Novel image analysis approach for quantifying expression of nuclear proteins assessed by immunohistochemistry: application to measurement of oestrogen and progesterone receptor levels in breast cancer

Deep learning applications in breast cancer histopathological imaging: diagnosis, treatment, and prognosis

Breast cancer is the most common malignant tumor among women worldwide and remains one of the leading causes of death among women. Its incidence and mortality rates are continuously rising. In recent years, with the rapid advancement of deep learning (DL) technology, DL has demonstrated significant potential in breast cancer diagnosis, prognosis evaluation, and treatment response prediction. This paper reviews relevant research progress and applies DL models to image enhancement, segmentation, and classification based on large-scale datasets from TCGA and multiple centers. We employed foundational models such as ResNet50, Transformer, and Hover-net to investigate the performance of DL models in breast cancer diagnosis, treatment, and prognosis prediction. The results indicate that DL techniques have significantly improved diagnostic accuracy and efficiency, particularly in predicting breast cancer metastasis and clinical prognosis. Furthermore, the study emphasizes the crucial role of robust databases in developing highly generalizable models. Future research will focus on addressing challenges related to data management, model interpretability, and regulatory compliance, ultimately aiming to provide more precise clinical treatment and prognostic evaluation programs for breast cancer patients.

Artificial intelligence algorithm accurately assesses oestrogen receptor immunohistochemistry in metastatic breast cancer cytology specimens: A pilot study

OBJECTIVE

The Visiopharm artificial intelligence (AI) algorithm for oestrogen receptor (ER) immunohistochemistry (IHC) in whole slide images (WSIs) has been successfully validated in surgical pathology. This study aimed to assess its efficacy in cytology specimens.

METHODS

The study cohort comprised 105 consecutive cytology specimens with metastatic breast carcinoma. ER IHC WSIs were seamlessly integrated into the Visiopharm platform from the Image Management System (IMS) during our routine digital workflow, and an AI algorithm was employed for analysis. ER AI scores were compared with pathologists' manual consensus scores. Optimization steps were implemented and evaluated to reduce discordance.

RESULTS

The overall concordance between pathologists' scores and AI scores was excellent (99/105, 94.3%). Six cases exhibited discordant results, including two false-negative (FN) cases due to abundant histiocytes incorrectly counted as negatively stained tumour cells by AI, two FN cases owing to weak staining, and two false-positive (FP) cases where pigmented macrophages were erroneously counted as positively stained tumour cells by AI. The Pearson correlation coefficient of ER-positive percentages between pathologists' and AI scores was 0.8483. Optimization steps, such as lowering the cut-off threshold and additional training using higher input magnification, significantly improved accuracy.

CONCLUSIONS

The automated ER AI algorithm demonstrated excellent concordance with pathologists' assessments and accurately differentiated ER-positive from ER-negative metastatic breast carcinoma cytology cases. However, precision in identifying tumour cells in cytology specimens requires further enhancement.

Artificial Intelligence in Breast Cancer Diagnosis and Personalized Medicine

Breast cancer is a significant cause of cancer-related mortality in women worldwide. Early and precise diagnosis is crucial, and clinical outcomes can be markedly enhanced. The rise of artificial intelligence (AI) has ushered in a new era, notably in image analysis, paving the way for major advancements in breast cancer diagnosis and individualized treatment regimens. In the diagnostic workflow for patients with breast cancer, the role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction. Although its potential is immense, its complete integration into clinical practice is challenging. Particularly, these challenges include the imperatives for extensive clinical validation, model generalizability, navigating the "black-box" conundrum, and pragmatic considerations of embedding AI into everyday clinical environments. In this review, we comprehensively explored the diverse applications of AI in breast cancer care, underlining its transformative promise and existing impediments. In radiology, we specifically address AI in mammography, tomosynthesis, risk prediction models, and supplementary imaging methods, including magnetic resonance imaging and ultrasound. In pathology, our focus is on AI applications for pathologic diagnosis, evaluation of biomarkers, and predictions related to genetic alterations, treatment response, and prognosis in the context of breast cancer diagnosis and treatment. Our discussion underscores the transformative potential of AI in breast cancer management and emphasizes the importance of focused research to realize the full spectrum of benefits of AI in patient care.

Use of a Novel Deep Learning Open-Source Model for Quantification of Ki-67 in Breast Cancer Patients in Pakistan: A Comparative Study between the Manual and Automated Methods

Introduction: Breast cancer is the most common cancer in women; its early detection plays a crucial role in improving patient outcomes. Ki-67 is a biomarker commonly used for evaluating the proliferation of cancer cells in breast cancer patients. The quantification of Ki-67 has traditionally been performed by pathologists through a manual examination of tissue samples, which can be time-consuming and subject to inter- and intra-observer variability. In this study, we used a novel deep learning model to quantify Ki-67 in breast cancer in digital images prepared by a microscope-attached camera. Objective: To compare the automated detection of Ki-67 with the manual eyeball/hotspot method. Place and duration of study: This descriptive, cross-sectional study was conducted at the Jinnah Sindh Medical University. Glass slides of diagnosed cases of breast cancer were obtained from the Aga Khan University Hospital after receiving ethical approval. The duration of the study was one month. Methodology: We prepared 140 digital images stained with the Ki-67 antibody using a microscope-attached camera at 10×. An expert pathologist (P1) evaluated the Ki-67 index of the hotspot fields using the eyeball method. The images were uploaded to the DeepLiif software to detect the exact percentage of Ki-67 positive cells. SPSS version 24 was used for data analysis. Diagnostic accuracy was also calculated by other pathologists (P2, P3) and by AI using a Ki-67 cut-off score of 20 and taking P1 as the gold standard. Results: The manual and automated scoring methods showed a strong positive correlation as the kappa coefficient was significant. The p value was <0.001. The highest diagnostic accuracy, i.e., 95%, taking P1 as gold standard, was found for AI, compared to pathologists P2 and P3. Conclusions: Use of quantification-based deep learning models can make the work of pathologists easier and more reproducible. Our study is one of the earliest studies in this field. More studies with larger sample sizes are needed in future to develop a cohort.

Applications of Artificial Intelligence in Breast Pathology

CONTEXT.—

Increasing implementation of whole slide imaging together with digital workflow and advances in computing capacity enable the use of artificial intelligence (AI) in pathology, including breast pathology. Breast pathologists often face a significant workload, with diagnosis complexity, tedious repetitive tasks, and semiquantitative evaluation of biomarkers. Recent advances in developing AI algorithms have provided promising approaches to meet the demand in breast pathology.

OBJECTIVE.—

To provide an updated review of AI in breast pathology. We examined the success and challenges of current and potential AI applications in diagnosing and grading breast carcinomas and other pathologic changes, detecting lymph node metastasis, quantifying breast cancer biomarkers, predicting prognosis and therapy response, and predicting potential molecular changes.

DATA SOURCES.—

We obtained data and information by searching and reviewing literature on AI in breast pathology from PubMed and based our own experience.

CONCLUSIONS.—

With the increasing application in breast pathology, AI not only assists in pathology diagnosis to improve accuracy and reduce pathologists' workload, but also provides new information in predicting prognosis and therapy response.

Reliability of CD44, CD24, and ALDH1A1 immunohistochemical staining: Pathologist assessment compared to quantitative image analysis

Background

The data on the expression of stem cell markers CD44, CD24, and ALDH1A1 in the breast tissue of cancer-free women is very limited and no previous studies have explored the agreement between pathologist and computational assessments of these markers. We compared the immunohistochemical (IHC) expression assessment for CD44, CD24, and ALDH1A1 by an expert pathologist with the automated image analysis results and assessed the homogeneity of the markers across multiple cores pertaining to each woman.

