Automated quantitative assessment of HER-2/neu immunohistochemical expression in breast cancer

High contrast breast cancer biomarker semi-quantification and immunohistochemistry imaging using upconverting nanoparticles

Breast cancer is the second leading cause of cancer death in women. Current clinical treatment stratification practices open up an avenue for significant improvements, potentially through advancements in immunohistochemistry (IHC) assessments of biopsies. We report a high contrast upconverting nanoparticles (UCNP) labeling to distinguish different levels of human epidermal growth factor receptor 2 (HER2) in HER2 control pellet arrays (CPAs) and HER2-positive breast cancer tissue. A simple Fourier transform algorithm trained on CPAs was sufficient to provide a semi-quantitative HER2 assessment tool for breast cancer tissues. The UCNP labeling had a signal-to-background ratio of 40 compared to the negative control.

Deep Learning-Based H-Score Quantification of Immunohistochemistry-Stained Images

Immunohistochemistry (IHC) is a well-established and commonly used staining method for clinical diagnosis and biomedical research. In most IHC images, the target protein is conjugated with a specific antibody and stained using diaminobenzidine (DAB), resulting in a brown coloration, whereas hematoxylin serves as a blue counterstain for cell nuclei. The protein expression level is quantified through the H-score, calculated from DAB staining intensity within the target cell region. Traditionally, this process requires evaluation by 2 expert pathologists, which is both time consuming and subjective. To enhance the efficiency and accuracy of this process, we have developed an automatic algorithm for quantifying the H-score of IHC images. To characterize protein expression in specific cell regions, a deep learning model for region recognition was trained based on hematoxylin staining only, achieving pixel accuracy for each class ranging from 0.92 to 0.99. Within the desired area, the algorithm categorizes DAB intensity of each pixel as negative, weak, moderate, or strong staining and calculates the final H-score based on the percentage of each intensity category. Overall, this algorithm takes an IHC image as input and directly outputs the H-score within a few seconds, significantly enhancing the speed of IHC image analysis. This automated tool provides H-score quantification with precision and consistency comparable to experienced pathologists but at a significantly reduced cost during IHC diagnostic workups. It holds significant potential to advance biomedical research reliant on IHC staining for protein expression quantification.

Immunohistochemical HER2 Recognition and Analysis of Breast Cancer Based on Deep Learning

Breast cancer is one of the common malignant tumors in women. It seriously endangers women's life and health. The human epidermal growth factor receptor 2 (HER2) protein is responsible for the division and growth of healthy breast cells. The overexpression of the HER2 protein is generally evaluated by immunohistochemistry (IHC). The IHC evaluation criteria mainly includes three indexes: staining intensity, circumferential membrane staining pattern, and proportion of positive cells. Manually scoring HER2 IHC images is an error-prone, variable, and time-consuming work. To solve these problems, this study proposes an automated predictive method for scoring whole-slide images (WSI) of HER2 slides based on a deep learning network. A total of 95 HER2 pathological slides from September 2021 to December 2021 were included. The average patch level precision and f1 score were 95.77% and 83.09%, respectively. The overall accuracy of automated scoring for slide-level classification was 97.9%. The proposed method showed excellent specificity for all IHC 0 and 3+ slides and most 1+ and 2+ slides. The evaluation effect of the integrated method is better than the effect of using the staining result only.

Determining HER2 Status by Artificial Intelligence: An Investigation of Primary, Metastatic, and HER2 Low Breast Tumors

The expression of human epidermal growth factor receptor 2 (HER2) protein or gene transcripts is critical for therapeutic decision making in breast cancer. We examined the performance of a digitalized and artificial intelligence (AI)-assisted workflow for HER2 status determination in accordance with the American Society of Clinical Oncology (ASCO)/College of Pathologists (CAP) guidelines. Our preliminary cohort consisted of 495 primary breast carcinomas, and our study cohort included 67 primary breast carcinomas and 30 metastatic deposits, which were evaluated for HER2 status by immunohistochemistry (IHC) and in situ hybridization (ISH). Three practicing breast pathologists independently assessed and scored slides, building the ground truth. Following a washout period, pathologists were provided with the results of the AI digital image analysis (DIA) and asked to reassess the slides. Both rounds of assessment from the pathologists were compared to the AI results and ground truth for each slide. We observed an overall HER2 positivity rate of 15% in our study cohort. Moderate agreement (Cohen's κ 0.59) was observed between the ground truth and AI on IHC, with most discrepancies occurring between 0 and 1+ scores. Inter-observer agreement amongst pathologists was substantial (Fleiss´ κ 0.77) and pathologists' agreement with AI scores was 80.6%. Substantial agreement of the AI with the ground truth (Cohen´s κ 0.80) was detected on ISH-stained slides, and the accuracy of AI was similar for the primary and metastatic tumors. We demonstrated the feasibility of a combined HER2 IHC and ISH AI workflow, with a Cohen's κ of 0.94 when assessed in accordance with the ASCO/CAP recommendations.

Using Whole Slide Gray Value Map to Predict HER2 Expression and FISH Status in Breast Cancer

Accurate detection of HER2 expression through immunohistochemistry (IHC) is of great clinical significance in the treatment of breast cancer. However, manual interpretation of HER2 is challenging, due to the interobserver variability among pathologists. We sought to explore a deep learning method to predict HER2 expression level and gene status based on a Whole Slide Image (WSI) of the HER2 IHC section. When applied to 228 invasive breast carcinoma of no special type (IBC-NST) DAB-stained slides, our GrayMap+ convolutional neural network (CNN) model accurately classified HER2 IHC level with mean accuracy 0.952 ± 0.029 and predicted HER2 FISH status with mean accuracy 0.921 ± 0.029. Our result also demonstrated strong consistency in HER2 expression score between our system and experienced pathologists (intraclass correlation coefficient (ICC) = 0.903, Cohen's κ = 0.875). The discordant cases were found to be largely caused by high intra-tumor staining heterogeneity in the HER2 IHC group and low copy number in the HER2 FISH group.

A Deep Learning Quantification Algorithm for HER2 Scoring of Gastric Cancer

Gastric cancer is the third most common cause of cancer-related death in the world. Human epidermal growth factor receptor 2 (HER2) positive is an important subtype of gastric cancer, which can provide significant diagnostic information for gastric cancer pathologists. However, pathologists usually use a semi-quantitative assessment method to assign HER2 scores for gastric cancer by repeatedly comparing hematoxylin and eosin (H&E) whole slide images (WSIs) with their HER2 immunohistochemical WSIs one by one under the microscope. It is a repetitive, tedious, and highly subjective process. Additionally, WSIs have billions of pixels in an image, which poses computational challenges to Computer-Aided Diagnosis (CAD) systems. This study proposed a deep learning algorithm for HER2 quantification evaluation of gastric cancer. Different from other studies that use convolutional neural networks for extracting feature maps or pre-processing on WSIs, we proposed a novel automatic HER2 scoring framework in this study. In order to accelerate the computational process, we proposed to use the re-parameterization scheme to separate the training model from the deployment model, which significantly speedup the inference process. To the best of our knowledge, this is the first study to provide a deep learning quantification algorithm for HER2 scoring of gastric cancer to assist the pathologist's diagnosis. Experiment results have demonstrated the effectiveness of our proposed method with an accuracy of 0.94 for the HER2 scoring prediction.

