Automated Ki-67 Quantification of Immunohistochemical Staining Image of Human Nasopharyngeal Carcinoma Xenografts

Automated AI-based grading of neuroendocrine tumors using Ki-67 proliferation index: comparative evaluation and performance analysis

Early detection is critical for successfully diagnosing cancer, and timely analysis of diagnostic tests is increasingly important. In the context of neuroendocrine tumors, the Ki-67 proliferation index serves as a fundamental biomarker, aiding pathologists in grading and diagnosing these tumors based on histopathological images. The appropriate treatment plan for the patient is determined based on the tumor grade. An artificial intelligence-based method is proposed to aid pathologists in the automated calculation and grading of the Ki-67 proliferation index. The proposed system first performs preprocessing to enhance image quality. Then, segmentation process is performed using the U-Net architecture, which is a deep learning algorithm, to separate the nuclei from the background. The identified nuclei are then evaluated as Ki-67 positive or negative based on basic color space information and other features. The Ki-67 proliferation index is then calculated, and the neuroendocrine tumor is graded accordingly. The proposed system's performance was evaluated on a dataset obtained from the Department of Pathology at Meram Faculty of Medicine Hospital, Necmettin Erbakan University. The results of the pathologist and the proposed system were compared, and the proposed system was found to have an accuracy of 95% in tumor grading when compared to the pathologist's report.

Immunohistochemical staining of versican as a potential marker for predicting lymph node metastasis in gastric cancer

Gastric cancer is one of the most common cancers and has a high mortality rate. Lymph node metastasis is a key determinant of prognosis, and an essential mechanism involved in metastasis is the epithelial-mesenchymal transition. In this study, we aimed to assess the diagnostic role of versican (VCAN), a molecule participating in the epithelial-mesenchymal transition, on the detection of metastatic cancer. The expression of VCAN was evaluated using immunohistochemistry, and its biological activity was examined using gastric cancer cell lines. In patients with lymph node metastasis, VCAN expression was more prominent at primary tumor sites. In addition, VCAN was found to promote cell migration in vitro, thus potentially facilitating the distribution of metastases. Overall, increased expression of VCAN at the primary site may signify the development of metastases in lymph nodes because this protein is recognized as contributing to the migration of cancer cells into lymph nodes.

Reovirus combined with a STING agonist enhances anti-tumor immunity in a mouse model of colorectal cancer

Reovirus, a naturally occurring oncolytic virus, initiates the lysis of tumor cells while simultaneously releasing tumor antigens or proapoptotic cytokines in the tumor microenvironment to augment anticancer immunity. However, reovirus has developed a strategy to evade antiviral immunity via its inhibitory effect on interferon production, which negatively affects the induction of antitumor immune responses. The mammalian adaptor protein Stimulator of Interferon Genes (STING) was identified as a key regulator that orchestrates immune responses by sensing cytosolic DNA derived from pathogens or tumors, resulting in the production of type I interferon. Recent studies reported the role of STING in innate immune responses to RNA viruses leading to the restriction of RNA virus replication. In the current study, we found that reovirus had a reciprocal reaction with a STING agonist regarding type I interferon responses in vitro; however, we found that the combination of reovirus and STING agonist enhanced anti-tumor immunity by enhancing cytotoxic T cell trafficking into tumors, leading to significant tumor regression and survival benefit in a syngeneic colorectal cancer model. Our data indicate the combination of reovirus and a STING agonist to enhance inflammation in the tumor microenvironment might be a strategy to improve oncolytic reovirus immunotherapy.

Application of Artificial Intelligence Techniques to Predict Risk of Recurrence of Breast Cancer: A Systematic Review