Methods

We included 81 cancer-free women (399 cores) with biopsy-confirmed benign breast disease in the Nurses' Health Study (NHS) and NHSII cohorts. IHC was conducted with commercial antibodies [CD44 (Dako, Santa Clara, CA, USA) 1:25 dilution; CD24 (Invitrogen, Waltham, MA, USA) 1:200 dilution and ALDH1A1 (Abcam, Cambridge, United Kingdom) 1:300 dilution]. For each core, the percent positivity was quantified by the pathologist and Definiens Tissue Studio. Correlations between pathologist and computational scores were evaluated with Spearman correlation (for categorical positivity: 0, >0-<1, 1-10, >10-50, and >50%) and sensitivity/specificity (for binary positivity defined with 1 and 10% cut-offs), using the pathologist scores as the gold standard. Expression homogeneity was examined with intra-class correlation (ICC). Analyses were stratified by core [normal terminal duct-lobular units (TDLUs), benign lesions] and tissue type (epithelium, stroma).

Results

Spearman correlation between pathologist and Definiens ranged between 0.40-0.64 for stroma and 0.66-0.68 for epithelium in normal TDLUs cores and between 0.24-0.60 for stroma and 0.61-0.64 for epithelium in benign lesions. For stroma, sensitivity and specificity ranged between 0.92-0.95 and 0.24-0.60, respectively, with 1% cut-off and between 0.43-0.88 and 0.73-0.85, respectively, with 10% cut-off. For epithelium, 10% cut-off resulted in better estimates for both sensitivity and specificity. ICC between the cores was strongest for CD44 for both stroma and epithelium in normal TDLUs cores and benign lesions (range 0.74-0.80). ICC for CD24 and ALDH1A ranged between 0.42-0.63 and 0.44-0.55, respectively.

Conclusion

Our findings show that computational assessments for CD44, CD24, and ALDH1A1 exhibit variable correlations with manual assessment. These findings support the use of computational platforms for IHC evaluation of stem cell markers in large-scale epidemiologic studies. Pilot studies maybe also needed to determine appropriate cut-offs for defining staining positivity.

Computer-Assisted Annotation of Digital H&E/SOX10 Dual Stains Generates High-Performing Convolutional Neural Network for Calculating Tumor Burden in H&E-Stained Cutaneous Melanoma

Deep learning for the analysis of H&E stains requires a large annotated training set. This may form a labor-intensive task involving highly skilled pathologists. We aimed to optimize and evaluate computer-assisted annotation based on digital dual stains of the same tissue section. H&E stains of primary and metastatic melanoma (N = 77) were digitized, re-stained with SOX10, and re-scanned. Because images were aligned, annotations of SOX10 image analysis were directly transferred to H&E stains of the training set. Based on 1,221,367 annotated nuclei, a convolutional neural network for calculating tumor burden (CNN_TB) was developed. For primary melanomas, precision of annotation was 100% (95%CI, 99% to 100%) for tumor cells and 99% (95%CI, 98% to 100%) for normal cells. Due to low or missing tumor-cell SOX10 positivity, precision for normal cells was markedly reduced in lymph-node and organ metastases compared with primary melanomas (p < 0.001). Compared with stereological counts within skin lesions, mean difference in tumor burden was 6% (95%CI, -1% to 13%, p = 0.10) for CNN_TB and 16% (95%CI, 4% to 28%, p = 0.02) for pathologists. Conclusively, the technique produced a large annotated H&E training set with high quality within a reasonable timeframe for primary melanomas and subcutaneous metastases. For these lesion types, the training set generated a high-performing CNN_TB, which was superior to the routine assessments of pathologists.

Update on prognostic and predictive biomarkers of breast cancer

Breast cancer represents a heterogeneous group of human cancer at both histological and molecular levels. Estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor 2 (HER2) are the most commonly used biomarkers in clinical practice for making treatment plans for breast cancer patients by oncologists. Recently, PD-L1 testing plays an important role for immunotherapy for triple-negative breast cancer. With the increased understanding of the molecular characterization of breast cancer and the emergence of novel targeted therapies, more potential biomarkers are needed for the development of more personalized treatments. In this review, we summarized several main prognostic and predictive biomarkers in breast cancer at genomic, transcriptomic and proteomic levels, including hormone receptors, HER2, Ki67, multiple gene expression assays, PD-L1 testing, mismatch repair deficiency/microsatellite instability, tumor mutational burden, PIK3CA, ESR1 andNTRK and briefly introduced the roles of digital imaging analysis in breast biomarker evaluation.

Integrating and validating automated digital imaging analysis of estrogen receptor immunohistochemistry in a fully digital workflow for clinical use

Background

Design

Results

Conclusions

Immunohistochemistry scoring of breast tumor tissue microarrays: A comparison study across three software applications

Digital pathology can efficiently assess immunohistochemistry (IHC) data on tissue microarrays (TMAs). Yet, it remains important to evaluate the comparability of the data acquired by different software applications and validate it against pathologist manual interpretation. In this study, we compared the IHC quantification of 5 clinical breast cancer biomarkers-estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), epidermal growth factor receptor (EGFR), and cytokeratin 5/6 (CK5/6)-across 3 software applications (Definiens Tissue Studio, inForm, and QuPath) and benchmarked the results to pathologist manual scores. IHC expression for each marker was evaluated across 4 TMAs consisting of 935 breast tumor tissue cores from 367 women within the Nurses' Health Studies; each women contributing three 0.6-mm cores. The correlation and agreement between manual and software-derived results were primarily assessed using Spearman's ρ, percentage agreement, and area under the curve (AUC). At the TMA core-level, the correlations between manual and software-derived scores were the highest for HER2 (ρ ranging from 0.75 to 0.79), followed by ER (0.69-0.71), PR (0.67-0.72), CK5/6 (0.43-0.47), and EGFR (0.38-0.45). At the case-level, there were good correlations between manual and software-derived scores for all 5 markers (ρ ranging from 0.43 to 0.82), where QuPath had the highest correlations. Software-derived scores were highly comparable to each other (ρ ranging from 0.80 to 0.99). The average percentage agreements between manual and software-derived scores were excellent for ER (90.8%-94.5%) and PR (78.2%-85.2%), moderate for HER2 (65.4%-77.0%), highly variable for EGFR (48.2%-82.8%), and poor for CK5/6 (22.4%-45.0%). All AUCs across markers and software applications were ≥0.83. The 3 software applications were highly comparable to each other and to manual scores in quantifying these 5 markers. QuPath consistently produced the best performance, indicating this open-source software is an excellent alternative for future use.

Determination of the number of observers needed to evaluate a subjective test and its application in two PD-L1 studies

In pathological studies, subjective assays, especially companion diagnostic tests, can dramatically affect treatment of cancer. Binary diagnostic test results (ie, positive vs negative) may vary between pathologists or observers who read the tumor slides. Some tests have clearly defined criteria resulting in highly concordant outcomes, even with minimal training. Other tests are more challenging. Observers may achieve poor concordance even with training. While there are many statistically rigorous methods for measuring concordance between observers, we are unaware of a method that can identify how many observers are needed to determine whether a test can reach an acceptable concordance, if at all. Here we introduce a statistical approach to the assessment of test performance when the test is read by multiple observers, as would occur in the real world. By plotting the number of observers against the estimated overall agreement proportion, we can obtain a curve that plateaus to the average observer concordance. Diagnostic tests that are well-defined and easily judged show high concordance and plateau with few interobserver comparisons. More challenging tests do not plateau until many interobserver comparisons are made, and typically reach a lower plateau or even 0. We further propose a statistical test of whether the overall agreement proportion will drop to 0 with a large number of pathologists. The proposed analytical framework can be used to evaluate the difficulty in the interpretation of pathological test criteria and platforms, and to determine how pathology-based subjective tests will perform in the real world. The method could also be used outside of pathology, where concordance of a diagnosis or decision point relies on the subjective application of multiple criteria. We apply this method in two recent PD-L1 studies to test whether the curve of overall agreement proportion will converge to 0 and determine the minimal sufficient number of observers required to estimate the concordance plateau of their reads.

