Privacy-Preserving Deep Learning NLP Models for Cancer Registries
Not Available
60 APPLIED LIFE SCIENCES↗
SEARCH · Engineering Papers
Results for “Cancer pathology reports”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Deep learning uncertainty quantification for clinical text classification
Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network’s confidence, in-depth analyses are needed to establish whether they are well calibrated. In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount—that is, the number of electronic pathology reports for which the model’s predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining—thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.
59 BASIC BIOLOGICAL SCIENCES↗
Machine learning and deep learning tools for the automated capture of cancer surveillance data
The National Cancer Institute and the Department of Energy strategic partnership applies advanced computing and predictive machine learning and deep learning models to automate the capture of information from unstructured clinical text for inclusion in cancer registries. Applications include extraction of key data elements from pathology reports, determination of whether a pathology or radiology report is related to cancer, extraction of relevant biomarker information, and identification of recurrence. With the growing complexity of cancer diagnosis and treatment, capturing essential information with purely manual methods is increasingly difficult. These new methods for applying advanced computational capabilities to automate data extraction represent an opportunity to close critical information gaps and create a nimble, flexible platform on which new information sources, such as genomics, can be added. This will ultimately provide a deeper understanding of the drivers of cancer and outcomes in the population and increase the timeliness of reporting. These advances will enable better understanding of how real-world patients are treated and the outcomes associated with those treatments in the context of our complex medical and social environment.
60 APPLIED LIFE SCIENCES↗
Deformable phrase level attention: A flexible approach for improving AI based medical coding
Objective: Improving the AI-driven automated medical encoding of clinical text plays a vital role in gathering information on the occurrence of diseases to improve population-level health. This work presents a novel attention mechanism designed to enhance text classification models and ensure appropriate classification of medical concepts in unstructured electronic health records. Materials and Methods: We developed a deformable, phrase-level attention mechanism to identify important lexical word-level and contextual phrase-level information from clinical text documents. We evaluated conventional and transformer-based deep learning models that we extended with our attention mechanism on the extraction of critical cancer information (e.g., site, subsite, laterality, histology, behavior) from 629,908 electronic pathology reports and on the automated medical encoding of 52,722 hospital discharge summaries. Results: Transformer-based models with the deformable, phrase-level attention mechanism achieved the best performance on the extraction of critical cancer information from pathology reports. Conventional- and transformer-based models show similar or better performance than their baseline counterparts on the automated medical encoding of clinical documents. Discussion: The addition of phrase-level information allowed models extended with our proposed method to outperform standard word-level attention. Our method showed favorable properties for the real-world application in terms of model robustness and phenotyping. These results indicate that our method is promising for automated data harmonization for common data models. Conclusion: This work proposes a novel deformable, phrase-level attention mechanism that enhances text classification models in the extraction of medical concepts from clinical text documents. We demonstrate strong performances on two clinical text datasets and showcase real-world deployability of our method.
Automated medical encoding↗
Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text
This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.
Alawad, Mohammed↗
A Comprehensive Urine Proteome Database Generated From Patients With Various Renal Conditions and Prostate Cancer
Urine proteins can serve as viable biomarkers for diagnosing and monitoring various diseases. A comprehensive urine proteome database, generated from a variety of urine samples with different disease conditions, can serve as a reference resource for facilitating discovery of potential urine protein biomarkers. Herein, we present a urine proteome database generated from multiple datasets using 2D LC-MS/MS proteome profiling of urine samples from healthy individuals (HI), renal transplant patients with acute rejection (AR) and stable graft (STA), patients with non-specific proteinuria (NS), and patients with prostate cancer (PC). A total of ~28,000 unique peptides spanning ~2,200 unique proteins were identified with a false discovery rate of <0.5% at the protein level. Over one third of the annotated proteins were plasma membrane proteins and another one third were extracellular proteins according to gene ontology analysis. Ingenuity Pathway Analysis of these proteins revealed 349 potential biomarkers in the literature-curated database. Forty-three percentage of all known cluster of differentiation (CD) proteins were identified in the various human urine samples. Interestingly, following comparisons with five recently published urine proteome profiling studies, which applied similar approaches, there are still ~400 proteins which are unique to this current study. These may represent potential disease-associated proteins. Among them, several proteins such as serpin B3, renin receptor, and periostin have been reported as pathological markers for renal failure and prostate cancer, respectively. Taken together, our data should provide valuable information for future discovery and validation studies of urine protein biomarkers for various diseases.
60 APPLIED LIFE SCIENCES↗
Direct evidence that tumor cells soften when navigating confined spaces.