Breast cancer is the most common disease among women, with over 2.1 million new diagnoses each year worldwide. About 30% of patients initially presenting with early stage disease have a recurrence of cancer within 10 years. Predicting who will have a recurrence and who will not remains challenging, with consequent implications for associated treatment. Artificial intelligence strategies that can predict the risk of recurrence of breast cancer could help breast cancer clinicians avoid ineffective overtreatment. Despite its significance, most breast cancer recurrence datasets are insufficiently large, not publicly available, or imbalanced, making these studies more difficult. This systematic review investigates the role of artificial intelligence in the prediction of breast cancer recurrence. We summarise common techniques, features, training and testing methodologies, metrics, and discuss current challenges relating to implementation in clinical practice. We systematically reviewed works published between 1 January 2011 and 1 November 2021 using the methodology of Kitchenham and Charter. We leveraged Springer, Google Scholar, PubMed, and IEEE search engines. This review found three areas that require further work. First, there is no agreement on artificial intelligence methodologies, feature predictors, or assessment metrics. Second, issues such as sampling strategies, missing data, and class imbalance problems are rarely addressed or discussed. Third, representative datasets for breast cancer recurrence are scarce, which hinders model validation and deployment. We conclude that predicting breast cancer recurrence remains an open problem despite the use of artificial intelligence.

Colorimetric histology using plasmonically active microscope slides

The human eye can distinguish as many as 10,000 different colours but is far less sensitive to variations in intensity¹, meaning that colour is highly desirable when interpreting images. However, most biological samples are essentially transparent, and nearly invisible when viewed using a standard optical microscope². It is therefore highly desirable to be able to produce coloured images without needing to add any stains or dyes, which can alter the sample properties. Here we demonstrate that colorimetric histology images can be generated using full-sized plasmonically active microscope slides. These slides translate subtle changes in the dielectric constant into striking colour contrast when samples are placed upon them. We demonstrate the biomedical potential of this technique, which we term histoplasmonics, by distinguishing neoplastic cells from normal breast epithelium during the earliest stages of tumorigenesis in the mouse MMTV-PyMT mammary tumour model. We then apply this method to human diagnostic tissue and validate its utility in distinguishing normal epithelium, usual ductal hyperplasia, and early-stage breast cancer (ductal carcinoma in situ). The colorimetric output of the image pixels is compared to conventional histopathology. The results we report here support the hypothesis that histoplasmonics can be used as a novel alternative or adjunct to general staining. The widespread availability of this technique and its incorporation into standard laboratory workflows may prove transformative for applications extending well beyond tissue diagnostics. This work also highlights opportunities for improvements to digital pathology that have yet to be explored.

How the variability between computer-assisted analysis procedures evaluating immune markers can influence patients' outcome prediction

Differences between computer-assisted image analysis (CAI) algorithms may cause discrepancies in the identification of immunohistochemically stained immune biomarkers in biopsies of breast cancer patients. These discrepancies have implications for their association with disease outcome. This study aims to compare three CAI procedures (A, B and C) to measure positive marker areas in post-neoadjuvant chemotherapy biopsies of patients with triple-negative breast cancer (TNBC) and to explore the differences in their performance in determining the potential association with relapse in these patients. A total of 3304 digital images of biopsy tissue obtained from 118 TNBC patients were stained for seven immune markers using immunohistochemistry (CD4, CD8, FOXP3, CD21, CD1a, CD83, HLA-DR) and were analyzed with procedures A, B and C. The three methods measure the positive pixel markers in the total tissue areas. The extent of agreement between paired CAI procedures, a principal component analysis (PCA) and Cox multivariate analysis was assessed. Comparisons of paired procedures showed close agreement for most of the immune markers at low concentration. The probability of differences between the paired procedures B/C and B/A was generally higher than those observed in C/A. The principal component analysis, largely based on data from CD8, CD1a and HLA-DR, identified two groups of patients with a significantly lower probability of relapse than the others. The multivariate regression models showed similarities in the factors associated with relapse for procedures A and C, as opposed to those obtained with procedure B. General agreement among the results of CAI procedures would not guarantee that the same predictive breast cancer markers were consistently identified. These results highlight the importance of developing additional strategies to improve the sensitivity of CAI procedures.

Preclinical ImmunoPET Imaging of Glioblastoma-Infiltrating Myeloid Cells Using Zirconium-89 Labeled Anti-CD11b Antibody

PURPOSE

Glioblastoma is a lethal brain tumor, heavily infiltrated by tumor-associated myeloid cells (TAMCs). TAMCs are emerging as a promising therapeutic target as they suppress anti-tumor immune responses and promote tumor cell growth. Quantifying TAMCs using non-invasive immunoPET could facilitate patient stratification for TAMC-targeted treatments and monitoring of treatment efficacy. As TAMCs uniformly express the cell surface marker, integrin CD11b, we evaluated a Zr-89 labeled anti-CD11b antibody for non-invasive imaging of TAMCs in a syngeneic orthotopic mouse glioma model.