Artificial intelligence applied to breast pathology

The convergence of digital pathology and computer vision is increasingly enabling computers to perform tasks performed by humans. As a result, artificial intelligence (AI) is having an astoundingly positive effect on the field of pathology, including breast pathology. Research using machine learning and the development of algorithms that learn patterns from labeled digital data based on "deep learning" neural networks and feature-engineered approaches to analyze histology images have recently provided promising results. Thus far, image analysis and more complex AI-based tools have demonstrated excellent success performing tasks such as the quantification of breast biomarkers and Ki67, mitosis detection, lymph node metastasis recognition, tissue segmentation for diagnosing breast carcinoma, prognostication, computational assessment of tumor-infiltrating lymphocytes, and prediction of molecular expression as well as treatment response and benefit of therapy from routine H&E images. This review critically examines the literature regarding these applications of AI in the area of breast pathology.

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.

Best Practices for Technical Reproducibility Assessment of Multiplex Immunofluorescence

Multiplex immunofluorescence (mIF) tyramide signal amplification is a new and useful tool for the study of cancer that combines the staining of multiple markers in a single slide. Several technical requirements are important to performing high-quality staining and analysis and to obtaining high internal and external reproducibility of the results. This review manuscript aimed to describe the mIF panel workflow and discuss the challenges and solutions for ensuring that mIF panels have the highest reproducibility possible. Although this platform has shown high flexibility in cancer studies, it presents several challenges in pre-analytic, analytic, and post-analytic evaluation, as well as with external comparisons. Adequate antibody selection, antibody optimization and validation, panel design, staining optimization and validation, analysis strategies, and correct data generation are important for reproducibility and to minimize or identify possible issues during the mIF staining process that sometimes are not completely under our control, such as the tissue fixation process, storage, and cutting procedures.

Reliability of a computational platform as a surrogate for manually interpreted immunohistochemical markers in breast tumor tissue microarrays

BACKGROUND

Pathologist and computational assessments have been used to evaluate immunohistochemistry (IHC) in epidemiologic studies. We compared Definiens Tissue Studio® to pathologist scores for 17 markers measured in breast tumor tissue microarrays (TMAs) [AR, CD20, CD4, CD8, CD163, EPRS, ER, FASN, H3K27, IGF1R, IR, Ki67, phospho-mTOR, PR, PTEN, RXR, and VDR].

METHODS

5 914 Nurses' Health Study participants, diagnosed 1976-2006 (NHS) and 1989-2006 (NHS-II), were included. IHC was conducted by the Dana-Farber/Harvard Cancer Center Specialized Histopathology Laboratory. The percent of cells staining positive was assessed by breast pathologists. Definiens output was used to calculate a weighted average of percent of cells staining positive across TMA cores for each marker. Correlations between pathologist and computational scores were evaluated with Spearman correlation coefficients. Receiver-operator characteristic curves were constructed, using pathologist scores as comparison.

RESULTS

Spearman correlations between pathologist and Definiens assessments ranged from weak (RXR, rho=-0.05; CD163, rho = 0.10) to strong (Ki67, rho = 0.79; pmTOR, rho = 0.77). The area under the curve was >0.70 for all markers except RXR.

CONCLUSION

Our data indicate that computational assessments exhibit variable correlations with interpretations made by an expert pathologist, depending on the marker evaluated. This study provides evidence supporting the use of computational platforms for IHC evaluation in large-scale epidemiologic studies, with the caveat that pilot studies are necessary to investigate agreement with expert assessments. In sum, computational platforms may provide greater efficiency and facilitate high-throughput epidemiologic analyses.

An Image Analysis Solution For Quantification and Determination of Immunohistochemistry Staining Reproducibility

Supplemental Digital Content is available in the text.

With immunohistochemical (IHC) staining increasingly being used to guide clinical decisions, variability in staining quality and reproducibility are becoming essential factors in generating diagnoses using IHC tissue preparations. The current study tested a method to track and quantify the interrun, intrarun, and intersite variability of IHC staining intensity. Our hypothesis was that staining precision between laboratory sites, staining runs, and individual slides may be verified quantitatively, efficiently and effectively utilizing algorithm-based, automated image analysis. To investigate this premise, we tested the consistency of IHC staining in 40 routinely processed (formalin-fixed, paraffin-embedded) human tissues using 10 common antibiomarker antibodies on 2 Dako Omnis instruments at 2 locations (Carpinteria, CA: 30 m above sea level and Longmont, CO: 1500 m above sea level) programmed with identical, default settings and sample pretreatments. Digital images of IHC-labeled sections produced by a whole slide scanner were analyzed by a simple commercially available algorithm and compared with a board-certified veterinary pathologist’s semiquantitative scoring of staining intensity. The image analysis output correlated well with pathology scores but had increased sensitivity for discriminating subtle variations and providing reproducible digital quantification across sites as well as within and among staining runs at the same site. Taken together, our data indicate that digital image analysis offers an objective and quantifiable means of verifying IHC staining parameters as a part of laboratory quality assurance systems.

Artificial Intelligence & Tissue Biomarkers: Advantages, Risks and Perspectives for Pathology

Tissue Biomarkers are information written in the tissue and used in Pathology to recognize specific subsets of patients with diagnostic, prognostic or predictive purposes, thus representing the key elements of Personalized Medicine. The advent of Artificial Intelligence (AI) promises to further reinforce the role of Pathology in the scenario of Personalized Medicine: AI-based devices are expected to standardize the evaluation of tissue biomarkers and also to discover novel information, which would otherwise be ignored by human review, and use them to make specific predictions. In this review we will present how AI has been used to support Tissue Biomarkers evaluation in the specific field of Pathology, give an insight to the intriguing field of AI-based biomarkers and discuss possible advantages, risk and perspectives for Pathology.

Advances in tissue-based imaging: impact on oncology research and clinical practice

INTRODUCTION

Tissue-based imaging has emerged as a critical tool in translational cancer research and is rapidly gaining traction within a clinical context. Significant progress has been made in the digital pathology arena, particularly in respect of brightfield and fluorescent imaging. Critically, the cellular context of molecular alterations occurring at DNA, RNA, or protein level within tumor tissue is now being more fully appreciated. Moreover, the emergence of novel multi-marker imaging approaches can now provide unprecedented insights into the tumor microenvironment, including the potential interplay between various cell types.

AREAS COVERED

This review summarizes the recent developments within the field of tissue-based imaging, centering on the application of these approaches in oncology research and clinical practice.

EXPERT OPINION

Significant advances have been made in digital pathology during the last 10 years. These include the use of quantitative image analysis algorithms, predictive artificial intelligence (AI) on large datasets of H&E images, and quantification of fluorescence multiplexed tissue imaging data. We believe that new methodologies that can integrate AI-derived histologic data with omic data, together with other forms of imaging data (such as radiologic image data), will enhance our ability to deliver better diagnostics and treatment decisions to the cancer patient.

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.