A novel ensemble feature selection method for pixel-level segmentation of HER2 overexpression

Classifying histopathology images on a pixel-level requires sets of features able to capture the complex characteristics of the images, like the irregular cell morphology and the color heterogeneity on the tissue aspect. In this context, feature selection becomes a crucial step in the classification process such that it reduces model complexity and computational costs, avoids overfitting, and thereby it improves the model performance. In this study, we propose a new ensemble feature selection method by combining a set of base selectors, classifiers, and rank aggregation methods, aiming to determine from any initial set of handcrafted features, a smaller set of relevant color and texture pixel-level features, subsequently used for segmenting HER2 overexpression on a pixel-level, in breast cancer tissue images. We have been able to significantly reduce the set of initial features, using the proposed ensemble feature selection method. The best results are obtained using $$\chi ^2$$ χ 2 , Random Forest, and Runoff as the based selector, classifier, and aggregation method, respectively. The classification performance of the best model trained on the selected features set results in 0.939 recall, 0.866 specificity, 0.903 accuracy, 0.875 precision, and 0.906 F1-score.

Changing Trends in Estrogen Receptors/Progesterone Receptors/Human Epidermal Growth Factor Receptor 2 Prevalence Rates Among Jordanian Patients With Breast Cancer Over the Years

PURPOSE

Estrogen receptors (ERs), progesterone receptors (PRs), and human epidermal growth factor receptor 2 (HER2) are the mainstay of breast cancer management, and their prevalence rates vary among different populations possibly related to ethnic/genetic and/or socioeconomic status. In a previous study conducted at the King Hussein Cancer Center (published 2006), Jordan ER/PR/HER2 rates for patients diagnosed in 2003-2004 were 50.8%/57.5%/17.5%, respectively. The aim of this study is to revisit the prevalence rates to see if they have changed over the years with changing socioeconomic status.

MATERIALS AND METHODS

We retrieved clinicopathologic data of all patients (1,185) diagnosed with breast cancer during 2018. The data included age, histologic type, grade, and ER/PR/HER2 status as determined by immunohistochemistry and/or fluorescence in situ hybridization for HER2.

RESULTS

The mean age of patients was 52 (median = 51, range = 25-92) years, and the majority (73.2%) had invasive carcinoma of no special type. ER/PR/HER2 were 77.0%/72.4%./23.8%, respectively. Triple-negative breast cancers were 10.1%. In comparison with previous results of 2006, the changes are statistically significant. Similar changes were seen in other Middle Eastern populations. The current rates are close to those of Western populations.

CONCLUSION

Rates of ER/PR/HER2 expression have significantly changed and are close to those of Western populations for ER/PR. We propose that such changes are secondary to the adoption of a westernized lifestyle and socioeconomic changes.

L’intelligence artificielle pourrait-elle intervenir dans l’aide au diagnostic des cancers du sein ? – L’exemple de HER2

HER2 is an important prognostic and predictive biomarker in breast cancer. Its detection makes it possible to define which patients will benefit from a targeted treatment. While assessment of HER2 status by immunohistochemistry in positive vs negative categories is well implemented and reproducible, the introduction of a new "HER2-low" category could raise some concerns about its scoring and reproducibility. We herein described the current HER2 testing methods and the application of innovative machine learning techniques to improve these determinations, as well as the main challenges and opportunities related to the implementation of digital pathology in the up-and-coming AI era.

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.

Validity and Reproducibility of Immunohistochemical Scoring by Trained Non-Pathologists on Tissue Microarrays

BACKGROUND

Scoring of immunohistochemistry (IHC) staining is often done by non-pathologists, especially in large-scale tissue microarray (TMA)-based studies. Studies on the validity and reproducibility of scoring results from non-pathologists are limited. Therefore, our main aim was to assess interobserver agreement between trained non-pathologists and an experienced histopathologist for three IHC markers with different subcellular localization (nucleus/membrane/cytoplasm).

METHODS

Three non-pathologists were trained in recognizing adenocarcinoma and IHC scoring by a senior histopathologist. Kappa statistics were used to analyze interobserver and intraobserver agreement for 6,249 TMA cores from a colorectal cancer series.

RESULTS

Interobserver agreement between non-pathologists (independently scored) and the histopathologist was "substantial" for nuclear and membranous IHC markers (κ_range = 0.67-0.75 and κ_range = 0.61-0.69, respectively), and "moderate" for the cytoplasmic IHC marker (κ_range = 0.43-0.57). Scores of the three non-pathologists were also combined into a "combination score" (if at least two non-pathologists independently assigned the same score to a core, this was the combination score). This increased agreement with the pathologist (κ_nuclear = 0.74; κ_membranous = 0.73; κ_cytopasmic = 0.57). Interobserver agreement between non-pathologists was "substantial" (κ_nuclear = 0.78; κ_membranous = 0.72; κ_cytopasmic = 0.61). Intraobserver agreement of non-pathologists was "substantial" to "almost perfect" (κ_{nuclear,range} = 0.83-0.87; κ_{membranous,range} = 0.75-0.82; κ_cytopasmic = 0.69). Overall, agreement was lowest for the cytoplasmic IHC marker.

CONCLUSIONS

This study shows that adequately trained non-pathologists are able to generate reproducible IHC scoring results, that are similar to those of an experienced histopathologist. A combination score of at least two non-pathologists yielded optimal results.

IMPACT

Non-pathologists can generate reproducible IHC results after appropriate training, making analyses of large-scale molecular pathological epidemiology studies feasible within an acceptable time frame.

Clinical Decision Support for Ovarian Carcinoma Subtype Classification: A Pilot Observer Study With Pathology Trainees

CONTEXT.—

Clinical decision support (CDS) systems could assist less experienced pathologists with certain diagnostic tasks for which subspecialty training or extensive experience is typically needed. The effect of decision support on pathologist performance for such diagnostic tasks has not been examined.

OBJECTIVE.—

To examine the impact of a CDS tool for the classification of ovarian carcinoma subtypes by pathology trainees in a pilot observer study using digital pathology.

DESIGN.—

Histologic review on 90 whole slide images from 75 ovarian cancer patients was conducted by 6 pathology residents using: (1) unaided review of whole slide images, and (2) aided review, where in addition to whole slide images observers used a CDS tool that provided information about the presence of 8 histologic features important for subtype classification that were identified previously by an expert in gynecologic pathology. The reference standard of ovarian subtype consisted of majority consensus from a panel of 3 gynecologic pathology experts.

