Morphoproteomic Characterization of Lung Squamous Cell Carcinoma Fragmentation, a Histological Marker of Increased Tumor Invasiveness

Prediction of Ovarian Cancer Response to Therapy Based on Deep Learning Analysis of Histopathology Images

BACKGROUND

Ovarian cancer remains the leading gynecological cause of cancer mortality. Predicting the sensitivity of ovarian cancer to chemotherapy at the time of pathological diagnosis is a goal of precision medicine research that we have addressed in this study using a novel deep-learning neural network framework to analyze the histopathological images.

METHODS

We have developed a method based on the Inception V3 deep learning algorithm that complements other methods for predicting response to standard platinum-based therapy of the disease. For the study, we used histopathological H&E images (pre-treatment) of high-grade serous carcinoma from The Cancer Genome Atlas (TCGA) Genomic Data Commons portal to train the Inception V3 convolutional neural network system to predict whether cancers had independently been labeled as sensitive or resistant to subsequent platinum-based chemotherapy. The trained model was then tested using data from patients left out of the training process. We used receiver operating characteristic (ROC) and confusion matrix analyses to evaluate model performance and Kaplan-Meier survival analysis to correlate the predicted probability of resistance with patient outcome. Finally, occlusion sensitivity analysis was piloted as a start toward correlating histopathological features with a response.

RESULTS

The study dataset consisted of 248 patients with stage 2 to 4 serous ovarian cancer. For a held-out test set of forty patients, the trained deep learning network model distinguished sensitive from resistant cancers with an area under the curve (AUC) of 0.846 ± 0.009 (SE). The probability of resistance calculated from the deep-learning network was also significantly correlated with patient survival and progression-free survival. In confusion matrix analysis, the network classifier achieved an overall predictive accuracy of 85% with a sensitivity of 73% and specificity of 90% for this cohort based on the Youden-J cut-off. Stage, grade, and patient age were not statistically significant for this cohort size. Occlusion sensitivity analysis suggested histopathological features learned by the network that may be associated with sensitivity or resistance to the chemotherapy, but multiple marker studies will be necessary to follow up on those preliminary results.

CONCLUSIONS

This type of analysis has the potential, if further developed, to improve the prediction of response to therapy of high-grade serous ovarian cancer and perhaps be useful as a factor in deciding between platinum-based and other therapies. More broadly, it may increase our understanding of the histopathological variables that predict response and may be adaptable to other cancer types and imaging modalities.

Towards artificial intelligence-enabled extracellular vesicle precision drug delivery

Extracellular Vesicles (EVs), particularly exosomes, recently exploded into nanomedicine as an emerging drug delivery approach due to their superior biocompatibility, circulating stability, and bioavailability in vivo. However, EV heterogeneity makes molecular targeting precision a critical challenge. Deciphering key molecular drivers for controlling EV tissue targeting specificity is in great need. Artificial intelligence (AI) brings powerful prediction ability for guiding the rational design of engineered EVs in precision control for drug delivery. This review focuses on cutting-edge nano-delivery via integrating large-scale EV data with AI to develop AI-directed EV therapies and illuminate the clinical translation potential. We briefly review the current status of EVs in drug delivery, including the current frontier, limitations, and considerations to advance the field. Subsequently, we detail the future of AI in drug delivery and its impact on precision EV delivery. Our review discusses the current universal challenge of standardization and critical considerations when using AI combined with EVs for precision drug delivery. Finally, we will conclude this review with a perspective on future clinical translation led by a combined effort of AI and EV research.

Label-free differential imaging of cellular components in mouse brain tissue by wide-band photoacoustic microscopy

Mapping diverse cellular components with high spatial resolution is important to interrogate biological systems and study disease pathogenesis. Conventional optical imaging techniques for mapping biomolecular profiles with differential staining and labeling methods are cumbersome. Different types of cellular components exhibit distinctive characteristic absorption spectra across a wide wavelength range. By virtue of this property, a lab-made wide-band optical-resolution photoacoustic microscopy (wbOR-PAM) system, which covers wavelengths from the ultraviolet and visible to the shortwave infrared regions, was designed and developed to capture multiple cellular components in 300-μm-thick brain slices at nine different wavelengths without repetitive staining and complicated processing. This wbOR-PAM system provides abundant spectral information. A reflective objective lens with an infinite conjugate design was applied to focus laser beams with different wavelengths, avoiding chromatic aberration. The molecular components of complex brain slices were probed without labeling. The findings of the present study demonstrated a distinctive absorption of phospholipids, a major component of the cell membrane, brain, and nervous system, at 1690 nm and revealed their precise distribution with microscopic resolution in a mouse brain, for the first time. This novel imaging modality provides a new opportunity to investigate important biomolecular components without either labeling or lengthy specimen processing, thus, laying the groundwork for revealing cellular mechanisms involved in disease pathogenesis.