The mechanical properties of cells strongly regulate many physiological and pathological processes. For example, in cancer, invasive and metastatic tumor cells have often been reported to be softer than nontumor cells, raising speculation that cancer cells might adaptively soften to facilitate migration through narrow tissue spaces. Despite growing interest in targeting cell softening to impede invasion and metastasis, it remains to be directly demonstrated that tumor cells soften as they migrate through confined spaces. Here, we address this open question by combining topographically patterned substrates with atomic force microscopy (AFM). Using a polydimethylsiloxane open-roof microdevice featuring tapered, fibronectin-coated channels, we followed the migration of U2OS cells through various stages of confinement while simultaneously performing AFM indentation. As cells progress from unconfined migration to fully confined migration, cells soften and exclude Yes-associated protein from the nucleus. Superresolution imaging reveals that confinement induces remodeling of actomyosin stress fiber architecture. Companion studies with flat one-dimensional microlines indicate that the changes in cytoarchitecture and mechanics are intrinsically driven by topographical confinement rather than changes in cellular aspect ratio. Our studies represent among the most direct evidence to date that tumor cells soften during confined migration and support cell softening as a mechanoadaptive mechanism during invasion.
59 BASIC BIOLOGICAL SCIENCES↗
Prognostic Importance of MRI-Detected Extramural Venous Invasion in Rectal Cancer: A Literature Review and Systematic Meta-Analysis
Extramural venous invasion (EMVI) is recognized as a poor prognostic factor in rectal cancer. There are well-documented limitations associated with pathology detection of EMVI, including variable reporting and the inability to use it preoperatively to guide neoadjuvant treatment. Magnetic resonance imaging (MRI)-detected EMVI (mrEMVI) has been proposed as an imaging biomarker. This review assesses the prognostic significance of mrEMVI on survival outcomes and whether regression of mrEMVI after neoadjuvant therapy is associated with improvements in survival.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Biology of extracellular vesicles secreted from senescent cells as senescence‐associated secretory phenotype factors
The increase of the morbidity rate in age‐related diseases, such as cancer, Alzheimer’s disease, arteriosclerosis and pulmonary fibrosis, has become a profound social problem. Recent reports have pointed out that senescent cells accumulated in the body with aging might cause these aged‐related pathologies. Cellular senescence is known as an irreversible cell cycle arrest induced by various stresses, and can function as an important tumor suppression mechanism to exclude the premalignant cells. In contrast, senescent cells provoke the phenomenon, termed the senescence‐associated secretory phenotype, which causes the secretion of various inflammatory proteins, and it is at risk of facilitating chronic inflammation and oncogenic transformation to surrounding cells. We have previously reported that senescent cells secrete not only inflammatory proteins, but also extracellular vesicles (EV). EV include various cellular components, such as proteins, lipids and nucleic acids, which are proven to be important factors for cell‐to‐cell communication. Recent evidence suggests that EV secreted from senescent cells might contribute to tumorigenesis and age‐associated pathologies as new senescence‐associated secretory phenotype factors. In addition, we also showed that the EV secretion pathway is one of the essential defense mechanisms to maintain cellular homeostasis by excretion of intercellular toxic substances into extracellular space. Herein, this review shows the biological functions of EV secreted from senescent cells. Geriatr Gerontol Int 2020; ••: ••–•• .
Misawa, Tomoka↗
Optical Microsystems for Molecular Sensing (CRADA Final Report)
As part of the Cyclotron Road program, NuSight Photonics sought to implement and investigate an optical Raman spectroscopy instrument for material and molecular analysis. Raman spectroscopy is widely used for quick and non-invasive material measurement when accurate results are needed – e.g., for monitoring manufacturing process in pharmaceutical plants, or identifying illicit substances and explosives by Law Enforcement. This technique is also growing rapidly in popularity as it is applied successfully to a broad range of applications, from pathology and non-invasive early cancer detection, to food and drug safety. The biggest challenge for Raman spectroscopy to achieve its full potential is the hardware cost, ranging from $\$ $25k to $\$ $250k, with the lower cost solutions significantly limited in sensitivity—or detection limit. NuSight Photonics aimed to tackle this obstacle through a novel hardware approach: Swept-Source Raman Spectroscopy.
