Digital image analysis outperforms manual biomarker assessment in breast cancer

Quantitative immunohistochemistry analysis of breast Ki67 based on artificial intelligence

Breast cancer is a common malignant tumor of women. Ki67 is an important biomarker of cell proliferation. With the quantitative analysis, it is an important indicator of malignancy for breast cancer diagnosis. However, it is difficult to accurately and quantitatively evaluate the count of positive nucleus during the diagnosis process of pathologists, and the process is time-consuming and labor-intensive. In this work, we employed a quantitative analysis method of Ki67 in breast cancer based on deep learning approach. For the diagnosis of breast cancer, according to breast cancer diagnosis guideline, we first identified the tumor region of Ki67 pathological image, neglecting the non-tumor region in the image. Then, we detect the nucleus in the tumor region to determine the nucleus location information. After that, we classify the detected nucleuses as positive and negative according to the expression level of Ki67. According to the results of quantitative analysis, the proportion of positive cells is counted. Combining the above process, we design a breast Ki67 quantitative analysis pipeline. The Ki67 quantitative analysis system was assessed on the validation set. The Dice coefficient of the tumor region segmentation model was 0.848, the Average Precision index of the nucleus detection model was 0.817, and the accuracy of the nucleus classification model was 96.66%. Besides, in clinical independent sample experiment, the results show that the proposed breast Ki67 quantitative analysis system achieve excellent correlation with the diagnosis efficiency of doctors improved more than ten times and the overall consistency of diagnosis is intra-group correlation coefficient: 0.964. The research indicates that our quantitative analysis method of Ki67 in breast cancer has high clinical application value.

Computational pathology in the identification of HER2-low breast cancer: Opportunities and challenges

For the past 2 decades, pathologists have been accustomed to reporting the HER2 status of breast cancer as either positive or negative, based on HER2 IHC. Today, however, there is a clinical imperative to employ a 3-tier approach to interpreting HER2 IHC that can also identify tumours categorised as HER2-low. Meeting this need for a finer degree of discrimination may be challenging, and in this article, we consider the potential for the integration of computational approaches to support pathologists in achieving accurate and reproducible HER2 IHC scoring as well as outlining some of the practicalities involved.

Recommendations for Performance Evaluation of Machine Learning in Pathology: A Concept Paper From the College of American Pathologists

CONTEXT.—

Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology.

OBJECTIVE.—

To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation.

DATA SOURCES.—

An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks.

CONCLUSIONS.—

Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice.

Human epidermal growth factor receptor 2 (HER2) status in breast cancer: practice points and challenges

Human epidermal growth factor receptor 2 (HER2)-enriched breast cancer benefits significantly from anti-HER2 targeted therapies. This highlights the critical need for precise HER2 immunohistochemistry (IHC) interpretation serving as a triage tool for selecting patients for anti-HER2 regimens. Recently, the emerging eligibility of patients with HER2-low breast cancers for a novel HER2-targeted antibody-drug conjugate (T-DXd) adds challenges to HER2 IHC scoring interpretation, notably in the 0-1+ range, which shows high interobserver and interlaboratory staining platform variability. In this review, we navigate evolving challenges and suggest practical recommendations for HER2 IHC interpretation.

The Performance and Clinical Applicability of HER2 Digital Image Analysis in Breast Cancer: A Systematic Review

This systematic review aims to address the research gap in the performance of computational algorithms for the digital image analysis of HER2 images in clinical settings. While numerous studies have explored various aspects of these algorithms, there is a lack of comprehensive evaluation regarding their effectiveness in real-world clinical applications. We conducted a search of the Web of Science and PubMed databases for studies published from 31 December 2013 to 30 June 2024, focusing on performance effectiveness and components such as dataset size, diversity and source, ground truth, annotation, and validation methods. The study was registered with PROSPERO (CRD42024525404). Key questions guiding this review include the following: How effective are current computational algorithms at detecting HER2 status in digital images? What are the common validation methods and dataset characteristics used in these studies? Is there standardization of algorithm evaluations of clinical applications that can improve the clinical utility and reliability of computational tools for HER2 detection in digital image analysis? We identified 6833 publications, with 25 meeting the inclusion criteria. The accuracy rate with clinical datasets varied from 84.19% to 97.9%. The highest accuracy was achieved on the publicly available Warwick dataset at 98.8% in synthesized datasets. Only 12% of studies used separate datasets for external validation; 64% of studies used a combination of accuracy, precision, recall, and F1 as a set of performance measures. Despite the high accuracy rates reported in these studies, there is a notable absence of direct evidence supporting their clinical application. To facilitate the integration of these technologies into clinical practice, there is an urgent need to address real-world challenges and overreliance on internal validation. Standardizing study designs on real clinical datasets can enhance the reliability and clinical applicability of computational algorithms in improving the detection of HER2 cancer.

The Ki67 dilemma: investigating prognostic cut-offs and reproducibility for automated Ki67 scoring in breast cancer

PURPOSE

Quantification of Ki67 in breast cancer is a well-established prognostic and predictive marker, but inter-laboratory variability has hampered its clinical usefulness. This study compares the prognostic value and reproducibility of Ki67 scoring using four automated, digital image analysis (DIA) methods and two manual methods.

METHODS

The study cohort consisted of 367 patients diagnosed between 1990 and 2004, with hormone receptor positive, HER2 negative, lymph node negative breast cancer. Manual scoring of Ki67 was performed using predefined criteria. DIA Ki67 scoring was performed using QuPath and Visiopharm® platforms. Reproducibility was assessed by the intraclass correlation coefficient (ICC). ROC curve survival analysis identified optimal cutoff values in addition to recommendations by the International Ki67 Working Group and Norwegian Guidelines. Kaplan-Meier curves, log-rank test and Cox regression analysis assessed the association between Ki67 scoring and distant metastasis (DM) free survival.

RESULTS

The manual hotspot and global scoring methods showed good agreement when compared to their counterpart DIA methods (ICC > 0.780), and good to excellent agreement between different DIA hotspot scoring platforms (ICC 0.781-0.906). Different Ki67 cutoffs demonstrate significant DM-free survival (p < 0.05). DIA scoring had greater prognostic value for DM-free survival using a 14% cutoff (HR 3.054-4.077) than manual scoring (HR 2.012-2.056). The use of a single cutoff for all scoring methods affected the distribution of prediction outcomes (e.g. false positives and negatives).

CONCLUSION

This study demonstrates that DIA scoring of Ki67 is superior to manual methods, but further study is required to standardize automated, DIA scoring and definition of a clinical cut-off.

Reliability and Variability of Ki-67 Digital Image Analysis Methods for Clinical Diagnostics in Breast Cancer

Ki-67 is a nuclear protein associated with proliferation, and a strong potential biomarker in breast cancer, but is not routinely measured in current clinical management owing to a lack of standardization. Digital image analysis (DIA) is a promising technology that could allow high-throughput analysis and standardization. There is a dearth of data on the clinical reliability as well as intra- and interalgorithmic variability of different DIA methods. In this study, we scored and compared a set of breast cancer cases in which manually counted Ki-67 has already been demonstrated to have prognostic value (n = 278) to 5 DIA methods, namely Aperio ePathology (Lieca Biosystems), Definiens Tissue Studio (Definiens AG), Qupath, an unsupervised immunohistochemical color histogram algorithm, and a deep-learning pipeline piNET. The piNET system achieved high agreement (interclass correlation coefficient: 0.850) and correlation (R = 0.85) with the reference score. The Qupath algorithm exhibited a high degree of reproducibility among all rater instances (interclass correlation coefficient: 0.889). Although piNET performed well against absolute manual counts, none of the tested DIA methods classified common Ki-67 cutoffs with high agreement or reached the clinically relevant Cohen's κ of at least 0.8. The highest agreement achieved was a Cohen's κ statistic of 0.73 for cutoffs 20% and 25% by the piNET system. The main contributors to interalgorithmic variation and poor cutoff characterization included heterogeneous tumor biology, varying algorithm implementation, and setting assignments. It appears that image segmentation is the primary explanation for semiautomated intra-algorithmic variation, which involves significant manual intervention to correct. Automated pipelines, such as piNET, may be crucial in developing robust and reproducible unbiased DIA approaches to accurately quantify Ki-67 for clinical diagnosis in the future.

