Automated tumor analysis for molecular profiling in lung cancer. Oncotarget. 2015;6:27938-27952. [PMID: 26317646 DOI: 10.18632/oncotarget.4391]

MetFinder: A Tool for Automated Quantitation of Metastatic Burden in Histological Sections From Preclinical Models

As efforts to study the mechanisms of melanoma metastasis and novel therapeutic approaches multiply, researchers need accurate, high-throughput methods to evaluate the effects on tumor burden resulting from specific interventions. We show that automated quantification of tumor content from whole slide images is a compelling solution to assess in vivo experiments. In order to increase the outflow of data collection from preclinical studies, we assembled a large dataset with annotations and trained a deep neural network for the quantitative analysis of melanoma tumor content on histopathological sections of murine models. After assessing its performance in segmenting these images, the tool obtained consistent results with an orthogonal method (bioluminescence) of measuring metastasis in an experimental setting. This AI-based algorithm, made freely available to academic laboratories through a web-interface called MetFinder, promises to become an asset for melanoma researchers and pathologists interested in accurate, quantitative assessment of metastasis burden.

Low densities of immune cells indicate unfavourable overall survival in patients suffering from squamous cell carcinoma of the lung

Carcinogenesis and tumor proliferation are characterized by a complex interaction of cancer cells with the tumor microenvironment. In particular, a tumor-promoting effect can be assumed for the stroma and its fibroblasts. An influence of the immune system on non small cell lung cancer (NSCLC) is now also suspected. In our study, we examined 309 sections of squamous cell carcinoma (SCC), a subtype of NSCLC. We determined the cell densities and areas of the different tissues in SCC using the software QuPath. Spearman rank correlation showed a significant positive correlation between the different tumor cell densities and stromal cell densities, and between tumor cell densities and immune cell densities. Overall survival curves by the Kaplan-Meier method revealed a prominent negative curve in cases of low immune cell density. Based on our results, we can assume a positive influence of the tumor microenvironment, especially the stromal cells, on tumor proliferation in SCC. We have also revealed that low density of immune cells is prognostically unfavorable.

Digital counting of tissue cells for molecular analysis: the QuANTUM pipeline

The estimation of tumor cellular fraction (TCF) is a crucial step in predictive molecular pathology, representing an entry adequacy criterion also in the next-generation sequencing (NGS) era. However, heterogeneity of quantification practices and inter-pathologist variability hamper the robustness of its evaluation, stressing the need for more reliable results. Here, 121 routine histological samples from non-small cell lung cancer (NSCLC) cases with complete NGS profiling were used to evaluate TCF interobserver variability among three different pathologists (pTCF), developing a computational tool (cTCF) and assessing its reliability vs ground truth (GT) tumor cellularity and potential impact on the final molecular results. Inter-pathologist reproducibility was fair to good, with overall Wk ranging between 0.46 and 0.83 (avg. 0.59). The obtained cTCF was comparable to the GT (p = 0.129, 0.502, and 0.130 for surgical, biopsies, and cell block, respectively) and demonstrated good reliability if elaborated by different pathologists (Wk = 0.9). Overall cTCF was lower as compared to pTCF (30 ± 10 vs 52 ± 19, p < 0.001), with more cases < 20% (17, 14%, p = 0.690), but none containing < 100 cells for the algorithm. Similarities were noted between tumor area estimation and pTCF (36 ± 29, p < 0.001), partly explaining variability in the human assessment of tumor cellularity. Finally, the cTCF allowed a reduction of the copy number variations (CNVs) called (27 vs 29, - 6.9%) with an increase of effective CNVs detection (13 vs 7, + 85.7%), some with potential clinical impact previously undetected with pTCF. An automated computational pipeline (Qupath Analysis of Nuclei from Tumor to Uniform Molecular tests, QuANTUM) has been created and is freely available as a QuPath extension. The computational method used in this study has the potential to improve efficacy and reliability of TCF estimation in NSCLC, with demonstrated impact on the final molecular results.

Responding to the healthcare workforce shortage: A scoping review exploring anatomical pathologists' professional identities over time

Anatomical pathology (AP) is an anatomy-centric medical specialty devoted to tissue-based diagnosis of disease. The field faces a current and predicted workforce shortage, likely increasing diagnostic wait times and delaying patient access to urgent treatment. A lack of AP exposure is proposed to preclude recruitment to the field, as medical students are afforded only a limited understanding of who a pathologist is and what they do (their professional identity/PI and role). Anatomical sciences educators may be well placed to increase student understanding of anatomical pathologists' PI features, but until features of anatomical pathologists' PI are understood, recommendations for anatomy educators are premature. Thus, this scoping review asked: "What are the professional identity features of anatomical pathologists reported in the literature, and how have these changed over time?" A six-stage scoping review was performed. Medline and PubMed, Global Health, and Embase were used to identify relevant studies (n = 74). Team-based framework analysis identified that features of anatomical pathologists' professional identity encompass five overarching themes: professional practice, views about the role, training and education, personal implications, and technology. Technology was identified as an important theme of anatomical pathologists' PI, as it intersected with many other PI feature themes, including diagnosis and collaboration. This review found that pathologists may sometimes perceive professional competition with technology, such as artificial intelligence. These findings suggest unique opportunities for integrating AP-specific PI features into anatomy teaching, which may foster student interest in AP, and potentially increase recruitment into the field.

