuvant chemotherapy after surgery in intermediate-risk early breast cancer patients. This study aimed to evaluate the utility of ODX testing in routine clinical practice in a National Health Service (NHS) hospital. 

Methods

Consecutive early breast cancer patients, identified through the multidisciplinary team (MDT) records, treated in our institution over 12 months (October 2017-September 2018) were included. PREDICT and Nottingham prognostic index (NPI) scores (from online clinicopathological recurrence risk tools) were calculated for each patient, and ODX data obtained through Genomic Health, Inc. (Redwood City, California). Patients were divided into two groups, those that underwent ODX testing (ODX group) and those that did not (non-ODX group). Descriptive statistics were used to analyse patient and tumour characteristics. The Gaussian distribution of each data set was assessed using the Anderson-Darling test. For comparisons between patient groups, the non-parametric equivalent of the two-tailed t-test (Mann-Whitney) was used. Dichotomous variables (e.g. chemotherapy decisions) were compared using chi-squared tests.

Results

One-hundred thirty-three patients (mean age 62 years) treated for 152 early breast cancers, were included in the final analysis. Breast cancers in the ODX group were of greater median tumour size (24 vs 16 mm; P<0.0001) and higher median tumour grade (3 vs 2; P<0.0001). PREDICT scores (3 vs 1, P<0.0001) and NPI scores (3.40 vs 2.30, P<0.0001) for the ODX group were also significantly higher than the non-ODX group. A greater proportion of patients were offered chemotherapy in the ODX group (39.9% vs 6.9%, P<0.001). However, for the PREDICT-calculated intermediate-risk patients, ODX testing resulted in a lower proportion of patients being offered chemotherapy compared to the intermediate-risk patients who were not genetically profiled (54.5% vs 83.3%, P=0.3547), although this result was not statistically significant.

Conclusions

Patients selected for ODX testing were younger, with significantly higher-grade and larger-sized tumours compared to patients not selected for genetic profiling. ODX testing significantly impacted the delivery of chemotherapy, as the recurrence score generated through ODX testing guided the final decision.

CACTUS: cancer image annotating, calibrating, testing, understanding and sharing in breast cancer histopathology

Objective

Develop CACTUS (cancer image annotating, calibrating, testing, understanding and sharing) as a novel web application for image archiving, annotation, grading, distribution, networking and evaluation. This helps pathologists to avoid unintended mistakes leading to quality assurance, teaching and evaluation in anatomical pathology. Effectiveness of the tool has been demonstrated by assessing pathologists performance in the grading of breast carcinoma and by comparing inter/intra-observer assessment of grading criteria amongst pathologists reviewing digital breast cancer images. Reproducibility has been assessed by inter-observer (kappa statistics) and intra-observer (intraclass correlation coefficient) concordance rates.

Results

CACTUS has been evaluated using a surgical pathology application—the assessment of breast cancer grade. We used CACTUS to present standardized images to four pathologists of differing experience. They were asked to evaluate all images to determine their assessment of Nottingham grade of a series of breast carcinoma cases. For each image, they were asked for their overall grade impression. CACTUS helps and guides pathologists to improve disease diagnosis with higher confidence and thereby reduces their workload and bias. CACTUS can be useful for both disseminating anatomical pathology images for teaching, as well as for evaluating agreement amongst pathologists or against a gold standard for evaluation or quality assurance.

Role of some circulating MiRNAs on breast cancer diagnosis

Aberrant expression of miRNAs has a link with tumorgenesis and their deregulation is reported in biological fluids of cancer patients. Authors aimed to investigate the diagnostic role of miRNA-17-5p, miR-155 and miRNA-222 in serum samples from breast cancer patients (n = 80), benign breast patients (n = 40) and healthy individuals (n = 30) using quantitative real-time PCR technique. Median levels of investigated markers revealed significant increase in primary breast cancer followed by benign and control groups. Investigated miRNAs reported significant relation with clinical stages and histological grading, while only miRNA-17-5p showed significant relation with hormone receptors. When considering investigated miRNAs as compared to tumor marker, their sensitivities were superior over tumor markers for early diagnosis of breast cancer, detection of early stages and low grades breast cancer patients. In conclusion, detection of the miRNA-17-5p, miR-155 and miRNA-222 expression levels in serum samples is significant promising molecular markers for early breast cancer diagnosis.