PROCEDURES

A human/mouse cross-reactive anti-CD11b antibody (clone M1/70) was conjugated to a DFO chelator and radiolabeled with Zr-89. PET/CT and biodistribution with or without a blocking dose of anti-CD11b Ab were performed 72 h post-injection (p.i.) of [⁸⁹Zr]anti-CD11b Ab in mice bearing established orthotopic syngeneic GL261 gliomas and in non tumor-bearing mice. Flow cytometry and immunohistochemistry of dissected GL261 tumors were conducted to confirm the presence of CD11b⁺ TAMCs.

RESULTS

Significant uptake of [⁸⁹Zr]anti-CD11b Ab was detected at the tumor site (SUVmean = 2.60 ± 0.24) compared with the contralateral hemisphere (SUVmean = 0.6 ± 0.11). Blocking with a 10-fold lower specific activity of [⁸⁹Zr]anti-CD11b Ab markedly reduced the SUV in the right brain (SUVmean = 0.11 ± 0.06), demonstrating specificity. Spleen and lymph nodes (myeloid cell rich organs) also showed high uptake of the tracer, and biodistribution analysis correlated with the imaging results. CD11b expression within the tumor was validated using flow cytometry and immunohistochemistry, which showed high CD11b expression primarily in the tumoral hemisphere compared with the contralateral hemisphere with very minimal accumulation in non tumor-bearing brain.

CONCLUSION

These data establish that [⁸⁹Zr]anti-CD11b Ab immunoPET targets CD11b⁺ cells (TAMCs) with high specificity in a mouse model of GBM, demonstrating the potential for non-invasive quantification of tumor-infiltrating CD11b⁺ immune cells during disease progression and immunotherapy in patients with GBM.

PathoNet introduced as a deep neural network backend for evaluation of Ki-67 and tumor-infiltrating lymphocytes in breast cancer

The nuclear protein Ki-67 and Tumor infiltrating lymphocytes (TILs) have been introduced as prognostic factors in predicting both tumor progression and probable response to chemotherapy. The value of Ki-67 index and TILs in approach to heterogeneous tumors such as Breast cancer (BC) that is the most common cancer in women worldwide, has been highlighted in literature. Considering that estimation of both factors are dependent on professional pathologists’ observation and inter-individual variations may also exist, automated methods using machine learning, specifically approaches based on deep learning, have attracted attention. Yet, deep learning methods need considerable annotated data. In the absence of publicly available benchmarks for BC Ki-67 cell detection and further annotated classification of cells, In this study we propose SHIDC-BC-Ki-67 as a dataset for the aforementioned purpose. We also introduce a novel pipeline and backend, for estimation of Ki-67 expression and simultaneous determination of intratumoral TILs score in breast cancer cells. Further, we show that despite the challenges that our proposed model has encountered, our proposed backend, PathoNet, outperforms the state of the art methods proposed to date with regard to harmonic mean measure acquired. Dataset is publicly available in http://shiraz-hidc.com and all experiment codes are published in https://github.com/SHIDCenter/PathoNet.

Development of an Automated Image Analyzer for Microvessel Density Measurement in Bone Marrow Biopsies

Angiogenesis is important for the proliferation and survival of multiple myeloma (MM) cells. Bone marrow (BM) microvessel density (MVD) is a useful marker of angiogenesis and an increase in MVD can be used as a marker of poor prognosis in MM patients. We developed an automated image analyzer to assess MVD from images of BM biopsies stained with anti-CD34 antibodies using two color models. MVD was calculated by merging images from the red and hue channels after eliminating non-microvessels. The analyzer results were compared with those obtained by two experienced hematopathologists in a blinded manner using the 84 BM samples of MM patients. Manual assessment of the MVD by two hematopathologists yielded mean±SD values of 19.4±11.8 and 20.0±11.8. The analyzer generated a mean±SD of 19.5±11.2. The intraclass correlation coefficient (ICC) and Bland-Altman plot of the MVD results demonstrated very good agreement between the automated image analyzer and both hematopathologists (ICC=0.893 [0.840–0.929] and ICC=0.906 [0.859–0.938]). This automated analyzer can provide time- and labor-saving benefits with more objective results in hematology laboratories.