Pathologist Computer-Aided Diagnostic Scoring of Tumor Cell Fraction: A Swiss National Study

Tumor cell fraction (TCF) estimation is a common clinical task with well-established large interobserver variability. It thus provides an ideal test bed to evaluate potential impacts of employing a tumor cell fraction computer-aided diagnostic (TCFCAD) tool to support pathologists' evaluation. During a National Slide Seminar event, pathologists (n = 69) were asked to visually estimate TCF in 10 regions of interest (ROIs) from hematoxylin and eosin colorectal cancer images intentionally curated for diverse tissue compositions, cellularity, and stain intensities. Next, they re-evaluated the same ROIs while being provided a TCFCAD-created overlay highlighting predicted tumor vs nontumor cells, together with the corresponding TCF percentage. Participants also reported confidence levels in their assessments using a 5-tier scale, indicating no confidence to high confidence, respectively. The TCF ground truth (GT) was defined by manual cell-counting by experts. When assisted, interobserver variability significantly decreased, showing estimates converging to the GT. This improvement remained even when TCFCAD predictions deviated slightly from the GT. The standard deviation (SD) of the estimated TCF to the GT across ROIs was 9.9% vs 5.8% with TCFCAD (P < .0001). The intraclass correlation coefficient increased from 0.8 to 0.93 (95% CI, 0.65-0.93 vs 0.86-0.98), and pathologists stated feeling more confident when aided (3.67 ± 0.81 vs 4.17 ± 0.82 with the computer-aided diagnostic [CAD] tool). TCFCAD estimation support demonstrated improved scoring accuracy, interpathologist agreement, and scoring confidence. Interestingly, pathologists also expressed more willingness to use such a CAD tool at the end of the survey, highlighting the importance of training/education to increase adoption of CAD systems.

Histopathological Images Analysis and Predictive Modeling Implemented in Digital Pathology-Current Affairs and Perspectives

In modern clinical practice, digital pathology has an essential role, being a technological necessity for the activity in the pathological anatomy laboratories. The development of information technology has majorly facilitated the management of digital images and their sharing for clinical use; the methods to analyze digital histopathological images, based on artificial intelligence techniques and specific models, quantify the required information with significantly higher consistency and precision compared to that provided by optical microscopy. In parallel, the unprecedented advances in machine learning facilitate, through the synergy of artificial intelligence and digital pathology, the possibility of diagnosis based on image analysis, previously limited only to certain specialties. Therefore, the integration of digital images into the study of pathology, combined with advanced algorithms and computer-assisted diagnostic techniques, extends the boundaries of the pathologist's vision beyond the microscopic image and allows the specialist to use and integrate his knowledge and experience adequately. We conducted a search in PubMed on the topic of digital pathology and its applications, to quantify the current state of knowledge. We found that computer-aided image analysis has a superior potential to identify, extract and quantify features in more detail compared to the human pathologist's evaluating possibilities; it performs tasks that exceed its manual capacity, and can produce new diagnostic algorithms and prediction models applicable in translational research that are able to identify new characteristics of diseases based on changes at the cellular and molecular level.

A Comparison of Two Different FFPE Tissue Dissection Methods for Routine Diagnostics in Molecular Pathology: Manual Macrodissection versus Automated Microdissection Using the Roche "AVENIO Millisect" System

Currently, in routine diagnostics, most molecular testing is performed on formalin-fixed, paraffin-embedded tissue after a histomorphological assessment. In order to find the best possible and targeted individual therapy, knowing the mutational status of the tumour is crucial. The "AVENIO Millisect" system Roche introduced an automation solution for the dissection of tissue on slides. This technology allows the precise and fully automated dissection of the tumour area without wasting limited and valuable patient material. In this study, the digitally guided microdissection was directly compared to the manual macrodissection regarding the precision and duration of the procedure, their DNA concentrations as well as DNA qualities, and the overall costs in 24 FFPE samples. In 21 of 24 cases (87.5%), the DNA yields of the manually dissected samples were higher in comparison to the automatically dissected samples. Shorter execution times and lower costs were also benefits of the manual scraping process. Nevertheless, the DNA quality achieved with both methods was comparable, which is essential for further molecular testing. Therefore, it could be used as an additional tool for precise tumour enrichment.

Automation: A revolutionary vision of artificial intelligence in theranostics

The last two decades have witnessed an extraordinary evolution of automation and artificial intelligence (AI), which has become an integral part of our daily lives. Lately, AI has also been assimilated in the field of medicine to upgrade overall healthcare system and encourage personalized treatment. Theranostics literally meaning combination of diagnosis and therapeutics, is a targeted pharmacotherapy, based on specific targeted diagnostic tests. Numerous theranostic agents/biomarkers are available which can identify the most beneficial treatment, correct dose or predict response to a medicine, thus, maximizing drug efficacy, minimizing toxicity and providing informed treatment choice. For instance, a statistics based Cluster-FLIM technology provides precise data on drug-receptor binding behavior in biological tissues using fluorescence real experimental imaging. Automated Idylla™ qPCR System is another approach in oncology to determine the EGFR mutations at initial stage as well as during the treatment and also assists the oncologist in designing the treatment protocol. Recent incorporation of automation and AI in theranostics has brought a drastic change in early detection and treatment protocols for various diseases such as cancer and diabetes. Also, it leads to quick analysis of number of diverse experimental datum with accuracy. The approach mainly uses computer algorithms to unveil relevant and significant information from clinical data, thereby assisting in making accurate, logical and pertinent decisions. This review highlights the emerging uses/role of automation and AI in theranostics, technical difficulties and focuses on its future prospects to facilitate a patient specific, reliable and efficient pharmacotherapy.

