Astronomical algorithms for automated analysis of tissue protein expression in breast cancer.
Ontology highlight
ABSTRACT: Background
High-throughput evaluation of tissue biomarkers in oncology has been greatly accelerated by the widespread use of tissue microarrays (TMAs) and immunohistochemistry. Although TMAs have the potential to facilitate protein expression profiling on a scale to rival experiments of tumour transcriptomes, the bottleneck and imprecision of manually scoring TMAs has impeded progress.Methods
We report image analysis algorithms adapted from astronomy for the precise automated analysis of IHC in all subcellular compartments. The power of this technique is demonstrated using over 2000 breast tumours and comparing quantitative automated scores against manual assessment by pathologists.Results
All continuous automated scores showed good correlation with their corresponding ordinal manual scores. For oestrogen receptor (ER), the correlation was 0.82, P<0.0001, for BCL2 0.72, P<0.0001 and for HER2 0.62, P<0.0001. Automated scores showed excellent concordance with manual scores for the unsupervised assignment of cases to 'positive' or 'negative' categories with agreement rates of up to 96%.Conclusion
The adaptation of astronomical algorithms coupled with their application to large annotated study cohorts, constitutes a powerful tool for the realisation of the enormous potential of digital pathology.
SUBMITTER: Ali HR
PROVIDER: S-EPMC3593538 | biostudies-literature | 2013 Feb
REPOSITORIES: biostudies-literature
Publications
Astronomical algorithms for automated analysis of tissue protein expression in breast cancer.
Ali H R HR Irwin M M Morris L L Dawson S-J SJ Blows F M FM Provenzano E E Mahler-Araujo B B Pharoah P D PD Walton N A NA Brenton J D JD Caldas C C
British journal of cancer 20130117 3
<h4>Background</h4>High-throughput evaluation of tissue biomarkers in oncology has been greatly accelerated by the widespread use of tissue microarrays (TMAs) and immunohistochemistry. Although TMAs have the potential to facilitate protein expression profiling on a scale to rival experiments of tumour transcriptomes, the bottleneck and imprecision of manually scoring TMAs has impeded progress.<h4>Methods</h4>We report image analysis algorithms adapted from astronomy for the precise automated ana ...[more]
Similar Datasets
Project description:Purpose: Mutations in BRCA1 are associated with familial as well as sporadic aggressive subtypes of breast cancer, but less is known about whether BRCA1 expression or subcellular localization contributes to progression in population-based settings.Methods: We examined BRCA1 expression and subcellular localization in invasive breast cancer tissues from an ethnically diverse sample of 286 patients and 36 normal breast tissue controls. Two different methods were used to label breast cancer tissues for BRCA1: (1) Dual immunofluoresent staining with BRCA1 and cytokeratin 8/18 and (2) immunohistochemical staining using the previously validated MS110 mouse monoclonal antibody. Slides were visualized and quantified using the VECTRA Automated Multispectral Image Analysis System and InForm software.Results: BRCA1 staining was more intense in normal than in invasive breast tissue for both cytoplasmic (p<0.0001) and nuclear (p<0.01) compartments. BRCA1 nuclear to cytoplasmic ratio was higher in breast cancer cells than in normal mammary epithelial cells. Reduced BRCA1 expression was associated with high tumor grade and negative hormone receptors (estrogen receptor, progesterone receptor and Her2). On the other hand, high BRCA1 expression correlated with basal-like tumors (high CK5/6 and EGFR), and high nuclear androgen receptor staining. Lower nuclear to cytoplasmic ratio of BRCA1 correlated significantly with high Ki67 labeling index (p< 0.05) and family history of breast cancer (p = 0.001).Conclusion: Findings of this study indicate that alterations in BRCA1 protein expression and subcellular localization in breast cancer correlate with poor prognostic markers and aggressive tumor features. Further large-scale studies are required to assess the potential relevance of BRCA1 protein expression and localization in routine classification of breast cancer.