A semi-automated brain atlas-based analysis pipeline for c-Fos immunohistochemical data

BACKGROUND

The use of immunohistochemistry to quantify neural markers in various brain regions is a staple of neuroscience research. Numerous programs exist to automate quantification, but manual assignment of regions of interest (ROIs) within individual brain sections remains time consuming and can introduce interobserver variability.

NEW METHOD

We have developed a novel open source FIJI-based immunohistochemical data analysis pipeline, Atlas-Based Analysis (ABA). ABA uses landmark-based image warping to adjust the experimental image to closely align with a published rat brain atlas. c-Fos positive cells are then quantified within predetermined ROI coordinates derived from the brain atlas. Image warping adjusts for natural variation in brain sections to ensure reliable alignment of ROIs for data analysis. This pipeline can be adapted for new atlases, landmarks, ROIs, and quantification measurements.

RESULTS

ABA permits rapid quantification of immunoreactivity in multiple ROIs and produces results with high levels of interobserver consistency.

COMPARISON WITH EXISTING METHODS

Compared to manual ROI designation, ABA reduces total analysis time by ∼70%. With correct use of landmarks for image warping, ABA produces similar results to manually drawn ROIs, results in no interobserver variability, and maintains c-Fos+ pixel dimensions.

CONCLUSIONS

ABA reduces time to obtain reliable results when performing automated immunoreactivity quantification and allows multiple users to analyze data without compromising the reliability of data obtained.

Establishment of PDX-derived salivary adenoid cystic carcinoma cell lines using organoid culture method

To generate a reliable preclinical model system exhibiting the molecular features of salivary adenoid cystic carcinoma (ACC) whose biology is still unclear due to the paucity of stable cell cultures. To develop new in vitro and in vivo models of ACC, the techniques of organoid culture and patient-derived tumor xenograft (PDX), which have attracted attention in other malignancies in recent years, were applied. Tumor specimens from surgically resected salivary ACC were proceeded for the preparation of PDX and organoid culture. The orthotopic transplantation of patient-derived or PDX-derived organoids was demonstrated into submandibular glands of NSG mice and those histology was evaluated. PDX-derived organoid cells were evaluated for the presence of MYB-mediated fusion genes and proceeded for in vitro drug sensitivity assay. Human ACC-derived organoids were successfully generated in three-dimensional culture and confirmed the ability of these cells to form tumors by orthotopic injection. Short-term organoid cell cultures from two individual ACC PDX tumors were also established that maintain the characteristic MYBL1 translocation and histological features of the original parent and PDX tumors. Finally, the establishment of drug sensitivity tests on these short-term cultured cells was confirmed using three different agents. This is the first to report an approach for the generation of human ACC-derived organoids as in vitro and in vivo cancer models, providing insights into understanding of the ACC biology and creating personalized therapy design for patients with ACC.

Deep Learning Model based Ki-67 Index estimation with Automatically Labelled Data

Ki-67 labelling index is a biomarker which is used across the world to predict the aggressiveness of cancer. To compute the Ki-67 index, pathologists normally count the tumour nuclei from the slide images manually; hence it is timeconsuming and is subject to inter pathologist variability. With the development of image processing and machine learning, many methods have been introduced for automatic Ki-67 estimation. But most of them require manual annotations and are restricted to one type of cancer. In this work, we propose a pooled Otsu's method to generate labels and train a semantic segmentation deep neural network (DNN). The output is postprocessed to find the Ki-67 index. Evaluation of two different types of cancer (bladder and breast cancer) results in a mean absolute error of 3.52%. The performance of the DNN trained with automatic labels is better than DNN trained with ground truth by an absolute value of 1.25%.

