Exploiting the CD200-CD200R immune checkpoint axis in multiple myeloma to enhance CAR T-cell therapy.

ABSTRACT: Patients with multiple myeloma (MM) treated with B-cell maturation antigen (BCMA)-specific chimeric antigen receptor (CAR) T cells usually relapse with BCMA+ disease, indicative of CAR T-cell suppression. CD200 is an immune checkpoint that is overexpressed on aberrant plasma cells (aPCs) in MM and is an independent negative prognostic factor for survival. However, CD200 is not present on MM cell lines, a potential limitation of current preclinical models. We engineered MM cell lines to express CD200 at levels equivalent to those found on aPCs in MM and show that these are sufficient to suppress clinical-stage CAR T-cells targeting BCMA or the Tn glycoform of mucin 1 (TnMUC1), costimulated by 4-1BB and CD2, respectively. To prevent CD200-mediated suppression of CAR T cells, we compared CRISPR-Cas9-mediated knockout of the CD200 receptor (CD200RKO), to coexpression of versions of the CD200 receptor that were nonsignaling, that is, dominant negative (CD200RDN), or that leveraged the CD200 signal to provide CD28 costimulation (CD200R-CD28 switch). We found that the CD200R-CD28 switch potently enhanced the polyfunctionality of CAR T cells, and improved cytotoxicity, proliferative capacity, CAR T-cell metabolism, and performance in a chronic antigen exposure assay. CD200RDN provided modest benefits, but surprisingly, the CD200RKO was detrimental to CAR T-cell activity, adversely affecting CAR T-cell metabolism. These patterns held up in murine xenograft models of plasmacytoma, and disseminated bone marrow predominant disease. Our findings underscore the importance of CD200-mediated immune suppression in CAR T-cell therapy of MM, and highlight a promising approach to enhance such therapies by leveraging CD200 expression on aPCs to provide costimulation via a CD200R-CD28 switch.

Microbiome signatures in prostate cancer.

We have established a microbiome signature for prostate cancer using an array-based metagenomic and capture-sequencing approach. A diverse microbiome signature (viral, bacterial, fungal and parasitic) was observed in the prostate cancer samples compared with benign prostate hyperplasia controls. Hierarchical clustering analysis identified three distinct prostate cancer-specific microbiome signatures. The three signatures correlated with different grades, stages and scores of the cancer. Thus, microbiome signature analysis potentially provides clinical diagnosis and outcome predictions. The array data were validated by PCR and targeted next-generation sequencing (NGS). Specific NGS data suggested that certain viral genomic sequences were inserted into the host somatic chromosomes of the prostate cancer samples. A randomly selected group of these was validated by direct PCR and sequencing. In addition, PCR validation of Helicobacter showed that Helicobacter cagA sequences integrated within specific chromosomes of prostate tumor cells. The viral and Helicobacter integrations are predicted to affect the expression of several cellular genes associated with oncogenic processes.

Comparative clinical utility of tumor genomic testing and cell-free DNA in metastatic breast cancer.

PURPOSE: Breast cancer metastases differ biologically from primary disease; therefore, metastatic biopsies may assist in treatment decision making. Commercial genomic testing of both tumor and circulating tumor DNA have become available clinically, but utility of these tests in breast cancer management remains unclear. METHODS: Patients undergoing a clinically indicated metastatic tumor biopsy were consented to the ongoing METAMORPH registry. Tumor and blood were collected at the time of disease progression before subsequent therapy, and patients were followed for response on subsequent treatment. Tumor testing (n = 53) and concurrent cell-free DNA (n = 32) in a subset of patients was performed using CLIA-approved assays. RESULTS: The proportion of patients with a genomic alteration was lower in tumor than in blood (69 vs. 91%; p = 0.06). After restricting analysis to alterations covered on both platforms, 83% of tumor alterations were detected in blood, while 90% of blood alterations were detected in tumor. Mutational load specific for the panel genes was calculated for both tumor and blood. Time to progression on subsequent treatment was significantly shorter for patients whose tumors had high panel-specific mutational load (HR 0.31, 95% CI 0.12-0.78) or a TP53 mutation (HR 0.35, 95% CI 0.20-0.79), after adjusting for stage at presentation, hormone receptor status, prior treatment type, and number of lines of metastatic treatment. CONCLUSIONS: Treating oncologists must distinguish platform differences from true biological heterogeneity when comparing tumor and cfDNA genomic testing results. Tumor and concurrent cfDNA contribute unique genomic information in metastatic breast cancer patients, providing potentially useful biomarkers for aggressive metastatic disease.