Developing image analysis methods for digital pathology

The potential to use quantitative image analysis and artificial intelligence is one of the driving forces behind digital pathology. However, despite novel image analysis methods for pathology being described across many publications, few become widely adopted and many are not applied in more than a single study. The explanation is often straightforward: software implementing the method is simply not available, or is too complex, incomplete, or dataset‐dependent for others to use. The result is a disconnect between what seems already possible in digital pathology based upon the literature, and what actually is possible for anyone wishing to apply it using currently available software. This review begins by introducing the main approaches and techniques involved in analysing pathology images. I then examine the practical challenges inherent in taking algorithms beyond proof‐of‐concept, from both a user and developer perspective. I describe the need for a collaborative and multidisciplinary approach to developing and validating meaningful new algorithms, and argue that openness, implementation, and usability deserve more attention among digital pathology researchers. The review ends with a discussion about how digital pathology could benefit from interacting with and learning from the wider bioimage analysis community, particularly with regard to sharing data, software, and ideas. © 2022 The Author. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Obtaining spatially resolved tumor purity maps using deep multiple instance learning in a pan-cancer study

Tumor purity is the percentage of cancer cells within a tissue section. Pathologists estimate tumor purity to select samples for genomic analysis by manually reading hematoxylin-eosin (H&E)-stained slides, which is tedious, time consuming, and prone to inter-observer variability. Besides, pathologists' estimates do not correlate well with genomic tumor purity values, which are inferred from genomic data and accepted as accurate for downstream analysis. We developed a deep multiple instance learning model predicting tumor purity from H&E-stained digital histopathology slides. Our model successfully predicted tumor purity in eight The Cancer Genome Atlas (TCGA) cohorts and a local Singapore cohort. The predictions were highly consistent with genomic tumor purity values. Thus, our model can be utilized to select samples for genomic analysis, which will help reduce pathologists' workload and decrease inter-observer variability. Furthermore, our model provided tumor purity maps showing the spatial variation within sections. They can help better understand the tumor microenvironment.

•

MIL model successfully predicts a sample's tumor purity from histopathology slides

•

MIL model learns to spatially resolve tumor purity from sample-level labels

•

Tumor purity varies spatially within a sample

•

Pathologists’ region selection is vital for correct percentage tumor nuclei estimation

Given some big data and coarse-level labels, extracting fine-level information is a demanding yet rewarding challenge in data science. This study develops a machine learning model utilizing big data and exploiting coarse-level labels to reveal fine-level details within the data. Although it can be applied to different data science tasks with enormous data and coarse labels, we applied it to a computational histopathology task with gigapixel histopathology slides and sample-level labels. Specifically, the model revealed spatial resolution of tumor purity within histopathology slides using only sample-level genomic tumor purity values during training. This can also be extended to other omics features, providing precious information about cancer biology and promising personalized, precision medicine. Such studies are of great clinical importance in discovering imaging biomarkers and better understanding the tumor microenvironment.

Artificial intelligence-augmented histopathologic review using image analysis to optimize DNA yield from formalin-fixed paraffin-embedded slides

To achieve minimum DNA input requirements for next-generation sequencing (NGS), pathologists visually estimate macrodissection and slide count decisions. Unfortunately, misestimation may cause tissue waste and increased laboratory costs. We developed an artificial intelligence (AI)-augmented smart pathology review system (SmartPath) to empower pathologists with quantitative metrics for accurately determining tissue extraction parameters. SmartPath uses two deep learning architectures, a U-Net based network for cell segmentation and a multi-field-of-view convolutional network for tumor area segmentation, to extract features from digitized H&E-stained formalin-fixed paraffin-embedded slides. From the segmented tumor area, SmartPath suggests a macrodissection area. To predict DNA yield per slide, the extracted features from within the macrodissection area are correlated with known DNA yields to fit a regularized linear model (R = 0.85). Then, a pathologist-defined target yield divided by the predicted DNA yield per slide gives the number of slides to scrape. Following model development, an internal validation trial was conducted within the Tempus Labs molecular sequencing laboratory. We evaluated our system on 501 clinical colorectal cancer slides, where half received SmartPath-augmented review and half traditional pathologist review. The SmartPath cohort had 25% more DNA yields within a desired target range of 100-2000 ng. The number of extraction attempts was statistically unchanged between cohorts. The SmartPath system recommended fewer slides to scrape for large tissue sections, saving tissue in these cases. Conversely, SmartPath recommended more slides to scrape for samples with scant tissue sections, especially those with degraded DNA, helping prevent costly re-extraction due to insufficient extraction yield. A statistical analysis was performed to measure the impact of covariates on the results, offering insights on how to improve future applications of SmartPath. With these improvements, AI-augmented histopathologic review has the potential to decrease tissue waste, sequencing time, and laboratory costs by optimizing DNA yields, especially for samples with scant tissue and/or degraded DNA.