Virtual Double Staining: A Digital Approach to Immunohistochemical Quantification of Estrogen Receptor Protein in Breast Carcinoma Specimens

Visual assessment of immunohistochemically detected estrogen receptor protein is prone to interobserver and intraobserver variation due to its subjective evaluation. The aim of this study was to validate a new image analysis system based on virtual double staining (VDS) by comparing visual and automated scorings of ER in tissue microarrays of breast carcinomas. Tissue microarrays were constructed of 112 consecutive resection specimens of breast carcinomas. Immunohistochemistry assays for ER and pancytokeratin was applied on separate serial sections. ER scoring was visually performed by 5 observers using the histoscore (H-score) method. The Visiopharm ER image analysis protocol (APP) software application using VDS technique was applied separating stromal cells from carcinoma and other epithelial cells based on the pancytokeratin reaction. Using color deconvolution, polynomial filters, and nuclear segmentation the APP determined the percentage of positive cells and their intensity, and calculated the resulting H-score. On the basis of 1% cutoff VDS was perfectly correlated with visual assessment (κ=1). Using H-score, a very high agreement between VDS and visual ER assessment was seen (R=0.950). Image analysis has the attributes to eliminate the shortcomings of visual ER evaluation by generating automated, reproducible, and objective results of ER assessment.

Collagen IV and laminin-1 expression in embryonic mouse lens using principal components analysis technique

Immunohistochemistry section staining is not always easy to interpret. Manual quantification of immunohistochemical staining is limited by the observer visual ability to detect changes in level staining. Hence, the quantification of immunostaining by means of digital image analysis allows us to measure accurately protein expression percentages in immunobiological stained tissues and ensures to overcome the visual limitations. We perform an experimental study to analyse the impact of folic acid (FA) deficiency into collagen IV and laminin-1 expression in the embryonic mouse lens. The study starts with microscope images of embryos mouse lens whose mothers fed a diet deficient in FA during 2 and 8 weeks. A principal component analysis (PCA) image processing is used to analyse these images coming from control and FA deficit groups. The method permits to define an index of over- or infraexpression of collagen IV and laminin-1 associated to different spatial organisation structures (PC processes). Additionally, it permits to determine in precise percentage the exact quantity of the overexpression or infraexpression and finally to comprehend molecular regionalisation and expression in both control and deficient groups. The results suggest that even with 2 weeks of deficit of FA the expression and distribution of both molecules is affected.

Apelin: A putative novel predictive biomarker for bevacizumab response in colorectal cancer

Bevacizumab (bvz) is currently employed as an anti-angiogenic therapy across several cancer indications. Bvz response heterogeneity has been well documented, with only 10-15% of colorectal cancer (CRC) patients benefitting in general. For other patients, clinical efficacy is limited and side effects are significant. This reinforces the need for a robust predictive biomarker of response. To identify such a biomarker, we performed a DNA microarray-based transcriptional profiling screen with primary endothelial cells (ECs) isolated from normal and tumour colon tissues. Thirteen separate populations of tumour-associated ECs and 10 of normal ECs were isolated using fluorescence-activated cell sorting. We hypothesised that VEGF-induced genes were overexpressed in tumour ECs; these genes could relate to bvz response and serve as potential predictive biomarkers. Transcriptional profiling revealed a total of 2,610 differentially expressed genes when tumour and normal ECs were compared. To explore their relation to bvz response, the mRNA expression levels of top-ranked genes were examined using quantitative PCR in 30 independent tumour tissues from CRC patients that received bvz in the adjuvant setting. These analyses revealed that the expression of MMP12 and APLN mRNA was significantly higher in bvz non-responders compared to responders. At the protein level, high APLN expression was correlated with poor progression-free survival in bvz-treated patients. Thus, high APLN expression may represent a novel predictive biomarker for bvz unresponsiveness.

Whole tumor section quantitative image analysis maximizes between-pathologists' reproducibility for clinical immunohistochemistry-based biomarkers

Pathologists have had increasing responsibility for quantitating immunohistochemistry (IHC) biomarkers with the expectation of high between-reader reproducibility due to clinical decision-making especially for patient therapy. Digital imaging-based quantitation of IHC clinical slides offers a potential aid for improvement; however, its clinical adoption is limited potentially due to a conventional field-of-view annotation approach. In this study, we implemented a novel solely morphology-based whole tumor section annotation strategy to maximize image analysis quantitation results between readers. We first compare the field-of-view image analysis annotation approach to digital and manual-based modalities across multiple clinical studies (~120 cases per study) and biomarkers (ER, PR, HER2, Ki-67, and p53 IHC) and then compare a subset of the same cases (~40 cases each from the ER, PR, HER2, and Ki-67 studies) using whole tumor section annotation approach to understand incremental value of all modalities. Between-reader results for each biomarker in relation to conventional scoring modalities showed similar concordance as manual read: ER field-of-view image analysis: 95.3% (95% CI 92.0-98.2%) vs digital read: 92.0% (87.8-95.8%) vs manual read: 94.9% (91.4-97.8%); PR field-of-view image analysis: 94.1% (90.3-97.2%) vs digital read: 94.0% (90.2-97.1%) vs manual read: 94.4% (90.9-97.2%); Ki-67 field-of-view image analysis: 86.8% (82.1-91.4%) vs digital read: 76.6% (70.9-82.2%) vs manual read: 85.6% (80.4-90.4%); p53 field-of-view image analysis: 81.7% (76.4-86.8%) vs digital read: 80.6% (75.0-86.0%) vs manual read: 78.8% (72.2-83.3%); and HER2 field-of-view image analysis: 93.8% (90.0-97.2%) vs digital read: 91.0 (86.6-94.9%) vs manual read: 87.2% (82.1-91.9%). Subset implementation and analysis on the same cases using whole tumor section image analysis approach showed significant improvement between pathologists over field-of-view image analysis and manual read (HER2 100% (97-100%), P=0.013 field-of-view image analysis and 0.013 manual read; Ki-67 100% (96.9-100%), P=0.040 and 0.012; ER 98.3% (94.1-99.5%), p=0.232 and 0.181; and PR 96.6% (91.5-98.7%), p=0.012 and 0.257). Overall, whole tumor section image analysis significantly improves between-pathologist's reproducibility and is the optimal approach for clinical-based image analysis algorithms.

AutoIHC-scoring: a machine learning framework for automated Allred scoring of molecular expression in ER- and PR-stained breast cancer tissue

In prognostic evaluation of breast cancer Immunohistochemical (IHC) markers namely, oestrogen receptor (ER) and progesterone receptor (PR) are widely used. The expert pathologist investigates qualitatively the stained tissue slide under microscope to provide the Allred score; which is clinically used for therapeutic decision making. Such qualitative judgment is time-consuming, tedious and more often suffers from interobserver variability. As a result, it leads to imprecise IHC score for ER and PR. To overcome this, there is an urgent need of developing a reliable and efficient IHC quantifier for high throughput decision making. In view of this, our study aims at developing an automated IHC profiler for quantitative assessment of ER and PR molecular expression from stained tissue images. We propose here to use CMYK colour space for positively and negatively stained cell extraction for proportion score. Also colour features are used for quantitative assessment of intensity scoring among the positively stained cells. Five different machine learning models namely artificial neural network, Naïve Bayes, K-nearest neighbours, decision tree and random forest are considered for learning the colour features using average red, green and blue pixel values of positively stained cell patches. Fifty cases of ER- and PR-stained tissues have been evaluated for validation with the expert pathologist's score. All five models perform adequately where random forest shows the best correlation with the expert's score (Pearson's correlation coefficient = 0.9192). In the proposed approach the average variation of diaminobenzidine (DAB) to nuclear area from the expert's score is found to be 7.58%, as compared to 27.83% for state-of-the-art ImmunoRatio software.