Automated classification of histopathology images using transfer learning

Early and accurate diagnosis of diseases can often save lives. Diagnosis of diseases from tissue samples is done manually by pathologists. Diagnostics process is usually time consuming and expensive. Hence, automated analysis of tissue samples from histopathology images has critical importance for early diagnosis and treatment. The computer aided systems can improve the quality of diagnoses and give pathologists a second opinion for critical cases. In this study, a deep learning based transfer learning approach has been proposed to classify histopathology images automatically. Two well-known and current pre-trained convolutional neural network (CNN) models, ResNet-50 and DenseNet-161, have been trained and tested using color and grayscale images. The DenseNet-161 tested on grayscale images and obtained the best classification accuracy of 97.89%. Additionally, ResNet-50 pre-trained model was tested on the color images of the Kimia Path24 dataset and achieved the highest classification accuracy of 98.87%. According to the obtained results, it may be said that the proposed pre-trained models can be used for fast and accurate classification of histopathology images and assist pathologists in their daily clinical tasks.

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.

Quantitative nuclear histomorphometric features are predictive of Oncotype DX risk categories in ductal carcinoma in situ: preliminary findings

Background

Oncotype DX (ODx) is a 12-gene assay assessing the recurrence risk (high, intermediate, and low) of ductal carcinoma in situ (pre-invasive breast cancer), which guides clinicians regarding prescription of radiotherapy. However, ODx is expensive, time-consuming, and tissue-destructive. In addition, the actual prognostic meaning for the intermediate ODx risk category remains unclear.

Methods

In this work, we evaluated the ability of quantitative nuclear histomorphometric features extracted from hematoxylin and eosin-stained slide images of 62 ductal carcinoma in situ (DCIS) patients to distinguish between the corresponding ODx risk categories. The prognostic value of the identified image signature was further evaluated on an independent validation set of 30 DCIS patients in its ability to distinguish those DCIS patients who progressed to invasive carcinoma versus those who did not. Following nuclear segmentation and feature extraction, feature ranking strategies were employed to identify the most discriminating features between individual ODx risk categories. The selected features were then combined with machine learning classifiers to establish models to predict ODx risk categories. The model performance was evaluated using the average area under the receiver operating characteristic curve (AUC) using cross validation. In addition, an unsupervised clustering approach was also implemented to evaluate the ability of nuclear histomorphometric features to discriminate between the ODx risk categories.

Results

Features relating to spatial distribution, orientation disorder, and texture of nuclei were identified as most discriminating between the high ODx and the intermediate, low ODx risk categories. Additionally, the AUC of the most discriminating set of features for the different classification tasks was as follows: (1) high vs low ODx (0.68), (2) high vs. intermediate ODx (0.67), (3) intermediate vs. low ODx (0.57), (4) high and intermediate vs. low ODx (0.63), (5) high vs. low and intermediate ODx (0.66). Additionally, the unsupervised clustering resulted in intermediate ODx risk category patients being co-clustered with low ODx patients compared to high ODx.

Conclusion

Our results appear to suggest that nuclear histomorphometric features can distinguish high from low and intermediate ODx risk category patients. Additionally, our findings suggest that histomorphometric features for intermediate ODx were more similar to low ODx compared to high ODx risk category.

Digital Assessment of Stained Breast Tissue Images for Comprehensive Tumor and Microenvironment Analysis

Current histopathological diagnosis involves human expert interpretation of stained images for diagnosis. This process is prone to inter-observer variability, often leading to low concordance rates amongst pathologists across many types of tissues. Further, since structural features are mostly just defined for epithelial alterations during tumor progression, the use of associated stromal changes is limited. Here we sought to examine whether digital analysis of commonly used hematoxylin and eosin-stained images could provide precise and quantitative metrics of disease from both epithelial and stromal cells. We developed a convolutional neural network approach to identify epithelial breast cells from their microenvironment. Second, we analyzed the microenvironment to further observe different constituent cells using unsupervised clustering. Finally, we categorized breast cancer by the combined effects of stromal and epithelial inertia. Together, the work provides insight and evidence of cancer association for interpretable features from deep learning methods that provide new opportunities for comprehensive analysis of standard pathology images.

CXCL1 stimulates migration and invasion in ER‑negative breast cancer cells via activation of the ERK/MMP2/9 signaling axis

Chemokine (C‑X‑C motif) ligand 1 (CXCL1), a member of the CXC chemokine family, has been reported to be a critical factor in inflammatory diseases and tumor progression; however, its functions and molecular mechanisms in estrogen receptor α (ER)‑negative breast cancer (BC) remain largely unknown. The present study demonstrated that CXCL1 was upregulated in ER‑negative BC tissues and cell lines compared with ER‑positive tissues and cell lines. Treatment with recombinant human CXCL1 protein promoted ER‑negative BC cell migration and invasion in a dose‑dependent manner, and stimulated the activation of phosphorylated (p)‑ extracellular signal‑regulated kinase (ERK)1/2, but not p‑STAT3 or p‑AKT. Conversely, knockdown of CXCL1 in BC cells attenuated these effects. Additionally, CXCL1 increased the expression of matrix metalloproteinase (MMP)2/9 via the ERK1/2 pathway. Inhibition of MEK1/2 by its antagonist U0126 reversed the effects of CXCL1 on MMP2/9 expression. Furthermore, immunohistochemical analysis revealed a strong positive association between CXCL1 and p‑ERK1/2 expression levels in BC tissues. In conclusion, the present study demonstrated that CXCL1 is highly expressed in ER‑negative BC, and stimulates BC cell migration and invasion via the ERK/MMP2/9 pathway. Therefore, CXCL1 may serve as a potential therapeutic target in ER‑negative BC.