A Means of Assessing Deep Learning-Based Detection of ICOS Protein Expression in Colon Cancer

Biomarkers identify patient response to therapy. The potential immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS), expressed on regulating T-cell activation and involved in adaptive immune responses, is of great interest. We have previously shown that open-source software for digital pathology image analysis can be used to detect and quantify ICOS using cell detection algorithms based on traditional image processing techniques. Currently, artificial intelligence (AI) based on deep learning methods is significantly impacting the domain of digital pathology, including the quantification of biomarkers. In this study, we propose a general AI-based workflow for applying deep learning to the problem of cell segmentation/detection in IHC slides as a basis for quantifying nuclear staining biomarkers, such as ICOS. It consists of two main parts: a simplified but robust annotation process, and cell segmentation/detection models. This results in an optimised annotation process with a new user-friendly tool that can interact with1 other open-source software and assists pathologists and scientists in creating and exporting data for deep learning. We present a set of architectures for cell-based segmentation/detection to quantify and analyse the trade-offs between them, proving to be more accurate and less time consuming than traditional methods. This approach can identify the best tool to deliver the prognostic significance of ICOS protein expression.

The Potential of Digital Image Analysis to Determine Tumor Cell Content in Biobanked Formalin-Fixed, Paraffin-Embedded Tissue Samples

Introduction: Best practices dictate that biobanks ensure accurate determination of tumor content before supplying formalin-fixed, paraffin-embedded (FFPE) tissue samples to researchers for nucleic acid extraction and downstream molecular testing. It is advisable that trained and competent individuals, who understand the requirements of the downstream molecular tests, perform the microscopic morphological examination. However, the special skills, time, and costs associated with these assessments can be prohibitive, especially in large case cohorts requiring extensive pathological review. Determination of tumor content reliably by digital image analysis (DIA) could represent a significant advantage if validated, utilized, and deployed by biobanks. Materials and Methods: Whole slide digital scanned images of colorectal, lung, and breast cancer specimens were created. The scanned images were imported into the DIA software QuPath and digital annotations were completed by biobank technicians, under the direction of trained histopathology senior scientists. Automated cell detection was conducted and tumor epithelial cells were classified and quantified. Results: DIA scores were highly concordant with the manual assessment for 376 of 435 samples (86%). A detailed review of discordant cases indicated digital scores had a higher accuracy than the manual estimation. Conclusion: Automated digital quantification has the potential to replace visual estimations with reduced subjectivity and increased reliability compared with manual tumor estimations. We recommend the use of DIA by biobanks involved in provision of FFPE tissue samples, especially in large research studies requiring high volumes of cases to be analyzed.

Morphological control for molecular testing: a practical approach

The determination of molecular aberrations within tumours is important for diagnostic, prognostic and predictive purposes. Pathologists play a critical role in the workflow of molecular diagnostics, by assuring accurate pathological diagnosis, requesting appropriate molecular testing, selecting the adequate tissue section for molecular analysis, enriching tumour cell content by manual macrodissection and estimating the tumour cellularity. Particularly, the assessment of the malignant cell fraction within a tumour section is a key determinant for an appropriate interpretation of the molecular findings. Several factors may impact the estimation of tumour cellularity and constitute a potential pitfall for the final interpretation of the molecular analysis. Evidence suggests that the reliability of morphological control could be improved by training. The scope of this commentary is to provide the training morpho-molecular pathologists with the practical tools necessary to master microscopic morphological control for solid tumours, as well as a set of images that could serve as a training set.

Translational AI and Deep Learning in Diagnostic Pathology

There has been an exponential growth in the application of AI in health and in pathology. This is resulting in the innovation of deep learning technologies that are specifically aimed at cellular imaging and practical applications that could transform diagnostic pathology. This paper reviews the different approaches to deep learning in pathology, the public grand challenges that have driven this innovation and a range of emerging applications in pathology. The translation of AI into clinical practice will require applications to be embedded seamlessly within digital pathology workflows, driving an integrated approach to diagnostics and providing pathologists with new tools that accelerate workflow and improve diagnostic consistency and reduce errors. The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI. AI and computational pathology will continue to mature as researchers, clinicians, industry, regulatory organizations and patient advocacy groups work together to innovate and deliver new technologies to health care providers: technologies which are better, faster, cheaper, more precise, and safe.

Artificial intelligence in cytopathology: a review of the literature and overview of commercial landscape

Artificial intelligence (AI) has made impressive strides recently in interpreting complex images, thanks to improvements in deep learning techniques and increasing computational power. Researchers have started applying these advanced techniques to pathology images, although most efforts have been focused on histopathology. Cytopathology, however, remains the original field of pathology for which AI models for clinical use were successfully commercialized, to assist with automating Papanicolaou test screening. Recent AI efforts have focused on whole slide images of both gynecologic and non-gynecologic cytopathology. This review summarizes the literature and commercial landscape of AI as applied to cytopathology.