Comprehensive DNA methylation study identifies novel progression-related and prognostic markers for cutaneous melanoma

BACKGROUND

Cutaneous melanoma is the deadliest skin cancer, with an increasing incidence and mortality rate. Currently, staging of patients with primary melanoma is performed using histological biomarkers such as tumor thickness and ulceration. As disruption of the epigenomic landscape is recognized as a widespread feature inherent in tumor development and progression, we aimed to identify novel biomarkers providing additional clinical information over current factors using unbiased genome-wide DNA methylation analyses.

METHODS

We performed a comprehensive DNA methylation analysis during all progression stages of melanoma using Infinium HumanMethylation450 BeadChips on a discovery cohort of benign nevi (n = 14) and malignant melanoma from both primary (n = 33) and metastatic (n = 28) sites, integrating the DNA methylome with gene expression data. We validated the discovered biomarkers in three independent validation cohorts by pyrosequencing and immunohistochemistry.

RESULTS

We identified and validated biomarkers for, and pathways involved in, melanoma development (e.g., HOXA9 DNA methylation) and tumor progression (e.g., TBC1D16 DNA methylation). In addition, we determined a prognostic signature with potential clinical applicability and validated PON3 DNA methylation and OVOL1 protein expression as biomarkers with prognostic information independent of tumor thickness and ulceration.

CONCLUSIONS

Our data underscores the importance of epigenomic regulation in triggering metastatic dissemination through the inactivation of central cancer-related pathways. Inactivation of cell-adhesion and differentiation unleashes dissemination, and subsequent activation of inflammatory and immune system programs impairs anti-tumoral defense pathways. Moreover, we identify several markers of tumor development and progression previously unrelated to melanoma, and determined a prognostic signature with potential clinical utility.

Trichinella Spiralis Impact on Mesenchymal Stem Cells: Immunohistochemical Study by Image Analyzer in Murine Model

This study aims to elucidate whether Trichinella spiralis infection or its crude antigen administration can stimulate recruitment of CD105^+ve/CD45^-ve cells that could represent MSCs in intestine and skeletal muscle of experimental BALB/c albino mice compared to healthy control mice. Studied mice were divided into: 20 healthy control, 20 with orally induced T. spiralis infection, 20 received adult worm crude antigen orally and 20 received larval crude antigen intramuscular. According to specific timing schedule, mice were sacrificed and tissue sections were examined for CD105 and CD45 immunohistochemical expression using image J image analyzing software, to compare different study groups. T. spiralis infection induced a significant increase in density of CD105^+ve/CD45^-ve cells that could represent MSCs in both intestinal and muscle sections, similarly the intramuscular injected larval crude antigen caused more infiltration of such cells in muscles compared to muscle sections from healthy control mice. However, no significant difference was noticed in intestinal sections after oral adult crude antigen administration compared to healthy control mice. So, injected T. spiralis crude antigen might be a successful stimulant to MSCs attraction and recruitment in tissues nearby injection site. This could be beneficial for cell regeneration and tissue repair in case of presence of a disease induced damage.

Image Analysis in Surgical Pathology

Digitization of glass slides of surgical pathology samples facilitates a number of value-added capabilities beyond what a pathologist could previously do with a microscope. Image analysis is one of the most fundamental opportunities to leverage the advantages that digital pathology provides. The ability to quantify aspects of a digital image is an extraordinary opportunity to collect data with exquisite accuracy and reliability. In this review, we describe the history of image analysis in pathology and the present state of technology processes as well as examples of research and clinical use.

Aldo-Keto Reductase AKR1C1-AKR1C4: Functions, Regulation, and Intervention for Anti-cancer Therapy

Aldo-keto reductases comprise of AKR1C1-AKR1C4, four enzymes that catalyze NADPH dependent reductions and have been implicated in biosynthesis, intermediary metabolism, and detoxification. Recent studies have provided evidences of strong correlation between the expression levels of these family members and the malignant transformation as well as the resistance to cancer therapy. Mechanistically, most studies focus on the catalytic-dependent function of AKR1C isoforms, like their impeccable roles in prostate cancer, breast cancer, and drug resistance due to the broad substrates specificity. However, accumulating clues showed that catalytic-independent functions also played critical roles in regulating biological events. This review summarizes the catalytic-dependent and -independent roles of AKR1Cs, as well as the small molecule inhibitors targeting these family members.

Validation of immunoexpression of tenascin-C in oral precancerous and cancerous tissues using ImageJ analysis with novel immunohistochemistry profiler plugin: An immunohistochemical quantitative analysis

BACKGROUND

Immunohistochemistry (IHC) is a molecular technique that has grown tremendously over the years. However, the assessment is only qualitative which is subjective and causes errors. Due to this limitation, several excellent markers have not gained importance and reached clinical trials. Hence, we aimed to quantify IHC by ImageJ analysis with a novel IHC profiler plugin. ImageJ has not been tried in oral precancerous tissues with minimal attempt for matrix markers.

AIM

This study aimed to validate the quantification of immunoexpression of tenascin-C (TN-C) in oral precancerous tissues and oral squamous cell carcinoma (OSCC) using ImageJ software with IHC profiler plugin.

MATERIALS AND METHODS

After IHC staining for TN-C and image acquisition, ImageJ analysis was performed as per the standard recommended algorithm. Assessment was done by two observers by blinding the histopathological diagnosis. The immunoscore was assessed for interobserver variability using Kohen's kappa statistics.

RESULTS

All our cases were in agreement and found to be statistically significant with P < 0.005. Moderate agreement was for mild dysplasia, moderate dysplasia and oral lichen planus. Substantial agreement was for oral submucous fibrosis and OSCC and almost perfect agreement noted for cases of severe dysplasia.

CONCLUSION

IHC can now be quantified using freely downloadable software ImageJ analysis in oral precancerous tissues and OSCC. This software with good threshold control can quantify matrix marker such as TN-C. Hence, herewith, we propose that IHC markers should be quantified using ImageJ by our entire oral pathology fraternity so as to have a standard immunoscore for all markers.

Low Ki67/high ATM protein expression in malignant tumors predicts favorable prognosis in a retrospective study of early stage hormone receptor positive breast cancer

INTRODUCTION

This study was designed to investigate the combined influence of ATM and Ki67 on clinical outcome in early stage hormone receptor positive breast cancer (ES-HPBC), particularly in patients with smaller tumors (< 4 cm) and fewer than four positive lymph nodes.

METHODS

532 formalin-fixed paraffin-embedded specimens of resected primary breast tumors were used to construct a tissue microarray. Samples from 297 patients were suitable for final statistical analysis. We detected ATM and Ki67 proteins using fluorescence and brightfield immunohistochemistry respectively, and quantified their expression with digital image analysis. Data on expression levels were subsequently correlated with clinical outcome.

RESULTS

Remarkably, ATM expression was useful to stratify the low Ki67 group into subgroups with better or poorer prognosis. Specifically, in the low Ki67 subgroup defined as having smaller tumors and no positive nodes, patients with high ATM expression showed better outcome than those with low ATM, with estimated survival rates of 96% and 89% respectively at 15 years follow up (p = 0.04). Similarly, low-Ki67 patients with smaller tumors, 1-3 positive nodes and high ATM also had significantly better outcomes than their low ATM counterparts, with estimated survival rates of 88% and 46% respectively (p = 0.03) at 15 years follow up. Multivariable analysis indicated that the combination of high ATM and low Ki67 is prognostic of improved survival, independent of tumor size, grade, and lymph node status (p = 0.02).

CONCLUSIONS

These data suggest that the prognostic value of Ki67 can be improved by analyzing ATM expression in ES-HPBC.