| S-EPMC5581176 | biostudies-literature
Project description:BackgroundA major challenge in studies of etiologic heterogeneity in breast cancer has been the limited throughput, accuracy, and reproducibility of measuring tissue markers. Computerized image analysis systems may help address these concerns, but published reports of their use are limited. We assessed agreement between automated and pathologist scores of a diverse set of immunohistochemical assays done on breast cancer tissue microarrays (TMA).MethodsTMAs of 440 breast cancers previously stained for estrogen receptor (ER)-alpha, progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), ER-beta, and aromatase were independently scored by two pathologists and three automated systems (TMALab II, TMAx, and Ariol). Agreement between automated and pathologist scores of negative/positive was measured using the area under the receiver operating characteristics curve (AUC) and weighted kappa statistics for categorical scores. We also investigated the correlation between immunohistochemical scores and mRNA expression levels.ResultsAgreement between pathologist and automated negative/positive and categorical scores was excellent for ER-alpha and PR (AUC range = 0.98-0.99; kappa range = 0.86-0.91). Lower levels of agreement were seen for ER-beta categorical scores (AUC = 0.99-1.0; kappa = 0.80-0.86) and both negative/positive and categorical scores for aromatase (AUC = 0.85-0.96; kappa = 0.41-0.67) and HER2 (AUC = 0.94-0.97; kappa = 0.53-0.72). For ER-alpha and PR, there was a strong correlation between mRNA levels and automated (rho = 0.67-0.74) and pathologist immunohistochemical scores (rho = 0.67-0.77). HER2 mRNA levels were more strongly correlated with pathologist (rho = 0.63) than automated immunohistochemical scores (rho = 0.41-0.49).ConclusionsAutomated analysis of immunohistochemical markers is a promising approach for scoring large numbers of breast cancer tissues in epidemiologic investigations. This would facilitate studies of etiologic heterogeneity, which ultimately may allow improved risk prediction and better prevention approaches.
| S-EPMC2852578 | biostudies-literature
Project description:ImportanceTrastuzumab deruxtecan (T-DXd) has shown efficacy in patients with breast cancer with ERBB2 immunohistochemistry (IHC) scores of 1+ or 2+ but not 0 as read in central pathology laboratories. The drug is currently being tested in large randomized clinical trials with registration intent for this patient population.ObjectiveTo determine the suitability of the current standard ERBB2 IHC assays to select patients with low ERBB2 positivity for treatment with T-DXd.Design and settingAssessment of data from College of American Pathologists surveys and assessment of analytic data from a Yale University-based study of concordance of 18 pathologists reading 170 breast cancer biopsies.ResultsThe total survey data set included scores over 2 years from 1391 to 1452 laboratories of 40 ERBB2 cores from each laboratory (20 cores twice a year for a total of 80). College of American Pathologists surveys show that 19% of cases read by the laboratories generate results with less than or equal to 70% concordance for IHC ERBB2 score 0 vs 1+. When 18 pathologists read the scanned slides from a selected set of breast cancer biopsies using a 4-point scale, there was only 26% concordance between 0 and 1+ compared with 58% concordance between 2+ and 3+.Conclusions and relevanceIn this study using a current standard ERBB2 IHC assay, the scoring accuracy for ERBB2 IHC in the low range (0 and 1+) was poor. This inaccuracy in the real world could lead to misassignment of many patients for treatment with T-DXd.
| S-EPMC8814969 | biostudies-literature
Project description: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.
| S-EPMC4958735 | biostudies-literature
Project description:BACKGROUND:Tissue microarray (TMA) data are commonly used to validate the prognostic accuracy of tumor markers. For example, breast cancer TMA data have led to the identification of several promising prognostic markers of survival time. Several studies have shown that TMA data can also be used to cluster patients into clinically distinct groups. Here we use breast cancer TMA data to cluster patients into distinct prognostic groups. METHODS:We apply weighted correlation network analysis (WGCNA) to TMA data consisting of 26 putative tumor biomarkers measured on 82 breast cancer patients. Based on this analysis we identify three groups of patients with low (5.4%), moderate (22%) and high (50%) mortality rates, respectively. We then develop a simple threshold rule using a subset of three markers (p53, Na-KATPase-?1, and TGF ? receptor II) that can approximately define these mortality groups. We compare the results of this correlation network analysis with results from a standard Cox regression analysis. RESULTS:We find that the rule-based grouping variable (referred to as WGCNA*) is an independent predictor of survival time. While WGCNA* is based on protein measurements (TMA data), it validated in two independent Affymetrix microarray gene expression data (which measure mRNA abundance). We find that the WGCNA patient groups differed by 35% from mortality groups defined by a more conventional stepwise Cox regression analysis approach. CONCLUSIONS:We show that correlation network methods, which are primarily used to analyze the relationships between gene products, are also useful for analyzing the relationships between patients and for defining distinct patient groups based on TMA data. We identify a rule based on three tumor markers for predicting breast cancer survival outcomes.