RESULTS.—

Aided review improved pairwise concordance with the reference standard for 5 of 6 observers by 3.3% to 17.8% (for 2 observers, increase was statistically significant) and mean interobserver agreement by 9.2% (not statistically significant). Observers benefited the most when the CDS tool prompted them to look for missed histologic features that were definitive for a certain subtype. Observer performance varied widely across cases with unanimous and nonunanimous reference classification, supporting the need for balancing data sets in terms of case difficulty.

CONCLUSIONS.—

Findings showed the potential of CDS systems to close the knowledge gap between pathologists for complex diagnostic tasks.

Comparing Deep Learning and Immunohistochemistry in Determining the Site of Origin for Well-Differentiated Neuroendocrine Tumors

Background

Determining the site of origin for metastatic well-differentiated neuroendocrine tumors (WDNETs) is challenging, and immunohistochemical (IHC) profiles do not always lead to a definitive diagnosis. We sought to determine if a deep-learning convolutional neural network (CNN) could improve upon established IHC profiles in predicting the site of origin in a cohort of WDNETs from the common primary sites.

Materials and Methods

Hematoxylin and eosin (H&E)-stained tissue microarrays (TMAs) were created using 215 WDNETs arising from the known primary sites. A CNN trained and tested on 60% (n = 130) and 40% (n = 85) of these cases, respectively. One hundred and seventy-nine cases had TMA tissue remaining for the IHC analysis. These cases were stained with IHC markers pPAX8, CDX2, SATB2, and thyroid transcription factor-1 (markers of pancreas/duodenum, ileum/jejunum/duodenum, colorectum/appendix, and lung WDNET sites of origin, respectively). The CNN diagnosis was deemed correct if it designated a majority or plurality of the tumor area as the known site of origin. The IHC diagnosis was deemed correct if the most specific marker for a particular site of origin met an H-score threshold determined by two pathologists.

Results

When all cases were considered, the CNN correctly identified the site of origin at a lower rate compared to IHC (72% vs. 82%, respectively). Of the 85 cases in the CNN test set, 66 had sufficient TMA material for IHC stains, thus 66 cases were available for a direct case-by-case comparison of IHC versus CNN. The CNN correctly identified 70% of these cases, while IHC correctly identified 76%, a finding that was not statistically significant (P = 0.56).

Conclusion

A CNN can identify WDNET site of origin at an accuracy rate close to the current gold standard IHC methods.

HER2 immunohistochemistry inter-observer reproducibility in 205 cases of invasive breast carcinoma additionally tested by ISH

Assessment of HER2 biomarker in invasive breast carcinoma patients allows a specific therapeutic approach. Clinical guidelines indicate immunohistochemistry (IHC) and in situ hybridization (ISH) to test HER2, however both have drawbacks which results in low reproducibility of results especially in equivocal cases. Our main objective is to quantify inter-observer IHC reproducibility and cross it with the ISH result. Our series includes 205 invasive breast carcinoma cases sent for ISH retest from 14 hospitals, 5 observers to assess the IHC and 2 observers for the ISH of each case. We found that the observers only achieve an absolute agreement for IHC in 1 out of 3 cases. The inter-observer concordance for IHC is low (0.2 ≤ k ≤ 0.4) or moderate (0.41 ≤ k ≤ 0.6). In ISH positive cases the concordance for IHC is higher than in the ISH negative cases. In conclusion, the study shows low and moderate IHC inter-observer concordance, finding the more worrying values among the ISH negative cases which are the most part of this particular sample. Subjective interpretation of the techniques, among other factors, has negative impact in HER2 evaluation. To offset this limitation we have checked that reaching a consensus from different observers for HER2 IHC assessment improves the results.

Automated identification of malignancy in whole-slide pathological images: identification of eyelid malignant melanoma in gigapixel pathological slides using deep learning

BACKGROUND/AIMS

To develop a deep learning system (DLS) that can automatically detect malignant melanoma (MM) in the eyelid from histopathological sections with colossal information density.

METHODS

Setting: Double institutional study.

STUDY POPULATION

We retrospectively reviewed 225 230 pathological patches (small section cut from pathologist-labelled area from an H&E image), cut from 155 H&E-stained whole-slide images (WSI).

OBSERVATION PROCEDURES

Labelled gigapixel pathological WSIs were used to train and test a model designed to assign patch-level classification. Using malignant probability from a convolutional neural network, the patches were embedded back into each WSI to generate a visualisation heatmap and leveraged a random forest model to establish a WSI-level diagnosis.

MAIN OUTCOME MEASURE(S)

For classification, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity were used to evaluate the efficacy of the DLS in detecting MM.

RESULTS

For patch diagnosis, the model achieved an AUC of 0.989 (95% CI 0.989 to 0.991), with an accuracy, sensitivity and specificity of 94.9%, 94.7% and 95.3%, respectively. We displayed the lesion area on the WSIs as graded by malignant potential. For WSI, the obtained sensitivity, specificity and accuracy were 100%, 96.5% and 98.2%, respectively, with an AUC of 0.998 (95% CI 0.994 to 1.000).

CONCLUSION

Our DLS, which uses artificial intelligence, can automatically detect MM in histopathological slides and highlight the lesion area on WSIs using a probabilistic heatmap. In addition, our approach has the potential to be applied to the histopathological sections of other tumour types.

Automated segmentation of cell membranes to evaluate HER2 status in whole slide images using a modified deep learning network

The uncontrollable growth of cells in the breast tissue causes breast cancer which is the second most common type of cancer affecting women in the United States. Normally, human epidermal growth factor receptor 2 (HER2) proteins are responsible for the division and growth of healthy breast cells. HER2 status is currently assessed using immunohistochemistry (IHC) as well as in situ hybridization (ISH) in equivocal cases. Manual HER2 evaluation of IHC stained microscopic images involves an error-prone, tedious, inter-observer variable, and time-consuming routine lab work due to diverse staining, overlapped regions, and non-homogeneous remarkable large slides. To address these issues, digital pathology offers reproducible, automatic, and objective analysis and interpretation of whole slide image (WSI). In this paper, we present a machine learning (ML) framework to segment, classify, and quantify IHC breast cancer images in an effective way. The proposed method consists of two major classifying and segmentation parts. Since HER2 is associated with tumors of an epithelial region and most of the breast tumors originate in epithelial tissue, it is crucial to develop an approach to segment different tissue structures. The proposed technique is comprised of three steps. In the first step, a superpixel-based support vector machine (SVM) feature learning classifier is proposed to classify epithelial and stromal regions from WSI. In the second stage, on classified epithelial regions, a convolutional neural network (CNN) based segmentation method is applied to segment membrane regions. Finally, divided tiles are merged and the overall score of each slide is evaluated. Experimental results for 127 slides are presented and compared with state-of-the-art handcraft and deep learning-based approaches. The experiments demonstrate that the proposed method achieved promising performance on IHC stained data. The presented automated algorithm was shown to outperform other approaches in terms of superpixel based classifying of epithelial regions and segmentation of membrane staining using CNN.