Emerging Landscape of Targeted Therapy of Breast Cancers With Low Human Epidermal Growth Factor Receptor 2 Protein Expression

CONTEXT.—

Human epidermal growth factor receptor 2 (HER2) status in breast cancer is currently classified as negative or positive for selecting patients for anti-HER2 targeted therapy. The evolution of the HER2 status has included a new HER2-low category defined as an HER2 immunohistochemistry score of 1+ or 2+ without gene amplification. This new category opens the door to a targetable HER2-low breast cancer population for which new treatments may be effective.

OBJECTIVE.—

To review the current literature on the emerging category of breast cancers with low HER2 protein expression, including the clinical, histopathologic, and molecular features, and outline the clinical trials and best practice recommendations for identifying HER2-low-expressing breast cancers by immunohistochemistry.

DATA SOURCES.—

We conducted a literature review based on peer-reviewed original articles, review articles, regulatory communications, ongoing and past clinical trials identified through ClinicalTrials.gov, and the authors' practice experience.

CONCLUSIONS.—

The availability of new targeted therapy potentially effective for patients with breast cancers with low HER2 protein expression requires multidisciplinary recognition. In particular, pathologists need to recognize and identify this category to allow the optimal selection of patients for targeted therapy.

Intratumoral heterogeneity of Ki67 proliferation index outperforms conventional immunohistochemistry prognostic factors in estrogen receptor-positive HER2-negative breast cancer

In breast cancer (BC), pathologists visually score ER, PR, HER2, and Ki67 biomarkers to assess tumor properties and predict patient outcomes. This does not systematically account for intratumoral heterogeneity (ITH) which has been reported to provide prognostic value. This study utilized digital image analysis (DIA) and computational pathology methods to investigate the prognostic value of ITH indicators in ER-positive (ER+) HER2-negative (HER2-) BC patients. Whole slide images (WSIs) of surgically excised specimens stained for ER, PR, Ki67, and HER2 from 254 patients were used. DIA with tumor tissue segmentation and detection of biomarker-positive cells was performed. The DIA-generated data were subsampled by a hexagonal grid to compute Haralick's texture indicators for ER, PR, and Ki67. Cox regression analyses were performed to assess the prognostic significance of the immunohistochemistry (IHC) and ITH indicators in the context of clinicopathologic variables. In multivariable analysis, the ITH of Ki67-positive cells, measured by Haralick's texture entropy, emerged as an independent predictor of worse BC-specific survival (BCSS) (hazard ratio (HR) = 2.64, p-value = 0.0049), along with lymph node involvement (HR = 2.26, p-value = 0.0195). Remarkably, the entropy representing the spatial disarrangement of tumor proliferation outperformed the proliferation rate per se established either by pathology reports or DIA. We conclude that the Ki67 entropy indicator enables a more comprehensive risk assessment with regard to BCSS, especially in cases with borderline Ki67 proliferation rates. The study further demonstrates the benefits of high-capacity DIA-generated data for quantifying the essentially subvisual ITH properties.

Digital pathology systems enabling quality patient care

Pathology laboratories are undergoing digital transformations, adopting innovative technologies to enhance patient care. Digital pathology systems impact clinical, education, and research use cases where pathologists use digital technologies to perform tasks in lieu of using glass slides and a microscope. Pathology professional societies have established clinical validation guidelines, and the US Food and Drug Administration have also authorized digital pathology systems for primary diagnosis, including image analysis and machine learning systems. Whole slide images, or digital slides, can be viewed and navigated similar to glass slides on a microscope. These modern tools not only enable pathologists to practice their routine clinical activities, but can potentially enable digital computational discovery. Assimilation of whole slide images in pathology clinical workflow can further empower machine learning systems to support computer assisted diagnostics. The potential enrichment these systems can provide is unprecedented in the field of pathology. With appropriate integration, these clinical decision support systems will allow pathologists to increase the delivery of quality patient care. This review describes the digital pathology transformation process, applicable clinical use cases, incorporation of image analysis and machine learning systems in the clinical workflow, as well as future technologies that may further disrupt pathology modalities to deliver quality patient care.

Future Practices of Breast Pathology Using Digital and Computational Pathology

Pathology clinical practice has evolved by adopting technological advancements initially regarded as potentially disruptive, such as electron microscopy, immunohistochemistry, and genomic sequencing. Breast pathology has a critical role as a medical domain, where the patient's pathology diagnosis has significant implications for prognostication and treatment of diseases. The advent of digital and computational pathology has brought about significant advancements in the field, offering new possibilities for enhancing diagnostic accuracy and improving patient care. Digital slide scanning enables to conversion of glass slides into high-fidelity digital images, supporting the review of cases in a digital workflow. Digitization offers the capability to render specimen diagnoses, digital archival of patient specimens, collaboration, and telepathology. Integration of image analysis and machine learning-based systems layered atop the high-resolution digital images offers novel workflows to assist breast pathologists in their clinical, educational, and research endeavors. Decision support tools may improve the detection and classification of breast lesions and the quantification of immunohistochemical studies. Computational biomarkers may help to contribute to patient management or outcomes. Furthermore, using digital and computational pathology may increase standardization and quality assurance, especially in areas with high interobserver variability. This review explores the current landscape and possible future applications of digital and computational techniques in the field of breast pathology.

Comparison of FNA-based conventional cytology specimens and digital image analysis in assessment of pancreatic lesions

Objectives

Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is one of the most important diagnostic tools for investigation of suspected pancreatic masses, although the interpretation of the results is controversial. In recent decades, digital image analysis (DIA) has been considered in pathology. The aim of this study was to assess the DIA in the evaluation of EUS-FNA based cytopathological specimens of pancreatic masses and comparing it with conventional cytology analysis by pathologist.

Material and Methods

This study was performed using cytological slides related to EUS-FNA samples of pancreatic lesions. The digital images were prepared and then analyzed by ImageJ software. Factors such as perimeter, circularity, area, minimum, maximum, mean, median of gray value, and integrated chromatin density of cell nucleus were extracted by software ImageJ and sensitivity, specificity, and cutoff point were evaluated in the diagnosis of malignant and benign lesions.

Results

In this retrospective study, 115 cytology samples were examined. Each specimen was reviewed by a pathologist and 150 images were prepared from the benign and malignant lesions and then analyzed by ImageJ software and a cut point was established by SPSS 26. The cutoff points for perimeter, integrated density, and the sum of three factors of perimeter, integrated density, and circularity to differentiate between malignant and benign lesions were reported to be 204.56, 131953, and 24643077, respectively. At this cutting point, the accuracy of estimation is based on the factors of perimeter, integrated density, and the sum of the three factors of perimeter, integrated density, and circularity were 92%, 92%, and 94%, respectively.

Conclusion

The results of this study showed that digital analysis of images has a high accuracy in diagnosing malignant and benign lesions in the cytology of EUS-FNA in patients with suspected pancreatic malignancy and by obtaining cutoff points by software output factors; digital imaging can be used to differentiate between benign and malignant pancreatic tumors.

Artificial intelligence in diagnostic pathology

Digital pathology (DP) is being increasingly employed in cancer diagnostics, providing additional tools for faster, higher-quality, accurate diagnosis. The practice of diagnostic pathology has gone through a staggering transformation wherein new tools such as digital imaging, advanced artificial intelligence (AI) algorithms, and computer-aided diagnostic techniques are being used for assisting, augmenting and empowering the computational histopathology and AI-enabled diagnostics. This is paving the way for advancement in precision medicine in cancer. Automated whole slide imaging (WSI) scanners are now rendering diagnostic quality, high-resolution images of entire glass slides and combining these images with innovative digital pathology tools is making it possible to integrate imaging into all aspects of pathology reporting including anatomical, clinical, and molecular pathology. The recent approvals of WSI scanners for primary diagnosis by the FDA as well as the approval of prostate AI algorithm has paved the way for starting to incorporate this exciting technology for use in primary diagnosis. AI tools can provide a unique platform for innovations and advances in anatomical and clinical pathology workflows. In this review, we describe the milestones and landmark trials in the use of AI in clinical pathology with emphasis on future directions.