Improving the accuracy of gastrointestinal neuroendocrine tumor grading with deep learning

The Ki-67 index is an established prognostic factor in gastrointestinal neuroendocrine tumors (GI-NETs) and defines tumor grade. It is currently estimated by microscopically examining tumor tissue single-immunostained (SS) for Ki-67 and counting the number of Ki-67-positive and Ki-67-negative tumor cells within a subjectively picked hot-spot. Intraobserver variability in this procedure as well as difficulty in distinguishing tumor from non-tumor cells can lead to inaccurate Ki-67 indices and possibly incorrect tumor grades. We introduce two computational tools that utilize Ki-67 and synaptophysin double-immunostained (DS) slides to improve the accuracy of Ki-67 index quantitation in GI-NETs: (1) Synaptophysin-KI-Estimator (SKIE), a pipeline automating Ki-67 index quantitation via whole-slide image (WSI) analysis and (2) deep-SKIE, a deep learner-based approach where a Ki-67 index heatmap is generated throughout the tumor. Ki-67 indices for 50 GI-NETs were quantitated using SKIE and compared with DS slide assessments by three pathologists using a microscope and a fourth pathologist via manually ticking off each cell, the latter of which was deemed the gold standard (GS). Compared to the GS, SKIE achieved a grading accuracy of 90% and substantial agreement (linear-weighted Cohen’s kappa 0.62). Using DS WSIs, deep-SKIE displayed a training, validation, and testing accuracy of 98.4%, 90.9%, and 91.0%, respectively, significantly higher than using SS WSIs. Since DS slides are not standard clinical practice, we also integrated a cycle generative adversarial network into our pipeline to transform SS into DS WSIs. The proposed methods can improve accuracy and potentially save a significant amount of time if implemented into clinical practice.

A Combinational Approach Towards Treatment of Breast Cancer: an Analysis of Noscapine-Loaded Polymeric Nanoparticles and Doxorubicin

Our aim in this study was to clarify the combination anticancer effect of Noscapine (Nos) loaded in a polymeric nanocarrier with Doxorubicin (Dox) on breast cancer cells. Nanoprecipitation method was used to prepare methoxy polyethylene glycol (mPEG), poly lactic-co-glycolic acid (PLGA) nanoparticles (NPs) containing Nos. Transmission electron microscopy (TEM) and dynamic light scattering (DLS) were used to characterize the prepared Nos NPs. The anticancer activity of Nos NPs alone and in combination with Dox was assessed on 4T1 breast cancer cell line and in mice model. Spherical-shaped Nos NPs were prepared, with size of 101 ± 4.80 nm and zeta potential of - 15.40 ± 1 mV. Fourier transform infrared (FTIR) spectroscopy results demonstrated that Nos chemical structure was kept stable during preparation process. However, differential scanning calorimetric (DSC) thermogram proved that crystalline state of Nos changed to amorphous state in Nos NPs. The entrapment efficacy % (EE%) and drug loading % (DL%) of Nos NPs were about 87.20 ± 3.50% and 12.50 ± 2.30%, respectively. Synergistic anticancer effects of Nos both in free form (in hydrochloride form, Nos HCl) and Nos NPs form with Dox hydrochloride (Dox HCl) were observed on 4T1 cells. Combination of Nos NPs and Dox HCl inhibited tumor growth (68.50%) in mice more efficiently than Nos NPs (55.10%) and Dox HCl (32%) alone. Immunohistochemical (IHC) analysis of the tumor tissues confirmed antiangiogenic effect of Nos NPs. The findings highlighted efficacy of Nos NPs alone and in combination with Dox HCl on breast cancer tumors.