High-Quality Immunohistochemical Stains Through Computational Assay Parameter Optimization

Accurate profiling of tumors using immunohistochemistry (IHC) is essential in cancer diagnosis. The inferences drawn from IHC-stained images depend to a great extent on the quality of immunostaining, which is in turn affected strongly by assay parameters. To optimize assay parameters, the available tissue sample is often limited. Moreover, with current practices in pathology, exploring the entire assay parameter space is not feasible. Thus, the evaluation of IHC stained slides is conventionally a subjective task, in which diagnoses are commonly drawn on images that are suboptimal. In this work, we introduce a framework to analyze IHC staining quality and its sensitivity to process parameters. To that extent, first histopathological sections are segmented automatically. Then, machine learning techniques are employed to extract disease-specific staining quality metrics (SQMs) targeting a quantitative assessment of staining quality. Finally, an approach to efficiently analyze the parameter space is introduced to infer sensitivity to process parameters. We present results on microscale IHC tissue samples of five breast tumor classes, based on disease state and protein expression. A disease-type classification F1-score of 0.82 and a contrast-level classification F1-score of 0.95 were achieved. With the proposed SQMs, an area under the curve of 0.85 was achieved on average over different disease types. Our methodology provides a promising step in automatically evaluating and quantifying staining quality of IHC stained tissue sections, and it can potentially standardize immunostaining across diagnostic laboratories.

Her2Net: A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation

We present an efficient deep learning framework for identifying, segmenting, and classifying cell membranes and nuclei from human epidermal growth factor receptor-2 (HER2)-stained breast cancer images with minimal user intervention. This is a long-standing issue for pathologists because the manual quantification of HER2 is error-prone, costly, and time-consuming. Hence, we propose a deep learning-based HER2 deep neural network (Her2Net) to solve this issue. The convolutional and deconvolutional parts of the proposed Her2Net framework consisted mainly of multiple convolution layers, max-pooling layers, spatial pyramid pooling layers, deconvolution layers, up-sampling layers, and trapezoidal long short-term memory (TLSTM). A fully connected layer and a softmax layer were also used for classification and error estimation. Finally, HER2 scores were calculated based on the classification results. The main contribution of our proposed Her2Net framework includes the implementation of TLSTM and a deep learning framework for cell membrane and nucleus detection, segmentation, and classification and HER2 scoring. Our proposed Her2Net achieved 96.64% precision, 96.79% recall, 96.71% F-score, 93.08% negative predictive value, 98.33% accuracy, and a 6.84% false-positive rate. Our results demonstrate the high accuracy and wide applicability of the proposed Her2Net in the context of HER2 scoring for breast cancer evaluation.

A Clinicopathological Study of Various Oral Cancer Diagnostic Techniques

Oral cancer is one of the most commonly occurring malignant tumors in the head and neck regions with high incident rate and mortality rate in the developed countries than in the developing countries. Generally, the survival rate of cancer patients may increase when diagnosed at early stage, followed by prompt treatment and therapy. Recently, cancer diagnosis and therapy design for a specific cancer patient have been performed with the advanced computer-aided techniques. The responses of the cancer therapy could be continuously monitored to ensure the effectiveness of the treatment process that hardly requires diagnostic result as quick as possible to improve the quality and patient care. This paper gives an overview of oral cancer occurrence, different types, and various diagnostic techniques. In addition, a brief introduction is given to various stages of immunoanalysis including tissue image preparation, whole slide imaging, and microscopic image analysis.

Automated segmentation and classification of cell nuclei in immunohistochemical breast cancer images with estrogen receptor marker

Breast cancer is the most common malignant tumor in women worldwide. In recent years, there has been an increasing use of immunohistochemistry (the process of detecting the expression of certain proteins in cytological images) to obtain useful information for diagnosis. This paper presents an efficient algorithm that automatically detects breast cancer cell nuclei and divides them into two groups: those that express the ER marker and those that do not. First, the areas that belong to the carcinoma are automatically identified. Then, the algorithm evaluates features such as size and shape to correctly segment the nuclei in these fields. Finally, the Fuzzy C-Means algorithm is used to classify the detected nuclei. The method proposed was evaluated with a set of 10 images which contained 4093 cell nuclei. The algorithm correctly identified 93.1% of the nuclei, and sensitivity and specificity of the classification were 95.7% and 93.2% respectively.

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.

Quantitative comparison and reproducibility of pathologist scoring and digital image analysis of estrogen receptor β2 immunohistochemistry in prostate cancer

Background

Digital image analysis offers advantages over traditional pathologist visual scoring of immunohistochemistry, although few studies examining the correlation and reproducibility of these methods have been performed in prostate cancer. We evaluated the correlation between digital image analysis (continuous variable data) and pathologist visual scoring (quasi-continuous variable data), reproducibility of each method, and association of digital image analysis methods with outcomes using prostate cancer tissue microarrays (TMAs) stained for estrogen receptor-β2 (ERβ2).

Methods

Prostate cancer TMAs were digitized and evaluated by pathologist visual scoring versus digital image analysis for ERβ2 staining within tumor epithelium. Two independent analysis runs were performed to evaluate reproducibility. Image analysis data were evaluated for associations with recurrence-free survival and disease specific survival following radical prostatectomy.

Results

We observed weak/moderate Spearman correlation between digital image analysis and pathologist visual scores of tumor nuclei (Analysis Run A: 0.42, Analysis Run B: 0.41), and moderate/strong correlation between digital image analysis and pathologist visual scores of tumor cytoplasm (Analysis Run A: 0.70, Analysis Run B: 0.69). For the reproducibility analysis, there was high Spearman correlation between pathologist visual scores generated for individual TMA spots across Analysis Runs A and B (Nuclei: 0.84, Cytoplasm: 0.83), and very high correlation between digital image analysis for individual TMA spots across Analysis Runs A and B (Nuclei: 0.99, Cytoplasm: 0.99). Further, ERβ2 staining was significantly associated with increased risk of prostate cancer-specific mortality (PCSM) when quantified by cytoplasmic digital image analysis (HR 2.16, 95 % CI 1.02–4.57, p = 0.045), nuclear image analysis (HR 2.67, 95 % CI 1.20–5.96, p = 0.016), and total malignant epithelial area analysis (HR 5.10, 95 % CI 1.70–15.34, p = 0.004). After adjusting for clinicopathologic factors, only total malignant epithelial area ERβ2 staining was significantly associated with PCSM (HR 4.08, 95 % CI 1.37–12.15, p = 0.012).

Conclusions

Digital methods of immunohistochemical quantification are more reproducible than pathologist visual scoring in prostate cancer, suggesting that digital methods are preferable and especially warranted for studies involving large sample sizes.

Electronic supplementary material

The online version of this article (doi:10.1186/s13000-016-0511-5) contains supplementary material, which is available to authorized users.