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

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

Applications of Artificial Intelligence in Breast Pathology

CONTEXT.—

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

OBJECTIVE.—

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

DATA SOURCES.—

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

CONCLUSIONS.—

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

Lessons Learned, Challenges Taken, and Actions Made for "Precision" Immunohistochemistry. Analysis and Perspectives From the NordiQC Proficiency Testing Program

Immunohistochemistry (IHC) has for decades been an integrated method within pathology applied to gain diagnostic, prognostic, and predictive information. However, the multimodality of the analytical phase of IHC is a challenge to ensure the reproducibility of IHC, which has been documented by external quality assessment (EQA) programs for many biomarkers. More than 600 laboratories participate in the Nordic immunohistochemical Quality Control EQA program for IHC. In the period, 2017-2021, 65 different biomarkers were assessed and a total of 31,967 results were evaluated. An overall pass rate of 79% was obtained being an improvement compared with 71% for the period, 2003-2015. The pass rates for established predictive biomarkers (estrogen receptor, progesterone receptor, and HER2) for breast carcinoma were most successful showing mean pass rates of 89% to 92%. Diagnostic IHC biomarkers as PAX8, SOX10, and different cytokeratins showed a wide spectrum of pass rates ranging from 37% to 95%, mean level of 75%, and attributed to central parameters as access to sensitive and specific antibodies but also related to purpose of the IHC test and validation performed accordingly to this. Seven new diagnostic biomarkers were introduced, and all showed inferior pass rates compared with the average level for diagnostic biomarkers emphasizing the challenge to optimize, validate, and implement new IHC biomarkers. Nordic immunohistochemical Quality Control operates by "Fit-For-Purpose" EQA principles and for programmed death-ligand 1, 2 segments are offered aligned to the "3-dimensional" approach-bridging diagnostic tests, drugs to be offered, and diseases addressed. Mean pass rates of 65% and 79% was obtained in the 2 segments for programmed death-ligand 1.

Overrepresentation of human epidermal growth factor receptor 2 positive- and Luminal B breast cancer metastases in the eyes and orbit

BACKGROUND

Breast cancer is the most common cancer to spread to the choroid and orbit. Depending on a set of prognostic and predictive biomarkers, breast cancer can be divided into at least four distinct subtypes with separate treatment and clinical course.

SUBJECTS

Thirty-two patients with metastases to the eye and periocular area diagnosed between 2005 and 2020, of which 11 also had primary tumour tissue available. Expression levels of oestrogen- (ER) and progesterone receptors (PR), Human epidermal growth factor receptor 2 (HER2) and the proliferation marker Ki67 were analysed.

RESULTS

Twenty-five of 32 patients (78%) had a history of primary breast cancer, whereas the remaining 7 (22%) presented with metastatic disease. Of available metastases, 83% were positive for ER, 37% for PR, 54% for HER2, and 50% for Ki67. Metastases had significantly lower proportions of PR-positive cells than primary tumours, and the distribution of the Luminal A, Luminal B, HER2 enriched and triple-negative subtypes differed between primary tumours and metastases (P = 0.012): Six of 9 patients with a full set of biomarkers on both primary tumours and metastases switched subtype (67%), and 23 of 32 metastases (77%) were of the Luminal B subtype.

CONCLUSIONS

Nearly 4 in 5 breast cancer metastases in the eyes and orbit are of the Luminal B subtype, and a majority are HER2 positive. The breast cancer subtype frequently switches between primary tumours and metastases. Future studies should evaluate these results in larger cohorts.

Digital morphometry and cluster analysis identifies four types of melanocyte during uveal melanoma progression

BACKGROUND

Several types of benign and malignant uveal melanocytes have been described based on their histological appearance. However, their characteristics have not been quantified, and their distribution during progression from normal choroidal melanocytes to primary tumors and metastases has not been reported.

METHODS

A total of 1,245,411 digitally scanned melanocytes from normal choroid, choroidal nevi, primary uveal melanomas, and liver metastases were entered into two-step cluster analyses to delineate cell types based on measured morphometric characteristics and expression of protein markers.

RESULTS

Here we show that a combination of the area and circularity of cell nuclei, and BAP-1 expression in nuclei and cytoplasms yields the highest silhouette of cohesion and separation. Normal choroidal melanocytes and three types of uveal melanoma cells are outlined: Epithelioid (large, rounded nuclei; BAP-1 low; IGF-1R, IDO, and TIGIT high), spindle A (small, elongated nuclei; BAP-1 high; IGF-1R low; IDO, and TIGIT intermediate), and spindle B (large, elongated nuclei; BAP-1, IGF-1R, IDO, and TIGIT low). In normal choroidal tissue and nevi, only normal melanocytes and spindle A cells are represented. Epithelioid and spindle B cells are overrepresented in the base and apex, and spindle A cells in the center of primary tumors. Liver metastases contain no normal melanocytes or spindle A cells.

CONCLUSIONS

Four basic cell types can be outlined in uveal melanoma progression: normal, spindle A and B, and epithelioid. Differential expression of tumor suppressors, growth factors, and immune checkpoints could contribute to their relative over- and underrepresentation in benign, primary tumor, and metastatic samples.

An emerging era of computational cytology

BACKGROUND

The significant advancement in digital imaging, data management, advanced computational power, and artificial neural network have an immense impact on the field of cytology. The amalgamation of these areas has generated a newer discipline known as computational cytology.

AIMS AND OBJECTIVE

In To discuss the various important aspects of computational cytology.

MATERIALS AND METHODS

We reviewed the different studies published in English during the last few years on computational cytology.

RESULT

Computational cytology is a newer and emerging discipline in pathology that deals with the patient's meta-data and digital image data to make a mathematical model to produce diagnostic interpretations and predictions. The role of the cytologist is now changing from a simple observational scientist and slide interpreter to a dynamic and integrated multi-parametric prediction-based scientist.

CONCLUSION

In the current stage, the cytologist must understand the situation and should have a vision of the complete scenario on computational cytology.

Artificial intelligence in liver cancers: Decoding the impact of machine learning models in clinical diagnosis of primary liver cancers and liver cancer metastases

Liver cancers are the fourth leading cause of cancer-related mortality worldwide. In the past decade, breakthroughs in the field of artificial intelligence (AI) have inspired development of algorithms in the cancer setting. A growing body of recent studies have evaluated machine learning (ML) and deep learning (DL) algorithms for pre-screening, diagnosis and management of liver cancer patients through diagnostic image analysis, biomarker discovery and predicting personalized clinical outcomes. Despite the promise of these early AI tools, there is a significant need to explain the 'black box' of AI and work towards deployment to enable ultimate clinical translatability. Certain emerging fields such as RNA nanomedicine for targeted liver cancer therapy may also benefit from application of AI, specifically in nano-formulation research and development given that they are still largely reliant on lengthy trial-and-error experiments. In this paper, we put forward the current landscape of AI in liver cancers along with the challenges of AI in liver cancer diagnosis and management. Finally, we have discussed the future perspectives of AI application in liver cancer and how a multidisciplinary approach using AI in nanomedicine could accelerate the transition of personalized liver cancer medicine from bench side to the clinic.

Expression, assessment and significance of Ki67 expression in breast cancer: an update

Ki67 expression is one of the most important and cost-effective surrogate markers to assess for tumour cell proliferation in breast cancer (BC). The Ki67 labelling index has prognostic and predictive value in patients with early-stage BC, particularly in the hormone receptor-positive, HER2 (human epidermal growth factor receptor 2)-negative (luminal) tumours. However, many challenges exist in using Ki67 in routine clinical practice and it is still not universally used in the clinical setting. Addressing these challenges can potentially improve the clinical utility of Ki67 in BC. In this article, we review the function, immunohistochemical (IHC) expression, methods for scoring and interpretation of results as well as address several challenges of Ki67 assessment in BC. The prodigious attention associated with use of Ki67 IHC as a prognostic marker in BC resulted in high expectation and overestimation of its performance. However, the realisation of some pitfalls and disadvantages, which are expected with any similar markers, resulted in an increasing criticism of its clinical use. It is time to consider a pragmatic approach and weigh the benefits against the weaknesses and identify factors to achieve the best clinical utility. Here we highlight the strengths of its performance and provide some insights to overcome the existing challenges.