| S-EPMC3142534 | biostudies-literature
Project description:PurposePrevious studies of breast tissue gene expression have shown that the extratumoral microenvironment has substantial variability across individuals, some of which can be attributed to epidemiologic factors. To evaluate how mammographic density and breast tissue composition relate to extratumoral microenvironment gene expression, we used data on 121 patients with breast cancer from the population-based Polish Women's Breast Cancer Study.Experimental designBreast cancer cases were classified on the basis of a previously reported, biologically defined extratumoral gene expression signature with two subtypes: an Active subtype, which is associated with high expression of genes related to fibrosis and wound response, and an Inactive subtype, which has high expression of cellular adhesion genes. Mammographic density of the contralateral breast was assessed using pretreatment mammograms and a quantitative, reliable computer-assisted thresholding method. Breast tissue composition was evaluated on the basis of digital image analysis of tissue sections.ResultsThe Inactive extratumoral subtype was associated with significantly higher percentage mammographic density (PD) and dense area (DA) in univariate analysis (PD: P = 0.001; DA: P = 0.049) and in multivariable analyses adjusted for age and body mass index (PD: P = 0.004; DA: P = 0.049). Inactive/higher mammographic density tissue was characterized by a significantly higher percentage of stroma and a significantly lower percentage of adipose tissue, with no significant change in epithelial content. Analysis of published gene expression signatures suggested that Inactive/higher mammographic density tissue expressed increased estrogen response and decreased TGF-β signaling.ConclusionsBy linking novel molecular phenotypes with mammographic density, our results indicate that mammographic density reflects broad transcriptional changes, including changes in both epithelia- and stroma-derived signaling.
| S-EPMC4073678 | biostudies-literature
Project description:Purpose: Previous studies of breast tissue gene expression have demonstrated that the extratumoral microenvironment has substantial variability across individuals, some of which can be attributed to epidemiologic factors. To evaluate how mammographic density (MD) and breast tissue composition relate to extratumoral microenvironment gene expression, we used data on 121 breast cancer patients from the population-based Polish Women’s Breast Cancer Study.Design: Breast cancer cases were classified based on a previously reported, biologically-defined extratumoral gene expression signature with two subtypes: an Active subtype, which is associated with high expression of genes related to fibrosis and wound response, and an Inactive subtype, which has high expression of cellular adhesion genes. MD of the contralateral breast was assessed using pre-treatment mammograms and a quantitative, reliable computer-assisted thresholding method. Breast tissue composition was evaluated based on digital image analysis of tissue sections. Results:The Inactive extratumoral subtype was associated with significantly higher percentage mammographic density (PD) and dense area (DA) in univariate analysis (PD: p=0.001; DA: p=0.049) and in multivariable analyses adjusted for age and body mass index (PD: p=0.004; DA: p=0.049). Inactive/higher MD tissue was characterized by a significantly higher percentage of stroma and a significantly lower percentage of adipose tissue, with no significant change in epithelial content. Analysis of published gene expression signatures suggested that Inactive/higher MD tissue expressed increased estrogen response and decreased TGF-ß signaling. Conclusions:By linking novel molecular phenotypes with MD, our results indicate that MD reflects broad transcriptional changes, including changes in both epithelia- and stroma-derived signaling. reference x sample
| S-ECPF-GEOD-49175 | biostudies-other
Project description:ImportanceImmunohistochemistry (IHC) is the most widely used assay for identification of molecular biomarkers. However, IHC is time consuming and costly, depends on tissue-handling protocols, and relies on pathologists' subjective interpretation. Image analysis by machine learning is gaining ground for various applications in pathology but has not been proposed to replace chemical-based assays for molecular detection.ObjectiveTo assess the prediction feasibility of molecular expression of biomarkers in cancer tissues, relying only on tissue architecture as seen in digitized hematoxylin-eosin (H&E)-stained specimens.Design, setting, and participantsThis single-institution retrospective diagnostic study assessed the breast cancer tissue microarrays library of patients from Vancouver General Hospital, British Columbia, Canada. The study and analysis were conducted from July 1, 2015, through July 1, 2018. A machine learning method, termed morphological-based molecular profiling (MBMP), was developed. Logistic regression was used to explore correlations between histomorphology and biomarker expression, and a deep convolutional neural network was