Computer-extracted Features Can Distinguish Noncancerous Confounding Disease from Prostatic Adenocarcinoma at Multiparametric MR Imaging.

PURPOSE: To determine the best features to discriminate prostate cancer from benign disease and its relationship to benign disease class and cancer grade. MATERIALS AND METHODS: The institutional review board approved this study and waived the need for informed consent. A retrospective cohort of 70 patients (age range, 48-70 years; median, 62 years), all of whom were scheduled to undergo radical prostatectomy and underwent preoperative 3-T multiparametric magnetic resonance (MR) imaging, including T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced imaging, were included. The digitized prostatectomy slides were annotated for cancer and noncancerous disease and coregistered to MR imaging with an interactive deformable coregistration scheme. Computer-identified features for each of the noncancerous disease categories (eg, benign prostatic hyperplasia [BPH], prostatic intraepithelial neoplasia [PIN], inflammation, and atrophy) and prostate cancer were extracted. Feature selection was performed to identify the features with the highest discriminatory power. The performance of these five features was evaluated by using the area under the receiver operating characteristic curve (AUC). RESULTS: High-b-value diffusion-weighted images were more discriminative in distinguishing BPH from prostate cancer than apparent diffusion coefficient, which was most suitable for distinguishing PIN from prostate cancer. The focal appearance of lesions on dynamic contrast-enhanced images may help discriminate atrophy and inflammation from cancer. Which imaging features are discriminative for different benign lesions is influenced by cancer grade. The apparent diffusion coefficient appeared to be the most discriminative feature in identifying high-grade cancer. Classification results showed increased performance by taking into account specific benign types (AUC = 0.70) compared with grouping all noncancerous findings together (AUC = 0.62). CONCLUSION: The best features with which to discriminate prostate cancer from noncancerous benign disease depend on the type of benign disease and cancer grade. Use of the best features may result in better diagnostic performance.

Identifying in vivo DCE MRI markers associated with microvessel architecture and gleason grades of prostate cancer.

BACKGROUND: To identify computer extracted in vivo dynamic contrast enhanced (DCE) MRI markers associated with quantitative histomorphometric (QH) characteristics of microvessels and Gleason scores (GS) in prostate cancer. METHODS: This study considered retrospective data from 23 biopsy confirmed prostate cancer patients who underwent 3 Tesla multiparametric MRI before radical prostatectomy (RP). Representative slices from RP specimens were stained with vascular marker CD31. Tumor extent was mapped from RP sections onto DCE MRI using nonlinear registration methods. Seventy-seven microvessel QH features and 18 DCE MRI kinetic features were extracted and evaluated for their ability to distinguish low from intermediate and high GS. The effect of temporal sampling on kinetic features was assessed and correlations between those robust to temporal resolution and microvessel features discriminative of GS were examined. RESULTS: A total of 12 microvessel architectural features were discriminative of low and intermediate/high grade tumors with area under the receiver operating characteristic curve (AUC) > 0.7. These features were most highly correlated with mean washout gradient (WG) (max rho = -0.62). Independent analysis revealed WG to be moderately robust to temporal resolution (intraclass correlation coefficient [ICC] = 0.63) and WG variance, which was poorly correlated with microvessel features, to be predictive of low grade tumors (AUC = 0.77). Enhancement ratio was the most robust (ICC = 0.96) and discriminative (AUC = 0.78) kinetic feature but was moderately correlated with microvessel features (max rho = -0.52). CONCLUSION: Computer extracted features of prostate DCE MRI appear to be correlated with microvessel architecture and may be discriminative of low versus intermediate and high GS.

Rare subclonal sequencing of breast cancers indicates putative metastatic driver mutations are predominately acquired after dissemination.