Systematically higher Ki67 scores on core biopsy samples compared to corresponding resection specimen in breast cancer: a multi-operator and multi-institutional study

Ki67 has potential clinical importance in breast cancer but has yet to see broad acceptance due to inter-laboratory variability. Here we tested an open source and calibrated automated digital image analysis (DIA) platform to: (i) investigate the comparability of Ki67 measurement across corresponding core biopsy and resection specimen cases, and (ii) assess section to section differences in Ki67 scoring. Two sets of 60 previously stained slides containing 30 core-cut biopsy and 30 corresponding resection specimens from 30 estrogen receptor-positive breast cancer patients were sent to 17 participating labs for automated assessment of average Ki67 expression. The blocks were centrally cut and immunohistochemically (IHC) stained for Ki67 (MIB-1 antibody). The QuPath platform was used to evaluate tumoral Ki67 expression. Calibration of the DIA method was performed as in published studies. A guideline for building an automated Ki67 scoring algorithm was sent to participating labs. Very high correlation and no systematic error (p = 0.08) was found between consecutive Ki67 IHC sections. Ki67 scores were higher for core biopsy slides compared to paired whole sections from resections (p ≤ 0.001; median difference: 5.31%). The systematic discrepancy between core biopsy and corresponding whole sections was likely due to pre-analytical factors (tissue handling, fixation). Therefore, Ki67 IHC should be tested on core biopsy samples to best reflect the biological status of the tumor.

Digital quantitative tissue image analysis of hypoxia in resected pancreatic ductal adenocarcinomas

Background

Tumor hypoxia is theorized to contribute to the aggressive biology of pancreatic ductal adenocarcinoma (PDAC). We previously reported that hypoxia correlated with rapid tumor growth and metastasis in patient-derived xenografts. Anticipating a prognostic relevance of hypoxia in patient tumors, we developed protocols for automated semi-quantitative image analysis to provide an objective, observer-independent measure of hypoxia. We further validated this method which can reproducibly estimate pimonidazole-detectable hypoxia in a high-through put manner.

Methods

We studied the performance of three automated image analysis platforms in scoring pimonidazole-detectable hypoxia in resected PDAC (n = 10) in a cohort of patients enrolled in PIMO-PANC. Multiple stained tumor sections were analyzed on three independent image-analysis platforms, Aperio Genie (AG), Definiens Tissue Studio (TS), and Definiens Developer (DD), which comprised of a customized rule set.

Results

The output from Aperio Genie (AG) had good concordance with manual scoring, but the workflow was resource-intensive and not suited for high-throughput analysis. TS analysis had high levels of variability related to misclassification of cells class, while the customized rule set of DD had a high level of reliability with an intraclass coefficient of more than 85%.

Discussion

This work demonstrates the feasibility of developing a robust, high-performance pipeline for an automated, quantitative scoring of pimonidazole-detectable hypoxia in patient tumors.

A Quantitative Digital Analysis of Tissue Immune Components Reveals an Immunosuppressive and Anergic Immune Response with Relevant Prognostic Significance in Glioblastoma

Objectives: Immunostimulatory therapies using immune checkpoint blockers show clinical activity in a subset of glioblastoma (GBM) patients. Several inhibitory mechanisms play a relevant role in the immune response to GBM. With the objective of analyzing the tumor immune microenvironment and its clinical significance, we quantified several relevant immune biomarkers. Design: We studied 76 primary (non-recurrent) GBMs with sufficient clinical follow-up, including a subgroup of patients treated with a dendritic cell vaccine. The IDH-mutation, EGFR-amplification, and MGMT methylation statuses were determined. Several relevant immune biomarkers, including CD163, CD8, PD1, and PDL1, were quantified in representative selected areas by digital image analysis and semiquantitative evaluation. The percentage of each immune expression was calculated with respect to the total number of tumor cells. Results: All GBMs were wild-type IDH, with a subgroup of classical GBMs according to the EGFR amplification (44%). Morphologically, CD163 immunostained microglia and intratumor clusters of macrophages were observed. A significant direct correlation was found between the expression of CD8 and the mechanisms of lymphocyte immunosuppression, in such a way that higher values of CD8 were directly associated with higher values of CD163 (p < 0.001), PDL1 (0.026), and PD1 (0.007). In a multivariate analysis, high expressions of CD8+ (HR = 2.05, 95%CI (1.02−4.13), p = 0.034) and CD163+ cells (HR 2.50, 95%CI (1.29−4.85), p = 0.007), were associated with shorter survival durations. The expression of immune biomarkers was higher in the non-classical (non-EGFR amplified tumors) GBMs. Other relevant prognostic factors were age, receipt of the dendritic cell vaccine, and MGMT methylation status. Conclusions: In accordance with the inverse correlation between CD8 and survival and the direct correlation between effector cells and CD163 macrophages and immune-checkpoint expression, we postulate that CD8 infiltration could be placed in a state of anergy or lymphocytic inefficient activity. Furthermore, the significant inverse correlation between CD163 tissue concentration and survival explains the relevance of this type of immune cell when creating a strong immunosuppressive environment. This information may potentially be used to support the selection of patients for immunotherapy.

Update on prognostic and predictive biomarkers of breast cancer

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

Quantitative Image Analysis as an Adjunct to Manual Scoring of ER, PgR, and HER2 in Invasive Breast Carcinoma

OBJECTIVES

Biomarker expression evaluation for estrogen receptor (ER), progesterone receptor (PgR), and human epidermal growth factor receptor 2 (HER2) is an essential prognostic and predictive parameter for breast cancer and critical for guiding hormonal and neoadjuvant therapy. This study compared quantitative image analysis (QIA) with pathologists' scoring for ER, PgR, and HER2.

METHODS

A retrospective analysis was undertaken of 1,367 invasive breast carcinomas, including all histopathology subtypes, for which ER, PgR, and HER2 were analyzed by manual scoring and QIA. The resulting scores were compared, and in a subset of HER2 cases (n = 373, 26%), scores were correlated with available fluorescence in situ hybridization (FISH) results.

RESULTS

Concordance between QIA and manual scores for ER, PgR, and HER2 was 93%, 96%, and 90%, respectively. Discordant cases had low positive scores (1%-10%) for ER (n = 33), were due to nonrepresentative region selection (eg, ductal carcinoma in situ) or tumor heterogeneity for PgR (n = 43), and were of one-step difference (negative to equivocal, equivocal to positive, or vice versa) for HER2 (n = 90). Among HER2 cases where FISH results were available, only four (1.0%) showed discordant QIA and FISH results.

CONCLUSIONS

QIA is a computer-aided diagnostic support tool for pathologists. It significantly improves ER, PgR, and HER2 scoring standardization. QIA demonstrated excellent concordance with pathologists' scores. To avoid pitfalls, pathologist oversight of representative region selection is recommended.

Regrowth factors of WHO grade I skull base meningiomas following incomplete resection

OBJECTIVE

The role of adjuvant radiation therapy following incomplete resection of WHO grade I skull base meningiomas (SBMs) is controversial, and little is known regarding the behavior of residual tumors. The authors investigated the factors that influence regrowth of residual WHO grade I SBMs following incomplete resection.

METHODS

From 2005 to 2019, a total of 710 patients underwent surgery for newly diagnosed WHO grade I SBMs. The data of 115 patients (16.2%) with incomplete resection and without any adjuvant radiotherapy were retrospectively assessed during a mean follow-up of 78 months (range 27-198 months). Pre-, intra-, and postoperative clinical and molecular factors were analyzed for relevance to regrowth-free survival (RFS).