A Review of Urine Ancillary Tests in the Era of the Paris System

Aside from its diagnostic importance, urinary tract endoscopy is an uncomfortable, expensive, and time-consuming procedure. Patients with a history of urothelial carcinoma remain at an increased risk for recurrence and the development of de novo disease; most have had exposure to carcinogenic risk factors for decades prior to their first diagnosis that have bathed the entire urothelial tract. Consequently, monitoring these patients over their lifetime has made urothelial carcinoma one of the most expensive cancers for the US healthcare system. This expense has provided a financial incentive for academic and commercial groups to develop a test with a sufficient negative predictive value to reduce the frequency of surveillance procedures. Slide-based tests require a separate slide prepared from a split urine sample or from an additional urinary tract specimen. This process can place an additional burden on the laboratory due to changes in the workflow, especially if the split specimens need to be stored until a cytologic diagnosis is rendered (i.e., when used as a reflex test). Importantly, slide-based tests allow for the result to be directly correlated with cytomorphologic findings; however, these tests require the cells of interest to be present. Thus, slide-based tests suffer from the same sensitivity issues as urinary tract cytology. In contrast, slide-free tests do not require an additional slide to be prepared, and laboratory testing may be centralized to a core facility or performed on-site. Some tests detect the expression of altered or abnormally expressed subcellular material (proteins, DNA, etc.) in urothelial neoplasms, which are found in tumor cells and/or in the urine specimen when the proteins are either excreted or leaked from degenerating tumor cells. Slide-free tests may also be developed into point-of-care tests, meaning that the result may be available to the urologist but not to the cytopathologist. Since these proteins are often disassociated from the tumor cells that produce them, such tests may have a positive result even if tumor cells are absent in the tested specimen. Here we review critical concepts as well as several ancillary tests that have been developed for urinary tract specimens.

The use of digital pathology and image analysis in clinical trials

Digital pathology and image analysis potentially provide greater accuracy, reproducibility and standardisation of pathology-based trial entry criteria and endpoints, alongside extracting new insights from both existing and novel features. Image analysis has great potential to identify, extract and quantify features in greater detail in comparison to pathologist assessment, which may produce improved prediction models or perform tasks beyond manual capability. In this article, we provide an overview of the utility of such technologies in clinical trials and provide a discussion of the potential applications, current challenges, limitations and remaining unanswered questions that require addressing prior to routine adoption in such studies. We reiterate the value of central review of pathology in clinical trials, and discuss inherent logistical, cost and performance advantages of using a digital approach. The current and emerging regulatory landscape is outlined. The role of digital platforms and remote learning to improve the training and performance of clinical trial pathologists is discussed. The impact of image analysis on quantitative tissue morphometrics in key areas such as standardisation of immunohistochemical stain interpretation, assessment of tumour cellularity prior to molecular analytical applications and the assessment of novel histological features is described. The standardisation of digital image production, establishment of criteria for digital pathology use in pre-clinical and clinical studies, establishment of performance criteria for image analysis algorithms and liaison with regulatory bodies to facilitate incorporation of image analysis applications into clinical practice are key issues to be addressed to improve digital pathology incorporation into clinical trials.

External Quality Assessment Identifies Training Needs to Determine the Neoplastic Cell Content for Biomarker Testing

Neoplastic cell content determination is crucial for biomarker testing. It is known that interobserver variation exists, but largescale data are missing about variation in tumor delineation and cell content determination. Results were obtained from the external quality assessment program for metastatic colorectal cancer from the European Society of Pathology (N = 5776 observations). The study included three parts: current practices were surveyed, neoplastic cell content estimations and delineations were retrieved from stained slides, and clinical reports were analyzed. Seventeen of 43 pathologists determined the neoplastic cell content in a tumor-rich area for DNA extraction and took immune cells (n = 37), tumor cell distribution (n = 33), desmoplastic stroma (n = 30), necrosis (n = 29), and mucus (n = 23) into account. The selected area was highly variable, and the average difference between the highest and lowest estimation ranged between 51% and 78% (2011 to 2017). The number of overestimations was alarmingly high in samples containing <30% tumor cells. Of concern is that 33 of 105 laboratories reported a wild-type result in a sample without tumor in 2017. Standardization of neoplastic cell content determination is needed for test outcome interpretation. The authors' data show variation in estimation practices, tumor delineations and estimations, and interpretation problems (n = 226 reports). Further training for selecting the most suitable block and creating clear reports is urgently needed.

Circumvent the uncertainty in the applications of transcriptional signatures to tumor tissues sampled from different tumor sites

The expression measurements of thousands of genes are correlated with the proportions of tumor epithelial cell (PTEC) in clinical samples. Thus, for a tumor diagnostic or prognostic signature based on a summarization of expression levels of the signature genes, the risk score for a patient may dependent on the tumor tissues sampled from different tumor sites with diverse PTEC for the same patient. Here, we proposed that the within-samples relative expression orderings (REOs) based gene pairs signatures should be insensitive to PTEC variations. Firstly, by analysis of paired tumor epithelial cell and stromal cell microdissected samples from 27 cancer patients, we showed that above 80% of gene pairs had consistent REOs between the two cells, indicating these REOs would be independent of PTEC in cancer tissues. Then, by simulating tumor tissues with different PTEC using each of the 27 paired samples, we showed that about 90% REOs of gene pairs in tumor epithelial cells were maintained in tumor samples even when PTEC decreased to 30%. Especially, the REOs of gene pairs with larger expression differences in tumor epithelial cells tend to be more robust against PTEC variations. Finally, as a case study, we developed a gene pair signature which could robustly distinguish colorectal cancer tissues with various PTEC from normal tissues. We concluded that the REOs-based signatures were robust against PTEC variations.

Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images

Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error. In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer. In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry (IHC) staining scores of bladder and breast cancers. Our classification pipeline includes a basic CNN architecture, Google's Inceptions with three training strategies, and an ensemble of two state-of-the-art algorithms, Inception and ResNet. Training strategies include training the last layer of Google's Inceptions, training the network from scratch, and fine-tunning the parameters for our data using two pre-trained version of Google's Inception architectures, Inception-V1 and Inception-V3. We demonstrate the power of deep learning approaches for identifying cancer subtypes, and the robustness of Google's Inceptions even in presence of extensive tumor heterogeneity. On average, our pipeline achieved accuracies of 100%, 92%, 95%, and 69% for discrimination of various cancer tissues, subtypes, biomarkers, and scores, respectively. Our pipeline and related documentation is freely available at https://github.com/ih-_lab/CNN_Smoothie.

Development and validation of a protocol for optimizing the use of paraffin blocks in molecular epidemiological studies: The example from the HPV-AHEAD study

Worldwide use of formalin-fixed paraffin-embedded blocks (FFPE) is extensive in diagnosis and research. Yet, there is a lack of optimized/standardized protocols to process the blocks and verify the quality and presence of the targeted tissue. In the context of an international study on head and neck cancer (HNC)-HPV-AHEAD, a standardized protocol for optimizing the use of FFPEs in molecular epidemiology was developed and validated. First, a protocol for sectioning the FFPE was developed to prevent cross-contamination and distributed between participating centers. Before processing blocks, all sectioning centers underwent a quality control to guarantee a satisfactory training process. The first and last sections of the FFPEs were used for histopathological assessment. A consensus histopathology evaluation form was developed by an international panel of pathologists and evaluated for four indicators in a pilot analysis in order to validate it: 1) presence/type of tumor tissue, 2) identification of other tissue components that could affect the molecular diagnosis and 3) quality of the tissue. No HPV DNA was found in sections from empty FFPE generated in any histology laboratories of HPV-AHEAD consortium and all centers passed quality assurance for processing after quality control. The pilot analysis to validate the histopathology form included 355 HNC cases. The form was filled by six pathologists and each case was randomly assigned to two of them. Most samples (86%) were considered satisfactory. Presence of >50% of invasive carcinoma was observed in all sections of 66% of cases. Substantial necrosis (>50%) was present in <2% of samples. The concordance for the indicators targeted to validate the histopathology form was very high (kappa > 0.85) between first and last sections and fair to high between pathologists (kappa/pabak 0.21-0.72). The protocol allowed to correctly process without signs of contamination all FFPE of the study. The histopathology evaluation of the cases assured the presence of the targeted tissue, identified the presence of other tissues that could disturb the molecular diagnosis and allowed the assessment of tissue quality.

The role of informatics in patient-centered care and personalized medicine

The practice of cytopathology has dramatically changed due to advances in genomics and information technology. Cytology laboratories have accordingly become increasingly dependent on pathology informatics support to meet the emerging demands of precision medicine. Pathology informatics deals with information technology in the laboratory, and the impact of this technology on workflow processes and staff who interact with these tools. This article covers the critical role that laboratory information systems, electronic medical records, and digital imaging plays in patient-centered personalized medicine. The value of integrated diagnostic reports, clinical decision support, and the use of whole-slide imaging to better evaluate cytology samples destined for molecular testing is discussed. Image analysis that offers more precise and quantitative measurements in cytology is addressed, as well as the role of bioinformatics tools to cope with Big Data from next-generation sequencing. This article also highlights the barriers to the widespread adoption of these disruptive technologies due to regulatory obstacles, limited commercial solutions, poor interoperability, and lack of standardization. Cancer Cytopathol 2017;125(6 suppl):494-501. © 2017 American Cancer Society.

An update on the validation of whole slide imaging systems following FDA approval of a system for a routine pathology diagnostic service in the United States

Pathologists have used light microscopes and glass slides to interpret the histologic appearance of normal and diseased tissues for more than 150 years. The quality of both microtomes used to cut tissue sections and microscopes has improved significantly during the past few decades, but the process of rendering diagnoses has changed little. By contrast, major advances in digital technology have occurred since the introduction of hand held electronic devices, including the development of whole slide imaging (WSI) systems with software packages that can convert microscope images into virtual (digital) slides that can be viewed on computer monitors and via the internet. To date, however, these technological developments have had minimal impact on the way pathologists perform their daily work, with the exception of using computers to access electronic medical records and scholarly web sites for pertinent information to assist interpretation of cases. Traditional practice is likely to change significantly during the next decade, especially since the Federal Drug Administration in the USA has approved the first WSI system for routine diagnostic practice. I review here the development and slow acceptance of WSI by pathology departments. I focus on recent advances in validation of WSI systems that is required for routine diagnostic reporting of pathology cases using this technology.