Prognostic Value of Selected Histologic Features for Lung Squamous Cell Carcinoma

The recent histologic subtyping of lung adenocarcinoma has demonstrated the prognostic values of histologic patterns in this malignancy. However, the histological features of lung squamous cell carcinoma (SCC) are much less established. This short review discusses several promising histological prognostic markers for SCC, including tumor budding, tumor cell nesting, and the spreading of tumors through air spaces. Wherever appropriate, the biological significance of these morphological features was also discussed. The investigators consider that histological prognostic markers are highly valuable in understanding the cancer biology of SCC, and in guiding clinical treatment. However, larger clinical cohorts are needed to better establish the prognostic values of the aforementioned histological markers. The application of modern technologies, including machine-learning, would make the histological analysis accurate and reproducible.

Identification-Free Control over the Precursor Isotopic Mass Misassignment in Orbitrap-Based Proteomics

Selection of a precursor ion from a peptide isotopic cluster to obtain a fragmentation mass spectrum is a crucial step in data-dependent proteome analysis. However, the monoisotopic mass assignment performed in this step is often an issue confronted by the data acquisition software of hybrid Orbitrap FTMS that is most widely used in proteomics. To address the problem, many data processing tools, such as raw data converters and search engines, have optional accounting for the precursor mass shift due to the isotopic error. These solutions require additional data preprocessing steps and lead to an increase in the search space, thus making the analysis longer and/or less reliable. In this work, we processed 100 Orbitrap-based LC-MS/MS runs from 10 publicly available data sets to examine the rate of precursor isotope misassignment. The effect from taking the isotope error into account during the search on the number of identified peptides varied in a wide range from 0 to 33%. Thus, it may be tempting to spend extra time before or during a search to account for the mass assignment issue. Alternatively, this effect can be predicted a priori using an identification-free metric, which can be a part of data quality control software. Based on the results obtained in this work, we propose such a metric be further added into the visual and intuitive quality control software, viQC, developed previously and available at https://github.com/lisavetasol/viQC. It takes about a minute to calculate and plot nine quality metrics, including the proposed one for typical proteome analysis.

Immunocytokines are a promising immunotherapeutic approach against glioblastoma

Glioblastoma is a poorly immunogenic cancer, and the successes with recent immunotherapies in extracranial malignancies have, so far, not been translated to this devastating disease. Therefore, there is an urgent need for new strategies to convert the immunologically cold glioma microenvironment into a hot one to enable effective antitumor immunity. Using the L19 antibody, which is specific to a tumor-associated epitope of extracellular fibronectin, we developed antibody-cytokine fusions—immunocytokines—with interleukin-2 (IL2), IL12, or tumor necrosis factor (TNF). We showed that L19 accumulated in the tumor microenvironment of two orthotopic immunocompetent mouse glioma models. Furthermore, intravenous administration of L19-mIL12 or L19-mTNF cured a proportion of tumor-bearing mice, whereas L19-IL2 did not. This therapeutic activity was abolished in RAG−/− mice or upon depletion of CD4 or CD8 T cells, suggesting adaptive immunity. Mechanistically, both immunocytokines promoted tumor-infiltrating lymphocytes and increased the amounts of proinflammatory cytokines within the tumor microenvironment. In addition, L19-mTNF induced tumor necrosis. Systemic administration of the fully human L19-TNF fusion protein to patients with glioblastoma (NCT03779230) was safe, decreased regional blood perfusion within the tumor, and was associated with increasing tumor necrosis and an increase in tumor-infiltrating CD4 and CD8 T cells. The extensive preclinical characterization and subsequent clinical translation provide a robust basis for future studies with immunocytokines to treat malignant brain tumors.

Enhanced prognostic stratification of neoadjuvant treated lung squamous cell carcinoma by computationally-guided tumor regression scoring

INTRODUCTION

The amount of residual tumor burden after neoadjuvant chemotherapy is an important prognosticator, but for non-small cell lung carcinoma (NSCLC), no official regression scoring system is yet established. Computationally derived histological regression scores could provide unbiased and quantitative readouts to complement the clinical assessment of treatment response.

METHODS

Histopathologic tumor regression was microscopically assessed on whole cases in a neoadjuvant chemotherapy-treated cohort (NAC, n = 55 patients) of lung squamous cell carcinomas (LSCC). For each patient, the slide showing the least pathologic regression was selected for subsequent computational analysis and histological features were quantified: percentage of vital tumor cells (cTu.Percentage), total surface covered by vital tumor cells (cTu.Area), area of the largest vital tumor fragment (cTu.Size.max), and total number of vital tumor fragments (cTu.Fragments). A chemo-naïve LSCC cohort (CN, n = 104) was used for reference. For 23 of the 55 patients [¹⁸F]-Fluorodeoxyglucose (FDG) PET/CT measurements of maximum standard uptake value (SUV_max), background subtracted lesion activity (BSL) and background subtracted volume (BSV) were correlated with pathologic regression. Survival analysis was carried out using Cox regression and receiver operating characteristic (ROC) curve analysis using a 3-years cutoff.