RESULTS

Eighty patients were eligible for analysis, excluding those who were lost to follow-up (n = 10) or had adjuvant radiotherapy (n = 25). Regrowth occurred in 39 patients (48.7%), with a mean RFS of 50 months (range 3-191 months). Significant predictors of regrowth were Ki-67 proliferative index (PI) ≥ 4% (p = 0.017), Simpson resection grades IV and V (p = 0.005), and invasion of the cavernous sinus (p = 0.027) and Meckel's cave (p = 0.027). After Cox regression analysis, only Ki-67 PI ≥ 4% (hazard ratio [HR] 9.39, p = 0.003) and Simpson grades IV and V (HR 8.65, p = 0.001) showed significant deterioration of RFS. When stratified into 4 scoring groups, the mean RFSs were 110, 70, 38, and 9 months for scores 1 (Ki-67 PI < 4% and Simpson grade III), 2 (Ki-67 PI < 4% and Simpson grades IV and V), 3 (Ki-67 PI ≥ 4% and Simpson grade III), and 4 (Ki-67 PI ≥ 4% and Simpson grades IV and V), respectively. RFS was significantly longer for score 1 versus scores 2-4 (p < 0.01). Tumor consistency, histology, location, peritumoral edema, vascular encasement, and telomerase reverse transcriptase promoter mutation had no impact on regrowth.

CONCLUSIONS

Ki-67 PI and Simpson resection grade showed significant associations with RFS for WHO grade I SBMs following incomplete resection. Ki-67 PI and Simpson resection grade could be utilized to stratify the level of risk for regrowth.

Progress on deep learning in digital pathology of breast cancer: a narrative review

BACKGROUND AND OBJECTIVE

Pathology is the gold standard criteria for breast cancer diagnosis and has important guiding value in formulating the clinical treatment plan and predicting the prognosis. However, traditional microscopic examinations of tissue sections are time consuming and labor intensive, with unavoidable subjective variations. Deep learning (DL) can evaluate and extract the most important information from images with less need for human instruction, providing a promising approach to assist in the pathological diagnosis of breast cancer. To provide an informative and up-to-date summary on the topic of DL-based diagnostic systems for breast cancer pathology image analysis and discuss the advantages and challenges to the routine clinical application of digital pathology.

METHODS

A PubMed search with keywords ("breast neoplasm" or "breast cancer") and ("pathology" or "histopathology") and ("artificial intelligence" or "deep learning") was conducted. Relevant publications in English published from January 2000 to October 2021 were screened manually for their title, abstract, and even full text to determine their true relevance. References from the searched articles and other supplementary articles were also studied.

KEY CONTENT AND FINDINGS

DL-based computerized image analysis has obtained impressive achievements in breast cancer pathology diagnosis, classification, grading, staging, and prognostic prediction, providing powerful methods for faster, more reproducible, and more precise diagnoses. However, all artificial intelligence (AI)-assisted pathology diagnostic models are still in the experimental stage. Improving their economic efficiency and clinical adaptability are still required to be developed as the focus of further researches.

CONCLUSIONS

Having searched PubMed and other databases and summarized the application of DL-based AI models in breast cancer pathology, we conclude that DL is undoubtedly a promising tool for assisting pathologists in routines, but further studies are needed to realize the digitization and automation of clinical pathology.

Low correlation between Ki67 assessed by qRT-PCR in Oncotype Dx score and Ki67 assessed by Immunohistochemistry

Breast cancers expressing high levels of Ki67 are associated with poor outcomes. Oncotype DX test was designed for ER+/HER2- early-stage breast cancers to help adjuvant chemotherapy decision by providing a Recurrent Score (RS). RS measures the expression of 21 specific genes from tumor tissue, including Ki67. The primary aim of this study was to assess the agreement between Ki67_RNA obtained with Oncotype DX RS and Ki67_IHC. Other objectives were to analyze the association between the event free survival (EFS) and the expression level of Ki67_RNA; and association between RS and Ki67_RNA. Herein, we report a low agreement of 0.288 by Pearson correlation coefficient test between Ki67_IHC and Ki67_RNA in a cohort of 98 patients with early ER+/HER2- breast cancers. Moreover, Ki67_RNA^high tumors were significantly associated with the occurrence of events (p = 0.03). On the other hand, we did not find any association between Ki67_IHC and EFS (p = 0.26). We observed a low agreement between expression level of Ki67_RNA and Ki67 protein labelling by IHC. Unlike Ki67_IHC and independently of the RS, Ki67_RNA could have a prognostic value. It would be interesting to better assess the prognosis and predictive value of Ki67_RNA measured by qRT-PCR. The Ki67_RNA in medical routine could be a good support in countries where Oncotype DX is not accessible.

Gain of Chromosome 6p Correlates with Severe Anaplasia, Cellular Hyperchromasia, and Extraocular Spread of Retinoblastoma

PURPOSE

Gain of chromosome 6p has been associated with poor ocular survival in retinoblastoma and histopathologic grading of anaplasia with increased risk of metastatic spread and death. This study examined the correlation between these factors and other chromosomal abnormalities as well as results of whole genome sequencing, digital morphometry, and progression-free survival.

DESIGN

Retrospective cohort study from 2 United States tertiary referral centers.

PARTICIPANTS

Forty-two children who had undergone enucleation for retinoblastoma from January 2000 through December 2017.

METHODS

Status of chromosomes 6p, 1q, 9q, and 16q was evaluated with fluorescence in situ hybridization, the degree of anaplasia and presence of histologic high-risk features were assessed by ocular pathologists, digital morphometry was performed on scanned tumor slides, and whole genome sequencing was performed on a subset of tumors. Progression-free survival was defined as absence of distant or local metastases or tumor growth beyond the cut end of the optic nerve.

MAIN OUTCOME MEASURES

Correlation between each of chromosomal abnormalities, anaplasia, morphometry and sequencing results, and survival.

RESULTS

Forty-one of 42 included patients underwent primary enucleation and 1 was treated first with intra-arterial chemotherapy. Seven tumors showed mild anaplasia, 19 showed moderate anaplasia, and 16 showed severe anaplasia. All tumors had gain of 1q, 18 tumors had gain of 6p, 6 tumors had gain of 9q, and 36 tumors had loss of 16q. Tumors with severe anaplasia were significantly more likely to harbor 6p gains than tumors with nonsevere anaplasia (P < 0.001). Further, the hematoxylin staining intensity was significantly greater and that of eosin staining significantly lower in tumors with severe anaplasia (P < 0.05). Neither severe anaplasia (P = 0.10) nor gain of 6p (P = 0.21) correlated with histologic high-risk features, and severe anaplasia did not correlate to RB1, CREBBP, NSD1, or BCOR mutations in a subset of 14 tumors (P > 0.5). Patients with gain of 6p showed significantly shorter progression-free survival (P = 0.03, Wilcoxon test).

CONCLUSIONS

Gain of chromosome 6p emerges as a strong prognostic biomarker in retinoblastoma because it correlates with severe anaplasia, quantifiable changes in tumor cell staining characteristics, and extraocular spread.

Analysis of Ki-67 expression in women with breast cancer: Comparative evaluation of two different methodologies by immunophenotyping

The Ki-67 antigen is a nuclear protein with proven prognostic value in different neoplasms and recognizes the predictive value in breast cancer (BC). No consensus exists on the ideal cutoff point. In this study, Ki-67 expression was evaluated in samples of BC by flow cytometry (FC) and compared with immunohistochemical (IHC) examination. For this, the BC tissue samples were sectioned, macerated, filtered, and marked with anti-Ki-67 FITC and anti-CD45 V500 antibodies. We selected the neoplastic cells according to CD45 expression and size and internal complexity (FSC × SSC) using the Infinicity 1.7 software. Lymphocytes were negative control. We compared the results with IHC analyses carried out in parallel and independently. The expression of Ki-67 was evaluated in both methodologies through Bland-Altman analysis. Among the 44 samples analyzed, only three showed bias higher than the established confidence interval (mean bias 2.1%, p = 0.62), with no significant difference for the perfect mean bias (0%). Therefore, one can state that FC provides results equivalent to IHC analysis and possibly analyzes more cells simultaneously. The results obtained in this study show the absence of observational bias through software analysis in a larger number of tumor cell populations. We can conclude that FC may be a promising alternative method for investigating Ki-67 in solid tumours.