BACKGROUND: Evolutionary models of breast cancer progression differ on the extent to which metastatic potential is pre-encoded within primary tumors. Although metastatic recurrences often harbor putative driver mutations that are not detected in their antecedent primary tumor using standard sequencing technologies, whether these mutations were acquired before or after dissemination remains unclear. METHODS: To ascertain whether putative metastatic driver mutations initially deemed specific to the metastasis by whole exome sequencing were, in actuality, present within rare ancestral subclones of the primary tumors from which they arose, we employed error-controlled ultra-deep sequencing (UDS-UMI) coupled with FFPE artifact mitigation by uracil-DNA glycosylase (UDG) to assess the presence of 132 "metastasis-specific" mutations within antecedent primary tumors from 21 patients. Maximum mutation detection sensitivity was ~1% of primary tumor cells. A conceptual framework was developed to estimate relative likelihoods of alternative models of mutation acquisition. RESULTS: The ancestral primary tumor subclone responsible for seeding the metastasis was identified in 29% of patients, implicating several putative drivers in metastatic seeding including LRP5 A65V and PEAK1 K140Q. Despite this, 93% of metastasis-specific mutations in putative metastatic driver genes remained undetected within primary tumors, as did 96% of metastasis-specific mutations in known breast cancer drivers, including ERRB2 V777L, ESR1 D538G, and AKT1 D323H. Strikingly, even in those cases in which the rare ancestral subclone was identified, 87% of metastasis-specific putative driver mutations remained undetected. Modeling indicated that the sequential acquisition of multiple metastasis-specific driver or passenger mutations within the same rare subclonal lineage of the primary tumor was highly improbable. CONCLUSIONS: Our results strongly suggest that metastatic driver mutations are sequentially acquired and selected within the same clonal lineage both before, but more commonly after, dissemination from the primary tumor, and that these mutations are biologically consequential. Despite inherent limitations in sampling archival primary tumors, our findings indicate that tumor cells in most patients continue to undergo clinically relevant genomic evolution after their dissemination from the primary tumor. This provides further evidence that metastatic recurrence is a multi-step, mutation-driven process that extends beyond primary tumor dissemination and underscores the importance of longitudinal tumor assessment to help guide clinical decisions.

Cascaded discrimination of normal, abnormal, and confounder classes in histopathology: Gleason grading of prostate cancer.

BACKGROUND: Automated classification of histopathology involves identification of multiple classes, including benign, cancerous, and confounder categories. The confounder tissue classes can often mimic and share attributes with both the diseased and normal tissue classes, and can be particularly difficult to identify, both manually and by automated classifiers. In the case of prostate cancer, they may be several confounding tissue types present in a biopsy sample, posing as major sources of diagnostic error for pathologists. Two common multi-class approaches are one-shot classification (OSC), where all classes are identified simultaneously, and one-versus-all (OVA), where a "target" class is distinguished from all "non-target" classes. OSC is typically unable to handle discrimination of classes of varying similarity (e.g. with images of prostate atrophy and high grade cancer), while OVA forces several heterogeneous classes into a single "non-target" class. In this work, we present a cascaded (CAS) approach to classifying prostate biopsy tissue samples, where images from different classes are grouped to maximize intra-group homogeneity while maximizing inter-group heterogeneity. RESULTS: We apply the CAS approach to categorize 2000 tissue samples taken from 214 patient studies into seven classes: epithelium, stroma, atrophy, prostatic intraepithelial neoplasia (PIN), and prostate cancer Gleason grades 3, 4, and 5. A series of increasingly granular binary classifiers are used to split the different tissue classes until the images have been categorized into a single unique class. Our automatically-extracted image feature set includes architectural features based on location of the nuclei within the tissue sample as well as texture features extracted on a per-pixel level. The CAS strategy yields a positive predictive value (PPV) of 0.86 in classifying the 2000 tissue images into one of 7 classes, compared with the OVA (0.77 PPV) and OSC approaches (0.76 PPV). CONCLUSIONS: Use of the CAS strategy increases the PPV for a multi-category classification system over two common alternative strategies. In classification problems such as histopathology, where multiple class groups exist with varying degrees of heterogeneity, the CAS system can intelligently assign class labels to objects by performing multiple binary classifications according to domain knowledge.

Unusual cold denaturation of a small protein domain.

A thermal unfolding study of the 45-residue α-helical domain UBA(2) using circular dichroism is presented. The protein is highly thermostable and exhibits a clear cold unfolding transition with the onset near 290 K without denaturant. Cold denaturation in proteins is rarely observed in general and is quite unique among small helical protein domains. The cold unfolding was further investigated in urea solutions, and a simple thermodynamic model was used to fit all thermal and urea unfolding data. The resulting thermodynamic parameters are compared to those of other small protein domains. Possible origins of the unusual cold unfolding of UBA(2) are discussed.

Prognostic correlations with the microbiome of breast cancer subtypes.

Alterations to the natural microbiome are linked to different diseases, and the presence or absence of specific microbes is directly related to disease outcomes. We performed a comprehensive analysis with unique cohorts of the four subtypes of breast cancer (BC) characterized by their microbial signatures, using a pan-pathogen microarray strategy. The signature (includes viruses, bacteria, fungi, and parasites) of each tumor subtype was correlated with clinical data to identify microbes with prognostic potential. The subtypes of BC had specific viromes and microbiomes, with ER+ and TN tumors showing the most and least diverse microbiome, respectively. The specific microbial signatures allowed discrimination between different BC subtypes. Furthermore, we demonstrated correlations between the presence and absence of specific microbes in BC subtypes with the clinical outcomes. This study provides a comprehensive map of the oncobiome of BC subtypes, with insights into disease prognosis that can be critical for precision therapeutic intervention strategies.