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

Digital pathology and microscopy image analysis is widely used for comprehensive studies of cell morphology or tissue structure. Manual assessment is labor intensive and prone to interobserver variations. Computer-aided methods, which can significantly improve the objectivity and reproducibility, have attracted a great deal of interest in recent literature. Among the pipeline of building a computer-aided diagnosis system, nucleus or cell detection and segmentation play a very important role to describe the molecular morphological information. In the past few decades, many efforts have been devoted to automated nucleus/cell detection and segmentation. In this review, we provide a comprehensive summary of the recent state-of-the-art nucleus/cell segmentation approaches on different types of microscopy images including bright-field, phase-contrast, differential interference contrast, fluorescence, and electron microscopies. In addition, we discuss the challenges for the current methods and the potential future work of nucleus/cell detection and segmentation.

Localization of spots in FISH images of breast cancer using 3-D shape analysis

The fluorescence in situ (FISH) belongs to the most often used molecular cytogenetic techniques, applied in many areas of diagnosis and research. The analysis of FISH images relies on localization and counting the red and green spots in order to determine HER2 status of the breast cancer samples. The algorithm of spot localization presented in the paper is based on 3-D shape analysis of the image objects. The subsequent regions of the image are matched to the reference pattern and the results of this matching influence localization of spots. The paper compares different shapes of the reference pattern and their efficiency in spot localization. The numerical experiments have been performed on the basis of 12 cases (patients), each represented by three images. Few thousands of cells have been analysed. The quantitative analyses comparing different versions of algorithm are presented and compared to the expert results. The best version of the procedure provides the absolute relative difference to the expert results smaller than 3%. These results confirm high efficiency of the proposed approach to the spot identification. The proposed method of FISH image analysis improves the efficiency of detecting fluorescent signals in FISH images. The evaluation results are encouraging for further testing of the developed automatic system directed to application in medical practice.

Free digital image analysis software helps to resolve equivocal scores in HER2 immunohistochemistry

Evaluation of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) is subject to interobserver variation and lack of reproducibility. Digital image analysis (DIA) has been shown to improve the consistency and accuracy of the evaluation and its use is encouraged in current testing guidelines. We studied whether digital image analysis using a free software application (ImmunoMembrane) can assist in interpreting HER2 IHC in equivocal 2+ cases. We also compared digital photomicrographs with whole-slide images (WSI) as material for ImmunoMembrane DIA. We stained 750 surgical resection specimens of invasive breast cancers immunohistochemically for HER2 and analysed staining with ImmunoMembrane. The ImmunoMembrane DIA scores were compared with the originally responsible pathologists' visual scores, a researcher's visual scores and in situ hybridisation (ISH) results. The originally responsible pathologists reported 9.1 % positive 3+ IHC scores, for the researcher this was 8.4 % and for ImmunoMembrane 9.5 %. Equivocal 2+ scores were 34 % for the pathologists, 43.7 % for the researcher and 10.1 % for ImmunoMembrane. Negative 0/1+ scores were 57.6 % for the pathologists, 46.8 % for the researcher and 80.8 % for ImmunoMembrane. There were six false positive cases, which were classified as 3+ by ImmunoMembrane and negative by ISH. Six cases were false negative defined as 0/1+ by IHC and positive by ISH. ImmunoMembrane DIA using digital photomicrographs and WSI showed almost perfect agreement. In conclusion, digital image analysis by ImmunoMembrane can help to resolve a majority of equivocal 2+ cases in HER2 IHC, which reduces the need for ISH testing.

Evaluation of cytokeratin-19 in breast cancer tissue samples: a comparison of automatic and manual evaluations of scanned tissue microarray cylinders

BACKGROUND

Digital image (DI) analysis avoids visual subjectivity in interpreting immunohistochemical stains and provides more reproducible results. An automated procedure consisting of two variant methods for quantifying the cytokeratin-19 (CK19) marker in breast cancer tissues is presented.

METHODS

The first method (A) excludes the holes inside selected CK19 stained areas, and the second (B) includes them. 93 DIs scanned from complete cylinders of tissue microarrays were evaluated visually by two pathologists and by the automated procedures.

RESULTS AND CONCLUSIONS

There was good concordance between the two automated methods, both of which tended to identify a smaller CK19-positive area than did the pathologists. The results obtained with method B were more similar to those of the pathologists; probably because it takes into account the entire positive tumoural area, including the holes. However, the pathologists overestimated the positive area of CK19. Further studies are needed to confirm the utility of this automated procedure in prognostic studies.

Comparative study between quantitative digital image analysis and fluorescence in situ hybridization of breast cancer equivocal human epidermal growth factor receptors 2 score 2(+) cases

Background:

Optimization of workflow for breast cancer samples with equivocal human epidermal growth factor receptors 2 (HER2)/neu score 2⁺ results in routine practice, remains to be a central focus of the on-going efforts to assess HER2 status. According to the College of American Pathologists/American Society of Clinical Oncology guidelines equivocal HER2/neu score 2⁺ cases are subject for further testing, usually by fluorescence in situ hybridization (FISH) investigations. It still remains on open question, whether quantitative digital image analysis of HER2 immunohistochemistry (IHC) stained slides can assist in further refining the HER2 score 2⁺.

Aim of this Work:

To assess utility of quantitative digital analysis of IHC stained slides and compare its performance to FISH in cases of breast cancer with equivocal HER2 score 2⁺.

Materials and Methods:

Fifteen specimens (previously diagnosed as breast cancer and was evaluated as HER 2^- score 2⁺) represented the study population. Contemporary new cuts were prepared for re-evaluation of HER2 immunohistochemical studies and FISH examination. All the cases were digitally scanned by iScan (Produced by BioImagene [Now Roche-Ventana]). The IHC signals of HER2 were measured using an automated image analyzing system (MECES, www.Diagnomx.eu/meces). Finally, a comparative study was done between the results of the FISH and the quantitative analysis of the virtual slides.

Results:

Three out of the 15 cases with equivocal HER2 score 2⁺, turned out to be positive (3⁺) by quantitative digital analysis, and 12 were found to be negative in FISH too. Two of these three positive cases proved to be positive with FISH, and only one was negative.

Conclusions:

Quantitative digital analysis is highly sensitive and relatively specific when compared to FISH in detecting HER2/neu overexpression. Therefore, it represents a potential reliable substitute for FISH in breast cancer cases, which desire further refinement of equivocal IHC results.

Whole slide imaging for human epidermal growth factor receptor 2 immunohistochemistry interpretation: Accuracy, Precision, and reproducibility studies for digital manual and paired glass slide manual interpretation

Background:

The use of digital whole slide imaging for human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) could create improvements in workflow and performance, allowing for central archiving of specimens, distributed and remote interpretation, and the potential for additional computerized automation.

Procedures:

The accuracy, precision, and reproducibility of manual digital interpretation for HER2 IHC were determined by comparison to manual glass slide interpretation. Inter- and intra-pathologist reproducibility and precision between the glass slide and digital interpretations of HER2 IHC were determined in 5 studies using DAKO HercepTest-stained breast cancer slides with the Philips Digital Pathology System. In 2 inter-method studies, 3 pathologists interpreted glass and digital slides in sequence or in random order with a minimum of 7 days as a washout period. These studies also measured inter-observer reproducibility and precision. Another two studies measured intra-pathologist reproducibility on cases read 10 times by glass and digital methods. One additional study evaluated the effects of adding IHC control slides with each run, using 1 pathologist interpreting glass and digital slides randomized from the sets above along with appropriate controls for each slide in the set.