Evaluating Cancer-Related Biomarkers Based on Pathological Images: A Systematic Review

Many diseases are accompanied by changes in certain biochemical indicators called biomarkers in cells or tissues. A variety of biomarkers, including proteins, nucleic acids, antibodies, and peptides, have been identified. Tumor biomarkers have been widely used in cancer risk assessment, early screening, diagnosis, prognosis, treatment, and progression monitoring. For example, the number of circulating tumor cell (CTC) is a prognostic indicator of breast cancer overall survival, and tumor mutation burden (TMB) can be used to predict the efficacy of immune checkpoint inhibitors. Currently, clinical methods such as polymerase chain reaction (PCR) and next generation sequencing (NGS) are mainly adopted to evaluate these biomarkers, which are time-consuming and expansive. Pathological image analysis is an essential tool in medical research, disease diagnosis and treatment, functioning by extracting important physiological and pathological information or knowledge from medical images. Recently, deep learning-based analysis on pathological images and morphology to predict tumor biomarkers has attracted great attention from both medical image and machine learning communities, as this combination not only reduces the burden on pathologists but also saves high costs and time. Therefore, it is necessary to summarize the current process of processing pathological images and key steps and methods used in each process, including: (1) pre-processing of pathological images, (2) image segmentation, (3) feature extraction, and (4) feature model construction. This will help people choose better and more appropriate medical image processing methods when predicting tumor biomarkers.

Bridging the Gap: The Critical Role of Regulatory Affairs and Clinical Affairs in the Total Product Life Cycle of Pathology Imaging Devices and Software

Manufacturers of pathology imaging devices and associated software engage regulatory affairs and clinical affairs (RACA) throughout the Total Product Life Cycle (TPLC) of regulated products. A number of manufacturers, pathologists, and end users are not familiar with how RACA involvement benefits each stage of the TPLC. RACA professionals are important contributors to product development and deployment strategies because these professionals maintain an understanding of the scientific, technical, and clinical aspects of biomedical product regulation, as well as the relevant knowledge of regulatory requirements, policies, and market trends for both local and global regulations and standards. Defining a regulatory and clinical strategy at the beginning of product design enables early evaluation of risks and provides assurance that the collected evidence supports the product's clinical claims (e.g., in a marketing application), its safe and effective use, and potential reimbursement strategies. It is recommended to involve RACA early and throughout the TPLC to assist with navigating changes in the regulatory environment and dynamic diagnostic market. Here we outline how various stakeholders can utilize RACA to navigate the nuanced landscape behind the development and use of clinical diagnostic products. Collectively, this work emphasizes the critical importance of RACA as an integral part of product development and, thereby, sustained innovation.

Nature and Significance of Stromal Differentiation,, PD-L1, and VISTA in GIST

The role of stromal differentiation (SD), program death-ligand 1 (PD-L1), and v-domain Ig suppressor of T cell activation (VISTA) in gastrointestinal stromal tumor (GIST) is largely unknown. Looking forward, the assessment of SD and immune check point inhibition will become more ubiquitous in surgical pathology. Immature, myxoid stroma has been found to be a poor prognostic signature in many cancer subtypes (colon, breast, cervix, esophagus, stomach); although little is known regarding its significance in GIST. For immune check-point inhibition, studies have demonstrated expression to be associated with patient outcomes in numerous cancer subtypes. The present body of work aims to evaluate SD, PD-L1 and VISTA; both in terms of its nature and significance in a clinical setting. Here we found PD-L1 expression in immune cells (IC) and immature SD to be associated with worse cancer free survival, while positive VISTA expression was found to be associated with improved outcomes. High-grade, immature SD had the highest propensity for death/recurrence and was the only variable found to have prognostic significance on multivariate analysis. Our findings support the evaluation of SD, PD-L1 and VISTA in GIST, with clinical practice implications for pathologists. Ultimately, we hope our findings lead to improved prognostication, further optimization of therapeutics, and improved outcomes in a true clinical environment. For GIST, PD-L1 and VISTA could be both clinically relevant and targetable, while SD may be the answer to clinical heterogeneity.

Independent Clinical Validation of the Automated Ki67 Scoring Guideline from the International Ki67 in Breast Cancer Working Group

Ki67 is an important biomarker with prognostic and potential predictive value in breast cancer. However, the lack of standardization hinders its clinical applicability. In this study, we aimed to investigate the reproducibility among pathologists following the guidelines of the International Ki67 in Breast Cancer Working Group (IKWG) for Ki67 scoring and to evaluate the prognostic potential of this platform in an independent cohort. Four algorithms were independently built by four pathologists based on our study cohort using an open-source digital image analysis (DIA) platform (QuPath) following the detailed guideline of the IKWG. The algorithms were applied on an ER+ breast cancer study cohort of 157 patients with 15 years of follow-up. The reference Ki67 score was obtained by a DIA algorithm trained on a subset of the study cohort. Intraclass correlation coefficient (ICC) was used to measure reproducibility. High interobserver reliability was reached with an ICC of 0.938 (CI: 0.920-0.952) among the algorithms and the reference standard. Comparing each machine-read score against relapse-free survival, the hazard ratios were similar (2.593-4.165) and showed independent prognostic potential (p ≤ 0.018, for all comparisons). In conclusion, we demonstrate high reproducibility and independent prognostic potential using the IKWG DIA instructions to score Ki67 in breast cancer. A prospective study is needed to assess the clinical utility of the IKWG DIA Ki67 instructions.

A New Automated Histomorphometric MATLAB Algorithm for Immunohistochemistry Analysis Using Whole Slide Imaging

The use of animal models along with the employment of advanced and sophisticated stereological methods for assessing bone quality combined with the use of statistical methods to evaluate the effectiveness of bone therapies has made it possible to investigate the pathways that regulate bone responses to medical devices. Image analysis of histomorphometric measurements remains a time-consuming task, as the image analysis software currently available does not allow for automated image segmentation. Such a feature is usually obtained by machine learning and with software platforms that provide image-processing tools such as MATLAB. In this study, we introduce a new MATLAB algorithm to quantify immunohistochemically stained critical-sized bone defect samples and compare the results with the commonly available Aperio Image Scope Positive Pixel Count (PPC) algorithm. Bland and Altman analysis and Pearson correlation showed that the measurements acquired with the new MATLAB algorithm were in excellent agreement with the measurements obtained with the Aperio PPC algorithm, and no significant differences were found within the histomorphometric measurements. The ability to segment whole slide images, as well as defining the size and the number of regions of interest to be quantified, makes this MATLAB algorithm a potential histomorphometric tool for obtaining more objective, precise, and reproducible quantitative assessments of entire critical-sized bone defect image data sets in an efficient and manageable workflow.

Deep learning in cancer diagnosis, prognosis and treatment selection

Deep learning is a subdiscipline of artificial intelligence that uses a machine learning technique called artificial neural networks to extract patterns and make predictions from large data sets. The increasing adoption of deep learning across healthcare domains together with the availability of highly characterised cancer datasets has accelerated research into the utility of deep learning in the analysis of the complex biology of cancer. While early results are promising, this is a rapidly evolving field with new knowledge emerging in both cancer biology and deep learning. In this review, we provide an overview of emerging deep learning techniques and how they are being applied to oncology. We focus on the deep learning applications for omics data types, including genomic, methylation and transcriptomic data, as well as histopathology-based genomic inference, and provide perspectives on how the different data types can be integrated to develop decision support tools. We provide specific examples of how deep learning may be applied in cancer diagnosis, prognosis and treatment management. We also assess the current limitations and challenges for the application of deep learning in precision oncology, including the lack of phenotypically rich data and the need for more explainable deep learning models. Finally, we conclude with a discussion of how current obstacles can be overcome to enable future clinical utilisation of deep learning.