Computationally Derived Cribriform Area Index from Prostate Cancer Hematoxylin and Eosin Images Is Associated with Biochemical Recurrence Following Radical Prostatectomy and Is Most Prognostic in Gleason Grade Group 2.

BACKGROUND: The presence of invasive cribriform adenocarcinoma (ICC), an expanse of cells containing punched-out lumina uninterrupted by stroma, in radical prostatectomy (RP) specimens has been associated with biochemical recurrence (BCR). However, ICC identification has only moderate inter-reviewer agreement. OBJECTIVE: To investigate quantitative machine-based assessment of the extent and prognostic utility of ICC, especially within individual Gleason grade groups. DESIGN, SETTING, AND PARTICIPANTS: A machine learning approach was developed for ICC segmentation using 70 RP patients and validated in a cohort of 749 patients from four sites whose median year of surgery was 2007 and with median follow-up of 28 mo. ICC was segmented on one representative hematoxylin and eosin RP slide per patient and the fraction of tumor area composed of ICC, the cribriform area index (CAI), was measured. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The association between CAI and BCR was measured in terms of the concordance index (c index) and hazard ratio (HR). RESULTS AND LIMITATIONS: CAI was correlated with BCR (c index 0.62) in the validation set of 411 patients with ICC morphology, especially those with Gleason grade group 2 cancer (n = 192; c index 0.66), and was less prognostic when patients without ICC were included (c index 0.54). A doubling of CAI in the group with ICC morphology was prognostic after controlling for Gleason grade, surgical margin positivity, preoperative prostate-specific antigen level, pathological T stage, and age (HR 1.19, 95% confidence interval 1.03-1.38; p = 0.018). CONCLUSIONS: Automated image analysis and machine learning could provide an objective, quantitative, reproducible, and high-throughput method of quantifying ICC area. The performance of CAI for grade group 2 cancer suggests that for patients with little Gleason 4 pattern, the ICC fraction has a strong prognostic role. PATIENT SUMMARY: Machine-based measurement of a specific cell pattern (cribriform; sieve-like, with lots of spaces) in images of prostate specimens could improve risk stratification for patients with prostate cancer. In the future, this could help in expanding the criteria for active surveillance.

Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study.

Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03-3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40-3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.

Genomic landscape of metastatic breast cancer identifies preferentially dysregulated pathways and targets.

Nearly all breast cancer deaths result from metastatic disease. Despite this, the genomic events that drive metastatic recurrence are poorly understood. We performed whole-exome and shallow whole-genome sequencing to identify genes and pathways preferentially mutated or copy-number altered in metastases compared with the paired primary tumors from which they arose. Seven genes were preferentially mutated in metastases - MYLK, PEAK1, SLC2A4RG, EVC2, XIRP2, PALB2, and ESR1 - 5 of which are not significantly mutated in any type of human primary cancer. Four regions were preferentially copy-number altered: loss of STK11 and CDKN2A/B, as well as gain of PTK6 and the membrane-bound progesterone receptor, PAQR8. PAQR8 gain was mutually exclusive with mutations in the nuclear estrogen and progesterone receptors, suggesting a role in treatment resistance. Several pathways were preferentially mutated or altered in metastases, including mTOR, CDK/RB, cAMP/PKA, WNT, HKMT, and focal adhesion. Immunohistochemical analyses revealed that metastases preferentially inactivate pRB, upregulate the mTORC1 and WNT signaling pathways, and exhibit nuclear localization of activated PKA. Our findings identify multiple therapeutic targets in metastatic recurrence that are not significantly mutated in primary cancers, implicate membrane progesterone signaling and nuclear PKA in metastatic recurrence, and provide genomic bases for the efficacy of mTORC1, CDK4/6, and PARP inhibitors in metastatic breast cancer.

Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study.

Site variation in fixation, staining, and scanning can confound automated tissue based image classifiers for disease characterization. In this study we incorporated stability into four feature selection methods for identifying the most robust and discriminating features for two prostate histopathology classification tasks. We evaluated 242 morphology features from N = 212 prostatectomy specimens from four sites for automated cancer detection and grading. We quantified instability as the rate of significant cross-site feature differences. We mapped feature stability and discriminability using 188 non-cancerous and 210 cancerous regions via 3-fold cross validation, then held one site out, creating independent training and testing sets. In training, one feature set was selected only for discriminability, another for discriminability and stability. We trained a classifier with each feature set, testing on the hold out site. Experiments were repeated with 117 Gleason grade 3 and 112 grade 4 regions. Stability was calculated across non-cancerous regions. Gland shape features yielded the best stability and area under the receiver operating curve (AUC) trade-off while co-occurrence texture features were generally unstable. Our stability-informed method produced a cancer detection AUC of 0.98 ± 0.05 and increased average Gleason grading AUC by 4.38%. Color normalization of the images tended to exacerbate feature instability.