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

Automated image analysis tools for Ki67 breast cancer digital pathology images would have significant value if integrated into diagnostic pathology workflows. Such tools would reduce the workload of pathologists, while improving efficiency, and accuracy. Developing tools that are robust and reliable to multicentre data is challenging, however, differences in staining protocols, digitization equipment, staining compounds, and slide preparation can create variabilities in image quality and color across digital pathology datasets. In this work, a novel unsupervised color separation framework based on the IHC color histogram (IHCCH) is proposed for the robust analysis of Ki67 and hematoxylin stained images in multicentre datasets. An "overstaining" threshold is implemented to adjust for background overstaining, and an automated nuclei radius estimator is designed to improve nuclei detection. Proliferation index and F1 scores were compared between the proposed method and manually labeled ground truth data for 30 TMA cores that have ground truths for Ki67+ and Ki67- nuclei. The method accurately quantified the PI over the dataset, with an average proliferation index difference of 3.25%. To ensure the method generalizes to new, diverse datasets, 50 Ki67 TMAs from the Protein Atlas were used to test the validated approach. As the ground truth for this dataset is PI ranges, the automated result was compared to the PI range. The proposed method correctly classified 74 out of 80 TMA images, resulting in a 92.5% accuracy. In addition to these validations experiments, performance was compared to two color-deconvolution based methods, and to six machine learning classifiers. In all cases, the proposed work maintained more consistent (reproducible) results, and higher PI quantification accuracy.

In Silico Approach for Immunohistochemical Evaluation of a Cytoplasmic Marker in Breast Cancer

Breast cancer is the most frequently diagnosed cancer in women and the second most common cancer overall, with nearly 1.7 million new cases worldwide every year. Breast cancer patients need accurate tools for early diagnosis and to improve treatment. Biomarkers are increasingly used to describe and evaluate tumours for prognosis, to facilitate and predict response to therapy and to evaluate residual tumor, post-treatment. Here, we evaluate different methods to separate Diaminobenzidine (DAB) from Hematoxylin and Eosin (H&E) staining for Wnt-1, a potential cytoplasmic breast cancer biomarker. A method comprising clustering and Color deconvolution allowed us to recognize and quantify Wnt-1 levels accurately at pixel levels. Experimental validation was conducted using a set of 12,288 blocks of m×n pixels without overlap, extracted from a Tissue Microarray (TMA) composed of 192 tissue cores. Intraclass Correlations (ICC) among evaluators of the data of 0.634, 0.791, 0.551 and 0.63 for each Allred class and an average ICC of 0.752 among evaluators and automatic classification were obtained. Furthermore, this method received an average rating of 4.26 out of 5 in the Wnt-1 segmentation process from the evaluators.

Claudin1 promotes the proliferation, invasion and migration of nasopharyngeal carcinoma cells by upregulating the expression and nuclear entry of β-catenin

The aim of the present study was to measure the expression of Claudin (CLDN) 1 in nasopharyngeal carcinoma (NPC) and to determine its biological function and mechanism of action. Reverse transcription-quantitative polymerase chain reaction and western blotting were performed to measure the expression of CLDN1 mRNA and protein, respectively, in the immortalized human nasopharyngeal epithelial cell line NP69 and NPC-TW01 cells. Subsequently, small interfering RNA against CLDN1 and the LV-GFP-PURO-CLDN1 lentivirus were transfected into NPC-TW01 cells. Western blotting was used to determine the effects of CLDN1 down- and upregulation on the expression of the epithelial mesenchymal transition (EMT) markers E-cadherin and vimentin. In addition, the effect of CLDN1 on the expression of β-Catenin was determined. The results demonstrated that levels of CLDN1 mRNA and protein in NPC cells were significantly higher than in NP69 cells. Furthermore, the downregulation of CLDN1 inhibited the proliferation, invasion and migration of NPC-TW01 cells. The results of western blotting demonstrated that the downregulation of CLDN1 resulted in the upregulation of E-cadherin and inhibition of vimentin in NPC-TW01 cells. By contrast, the overexpression of CLDN1 resulted in the downregulation of E-cadherin and upregulation of vimentin in NPC-TW01 cells. The downregulation of β-catenin attenuated the cancer-promoting effect of CLDN1 on NPC-TW01 cells, whereas the upregulation of β-catenin reversed the tumor-suppressing effect of CLDN1 downregulation on NPC-TW01 cells. The results of the present study therefore demonstrate that CLDN1 expression is elevated in NPC cells. As an oncogene, CLDN1 promotes the proliferation, invasion and migration of NPC cells by upregulating the expression and nuclear entry of β-catenin.