Results:

The overall results show that there is no statistical difference between the variance of performance when comparing glass and digital HER2 interpretations; and there were no effects noted when control tissues were evaluated in conjunction with the test slides.

Conclusions:

The results show that there is an equivalence of result when interpreting HER2 IHC slides in breast cancer by either glass slides or digital images. Digital interpretation can therefore be safely and effectively used for this purpose.

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.

Observer performance in the use of digital and optical microscopy for the interpretation of tissue-based biomarkers

BACKGROUND

We conducted a validation study of digital pathology for the quantitative assessment of tissue-based biomarkers with immunohistochemistry.

OBJECTIVE

To examine observer agreement as a function of viewing modality (digital versus optical microscopy), whole slide versus tissue microarray (TMA) review, biomarker type (HER2 incorporating membranous staining and Ki-67 with nuclear staining), and data type (continuous and categorical).

METHODS

Eight pathologists reviewed 50 breast cancer whole slides (25 stained with HER2 and 25 with Ki-67) and 2 TMAs (1 stained with HER2, 1 with Ki-67, each containing 97 cores), using digital and optical microscopy.

RESULTS

Results showed relatively high overall interobserver and intermodality agreement, with different patterns specific to biomarker type. For HER2, there was better interobserver agreement for optical compared to digital microscopy for whole slides as well as better interobserver and intermodality agreement for TMAs. For Ki-67, those patterns were not observed.

CONCLUSIONS

The differences in agreement patterns when examining different biomarkers and different scoring methods and reviewing whole slides compared to TMA stress the need for validation studies focused on specific pathology tasks to eliminate sources of variability that might dilute findings. The statistical uncertainty observed in our analyses calls for adequate sampling for each individual task rather than pooling cases.

A nuclear circularity-based classifier for diagnostic distinction of desmoplastic from spindle cell melanoma in digitized histological images

Context:

Distinction of spindle cell melanoma (SM) and desmoplastic melanoma (DM) is clinically important due to differences in metastatic rate and prognosis; however, histological distinction is not always straightforward. During a routine review of cases, we noted differences in nuclear circularity between SM and DM.

Aim:

The primary aim in our study was to determine whether these differences in nuclear circularity, when assessed using a basic ImageJ-based threshold extraction, can serve as a diagnostic classifier to distinguish DM from SM.

Settings and Design:

Our retrospective analysis of an established patient cohort (SM n = 9, DM n = 9) was employed to determine discriminatory power.

Subjects and Methods:

Regions of interest (total n = 108; 6 images per case) were selected from scanned H and E-stained histological sections, and nuclear circularity was extracted and quantified by computational image analysis using open source tools (plugins for ImageJ).

Statistical Analysis:

Using analysis of variance, t-tests, and Fisher's exact tests, we compared extracted quantitative shape measures; statistical significance was defined as P < 0.05.

Results:

Classifying circularity values into four shape categories (spindled, elongated, oval, round) demonstrated significant differences in the spindled and round categories. Paradoxically, DM contained more spindled nuclei than SM (P = 0.011) and SM contained more round nuclei than DM (P = 0.026). Performance assessment using a combined shape-classification of the round and spindled fractions showed 88.9% accuracy and a Youden index of 0.77.

Conclusions:

Spindle cell melanoma and DM differ significantly in their nuclear morphology with respect to fractions of round and spindled nuclei. Our study demonstrates that quantifying nuclear circularity can be used as an adjunct diagnostic tool for distinction of DM and SM.

High agreement between whole slide imaging and optical microscopy for assessment of HER2 expression in breast cancer: whole slide imaging for the assessment of HER2 expression

Whole slide imaging (WSI) technology has been used for training, teaching, researching, and remote consultation. Few studies compared HER2 expression using optical microscopy (OM) and WSI evaluations in breast carcinomas. However, no consensus has been achieved comparing both assessments.

MATERIAL AND METHODS

Sections from tissue microarray containing 200 preselected invasive breast carcinomas were submitted to immunohistochemistry applying three anti-HER2 antibodies (HercepTest™, CB11, SP3) and in situ hybridization (DDISH). Slides were evaluated using OM and WSI (Pannoramic MIDI and Viewer, 3DHISTECH). Sensitivity and specificity were calculated comparing the anti-HER2 antibodies and DDISH.

RESULTS

WSI and OM HER2 evaluations agreement was considered good (SP3, k=0.80) to very good (CB11 and HercepTest™, k=0.81). WSI evaluation led to higher sensitivity (ranging from 100 of SP3 and HercepTest™ to 97 of CB11) and lower specificity (ranging from 86.4 of SP3 to 89.4 of HercepTest™) compared to OM evaluation (sensitivity ranged from 92.1 of CB11 to 98 of SP3 and specificity ranged from 95.2 of SP3 and HercepTest™ to 97.1 of CB11 and SP3).

CONCLUSION

High agreement was achieved between WSI and OM evaluations. All three antibodies were highly sensitive and specific using both evaluations. WSI can be considered a useful tool for HER2 immunohistochemical assessment.

Recommendations for human epidermal growth factor receptor 2 testing in breast cancer: American Society of Clinical Oncology/College of American Pathologists clinical practice guideline update

PURPOSE

To update the American Society of Clinical Oncology (ASCO)/College of American Pathologists (CAP) guideline recommendations for human epidermal growth factor receptor 2 (HER2) testing in breast cancer to improve the accuracy of HER2 testing and its utility as a predictive marker in invasive breast cancer.

METHODS

ASCO/CAP convened an Update Committee that included coauthors of the 2007 guideline to conduct a systematic literature review and update recommendations for optimal HER2 testing.

RESULTS

The Update Committee identified criteria and areas requiring clarification to improve the accuracy of HER2 testing by immunohistochemistry (IHC) or in situ hybridization (ISH). The guideline was reviewed and approved by both organizations.

RECOMMENDATIONS

The Update Committee recommends that HER2 status (HER2 negative or positive) be determined in all patients with invasive (early stage or recurrence) breast cancer on the basis of one or more HER2 test results (negative, equivocal, or positive). Testing criteria define HER2-positive status when (on observing within an area of tumor that amounts to >10% of contiguous and homogeneous tumor cells) there is evidence of protein overexpression (IHC) or gene amplification (HER2 copy number or HER2/CEP17 ratio by ISH based on counting at least 20 cells within the area). If results are equivocal (revised criteria), reflex testing should be performed using an alternative assay (IHC or ISH). Repeat testing should be considered if results seem discordant with other histopathologic findings. Laboratories should demonstrate high concordance with a validated HER2 test on a sufficiently large and representative set of specimens. Testing must be performed in a laboratory accredited by CAP or another accrediting entity. The Update Committee urges providers and health systems to cooperate to ensure the highest quality testing.