Pixelwise H-score: A novel digital image analysis-based metric to quantify membrane biomarker expression from immunohistochemistry images

Immunohistochemistry (IHC) assays play a central role in evaluating biomarker expression in tissue sections for diagnostic and research applications. Manual scoring of IHC images, which is the current standard of practice, is known to have several shortcomings in terms of reproducibility and scalability to large scale studies. Here, by using a digital image analysis-based approach, we introduce a new metric called the pixelwise H-score (pix H-score) that quantifies biomarker expression from whole-slide scanned IHC images. The pix H-score is an unsupervised algorithm that only requires the specification of intensity thresholds for the biomarker and the nuclear-counterstain channels. We present the detailed implementation of the pix H-score in two different whole-slide image analysis software packages Visiopharm and HALO. We consider three biomarkers P-cadherin, PD-L1, and 5T4, and show how the pix H-score exhibits tight concordance to multiple orthogonal measurements of biomarker abundance such as the biomarker mRNA transcript and the pathologist H-score. We also compare the pix H-score to existing automated image analysis algorithms and demonstrate that the pix H-score provides either comparable or significantly better performance over these methodologies. We also present results of an empirical resampling approach to assess the performance of the pix H-score in estimating biomarker abundance from select regions within the tumor tissue relative to the whole tumor resection. We anticipate that the new metric will be broadly applicable to quantify biomarker expression from a wide variety of IHC images. Moreover, these results underscore the benefit of digital image analysis-based approaches which offer an objective, reproducible, and highly scalable strategy to quantitatively analyze IHC images.

Ki-67 as a Prognostic Biomarker in Invasive Breast Cancer

The advent of molecular medicine has transformed breast cancer management. Breast cancer is now recognised as a heterogenous disease with varied morphology, molecular features, tumour behaviour, and response to therapeutic strategies. These parameters are underpinned by a combination of genomic and immunohistochemical tumour factors, with estrogen receptor (ER) status, progesterone receptor (PgR) status, human epidermal growth factor receptor-2 (HER2) status, Ki-67 proliferation indices, and multigene panels all playing a contributive role in the substratification, prognostication and personalization of treatment modalities for each case. The expression of Ki-67 is strongly linked to tumour cell proliferation and growth and is routinely evaluated as a proliferation marker. This review will discuss the clinical utility, current pitfalls, and promising strategies to augment Ki-67 proliferation indices in future breast oncology.

Detecting breast cancer using artificial intelligence: Convolutional neural network

BACKGROUND

One of the most broadly founded approaches to envisage cancer treatment relies upon a pathologist's efficiency to visually inspect the appearances of bio-markers on the invasive tumor tissue section. Lately, deep learning techniques have radically enriched the ability of computers to identify objects in images fostering the prospect for fully automated computer-aided diagnosis. Given the noticeable role of nuclear structure in cancer detection, AI's pattern recognizing ability can expedite the diagnostic process.

OBJECTIVE

In this study, we propose and implement an image classification technique to identify breast cancer.

METHODS

We implement the convolutional neural network (CNN) on breast cancer image data set to identify invasive ductal carcinoma (IDC).

RESULT

The proposed CNN model after data augmentation yielded 78.4% classification accuracy. 16% of IDC (-) were predicted incorrectly (false negative) whereas 25% of IDC (+) were predicted incorrectly (false positive).

CONCLUSION

The results achieved by the proposed approach have shown that it is feasible to employ a convolutional neural network particularly for breast cancer classification tasks. However, a common problem in any artificial intelligence algorithm is its dependence on the data set. Therefore, the performance of the proposed model might not be generalized.

DeepHistoClass: A Novel Strategy for Confident Classification of Immunohistochemistry Images Using Deep Learning

A multitude of efforts worldwide aim to create a single-cell reference map of the human body, for fundamental understanding of human health, molecular medicine, and targeted treatment. Antibody-based proteomics using immunohistochemistry (IHC) has proven to be an excellent technology for integration with large-scale single-cell transcriptomics datasets. The golden standard for evaluation of IHC staining patterns is manual annotation, which is expensive and may lead to subjective errors. Artificial intelligence holds much promise for efficient and accurate pattern recognition, but confidence in prediction needs to be addressed. Here, the aim was to present a reliable and comprehensive framework for automated annotation of IHC images. We developed a multilabel classification of 7848 complex IHC images of human testis corresponding to 2794 unique proteins, generated as part of the Human Protein Atlas (HPA) project. Manual annotation data for eight different cell types was generated as a basis for training and testing a proposed Hybrid Bayesian Neural Network. By combining the deep learning model with a novel uncertainty metric, DeepHistoClass (DHC) Confidence Score, the average diagnostic performance improved from 86.9% to 96.3%. This metric not only reveals which images are reliably classified by the model, but can also be utilized for identification of manual annotation errors. The proposed streamlined workflow can be developed further for other tissue types in health and disease and has important implications for digital pathology initiatives or large-scale protein mapping efforts such as the HPA project.

•

A novel method for automated annotation of immunohistochemistry images.

•

Introduction of an uncertainty metric, the DeepHistoClass (DHC) confidence score.

•

Increased accuracy of automated image predictions.

•

Identification of manual annotation errors.

Quantitative Image Analysis for Tissue Biomarker Use: A White Paper From the Digital Pathology Association

Tissue biomarkers have been of increasing utility for scientific research, diagnosing disease, and treatment response prediction. There has been a steady shift away from qualitative assessment toward providing more quantitative scores for these biomarkers. The application of quantitative image analysis has thus become an indispensable tool for in-depth tissue biomarker interrogation in these contexts. This white paper reviews current technologies being employed for quantitative image analysis, their application and pitfalls, regulatory framework demands, and guidelines established for promoting their safe adoption in clinical practice.

Reliability of Ki67 visual scoring app compared to eyeball estimate and digital image analysis and its prognostic significance in hormone receptor-positive breast cancer

We analysed the reproducibility of Ki67 labelling index (LI) between two scorers using the International Ki67 Working Group (IKWG) global methods on an Android application (APP), correlated the APP and eyeball estimate (EBE) with digital image analysis (DIA) scores and determined the prognostic significance of Ki67LI. Global weighted (GW) and global unweighted (GUW) Ki67 app scores of hormone receptor-positive and HER2 (human epidermal growth factor receptor 2)-negative breast cancer patients were obtained. Reproducibility of Ki67LI between 2 scorers and correlation of APP and EBE scores with DIA scores were performed. The prognostic significance of APP scores and its correlation with other clinico-pathologic variables were evaluated. The intra-class correlation coefficient (ICC) between 2 scorers showed excellent reliability with both GW and GUW methods. ICC between DIA and APP scores was significantly greater than DIA versus EBE. The three categories of APP scores based on median value and cut points of 10%, 18% and 38% were significantly associated with poor DFS. On multivariate analysis, significant association between Ki67LI, tumour size, nodal involvement and DFS was noted. Our study shows that the visual Ki67 scoring app is effective in bringing consistency to KI67LI and APP scores showed significant correlation with DFS.

The human-in-the-loop: an evaluation of pathologists' interaction with artificial intelligence in clinical practice

AIMS

One of the major drivers of the adoption of digital pathology in clinical practice is the possibility of introducing digital image analysis (DIA) to assist with diagnostic tasks. This offers potential increases in accuracy, reproducibility, and efficiency. Whereas stand-alone DIA has great potential benefit for research, little is known about the effect of DIA assistance in clinical use. The aim of this study was to investigate the clinical use characteristics of a DIA application for Ki67 proliferation assessment. Specifically, the human-in-the-loop interplay between DIA and pathologists was studied.

METHODS AND RESULTS

We retrospectively investigated breast cancer Ki67 areas assessed with human-in-the-loop DIA and compared them with visual and automatic approaches. The results, expressed as standard deviation of the error in the Ki67 index, showed that visual estimation ('eyeballing') (14.9 percentage points) performed significantly worse (P < 0.05) than DIA alone (7.2 percentage points) and DIA with human-in-the-loop corrections (6.9 percentage points). At the overall level, no improvement resulting from the addition of human-in-the-loop corrections to the automatic DIA results could be seen. For individual cases, however, human-in-the-loop corrections could address major DIA errors in terms of poor thresholding of faint staining and incorrect tumour-stroma separation.