36 MATERIALS SCIENCE↗
Rutin is a potent senomorphic agent to target senescent cells and can improve chemotherapeutic efficacy
Aging is a major risk factor for most chronic disorders, for which cellular senescence is one of the central hallmarks. Senescent cells develop the pro-inflammatory senescence-associated secretory phenotype (SASP), which significantly contributes to organismal aging and age-related disorders. Development of senotherapeutics, an emerging class of therapeutic agents to target senescent cells, allows to effectively delay aging and alleviate chronic pathologies. Here we report preliminary outputs from screening of a natural medicinal agent (NMA) library for senotherapeutic candidates and validated several agents with prominent potential as senomorphics. Rutin, a phytochemical constituent found in a number of plants, showed remarkable capacity in targeting senescent cells by dampening expression of the full spectrum SASP. Further analysis indicated that rutin restrains the acute stress-associated phenotype (ASAP) by specifically interfering with the interactions of ATM with HIF1α, a master regulator of cellular and systemic homeostasis activated during senescence, and of ATM with TRAF6, part of a key signaling axis supporting the ASAP development toward the SASP. Conditioned media produced by senescent stromal cells enhanced the malignant phenotypes of prostate cancer cells, including in vitro proliferation, migration, invasion, and more importantly, chemoresistance, while rutin remarkably downregulated these gain-of-functions. Although classic chemotherapy reduced tumor progression, the treatment outcome was substantially improved upon combination of a chemotherapeutic agent with rutin. Our study provides a proof of concept for rutin as an emerging natural senomorphic agent, and presents an effective therapeutic avenue for alleviating age-related pathologies including cancer.
60 APPLIED LIFE SCIENCES↗
High-Content Clonogenic Survival Screen to Identify Chemoradiation Sensitizers
The combination of cytotoxic chemotherapy with radiation therapy (CRT) has resulted in significant improvements in clinical outcomes for patients with many locally advanced unresectable cancers. Only a small proportion of patients achieve pathologic complete responses to CRT; combination of CRT with targeted agents offers the promise of further improving treatment responses. However, numerous clinical trials have failed to show an improvement in clinical outcomes with the addition of targeted agents. To increase the accessibility of our screening method and accelerate the pace at which novel combinations with CRT are identified and incorporated into standard practices for treatments, we report details on screening method optimization, data generation, and downstream data analysis.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Next-generation poly-L-histidine formulations for miRNA mimic delivery
Many diseases, especially cancer, are caused by the abnormal expression of non-coding microRNAs (miRNAs), which regulate gene expression, leading to the development of miRNA-based therapeutics. Synthetic miRNA inhibitors have shown promising efficacy in blocking the activity of aberrant miRNAs that are upregulated in disease-specific pathologies. On the other hand, miRNAs that aid in preventing certain diseases and are reduced in expression in the disease state need different strategies. To tackle this, miRNA mimics, which mimic the activity of endogenous miRNAs, can be delivered for those miRNAs downregulated in different disease states. However, the delivery of miRNA mimics remains a challenge. Here, we report a cationic polylactic-co-glycolic acid (PLGA)-poly-L-histidine delivery system to deliver miRNA mimics. We chose miR-34a mimics as a proof of concept for miRNA delivery. miR-34a-loaded PLGA-poly-L-histidine nanoparticles (NPs) were formulated and biophysically characterized to analyze the structural properties of miRNA mimic-loaded NPs. In vitro efficacy was determined by investigating miR-34a and downstream target levels and performing cell viability and apoptosis assays. We confirmed in vivo efficacy through prolonged survival of miR-34a NP-treated A549-derived xenograft mice treated intratumorally. The results of these studies establish PLGA-poly-L-histidine NPs as an effective delivery system for miRNA mimics for treating diseases characterized by downregulated miRNAs.
60 APPLIED LIFE SCIENCES↗
Structural Insights into the SPRED1-Neurofibromin-KRAS Complex and Disruption of SPRED1-Neurofibromin Interaction by Oncogenic EGFR
Sprouty-related, EVH1 domain-containing (SPRED) proteins negatively regulate RAS/mitogen-activated protein kinase (MAPK) signaling following growth factor stimulation. This inhibition of RAS is thought to occur primarily through SPRED1 binding and recruitment of neurofibromin, a RasGAP, to the plasma membrane. Here, we report the structure of neurofibromin (GTPase-activating protein [GAP]-related domain) complexed with SPRED1 (EVH1 domain) and KRAS. The structure provides insight into how the membrane targeting of neurofibromin by SPRED1 allows simultaneous interaction with activated KRAS. SPRED1 and NF1 loss-of-function mutations occur across multiple cancer types and developmental diseases. Analysis of the neurofibromin-SPRED1 interface provides a rationale for mutations observed in Legius syndrome and suggests why SPRED1 can bind to neurofibromin but no other RasGAPs. We show that oncogenic EGFR(L858R) signaling leads to the phosphorylation of SPRED1 on serine 105, disrupting the SPRED1-neurofibromin complex. The structural, biochemical, and biological results provide new mechanistic insights about how SPRED1 interacts with neurofibromin and regulates active KRAS levels in normal and pathologic conditions.