RESULTS

All computational regression parameters significantly correlated with relative changes of BSV FDG PET/CT values after neoadjuvant chemotherapy. ROC curve analysis of histological parameters of NAC patients showed that cTu.Percentage was the most accurate prognosticator of overall survival (ROC curve AUC = 0.77, p-value = 0.001, Cox regression HR = 3.6, p = 0.001, variable cutoff < = 30 %).

CONCLUSIONS

This study demonstrates the prognostic relevance of computer-derived histopathologic scores. Additionally, the analysis carried out on slides displaying the least pathologic regression correlated with overall pathologic response and PET/CT values. This might improve the objective histopathologic assessment of tumor response in neoadjuvant setting.

Applications of machine learning in drug discovery and development

Drug discovery and development pipelines are long, complex and depend on numerous factors. Machine learning (ML) approaches provide a set of tools that can improve discovery and decision making for well-specified questions with abundant, high-quality data. Opportunities to apply ML occur in all stages of drug discovery. Examples include target validation, identification of prognostic biomarkers and analysis of digital pathology data in clinical trials. Applications have ranged in context and methodology, with some approaches yielding accurate predictions and insights. The challenges of applying ML lie primarily with the lack of interpretability and repeatability of ML-generated results, which may limit their application. In all areas, systematic and comprehensive high-dimensional data still need to be generated. With ongoing efforts to tackle these issues, as well as increasing awareness of the factors needed to validate ML approaches, the application of ML can promote data-driven decision making and has the potential to speed up the process and reduce failure rates in drug discovery and development.

Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death

PURPOSE

Biomarkers for disease-specific survival (DSS) in early-stage melanoma are needed to select patients for adjuvant immunotherapy and accelerate clinical trial design. We present a pathology-based computational method using a deep neural network architecture for DSS prediction.

EXPERIMENTAL DESIGN

The model was trained on 108 patients from four institutions and tested on 104 patients from Yale School of Medicine (YSM, New Haven, CT). A receiver operating characteristic (ROC) curve was generated on the basis of vote aggregation of individual image sequences, an optimized cutoff was selected, and the computational model was tested on a third independent population of 51 patients from Geisinger Health Systems (GHS).

RESULTS

Area under the curve (AUC) in the YSM patients was 0.905 (P < 0.0001). AUC in the GHS patients was 0.880 (P < 0.0001). Using the cutoff selected in the YSM cohort, the computational model predicted DSS in the GHS cohort based on Kaplan-Meier (KM) analysis (P < 0.0001).

CONCLUSIONS

The novel method presented is applicable to digital images, obviating the need for sample shipment and manipulation and representing a practical advance over current genetic and IHC-based methods.

IL-8 and CXCR1 expression is associated with cancer stem cell-like properties of clear cell renal cancer

Recent studies suggest that clear cell renal cell carcinoma (ccRCC) possesses a rare population of cancer stem cells (CSCs) that might contribute to tumor heterogeneity, metastasis and therapeutic resistance. Nevertheless, their relevance for renal cancer is still unclear. In this study, we successfully isolated CSCs from established human ccRCC cell lines. CSCs displayed high expression of the chemokine IL‐8 and its receptor CXCR1. While recombinant IL‐8 significantly increased CSC number and properties in vitro, CXCR1 inhibition using an anti‐CXCR1 antibody or repertaxin significantly reduced these features. After injection into immune‐deficient mice, CSCs formed primary tumors that metastasized to the lung and liver. All xenografted tumors in mice expressed high levels of IL‐8 and CXCR1. Furthermore, IL‐8/CXCR1 expression significantly correlated with decreased overall survival in ccRCC patients. These results suggest that the IL‐8/CXCR1 phenotype is associated with CSC‐like properties in renal cancer. © 2019 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

Computationally-Guided Development of a Stromal Inflammation Histologic Biomarker in Lung Squamous Cell Carcinoma

The goal of this study is to use computational pathology to help guide the development of human-based prognostic H&E biomarker(s) suitable for research and potential clinical use in lung squamous cell carcinoma (SCC). We started with high-throughput computational image analysis with tissue microarrays (TMAs) to screen for histologic features associated with patient overall survival, and found that features related to stromal inflammation were the most strongly prognostic. Based on this, we developed an H&E stromal inflammation (SI) score. The prognostic value of the SI score was validated by two blinded human observers on two large cohorts from a single institution. The SI score was found to be reproducible on TMAs (Spearman rho = 0.88 between the two observers), and highly prognostic (e.g. hazard ratio = 0.32; 95% confidence interval: 0.19-0.54; p-value = 2.5 × 10-5 in multivariate analyses), particularly in comparison to established histologic biomarkers. Guided by downstream molecular/biomarker correlation studies starting with TCGA cases, we investigated the hypothesis that epithelial PD-L1 expression modified the prognostic value of SI. Our research demonstrates that computational pathology can be an efficient hypothesis generator for human pathology research, and support the histologic evaluation of SI as a prognostic biomarker in lung SCCs.