Computer-based image analysis in breast pathology

Whole slide imaging (WSI) has the potential to be utilized in telepathology, teleconsultation, quality assurance, clinical education, and digital image analysis to aid pathologists. In this paper, the potential added benefits of computer-assisted image analysis in breast pathology are reviewed and discussed. One of the major advantages of WSI systems is the possibility of doing computer-based image analysis on the digital slides. The purpose of computer-assisted analysis of breast virtual slides can be (i) segmentation of desired regions or objects such as diagnostically relevant areas, epithelial nuclei, lymphocyte cells, tubules, and mitotic figures, (ii) classification of breast slides based on breast cancer (BCa) grades, the invasive potential of tumors, or cancer subtypes, (iii) prognosis of BCa, or (iv) immunohistochemical quantification. While encouraging results have been achieved in this area, further progress is still required to make computer-based image analysis of breast virtual slides acceptable for clinical practice.

Continuous measurement of breast tumour hormone receptor expression: a comparison of two computational pathology platforms

AIMS

Computational pathology platforms incorporate digital microscopy with sophisticated image analysis to permit rapid, continuous measurement of protein expression. We compared two computational pathology platforms on their measurement of breast tumour oestrogen receptor (ER) and progesterone receptor (PR) expression.

METHODS

Breast tumour microarrays from the Nurses' Health Study were stained for ER (n=592) and PR (n=187). One expert pathologist scored cases as positive if ≥1% of tumour nuclei exhibited stain. ER and PR were then measured with the Definiens Tissue Studio (automated) and Aperio Digital Pathology (user-supervised) platforms. Platform-specific measurements were compared using boxplots, scatter plots and correlation statistics. Classification of ER and PR positivity by platform-specific measurements was evaluated with areas under receiver operating characteristic curves (AUC) from univariable logistic regression models, using expert pathologist classification as the standard.

RESULTS

Both platforms showed considerable overlap in continuous measurements of ER and PR between positive and negative groups classified by expert pathologist. Platform-specific measurements were strongly and positively correlated with one another (r≥0.77). The user-supervised Aperio workflow performed slightly better than the automated Definiens workflow at classifying ER positivity (AUC_Aperio=0.97; AUC_Definiens=0.90; difference=0.07, 95% CI 0.05 to 0.09) and PR positivity (AUC_Aperio=0.94; AUC_Definiens=0.87; difference=0.07, 95% CI 0.03 to 0.12).

CONCLUSIONS

Paired hormone receptor expression measurements from two different computational pathology platforms agreed well with one another. The user-supervised workflow yielded better classification accuracy than the automated workflow. Appropriately validated computational pathology algorithms enrich molecular epidemiology studies with continuous protein expression data and may accelerate tumour biomarker discovery.

High-throughput automated scoring of Ki67 in breast cancer tissue microarrays from the Breast Cancer Association Consortium

Automated methods are needed to facilitate high-throughput and reproducible scoring of Ki67 and other markers in breast cancer tissue microarrays (TMAs) in large-scale studies. To address this need, we developed an automated protocol for Ki67 scoring and evaluated its performance in studies from the Breast Cancer Association Consortium. We utilized 166 TMAs containing 16,953 tumour cores representing 9,059 breast cancer cases, from 13 studies, with information on other clinical and pathological characteristics. TMAs were stained for Ki67 using standard immunohistochemical procedures, and scanned and digitized using the Ariol system. An automated algorithm was developed for the scoring of Ki67, and scores were compared to computer assisted visual (CAV) scores in a subset of 15 TMAs in a training set. We also assessed the correlation between automated Ki67 scores and other clinical and pathological characteristics. Overall, we observed good discriminatory accuracy (AUC = 85%) and good agreement (kappa = 0.64) between the automated and CAV scoring methods in the training set. The performance of the automated method varied by TMA (kappa range= 0.37-0.87) and study (kappa range = 0.39-0.69). The automated method performed better in satisfactory cores (kappa = 0.68) than suboptimal (kappa = 0.51) cores (p-value for comparison = 0.005); and among cores with higher total nuclei counted by the machine (4,000-4,500 cells: kappa = 0.78) than those with lower counts (50-500 cells: kappa = 0.41; p-value = 0.010). Among the 9,059 cases in this study, the correlations between automated Ki67 and clinical and pathological characteristics were found to be in the expected directions. Our findings indicate that automated scoring of Ki67 can be an efficient method to obtain good quality data across large numbers of TMAs from multicentre studies. However, robust algorithm development and rigorous pre- and post-analytical quality control procedures are necessary in order to ensure satisfactory performance.

Validation of the IHC4 Breast Cancer Prognostic Algorithm Using Multiple Approaches on the Multinational TEAM Clinical Trial

CONTEXT

Hormone receptors HER2/neu and Ki-67 are markers of residual risk in early breast cancer. An algorithm (IHC4) combining these markers may provide additional information on residual risk of recurrence in patients treated with hormone therapy.

OBJECTIVE

To independently validate the IHC4 algorithm in the multinational Tamoxifen Versus Exemestane Adjuvant Multicenter Trial (TEAM) cohort, originally developed on the trans-ATAC (Arimidex, Tamoxifen, Alone or in Combination Trial) cohort, by comparing 2 methodologies.

DESIGN

The IHC4 biomarker expression was quantified on TEAM cohort samples (n = 2919) by using 2 independent methodologies (conventional 3,3'-diaminobezidine [DAB] immunohistochemistry with image analysis and standardized quantitative immunofluorescence [QIF] by AQUA technology). The IHC4 scores were calculated by using the same previously established coefficients and then compared with recurrence-free and distant recurrence-free survival, using multivariate Cox proportional hazards modeling.

RESULTS

The QIF model was highly significant for prediction of residual risk (P < .001), with continuous model scores showing a hazard ratio (HR) of 1.012 (95% confidence interval [95% CI]: 1.010-1.014), which was significantly higher than that for the DAB model (HR: 1.008, 95% CI: 1.006-1.009); P < .001). Each model added significant prognostic value in addition to recognized clinical prognostic factors, including nodal status, in multivariate analyses. Quantitative immunofluorescence, however, showed more accuracy with respect to overall residual risk assessment than the DAB model.

CONCLUSIONS

The use of the IHC4 algorithm was validated on the TEAM trial for predicting residual risk in patients with breast cancer. These data support the use of the IHC4 algorithm clinically, but quantitative and standardized approaches need to be used.

Decrease of miR-146a is associated with the aggressiveness of human oral squamous cell carcinoma

With the aim to identify microRNAs that may contribute to oral squamous cell carcinoma (OSCC) progression, we compared the microRNA expression profiles of two related cell lines that form tumors with differential aggressiveness. A panel of 28 microRNAs was found to be more than 1.5-fold altered, among which miR-146a was the most significantly changed (-4.6-fold). Loss of miR-146a expression was validated in human high-grade tumors, while normal oral mucosa retained expression, using fluorescence in situ hybridization on a tissue microarray. Restoration of miR-146a in SCC25 and UMSCC1 cells decreased in vitro invasive activity, suppressed tumor growth in vivo, and decreased the incidence of UMSCC1 lung metastasis. The transcription factor Sox2 was found to be a putative target of miR-146a. In conclusion, the loss or decrease of miR-146a is a new feature that is associated with more aggressive behaviour in oral squamous carcinoma.