Carbonic Anhydrase IX is not a predictor of outcomes in non-metastatic clear cell renal cell carcinoma - a digital analysis of tissue microarray

INTRODUCTION

The knowledge about the molecular biology of clear cell renal cell carcinoma (ccRCC) is evolving, and Carbonic Anhydrase type IX (CA-IX) has emerged as a potential prognostic marker in this challenging disease. However, most of the literature about CA-IX on ccRCC comes from series on metastatic cancer, with a lack of series on non-metastatic cancer. The objective is to evaluate the expression of CA-IX in a cohort of non-metastatic ccRCC, correlating with 1) overall survival, and 2) with established prognostic parameters (T stage, tumor size, Fuhrman nuclear grade, microvascular invasion and peri-renal fat invasion).

MATERIALS AND METHODS

This is a retrospective cohort study. We evaluated 95 patients with non-metastatic clear cell renal cell carcinoma, as to the expression of CA-IX. The analyzed parameters where: overall survival (OS), TNM stage, tumor size (TS), Fuhrman nuclear grade (FNG), microvascular invasion (MVI), peri-renal fat invasion (PFI). We utilized a custom built tissue microarray, and the immunoexpression was digitally quantified using the Photoshop ® software.

RESULTS

The mean follow-up time was 7.9 years (range 1.9 to 19.5 years). The analysis of CA-IX expression against the selected prognostic parameters showed no correlation. The results are as follows: Overall survival (p = 0.790); T stage (p = 0.179); tumor size (p = 0.143); grouped Fuhrman nuclear grade (p = 0.598); microvascular invasion (p = 0.685), and peri-renal fat invasion (p = 0.104).

CONCLUSION

Carbonic anhydrase type IX expression does not correlate with overall survival and conventional prognostic parameters in non-metastatic clear cell renal cell carcinoma.

A generalized Laplacian of Gaussian filter for blob detection and its applications

In this paper, we propose a generalized Laplacian of Gaussian (LoG) (gLoG) filter for detecting general elliptical blob structures in images. The gLoG filter can not only accurately locate the blob centers but also estimate the scales, shapes, and orientations of the detected blobs. These functions can be realized by generalizing the common 3-D LoG scale-space blob detector to a 5-D gLoG scale-space one, where the five parameters are image-domain coordinates (x, y), scales (σ(x), σ(y)), and orientation (θ), respectively. Instead of searching the local extrema of the image's 5-D gLoG scale space for locating blobs, a more feasible solution is given by locating the local maxima of an intermediate map, which is obtained by aggregating the log-scale-normalized convolution responses of each individual gLoG filter. The proposed gLoG-based blob detector is applied to both biomedical images and natural ones such as general road-scene images. For the biomedical applications on pathological and fluorescent microscopic images, the gLoG blob detector can accurately detect the centers and estimate the sizes and orientations of cell nuclei. These centers are utilized as markers for a watershed-based touching-cell splitting method to split touching nuclei and counting cells in segmentation-free images. For the application on road images, the proposed detector can produce promising estimation of texture orientations, achieving an accurate texture-based road vanishing point detection method. The implementation of our method is quite straightforward due to a very small number of tunable parameters.

Recommendations for human epidermal growth factor receptor 2 testing in breast cancer: American Society of Clinical Oncology/College of American Pathologists clinical practice guideline update

PURPOSE

To update the American Society of Clinical Oncology (ASCO)/College of American Pathologists (CAP) guideline recommendations for human epidermal growth factor receptor 2 (HER2) testing in breast cancer to improve the accuracy of HER2 testing and its utility as a predictive marker in invasive breast cancer.

METHODS

ASCO/CAP convened an Update Committee that included coauthors of the 2007 guideline to conduct a systematic literature review and update recommendations for optimal HER2 testing.

RESULTS

The Update Committee identified criteria and areas requiring clarification to improve the accuracy of HER2 testing by immunohistochemistry (IHC) or in situ hybridization (ISH). The guideline was reviewed and approved by both organizations.

RECOMMENDATIONS

The Update Committee recommends that HER2 status (HER2 negative or positive) be determined in all patients with invasive (early stage or recurrence) breast cancer on the basis of one or more HER2 test results (negative, equivocal, or positive). Testing criteria define HER2-positive status when (on observing within an area of tumor that amounts to > 10% of contiguous and homogeneous tumor cells) there is evidence of protein overexpression (IHC) or gene amplification (HER2 copy number or HER2/CEP17 ratio by ISH based on counting at least 20 cells within the area). If results are equivocal (revised criteria), reflex testing should be performed using an alternative assay (IHC or ISH). Repeat testing should be considered if results seem discordant with other histopathologic findings. Laboratories should demonstrate high concordance with a validated HER2 test on a sufficiently large and representative set of specimens. Testing must be performed in a laboratory accredited by CAP or another accrediting entity. The Update Committee urges providers and health systems to cooperate to ensure the highest quality testing. This guideline was developed through a collaboration between the American Society of Clinical Oncology and the College of American Pathologists and has been published jointly by invitation and consent in both Journal of Clinical Oncology and the Archives of Pathology & Laboratory Medicine.

Downregulation of erythroid differentiation regulator 1 as a novel marker of skin tumors

BACKGROUND

Erythroid differentiation regulator 1 is decreased in malignant melanoma. However, the expression of erythroid differentiation regulator 1 has not been reported in normal epidermis, vessel, nerve, dermal adnexae, and various skin tumors.

METHODS

To investigate the expression of erythroid differentiation regulator 1 in normal skin and various skin tumors, immunohistochemical analysis of normal skin, epidermal tumors, sebaceous tumors, and eccrine tumors was performed. The image analysis was quantitatively performed using HistoQuant(™) software.

RESULTS

Erythroid differentiation regulator 1 was strongly expressed in the nuclei of normal epidermis, sebaceous gland, eccrine gland, vessel, and nerve. Expression of erythroid differentiation regulator 1 was weak in seborrheic keratosis, sebaceous hyperplasia, and eccrine spiradenoma. Erythroid differentiation regulator 1 was rarely observed in malignant skin tumors, including squamous cell carcinoma, basal cell carcinoma, malignant melanoma, sebaceous carcinoma, and eccrine porocarcinoma.

CONCLUSIONS

The expression of erythroid differentiation regulator 1 was negatively correlated with the malignant potential in various skin tumors. The results support the role of erythroid differentiation regulator 1 in cutaneous carcinogenesis and indicate its potential as a novel marker of skin tumors.

Reproducibility in the automated quantitative assessment of HER2/neu for breast cancer

Background:

With the emerging role of digital imaging in pathology and the application of automated image-based algorithms to a number of quantitative tasks, there is a need to examine factors that may affect the reproducibility of results. These factors include the imaging properties of whole slide imaging (WSI) systems and their effect on the performance of quantitative tools. This manuscript examines inter-scanner and inter-algorithm variability in the assessment of the commonly used HER2/neu tissue-based biomarker for breast cancer with emphasis on the effect of algorithm training.