59 BASIC BIOLOGICAL SCIENCES↗
A comparison of histopathology imaging comprehension algorithms based on multiple instance learning
Whole slide imaging (WSI), also called digital virtual microscopy, is a new imaging modality. It allows for the application of AI and machine learning methods to cancer pathology to help establish a means for the automatic diagnosis of cancer cases. However, designing machine-learning models for WSI is computationally challenging due to its required ultra-high resolution. The current state-of-the-art models use multiple instance learning (MIL). MIL is a weakly-supervised learning method in which the model uses an array of inferences from many smaller instances to make a final classification about the entire set. In the context of WSI, researchers divide the ultra-high-resolution image into many patches. The model then classifies the slide based on an array of inferences from the patches. Among several ways of making the final classification, attention-based mechanisms have resulted in superb accuracy scores. The Transformer, one attention-based algorithm, has reported substantial improvements for WSI comprehension tasks. In this project, we studied and compared several WSI comprehension algorithms. We used the following three datasets: CAMELYON16+17, TCGALung, and TCGA-Kidney. We found that attention-based MIL algorithms performed better than standard MIL algorithms for classifying WSI images, achieving a higher mean accuracy and AUC. However, none of the attention-based algorithms performed significantly better than the others, reporting accuracy scores that varied widely. Presumably, it is due to the limited availability of training samples in the data corpus. Since it is not easy to increase the samples from human subjects, some machine learning techniques like transfer learning could help mitigate this issue.
Saunders, Adam↗
PDK4-dependent hypercatabolism and lactate production of senescent cells promotes cancer malignancy
Abstract Senescent cells remain metabolically active, but their metabolic landscape and resulting implications remain underexplored. Here, we report upregulation of pyruvate dehydrogenase kinase 4 (PDK4) upon senescence, particularly in some stromal cell lines. Senescent cells display a PDK4-dependent increase in aerobic glycolysis and enhanced lactate production but maintain mitochondrial respiration and redox activity, thus adopting a special form of metabolic reprogramming. Medium from PDK4 + stromal cells promotes the malignancy of recipient cancer cells in vitro, whereas inhibition of PDK4 causes tumor regression in vivo. We find that lactate promotes reactive oxygen species production via NOX1 to drive the senescence-associated secretory phenotype, whereas PDK4 suppression reduces DNA damage severity and restrains the senescence-associated secretory phenotype. In preclinical trials, PDK4 inhibition alleviates physical dysfunction and prevents age-associated frailty. Together, our study confirms the hypercatabolic nature of senescent cells and reveals a metabolic link between cellular senescence, lactate production, and possibly, age-related pathologies, including but not limited to cancer.
Endocrinology & Metabolism↗
Cancer genomics predicts disease relapse and therapeutic response to neoadjuvant chemotherapy of hormone sensitive breast cancers
Several studies provide insight into the landscape of breast cancer genomics with the genomic characterization of tumors offering exceptional opportunities in defining therapies tailored to the patient’s specific need. However, translating genomic data into personalized treatment regimens has been hampered partly due to uncertainties in deviating from guideline based clinical protocols. Here we report a genomic approach to predict favorable outcome to treatment responses thus enabling personalized medicine in the selection of specific treatment regimens. The genomic data were divided into a training set of N = 835 cases and a validation set consisting of 1315 hormone sensitive, 634 triple negative breast cancer (TNBC) and 1365 breast cancer patients with information on neoadjuvant chemotherapy responses. Patients were selected by the following criteria: estrogen receptor (ER) status, lymph node invasion, recurrence free survival. The k-means classification algorithm delineated clusters with low- and high- expression of genes related to recurrence of disease; a multivariate Cox’s proportional hazard model defined recurrence risk for disease. Classifier genes were validated by Immunohistochemistry (IHC) using tissue microarray sections containing both normal and cancerous tissues and by evaluating findings deposited in the human protein atlas repository. Based on the leave-on-out cross validation procedure of 4 independent data sets we identified 51-genes associated with disease relapse and selected 10, i.e. TOP2A, AURKA, CKS2, CCNB2, CDK1 SLC19A1, E2F8, E2F1, PRC1, KIF11 for in depth validation. Expression of the mechanistically linked disease regulated genes significantly correlated with recurrence free survival among ER-positive and triple negative breast cancer patients and was independent of age, tumor size, histological grade and node status. Importantly, the classifier genes predicted pathological complete responses to neoadjuvant chemotherapy (P < 0.001) with high expression of these genes being associated with an improved therapeutic response toward two different anthracycline-taxane regimens; thus, highlighting the prospective for precision medicine. Our study demonstrates the potential of classifier genes to predict risk for disease relapse and treatment response to chemotherapies. The classifier genes enable rational selection of patients who benefit best from a given chemotherapy thus providing the best possible care. The findings encourage independent clinical validation.
59 BASIC BIOLOGICAL SCIENCES↗