CONCLUSION

The findings indicate that the primary value of human-in-the-loop corrections is to address major weaknesses of a DIA application, rather than fine-tuning the DIA quantifications.

Validation of a DKK1 RNAscope chromogenic in situ hybridization assay for gastric and gastroesophageal junction adenocarcinoma tumors

Dickkopf-1 (DKK1) is a secreted modulator of Wnt signaling that is frequently overexpressed in tumors and associated with poor clinical outcomes. DKN-01 is a humanized monoclonal therapeutic antibody that binds DKK1 with high affinity and has demonstrated clinical activity in gastric/gastroesophageal junction (G/GEJ) patients with elevated tumoral expression of DKK1. Here we report on the validation of a DKK1 RNAscope chromogenic in situ hybridization assay to assess DKK1 expression in G/GEJ tumor tissue. To reduce pathologist time, potential pathologist variability from manual scoring and support pathologist decision making, a digital image analysis algorithm that identifies tumor cells and quantifies the DKK1 signal was developed. Following CLIA guidelines the DKK1 RNAscope chromogenic in situ hybridization assay and digital image analysis algorithm were successfully validated for sensitivity, specificity, accuracy, and precision. The DKK1 RNAscope assay in conjunction with the digital image analysis solution is acceptable for prospective screening of G/GEJ adenocarcinoma patients. The work described here will further advance the companion diagnostic development of our DKK1 RNAscope assay and could generally be used as a guide for the validation of RNAscope assays with digital image quantification.

Improving DCIS diagnosis and predictive outcome by applying artificial intelligence

Breast ductal carcinoma in situ (DCIS) is a preinvasive lesion that is considered to be a precursor to invasive breast cancer. Nevertheless, not all DCIS will progress to invasion. Current histopathological classification systems are unable to predict which cases will or will not progress, and therefore many women with DCIS may be overtreated. Artificial intelligence (AI) image-based analysis methods have potential to identify and analyze novel features that may facilitate tumor identification, prediction of disease outcome and response to treatment. Indeed, these methods prove promising for accurately identifying DCIS lesions, and show potential clinical utility in the therapeutic stratification of DCIS patients. Here, we review how AI techniques in histopathology may aid diagnosis and clinical decisions in regards to DCIS, and how such techniques could be incorporated into clinical practice.

Integrating the Health-care Enterprise Pathology and Laboratory Medicine Guideline for Digital Pathology Interoperability

Integrating the health-care enterprise (IHE) is an international initiative to promote the use of standards to achieve interoperability among health information technology systems. The Pathology and Laboratory Medicine domain within IHE has brought together subject matter experts, electronic health record vendors, and digital imaging vendors, to initiate development of a series of digital pathology interoperability guidelines, called “integration profiles” within IHE. This effort begins with documentation of common use cases, followed by identification of available data and technology standards best utilized to achieve those use cases. An integration profile that describes the information flow and technology interactions is then published for trial use. Real world testing occurs in “connectathon” events, in which multiple vendors attempt to connect their products following the interoperability guidance parameters set forth in the profile. This paper describes the overarching set of integration profiles, one of which has been published, to support key digital pathology use cases.

Prognostic role of serum thymidine kinase 1 kinetics during neoadjuvant chemotherapy for early breast cancer

Background

Emerging data support the use of thymidine kinase 1 (TK1) activity as a prognostic marker and for monitoring of response in breast cancer (BC). The long-term prognostic value of TK1 kinetics during neoadjuvant chemotherapy is unclear, which this study aimed to elucidate.

Methods

Material from patients enrolled to the single-arm prospective PROMIX trial of neoadjuvant epirubicin, docetaxel and bevacizumab for early BC was used. Ki67 in baseline biopsies was assessed both centrally and by automated digital imaging analysis. TK1 activity was measured from blood samples obtained at baseline and following two cycles of chemotherapy. The associations of TK1 and its kinetics as well as Ki67 with event-free survival and overall survival (OS) were evaluated using multivariable Cox regression models.

Results

Central Ki67 counting had excellent correlation with the results of digital image analysis (r = 0.814), but not with the diagnostic samples (r = 0.234), while it was independently prognostic for worse OS [adjusted hazard ratio (HR_adj) = 2.72, 95% confidence interval (CI) 1.19-6.21, P = 0.02]. Greater increase in TK1 activity after two cycles of chemotherapy resulted in improved event-free survival (HR_adj = 0.50, 95% CI 0.26-0.97, P = 0.04) and OS (HR_adj = 0.46, 95% CI 0.95, P = 0.04). There was significant interaction between the prognostic value of TK1 kinetics and Ki67 (p_interaction 0.04).

Conclusion

Serial measurement of serum TK1 activity during neoadjuvant chemotherapy provides long-term prognostic information in BC patients. The ease of obtaining serial samples for TK1 assessment motivates further evaluation in larger studies.

•

This is a correlative analysis of a prospective phase II study on neoadjuvant chemotherapy for breast cancer.

•

Serial measurement of serum TK1 activity during treatment provides independent long-term prognostic information.

•

We demonstrate the validity and clinical utility of both central and automated image analysis-based Ki67 assessment.

•

Finally, we explore the biologic correlations between TK1 and Ki67.

Variability in Breast Cancer Biomarker Assessment and the Effect on Oncological Treatment Decisions: A Nationwide 5-Year Population-Based Study

We compared estrogen receptor (ER), progesterone receptor (PR), human epidermal growth-factor receptor 2 (HER2), Ki67, and grade scores among the pathology departments in Sweden. We investigated how ER and HER2 positivity rates affect the distribution of endocrine and HER2-targeted treatments among oncology departments. All breast cancer patients diagnosed between 2013 and 2018 in Sweden were identified in the National Quality Register for Breast Cancer. Cases with data on ER, PR, HER2, Ki67, grade, and treatment were selected (43,261 cases from 29 departments following the guidelines for biomarker testing). The ER positivity rates ranged from 84.2% to 97.6% with 6/29 labs out of the overall confidence intervals (CIs), while PR rates varied between 64.8% and 86.6% with 7/29 labs out of the CIs. HER2 positivity rates ranged from 9.4% to 16.3%, with 3/29 labs out of the overall CIs. Median Ki67 varied between 15% and 30%, where 19/29 labs showed significant intra-laboratory variability. The proportion of grade-II cases varied between 42.9% and 57.1%, and 13/29 labs were outside of the CI. Adjusting for patient characteristics, the proportion of endocrine and anti-HER2 treatments followed the rate of ER and HER2 positivity, illustrating the clinical effect of inter- and intra-laboratory variability. There was limited variability among departments in ER, PR, and HER2 testing. However, even a few outlier pathology labs affected endocrine and HER2-targeted treatment rates in a clinically relevant proportion, suggesting the need for improvement. High variability was found in grading and Ki67 assessment, illustrating the need for the adoption of new technologies in practice.

Intratumor Heterogeneity in Uveal Melanoma BAP-1 Expression

Malignant tumors are rarely homogenous on the morphological, genome, transcriptome or proteome level. In this study, we investigate the intratumor heterogeneity of BAP-1 expression in uveal melanoma with digital image analysis of 40 tumors. The proportion of BAP-1 positive cells was measured in full tumor sections, hot spots, cold spots and in scleral margins. The mean difference between hot spots and cold spots was 41 percentage points (pp, SD 29). Tumors with gene expression class 1 (associated with low metastatic risk) and 2 (high metastatic risk) had similar intratumor heterogeneity. Similarly, the level of intratumor heterogeneity was comparable in tumors from patients that later developed metastases as in patients that did not. BAP-1 measured in any tumor region added significant prognostic information to both American Joint Committee on Cancer (AJCC) tumor size category (p ≤ 0.001) and gene expression class (p ≤ 0.04). We conclude that there is substantial intratumor heterogeneity in uveal melanoma BAP-1 expression. However, it is of limited prognostic importance. Regardless of region, analysis of BAP-1 expression adds significant prognostic information beyond tumor size and gene expression class.