Materials and Methods:

A total of 241 regions of interest from 64 breast cancer tissue glass slides were scanned using three different whole-slide images and were analyzed using two different automated image analysis algorithms, one with preset parameters and another incorporating a procedure for objective parameter optimization. Ground truth from a panel of seven pathologists was available from a previous study. Agreement analysis was used to compare the resulting HER2/neu scores.

Results:

The results of our study showed that inter-scanner agreement in the assessment of HER2/neu for breast cancer in selected fields of view when analyzed with any of the two algorithms examined in this study was equal or better than the inter-observer agreement previously reported on the same set of data. Results also showed that discrepancies observed between algorithm results on data from different scanners were significantly reduced when the alternative algorithm that incorporated an objective re-training procedure was used, compared to the commercial algorithm with preset parameters.

Conclusion:

Our study supports the use of objective procedures for algorithm training to account for differences in image properties between WSI systems.

Quantitative assessment and classification of tissue-based biomarker expression with color content analysis

CONTEXT

The use of computer aids has been suggested as a way to reduce interobserver variability that is known to exist in the interpretation of immunohistochemical staining in pathology. Such computer aids should be automated in their usage but also they should be trained in an automated and reproducible fashion.

OBJECTIVE

To present a computer aid for the quantitative analysis of tissue-based biomarkers, based on color content analysis.

DESIGN

The developed system incorporates an automated algorithm to allow retraining based on the color properties of different training sets. The algorithm first generates a color palette containing the colors present in a training subset. Based on the palette, color histograms are derived and are used as feature vectors to a pattern recognition system, which returns an output proportional to biomarker continuous expression or a categorical classification. The method was evaluated on a database of HER2/neu digital breast cancer slides, for which expression scores from a pathologist panel were available. The system was retrained and evaluated on different transformations of the database, including compression, blurring, and changes in illumination, to examine its robustness to different imaging conditions frequently met in digital pathology.

RESULTS

Results showed high agreement between the results of the algorithm and the truth from the pathologist panel as well as robustness to image transformations.

CONCLUSIONS

The results of the study are encouraging for the potential of this method as a computer aid to assess biomarker expression in a consistent and reproducible manner.

Statistical Methods for Tissue Array Images - Algorithmic Scoring and Co-training

Recent advances in tissue microarray technology have allowed immunohistochemistry to become a powerful medium-to-high throughput analysis tool, particularly for the validation of diagnostic and prognostic biomarkers. However, as study size grows, the manual evaluation of these assays becomes a prohibitive limitation; it vastly reduces throughput and greatly increases variability and expense. We propose an algorithm-Tissue Array Co-Occurrence Matrix Analysis (TACOMA)-for quantifying cellular phenotypes based on textural regularity summarized by local inter-pixel relationships. The algorithm can be easily trained for any staining pattern, is absent of sensitive tuning parameters and has the ability to report salient pixels in an image that contribute to its score. Pathologists' input via informative training patches is an important aspect of the algorithm that allows the training for any specific marker or cell type. With co-training, the error rate of TACOMA can be reduced substantially for a very small training sample (e.g., with size 30). We give theoretical insights into the success of co-training via thinning of the feature set in a high dimensional setting when there is "sufficient" redundancy among the features. TACOMA is flexible, transparent and provides a scoring process that can be evaluated with clarity and confidence. In a study based on an estrogen receptor (ER) marker, we show that TACOMA is comparable to, or outperforms, pathologists' performance in terms of accuracy and repeatability.

Quantitative comparison of immunohistochemical staining measured by digital image analysis versus pathologist visual scoring

Abstract

Immunohistochemical (IHC) assays performed on formalin-fixed paraffin-embedded (FFPE) tissue sections traditionally have been semi-quantified by pathologist visual scoring of staining. IHC is useful for validating biomarkers discovered through genomics methods as large clinical repositories of FFPE specimens support the construction of tissue microarrays (TMAs) for high throughput studies. Due to the ubiquitous availability of IHC techniques in clinical laboratories, validated IHC biomarkers may be translated readily into clinical use. However, the method of pathologist semi-quantification is costly, inherently subjective, and produces ordinal rather than continuous variable data. Computer-aided analysis of digitized whole slide images may overcome these limitations. Using TMAs representing 215 ovarian serous carcinoma specimens stained for S100A1, we assessed the degree to which data obtained using computer-aided methods correlated with data obtained by pathologist visual scoring. To evaluate computer-aided image classification, IHC staining within pathologist annotated and software-classified areas of carcinoma were compared for each case. Two metrics for IHC staining were used: the percentage of carcinoma with S100A1 staining (%Pos), and the product of the staining intensity (optical density [OD] of staining) multiplied by the percentage of carcinoma with S100A1 staining (OD*%Pos). A comparison of the IHC staining data obtained from manual annotations and software-derived annotations showed strong agreement, indicating that software efficiently classifies carcinomatous areas within IHC slide images. Comparisons of IHC intensity data derived using pixel analysis software versus pathologist visual scoring demonstrated high Spearman correlations of 0.88 for %Pos (p < 0.0001) and 0.90 for OD*%Pos (p < 0.0001). This study demonstrated that computer-aided methods to classify image areas of interest (e.g., carcinomatous areas of tissue specimens) and quantify IHC staining intensity within those areas can produce highly similar data to visual evaluation by a pathologist.

Virtual slides

The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1649068103671302

Utility of multispectral imaging in automated quantitative scoring of immunohistochemistry

BACKGROUND

Automated scanning devices and image analysis software provide a means to overcome the limitations of manual semiquantitative scoring of immunohistochemistry. Common drawbacks to automated imaging systems include an inability to classify tissue type and an inability to segregate cytoplasmic and nuclear staining.

METHODS

Immunohistochemistry for the membranous marker α-catenin, the cytoplasmic marker stathmin and the nuclear marker Ki-67 was performed on tissue microarrays (TMA) of archival formalin-fixed paraffin-embedded tissue comprising 471 (α-catenin and stathmin) and 511 (Ki-67) cases of prostate adenocarcinoma. These TMA were quantitatively analysed using two commercially available automated image analysers, the Ariol SL-50 system and the Nuance system from CRi. Both systems use brightfield microscopy for automated, unbiased and standardised quantification of immunohistochemistry, while the Nuance system has spectral deconvolution capabilities.

RESULTS

Overall concordance between scores from both systems was excellent (r=0.90; 0.83-0.95). The software associated with the multispectral imager allowed accurate automated classification of tissue type into epithelial glandular structures and stroma, and a single-step segmentation of staining into cytoplasmic or nuclear compartments allowing independent evaluation of these areas. The Nuance system, however, was not able to distinguish reliably between tumour and non-tumour tissue. In addition, variance in the labour and time required for analysis between the two systems was also noted.

CONCLUSION

Despite limitations, this study suggests some beneficial role for the use of a multispectral imaging system in automated analysis of immunohistochemistry.