Using Pharmacokinetic Profiles and Digital Quantification of Stained Tissue Microarrays as a Medium-Throughput, Quantitative Method for Measuring the Kinetics of Early Signaling Changes Following Integrin-Linked Kinase Inhibition in an In Vivo Model of Cancer

A small molecule inhibitor (QLT0267) targeting integrin-linked kinase is able to slow breast tumor growth in vivo; however, the mechanism of action remains unknown. Understanding how targeting molecules involved in intersecting signaling pathways impact disease is challenging. To facilitate this understanding, we used tumor tissue microarrays (TMA) and digital image analysis for quantification of immunohistochemistry (IHC) in order to investigate how QLT0267 affects signaling pathways in an orthotopic model of breast cancer over time. Female NCR nude mice were inoculated with luciferase-positive human breast tumor cells (LCC6^Luc) and tumor growth was assessed by bioluminescent imaging (BLI). The plasma levels of QLT0267 were determined by LC-MS/MS methods following oral dosing of QLT0267 (200 mg/kg). A TMA was constructed using tumor tissue collected at 2, 4, 6, 24, 78 and 168 hr after treatment. IHC methods were used to assess changes in ILK-related signaling. The TMA was digitized, and Aperio ScanScope and ImageScope software were used to provide semi-quantitative assessments of staining levels. Using medium-throughput IHC quantitation, we show that ILK targeting by QLT0267 in vivo influences tumor physiology through transient changes in pathways involving AKT, GSK-3 and TWIST accompanied by the translocation of the pro-apoptotic protein BAD and an increase in Caspase-3 activity.

Breast cancer histopathology image analysis: a review

This paper presents an overview of methods that have been proposed for the analysis of breast cancer histopathology images. This research area has become particularly relevant with the advent of whole slide imaging (WSI) scanners, which can perform cost-effective and high-throughput histopathology slide digitization, and which aim at replacing the optical microscope as the primary tool used by pathologist. Breast cancer is the most prevalent form of cancers among women, and image analysis methods that target this disease have a huge potential to reduce the workload in a typical pathology lab and to improve the quality of the interpretation. This paper is meant as an introduction for nonexperts. It starts with an overview of the tissue preparation, staining and slide digitization processes followed by a discussion of the different image processing techniques and applications, ranging from analysis of tissue staining to computer-aided diagnosis, and prognosis of breast cancer patients.

Performance of automated scoring of ER, PR, HER2, CK5/6 and EGFR in breast cancer tissue microarrays in the Breast Cancer Association Consortium

Breast cancer risk factors and clinical outcomes vary by tumour marker expression. However, individual studies often lack the power required to assess these relationships, and large-scale analyses are limited by the need for high throughput, standardized scoring methods. To address these limitations, we assessed whether automated image analysis of immunohistochemically stained tissue microarrays can permit rapid, standardized scoring of tumour markers from multiple studies. Tissue microarray sections prepared in nine studies containing 20 263 cores from 8267 breast cancers stained for two nuclear (oestrogen receptor, progesterone receptor), two membranous (human epidermal growth factor receptor 2 and epidermal growth factor receptor) and one cytoplasmic (cytokeratin 5/6) marker were scanned as digital images. Automated algorithms were used to score markers in tumour cells using the Ariol system. We compared automated scores against visual reads, and their associations with breast cancer survival. Approximately 65-70% of tissue microarray cores were satisfactory for scoring. Among satisfactory cores, agreement between dichotomous automated and visual scores was highest for oestrogen receptor (Kappa = 0.76), followed by human epidermal growth factor receptor 2 (Kappa = 0.69) and progesterone receptor (Kappa = 0.67). Automated quantitative scores for these markers were associated with hazard ratios for breast cancer mortality in a dose-response manner. Considering visual scores of epidermal growth factor receptor or cytokeratin 5/6 as the reference, automated scoring achieved excellent negative predictive value (96-98%), but yielded many false positives (positive predictive value = 30-32%). For all markers, we observed substantial heterogeneity in automated scoring performance across tissue microarrays. Automated analysis is a potentially useful tool for large-scale, quantitative scoring of immunohistochemically stained tissue microarrays available in consortia. However, continued optimization, rigorous marker-specific quality control measures and standardization of tissue microarray designs, staining and scoring protocols is needed to enhance results.

Effects of tissue decalcification on the quantification of breast cancer biomarkers by digital image analysis

Background

Recent technical advances in digital image capture and analysis greatly improve the measurement of protein expression in tissues. Breast cancer biomarkers provide a unique opportunity to utilize digital image analysis to evaluate sources of variability that are caused by the tissue preparation, in particular the decalcification treatment associated with the analysis of bone metastatic breast cancer, and to develop methods for comparison of digital data and categorical scores rendered by pathologists.

Methods

Tissues were prospectively decalcified for up to 24 hours and stained by immunohistochemistry (IHC) for ER, PR, Ki-67 and p53. HER2 positive breast cancer sections were retrieved from the pathology archives, and annotated with the categorical HER2 expression scores from the pathology reports. Digital images were captured with Leica and Aperio slide scanners. The conversion of the digital to categorical scores was accomplished with a Gaussian mixture model and tested for accuracy by comparison to clinical scores.

Results

We observe significant effects of the decalcification treatment on common breast cancer biomarkers that are used in the clinic. ER, PR and p53 staining intensities decreased 15 – 20%, whereas Ki-67 decreased > 90% during the first 6 hrs of treatment and stabilized thereafter. In comparison with the Aperio images, pixel intensities generated by the Leica system are lower. A novel statistical model for conversion of digital to categorical scores provides a systematic approach for conversion of nuclear and membrane stains and demonstrated a high concordance with clinical scores.

Conclusion

Digital image analysis greatly improves the quantification of protein expression in human tissues. Decalcification affects the accuracy of immunohistochemical staining results and cannot be reversed by image analysis. Measurement data obtained on a continuous scoring scale can be converted to categorical scores for comparison with categorical dataset that are generated by pathologists.

Virtual Slides

The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/13000_2014_213

Electronic supplementary material

The online version of this article (doi:10.1186/s13000-014-0213-9) contains supplementary material, which is available to authorized users.

Development of a computational high-throughput tool for the quantitative examination of dose-dependent histological features

High-resolution digitalizing of histology slides facilitates the development of computational alternatives to manual quantitation of features of interest. We developed a MATLAB-based quantitative histological analysis tool (QuHAnT) for the high-throughput assessment of distinguishable histological features. QuHAnT validation was demonstrated by comparison with manual quantitation using liver sections from mice orally gavaged with sesame oil vehicle or 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD; 0.001-30 μg/kg) every 4 days for 28 days, which elicits hepatic steatosis with mild fibrosis. A quality control module of QuHAnT reduced the number of quantifiable Oil Red O (ORO)-stained images from 3,123 to 2,756. Increased ORO staining was measured at 10 and 30 μg/kg TCDD with a high correlation between manual and computational volume densities (Vv ), although the dynamic range of QuHAnT was 10-fold greater. Additionally, QuHAnT determined the size of each ORO vacuole, which could not be accurately quantitated by visual examination or manual point counting. PicroSirius Red quantitation demonstrated superior collagen deposition detection due to the ability to consider all images within each section. QuHAnT dramatically reduced analysis time and facilitated the comprehensive assessment of features improving accuracy and sensitivity and represents a complementary tool for tissue/cellular features that are difficult and tedious to assess via subjective or semiquantitative methods.

Circadian rhythm reprogramming during lung inflammation

Circadian rhythms are known to regulate immune responses in healthy animals, but it is unclear whether they persist during acute illnesses where clock gene expression is disrupted by systemic inflammation. Here, we use a genome-wide approach to investigate circadian gene and metabolite expression in the lungs of endotoxemic mice and find that novel cellular and molecular circadian rhythms are elicited in this setting. The endotoxin-specific circadian program exhibits unique features, including a divergent group of rhythmic genes and metabolites compared to the basal state and a distinct periodicity and phase distribution. At the cellular level endotoxin treatment also alters circadian rhythms of leukocyte counts within the lung in a bmal1-dependent manner, such that granulocytes rather than lymphocytes become the dominant oscillating cell type. Our results show that inflammation produces a complex reorganization of cellular and molecular circadian rhythms that are relevant to early events in lung injury.