used to predict the biomarker expression in examined tissues.Main outcomes and measuresPositive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristics curve measures of MBMP for assessment of molecular biomarkers.ResultsThe database consisted of 20 600 digitized, publicly available H&E-stained sections of 5356 patients with breast cancer from 2 cohorts. The median age at diagnosis was 61 years for cohort 1 (412 patients) and 62 years for cohort 2 (4944 patients), and the median follow-up was 12.0 years and 12.4 years, respectively. Tissue histomorphology was significantly correlated with the molecular expression of all 19 biomarkers assayed, including estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (formerly HER2). Expression of ER was predicted for 105 of 207 validation patients in cohort 1 (50.7%) and 1059 of 2046 validation patients in cohort 2 (51.8%), with PPVs of 97% and 98%, respectively, NPVs of 68% and 76%, respectively, and accuracy of 91% and 92%, respectively, which were noninferior to traditional IHC (PPV, 91%-98%; NPV, 51%-78%; and accuracy, 81%-90%). Diagnostic accuracy improved given more data. Morphological analysis of patients with ER-negative/PR-positive status by IHC revealed resemblance to patients with ER-positive status (Bhattacharyya distance, 0.03) and not those with ER-negative/PR-negative status (Bhattacharyya distance, 0.25). This suggests a false-negative IHC finding and warrants antihormonal therapy for these patients.Conclusions and relevanceFor at least half of the patients in this study, MBMP appeared to predict biomarker expression with noninferiority to IHC. Results suggest that prediction accuracy is likely to improve as data used for training expand. Morphological-based molecular profiling could be used as a general approach for mass-scale molecular profiling based on digitized H&E-stained images, allowing quick, accurate, and inexpensive methods for simultaneous profiling of multiple biomarkers in cancer tissues.
| S-EPMC6661721 | biostudies-literature
Project description:ACBD3 overexpression has previously been found to correlate with worse prognosis for breast cancer patients and, as an incredibly diverse protein in both function and cellular localisation, ACBD3 may have a larger role in breast cancer than previously thought. This study further investigated ACBD3's role in breast cancer. Bioinformatic databases were queried to characterise ACBD3 expression and mutation in breast cancer and to investigate how overexpression affects breast cancer patient outcomes. Immunohistochemistry was carried out to examine ACBD3 location within cells and tissue structures. ACBD3 was more highly expressed in breast cancer than in any other cancer or matched normal tissue, and expression over the median level resulted in reduced relapse-free, overall, and distant metastasis-free survival for breast cancer patients as a whole, with some differences observed between subtypes. IHC analysis found that ACBD3 levels varied based on hormone receptor status, indicating that ACBD3 could be a candidate biomarker for poor patient prognosis in breast cancer and may possibly be a biomarker for ER signal reprogramming of precancerous breast tissue.
| S-EPMC9408326 | biostudies-literature
Project description:The objective of this study was to compare the predictive ability of potential tissue biomarkers to known prognostic factors that predict renal cell carcinoma (RCC) recurrence using an automated system of immunohistochemical analysis. After institutional review board approval, a tissue microarray was constructed using tissue from patients who had partial or radical nephrectomy for RCC. Patients with metastatic disease were excluded. Immunohistochemical staining of the tissue microarray for Ki-67, C-reactive protein, carbonic anhydrase 9, and hypoxia-inducible factors 1α and 2α was analyzed using automated image analysis. Univariable and multivariable analyses were performed to evaluate the association of putative biomarkers and known prognostic factors. Of 216 patients who met the entrance criteria, 34 (16%) patients developed metastatic recurrence within a median follow-up interval of 60.9 (interquartile range, 13.9-87.1) months. RCC morphotypes analyzed in this study include clear cell (n = 156), papillary (n = 38), chromophobe (n = 16), and collecting duct/unclassified (n = 6). Univariate analysis identified that only increased Ki-67 was predictive of RCC recurrence among the proteins evaluated, in addition to other known clinicopathological prognostic factors. After multivariate analysis, Ki-67 was identified as an independently predictive risk factor for RCC recurrence (hazard ratio [HR], 3.73 [confidence interval {CI}, 1.60-8.68]). Other independent predictors of RCC recurrence included tumor diameter (HR, 1.20 [CI, 1.02-1.41]) and perinephric fat invasion (HR, 4.49 [CI, 1.11-18.20]). We conclude that Ki-67 positivity is independently predictive of RCC recurrence after surgery in nonmetastatic patients. Automated analysis of tissue protein expression can facilitate a more objective and expedient investigation of tissue biomarkers for RCC.
| S-EPMC4134351 | biostudies-literature