Standardising RNA profiling based biomarker application in cancer-The need for robust control of technical variables

Histopathology-based staging of colorectal cancer (CRC) has utility in assessing the prognosis of patient subtypes, but as yet cannot accurately predict individual patient's treatment response. Transcriptomics approaches, using array based or next generation sequencing (NGS) platforms, of formalin fixed paraffin embedded tissue can be harnessed to develop multi-gene biomarkers for predicting both prognosis and treatment response, leading to stratification of treatment. While transcriptomics can shape future biomarker development, currently <1% of published biomarkers become clinically validated tests, often due to poor study design or lack of independent validation. In this review of a large number of CRC transcriptional studies, we identify recurrent sources of technical variability that encompass collection, preservation and storage of malignant tissue, nucleic acid extraction, methods to quantitate RNA transcripts and data analysis pipelines. We propose a series of defined steps for removal of these confounding issues, to ultimately aid in the development of more robust clinical biomarkers.

计算机深度学习与智能图像诊断对胃高分化腺癌病理诊断的价值

随着计算机技术的发展, 机器学习被深入研究并应用到各个领域, 机器学习在医学中的应用将转换现在的医学模式, 利用机器学习处理医学中庞大数据可提高医生诊断准确率, 指导治疗, 评估预后. 机器学习中的深度学习已广泛应用在病理智能图像诊断方面, 目前在有丝分裂检测, 细胞核的分割和检测, 组织分类中已取得较好成效. 在病理组织学上, 胃高分化腺癌因其组织结构和细胞形态异型性小, 取材标本表浅等原因容易漏诊. 现有的早期胃癌的病理智能图像诊断系统中没有关于腺腔圆度的研究, 圆度测量可以将腺腔结构的不规则, 腺腔扩张等特征转换为具体数值的定量指标, 通过数值大小来进行诊断分析, 为病理诊断提供参考价值.

Construction and analysis of tissue microarrays in the era of digital pathology: a pilot study targeting CDX1 and CDX2 in a colon cancer cohort of 612 patients

CDX1 and CDX2 are possibly predictive biomarkers in colorectal cancer. We combined digitally‐guided (next generation) TMA construction (ngTMA) and the utility of digital image analysis (DIA) to assess accuracy, tumour heterogeneity and the selective impact of different combined intensity‐percentage levels on prognosis.CDX1 and CDX2 immunohistochemistry was performed on ngTMAs covering normal tissue, tumour centre and invasive front. The percentages of all epithelial cells per staining intensity per core were analysed digitally. Beyond classical prognosis analysis following REMARK guidelines, we investigated pre‐analytical conditions, three different types of heterogeneity (mosaic‐like, targeted and haphazard) and influences on cohort segregation and patient selection. The ngTMA‐DIA approach produced robust biomarker data with infrequent core loss and excellent on‐target punching. The detailed assessment of tumour heterogeneity could – except for a certain diffuse mosaic‐like heterogeneity – exclude differences between the invasive front and tumour centre, as well as detect haphazard clonal heterogeneous elements. Moreover, lower CDX1 and CDX2 counts correlated with mucinous histology, higher TNM stage, higher tumour grade and worse survival (p < 0.01, all). Different protein expression intensity levels shared comparable prognostic power and a great overlap in patient selection. The combination of ngTMA with DIA enhances accuracy and controls for biomarker analysis. Beyond the confirmation of CDX1 and CDX2 as prognostically relevant markers in CRC, this study highlights the greater robustness of CDX2 in comparison to CDX1. For the assessment of CDX2 protein loss, cut‐points as percentage data of complete protein loss can be deduced as a recommendation.

The Challenges Faced in Developing Novel Drug Radiation Combinations in Non-small Cell Lung Cancer

Lung cancer is the most common cancer diagnosed in the UK. Outcomes for patients with this disease remain poor and new strategies to treat this disease require investigation. One potential option is to combine novel agents with radiotherapy in clinical studies. Here we discuss some of the important issues to consider when combining novel agents with radiotherapy, together with potential solutions as discussed at a recent Clinical Translational Radiotherapy Group (CTRad) workshop.

Quantitative assessment of cell block cellularity and correlation with molecular testing adequacy in lung cancer

INTRODUCTION

Determination of fine-needle aspiration (FNA) material adequacy is essential prior to performing molecular testing (MT) in order to ensure good results and maximize resources. This study investigates several quantitative measures of cellularity in FNA samples of lung carcinoma, and correlates the results with MT adequacy.

MATERIALS AND METHODS

A blinded retrospective analysis of 20 non-small-cell lung carcinoma cases was conducted: 13 contained "sufficient" material for EGFR/KRAS sequencing and ALK FISH studies; and 7 contained "insufficient" material for these tests. Three 400x fields-of-view (FOVs) were analyzed from digitized cell block glass slides of these cases. Cellularity in these FOVs was quantified using three methods: (1) visual estimation by cytopathologist; (2) manually annotated contours (MACs); (3) software derived, manually adjusted contours (SDMACs) using a custom segmentation script with adjustable parameters. These methods were evaluated using the Mann-Whitney-Wilcoxon test, paired t test, and receiver operating characteristic/area under the curve (AUC) analysis.