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

Distinct Microbial Signatures Associated With Different Breast Cancer Types.

A dysbiotic microbiome can potentially contribute to the pathogenesis of many different diseases including cancer. Breast cancer is the second leading cause of cancer death in women. Thus, we investigated the diversity of the microbiome in the four major types of breast cancer: endocrine receptor (ER) positive, triple positive, Her2 positive and triple negative breast cancers. Using a whole genome and transcriptome amplification and a pan-pathogen microarray (PathoChip) strategy, we detected unique and common viral, bacterial, fungal and parasitic signatures for each of the breast cancer types. These were validated by PCR and Sanger sequencing. Hierarchical cluster analysis of the breast cancer samples, based on their detected microbial signatures, showed distinct patterns for the triple negative and triple positive samples, while the ER positive and Her2 positive samples shared similar microbial signatures. These signatures, unique or common to the different breast cancer types, provide a new line of investigation to gain further insights into prognosis, treatment strategies and clinical outcome, as well as better understanding of the role of the micro-organisms in the development and progression of breast cancer.

Identifying the morphologic basis for radiomic features in distinguishing different Gleason grades of prostate cancer on MRI: Preliminary findings.

Translation of radiomics into the clinic may require a more comprehensive understanding of the underlying morphologic tissue characteristics they reflect. In the context of prostate cancer (PCa), some studies have correlated gross histological measurements of gland lumen, epithelium, and nuclei with disease appearance on MRI. Quantitative histomorphometry (QH), like radiomics for radiologic images, is the computer based extraction of features for describing tumor morphology on digitized tissue images. In this work, we attempt to establish the histomorphometric basis for radiomic features for prostate cancer by (1) identifying the radiomic features from T2w MRI most discriminating of low vs. intermediate/high Gleason score, (2) identifying QH features correlated with the most discriminating radiomic features previously identified, and (3) evaluating the discriminative ability of QH features found to be correlated with spatially co-localized radiomic features. On a cohort of 36 patients (23 for training, 13 for validation), Gabor texture features were identified as being most predictive of Gleason grade on MRI (AUC of 0.69) and gland lumen shape features were identified as the most predictive QH features (AUC = 0.75). Our results suggest that the PCa grade discriminability of Gabor features is a consequence of variations in gland shape and morphology at the tissue level.

The ovarian cancer oncobiome.

Humans and other mammals are colonized by microbial agents across the kingdom which can represent a unique microbiome pattern. Dysbiosis of the microbiome has been associated with pathology including cancer. We have identified a microbiome signature unique to ovarian cancers, one of the most lethal malignancies of the female reproductive system, primarily because of its asymptomatic nature during the early stages in development. We screened ovarian cancer samples along with matched, and non-matched control samples using our pan-pathogen array (PathoChip), combined with capture-next generation sequencing. The results show a distinct group of viral, bacterial, fungal and parasitic signatures of high significance in ovarian cases. Further analysis shows specific viral integration sites within the host genome of tumor samples, which may contribute to the carcinogenic process. The ovarian cancer microbiome signature provides insights for the development of targeted therapeutics against ovarian cancers.

Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent.

With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma.

Microbial Signatures Associated with Oropharyngeal and Oral Squamous Cell Carcinomas.

The microbiome is fundamentally one of the most unique organs in the human body. Dysbiosis can result in critical inflammatory responses and result in pathogenesis contributing to neoplastic events. We used a pan-pathogen array technology (PathoChip) coupled with next-generation sequencing to establish microbial signatures unique to human oral and oropharyngeal squamous cell carcinomas (OCSCC/OPSCC). Signatures for DNA and RNA viruses including oncogenic viruses, gram positive and negative bacteria, fungi and parasites were detected. Cluster and topological analyses identified 2 distinct groups of microbial signatures related to OCSCCs/OPSCCs. Results were validated by probe capture next generation sequencing; the data from which also provided a comprehensive map of integration sites and chromosomal hotspots for micro-organism genomic insertions. Identification of these microbial signatures and their integration sites may provide biomarkers for OCSCC/OPSCC diagnosis and prognosis as well as novel avenues for study of their potential role in OCSCCs/OPSCCs.