Clinical significance of blood-based miRNAs as diagnostic and prognostic nucleic acid markers in breast cancer: Comparative to conventional tumor markers

microRNAs (miRNAs) are implicated in carcinogenesis and their expression in biological fluids offer great potential as nucleic acid markers for cancer detection and progression. Authors investigated the expression level of miRNAs (miRNA-21, miRNA-126, and miRNA-155) to evaluate their role as diagnostic and prognostic markers for breast cancer compared with other commonly used protein-based markers (CEA and CA15-3). Serum samples from patients with breast cancer (n = 96), patients with benign breast lesion (n = 47), and healthy individuals (n = 39) were enrolled for detection of miRNA expression levels and protein-based tumor markers using fluorescent real-time quantitative polymerase chain reaction and enzyme-linked immunosorbent assay, respectively. Correlation among investigated markers with clinicopathological factors and clinical outcomes were determined. Expression of miRNA-21 and miRNA-155 revealed significant increases in patients with breast cancer compared with both benign and control groups, the same result was reported for tumor markers; on the other hand, miRNA-126 was significantly decreased in breast cancer group as compared with the other two groups. miRNA frequencies were significantly related to clinical staging and histological grading as compared with tumor markers. Patients with breast cancer with increased miRNA-21 and miRNA-155 and decreased miRNA-126 expressions had significantly worse disease-free survival, while only miRNA-21 and miRNA-126 showed poor OS (P< 0.005). In conclusion, investigated miRNAs were superior over tumor markers for the early stage of breast cancer especially those with high-risk factor and their assessment in blood facilitates their role as a potential prognostic molecular marker.

Predicting breast tumor proliferation from whole-slide images: The TUPAC16 challenge

Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is a highly subjective and labor-intensive task. Previous efforts to automate tumor proliferation assessment by image analysis only focused on mitosis detection in predefined tumor regions. However, in a real-world scenario, automatic mitosis detection should be performed in whole-slide images (WSIs) and an automatic method should be able to produce a tumor proliferation score given a WSI as input. To address this, we organized the TUmor Proliferation Assessment Challenge 2016 (TUPAC16) on prediction of tumor proliferation scores from WSIs. The challenge dataset consisted of 500 training and 321 testing breast cancer histopathology WSIs. In order to ensure fair and independent evaluation, only the ground truth for the training dataset was provided to the challenge participants. The first task of the challenge was to predict mitotic scores, i.e., to reproduce the manual method of assessing tumor proliferation by a pathologist. The second task was to predict the gene expression based PAM50 proliferation scores from the WSI. The best performing automatic method for the first task achieved a quadratic-weighted Cohen's kappa score of κ = 0.567, 95% CI [0.464, 0.671] between the predicted scores and the ground truth. For the second task, the predictions of the top method had a Spearman's correlation coefficient of r = 0.617, 95% CI [0.581 0.651] with the ground truth. This was the first comparison study that investigated tumor proliferation assessment from WSIs. The achieved results are promising given the difficulty of the tasks and weakly-labeled nature of the ground truth. However, further research is needed to improve the practical utility of image analysis methods for this task.

BreCaHAD: a dataset for breast cancer histopathological annotation and diagnosis

OBJECTIVES

Histopathological tissue analysis by a pathologist determines the diagnosis and prognosis of most tumors, such as breast cancer. To estimate the aggressiveness of cancer, a pathologist evaluates the microscopic appearance of a biopsied tissue sample based on morphological features which have been correlated with patient outcome.

DATA DESCRIPTION

This paper introduces a dataset of 162 breast cancer histopathology images, namely the breast cancer histopathological annotation and diagnosis dataset (BreCaHAD) which allows researchers to optimize and evaluate the usefulness of their proposed methods. The dataset includes various malignant cases. The task associated with this dataset is to automatically classify histological structures in these hematoxylin and eosin (H&E) stained images into six classes, namely mitosis, apoptosis, tumor nuclei, non-tumor nuclei, tubule, and non-tubule. By providing this dataset to the biomedical imaging community, we hope to encourage researchers in computer vision, machine learning and medical fields to contribute and develop methods/tools for automatic detection and diagnosis of cancerous regions in breast cancer histology images.