Cell Counting and Segmentation of Immunohistochemical Images in the Spinal Cord: Comparing Deep Learning and Traditional Approaches

Estimation of cell nuclei in images stained for the c-fos protein using immunohistochemistry (IHC) is infeasible in large image sets. Use of multiple human raters to increase throughput often creates variance in the data analysis. Machine learning techniques for biomedical image analysis have been explored for cell-counting in pathology, but their performance on IHC staining, especially to label activated cells in the spinal cord is unknown. In this study, we evaluate different machine learning techniques to segment and count spinal cord neurons that have been active during stepping. We present a qualitative as well as quantitative comparison of algorithmic performance versus two human raters. Quantitative ratings are presented with cell-count statistics and Dice (DSI) scores. We also show the degree of variability between multiple human raters' segmentations and observe that there is a higher degree of variability in segmentations produced by classic machine learning techniques (SVM and Random forest) as compared to the newer deep learning techniques. The work presented here, represents the first steps towards addressing the analysis time bottleneck of large image data sets generated by c-fos IHC staining techniques, a task that would be impossible to do manually.

Prognostic significance of downregulated BMAL1 and upregulated Ki-67 proteins in nasopharyngeal carcinoma

This study assessed the prognostic value of BMAL1 and Ki-67 expression in patients with nasopharyngeal carcinoma. Level of BMAL1 mRNA was assessed in tissue specimens from 36 nasopharyngeal carcinomas and 20 nasopharyngeal chronic inflammations using quantitative reverse transcriptase-polymerase chain reaction. Expression of BMAL1 and Ki-67 proteins was analyzed immunohistochemically in 90 paired nasopharyngeal carcinoma and distant normal tissues. The Kaplan-Meier curves and the Log-rank test were used to calculate prognostic significance stratified by BMAL1 and Ki67 protein expression and the COX regression model was to analyze the multivariate prognosis. BMAL1 mRNA was significantly reduced in nasopharyngeal carcinoma (4.67 ± 0.27 versus 6.64 ± 0.51 in chronic inflammation tissues, p = 0.002). Level of BMAL1 mRNA was associated with tumor distant metastasis (3.37 ± 0.66 versus 5.04 ± 0.27 compared with non-metastasis, p = 0.011). Level of BMAL1 protein was also reduced in tumor tissues and BMAL1 expression was associated with better 1-, 3- and 5-year overall survival (OS) of cancer patients (92.6%, 69.2% and 62.3% versus 59.1%, 40.9% and 0% in patients with low BMAL1 expressed tumors; p = 0.000). BMAL1 expression and age were independent prognostic factors for OS (p = 0.032). Furthermore, Ki-67 expression was high in tumor versus normal tissues and associated with poor OS of cancer patients (p = 0.035). The Pearson correlation analysis showed that there was an inverse association between BMAL1 and Ki-67 protein expression (p = 0.021). This study demonstrated that lost BMAL1 and Ki-67 overexpression were associated with poor OS of nasopharyngeal carcinoma patients.

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

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

An Advanced Deep Learning Approach for Ki-67 Stained Hotspot Detection and Proliferation Rate Scoring for Prognostic Evaluation of Breast Cancer

Being a non-histone protein, Ki-67 is one of the essential biomarkers for the immunohistochemical assessment of proliferation rate in breast cancer screening and grading. The Ki-67 signature is always sensitive to radiotherapy and chemotherapy. Due to random morphological, color and intensity variations of cell nuclei (immunopositive and immunonegative), manual/subjective assessment of Ki-67 scoring is error-prone and time-consuming. Hence, several machine learning approaches have been reported; nevertheless, none of them had worked on deep learning based hotspots detection and proliferation scoring. In this article, we suggest an advanced deep learning model for computerized recognition of candidate hotspots and subsequent proliferation rate scoring by quantifying Ki-67 appearance in breast cancer immunohistochemical images. Unlike existing Ki-67 scoring techniques, our methodology uses Gamma mixture model (GMM) with Expectation-Maximization for seed point detection and patch selection and deep learning, comprises with decision layer, for hotspots detection and proliferation scoring. Experimental results provide 93% precision, 0.88% recall and 0.91% F-score value. The model performance has also been compared with the pathologists’ manual annotations and recently published articles. In future, the proposed deep learning framework will be highly reliable and beneficial to the junior and senior pathologists for fast and efficient Ki-67 scoring.