Global DNA methylation is altered by neoadjuvant chemoradiotherapy in rectal cancer and may predict response to treatment - A pilot study

AIM

In rectal cancer, not all tumours display a response to neoadjuvant treatment. An accurate predictor of response does not exist to guide patient-specific treatment. DNA methylation is a distinctive molecular pathway in colorectal carcinogenesis. Whether DNA methylation is altered by neoadjuvant treatment and a potential response predictor is unknown. We aimed to determine whether DNA methylation is altered by neoadjuvant chemoradiotherapy (CRT) and to determine its role in predicting response to treatment.

PATIENTS AND METHODS

Fifty-three (n = 53) patients with locally advanced rectal cancers treated with neoadjuvant CRT followed by surgery were identified from the pathology databases of 2 tertiary referral centres over a 4-year period. Immunohistochemical staining of treatment specimens was carried out using the 5-Methylcytidine (Eurogentec, Seraing, Belgium) antibody. Quantitative analysis of staining was performed using an automated image analysis platform. The modified tumour regression grading system was used to assess tumour response to neoadjuvant therapy.

RESULTS

Seven (13%) patients showed complete pathological response while 46 (87%) patients were partial responders to neoadjuvant treatment. In 38 (72%) patients, significant reduction in methylation was observed in post-treatment resection specimens compared to pre-treatment specimens (171.5 vs 152.7, p = 0.01); in 15 (28%) patients, methylation was increased. Pre-treatment methylation correlated significantly with tumour regression (p < 0.001), T-stage (p = 0.005), and was able to predict complete and partial pathological responders (p = 0.01).

CONCLUSION

Neoadjuvant CRT appears to alter the rectal cancer epigenome. The significant correlation between pre-treatment DNA methylation with tumour response suggests a potential role for methylation as a biomarker of response.

Image segmentation and identification of paired antibodies in breast tissue

Comparing staining patterns of paired antibodies designed towards a specific protein but toward different epitopes of the protein provides quality control over the binding and the antibodies' ability to identify the target protein correctly and exclusively. We present a method for automated quantification of immunostaining patterns for antibodies in breast tissue using the Human Protein Atlas database. In such tissue, dark brown dye 3,3′-diaminobenzidine is used as an antibody-specific stain whereas the blue dye hematoxylin is used as a counterstain. The proposed method is based on clustering and relative scaling of features following principal component analysis. Our method is able (1) to accurately segment and identify staining patterns and quantify the amount of staining and (2) to detect paired antibodies by correlating the segmentation results among different cases. Moreover, the method is simple, operating in a low-dimensional feature space, and computationally efficient which makes it suitable for high-throughput processing of tissue microarrays.

Reliable quantification of protein expression and cellular localization in histological sections

In targeted therapy, patient tumors are analyzed for aberrant activations of core cancer pathways, monitored based on biomarker expression, to ensure efficient treatment. Thus, diagnosis and therapeutic decisions are often based on the status of biomarkers determined by immunohistochemistry in combination with other clinical parameters. Standard evaluation of cancer specimen by immunohistochemistry is frequently impeded by its dependence on subjective interpretation, showing considerable intra- and inter-observer variability. To make treatment decisions more reliable, automated image analysis is an attractive possibility to reproducibly quantify biomarker expression in patient tissue samples. We tested whether image analysis could detect subtle differences in protein expression levels. Gene dosage effects generate well-graded expression patterns for most gene-products, which vary by a factor of two between wildtype and haploinsufficient cells lacking one allele. We used conditional mouse models with deletion of the transcription factors Stat5ab in the liver as well Junb deletion in a T-cell lymphoma model. We quantified the expression of total or activated STAT5AB or JUNB protein in normal (Stat5ab^+/+ or JunB^+/+), hemizygous (Stat5ab^+/Δ or JunB^+/Δ) or knockout (Stat5ab^Δ/Δ or JunB^Δ/Δ) settings. Image analysis was able to accurately detect hemizygosity at the protein level. Moreover, nuclear signals were distinguished from cytoplasmic expression and translocation of the transcription factors from the cytoplasm to the nucleus was reliably detected and quantified using image analysis. We demonstrate that image analysis supported pathologists to score nuclear STAT5AB expression levels in immunohistologically stained human hepatocellular patient samples and decreased inter-observer variability.

Novel nuclear localization of fatty acid synthase correlates with prostate cancer aggressiveness

Fatty acid synthase is up-regulated in a variety of cancers, including prostate cancer. Up-regulation of fatty acid synthase not only increases production of fatty acids in tumors but also contributes to the transformed phenotype by conferring growth and survival advantages. In addition, increased fatty acid synthase expression in prostate cancer correlates with poor prognosis, although the mechanism(s) by which this occurs are not completely understood. Because fatty acid synthase is expressed at low levels in normal cells, it is currently a major target for anticancer drug design. Fatty acid synthase is normally found in the cytosol; however, we have discovered that it also localizes to the nucleus in a subset of prostate cancer cells. Analysis of the fatty acid synthase protein sequence indicated the presence of a nuclear localization signal, and subcellular fractionation of LNCaP prostate cancer cells, as well as immunofluorescent confocal microscopy of patient prostate tumor tissue and LNCaPs confirmed nuclear localization of this protein. Finally, immunohistochemical analysis of prostate cancer tissue indicated that nuclear localization of fatty acid synthase correlates with Gleason grade, implicating a potentially novel role in prostate cancer progression. Possible clinical implications include improving the accuracy of prostate biopsies in the diagnosis of low- versus intermediate-risk prostate cancer and the uncovering of novel metabolic pathways for the therapeutic targeting of androgen-independent prostate cancer.

IHC Profiler: an open source plugin for the quantitative evaluation and automated scoring of immunohistochemistry images of human tissue samples

In anatomic pathology, immunohistochemistry (IHC) serves as a diagnostic and prognostic method for identification of disease markers in tissue samples that directly influences classification and grading the disease, influencing patient management. However, till today over most of the world, pathological analysis of tissue samples remained a time-consuming and subjective procedure, wherein the intensity of antibody staining is manually judged and thus scoring decision is directly influenced by visual bias. This instigated us to design a simple method of automated digital IHC image analysis algorithm for an unbiased, quantitative assessment of antibody staining intensity in tissue sections. As a first step, we adopted the spectral deconvolution method of DAB/hematoxylin color spectra by using optimized optical density vectors of the color deconvolution plugin for proper separation of the DAB color spectra. Then the DAB stained image is displayed in a new window wherein it undergoes pixel-by-pixel analysis, and displays the full profile along with its scoring decision. Based on the mathematical formula conceptualized, the algorithm is thoroughly tested by analyzing scores assigned to thousands (n = 1703) of DAB stained IHC images including sample images taken from human protein atlas web resource. The IHC Profiler plugin developed is compatible with the open resource digital image analysis software, ImageJ, which creates a pixel-by-pixel analysis profile of a digital IHC image and further assigns a score in a four tier system. A comparison study between manual pathological analysis and IHC Profiler resolved in a match of 88.6% (P<0.0001, CI = 95%). This new tool developed for clinical histopathological sample analysis can be adopted globally for scoring most protein targets where the marker protein expression is of cytoplasmic and/or nuclear type. We foresee that this method will minimize the problem of inter-observer variations across labs and further help in worldwide patient stratification potentially benefitting various multinational clinical trial initiatives.