RESULTS

There were significant differences between the insufficient/sufficient groups for each estimation method (visual P < 0.05, MAC P < 0.05, SDMAC P < 0.01). Variation of mean values was highest in the visual estimation method. AUC values were visual estimation = 0.903, MAC = 0.903, and SDMAC = 0.958. Mean variation of the 3 FOV values was found to be significantly higher for visual estimation compared with the other methods.

CONCLUSION

Quantitative analysis of cellularity in digitized cell block material is feasible using different methods. In this investigation, the SDMAC method provided the highest accuracy and lowest variability. This supports image analysis as an objective and quantitative tool to assess FNA sample adequacy for guiding supplemental MT.

A robust nonlinear tissue-component discrimination method for computational pathology

Advances in digital pathology, specifically imaging instrumentation and data management, have allowed for the development of computational pathology tools with the potential for better, faster, and cheaper diagnosis, prognosis, and prediction of disease. Images of tissue sections frequently vary in color appearance across research laboratories and medical facilities because of differences in tissue fixation, staining protocols, and imaging instrumentation, leading to difficulty in the development of robust computational tools. To address this challenge, we propose a novel nonlinear tissue-component discrimination (NLTD) method to register automatically the color space of histopathology images and visualize individual tissue components, independent of color differences between images. Our results show that the NLTD method could effectively discriminate different tissue components from different types of tissues prepared at different institutions. Further, we demonstrate that NLTD can improve the accuracy of nuclear detection and segmentation algorithms, compared with using conventional color deconvolution methods, and can quantitatively analyze immunohistochemistry images. Together, the NLTD method is objective, robust, and effective, and can be easily implemented in the emerging field of computational pathology.

Delivering a research-enabled multistakeholder partnership for enhanced patient care at a population level: The Northern Ireland Comprehensive Cancer Program

The last 20 years have seen significant advances in cancer care in Northern Ireland, leading to measureable improvements in patient outcomes. Crucial to this transformation has been an ethos that recognizes the primacy role of research in effecting heath care change. The authors' model of a cross‐sectoral partnership that unites patients, scientists, health care professionals, hospital trusts, bioindustry, and government agencies can be truly transformative, empowering tripartite clinical‐academic‐industry efforts that have already yielded significant benefit and will continue to inform strategy and its implementation going forward.

Phosphatidylethanolamine-binding protein 4 promotes lung cancer cells proliferation and invasion via PI3K/Akt/mTOR axis

BACKGROUND

While phosphatidylethanolamine-binding protein 4 (PEBP4) is a key factor in the malignant proliferation and metastasis of tumor cells, the exact regulatory network governing its roles remains unclear. This study was designed to investigate the effect of PEBP4 on PI3K/Akt/mTOR pathway and explore its molecular network that governs the proliferation and metastasis of tumor cells.

METHODS

After the recombinant plasmid pcDNA3.1-PEBP4 was constructed, the recombinant plasmid pcDNA3.1-PEBP4 and PEBP4-targeting siRNA were transfected into lung cancer HCC827 cell line. The expressions of PI3K/Akt/mTOR pathway components in HCC827 cells in each group were determined using Western blotting. In the HCC827 cells, the effect of PI3K pathway inhibitor LY294002 on the expressions of PI3K/Akt/mTOR pathway components under the effect of PEBP4 was determined using Western blotting, and the effects of LY294002 on the cell viability, proliferation, and migration capabilities under the overexpression of PEBP4 were determined using MTT method, flow cytometry, and Transwell migration assay. Furthermore, the effect of mTOR inhibitor rapamycin (RAPA) on the expressions of PI3K/Akt/mTOR pathway components under the effect of PEBP4 was determined using Western blotting, and the effects of RAPA on the cell viability, proliferation, and migration capabilities under the overexpression of PEBP4 were determined using MTT method, flow cytometry, and Transwell migration assay.

RESULTS

As shown by Western blotting, the protein expressions of p-Akt and phosphorylated mTOR (p-mTOR) were significantly higher in the pcDNA3.1-PEBP4-transfected group than in the normal control group and PEBP4 siRNA group (P<0.05); furthermore, the protein expressions of p-Akt and p-mTOR significantly decreased in the PEBP4 targeting siRNA-transfected group (P<0.05). Treatment with LY294002 significantly inhibited the protein expressions of p-Akt and p-mTOR in HCC827 cells (P<0.05). In contrast, treatment with RAPA only significantly inhibited the protein expression of p-mTOR (P<0.05). As shown by MTT, flow cytometry, and Transwell migration assay, both LY294002 and RAPA could significantly lower the viability of HCC827 cells and inhibit their proliferation and invasion (P<0.05); meanwhile, they could reverse the effect of PEBP4 in promoting the proliferation and migration of HCC827 cells (P<0.05).

CONCLUSIONS

The overexpression of PEBP4 increases the phosphorylation levels of Akt and mTOR in lung cancer cells. The PI3K/Akt/mTOR signaling axis may be a key molecular pathway via which PEBP4 promotes the proliferation and invasion of non-small cell lung cancer (NSCLC) cells; also, it may serve as a potential therapeutic target.