OARD: Open annotations for rare diseases and their phenotypes based on real-world data.

Diagnosis for rare genetic diseases often relies on phenotype-driven methods, which hinge on the accuracy and completeness of the rare disease phenotypes in the underlying annotation knowledgebase. Existing knowledgebases are often manually curated with additional annotations found in published case reports. Despite their potential, real-world data such as electronic health records (EHRs) have not been fully exploited to derive rare disease annotations. Here, we present open annotation for rare diseases (OARD), a real-world-data-derived resource with annotation for rare-disease-related phenotypes. This resource is derived from the EHRs of two academic health institutions containing more than 10 million individuals spanning wide age ranges and different disease subgroups. By leveraging ontology mapping and advanced natural-language-processing (NLP) methods, OARD automatically and efficiently extracts concepts for both rare diseases and their phenotypic traits from billing codes and lab tests as well as over 100 million clinical narratives. The rare disease prevalence derived by OARD is highly correlated with those annotated in the original rare disease knowledgebase. By performing association analysis, we identified more than 1 million novel disease-phenotype association pairs that were previously missed by human annotation, and >60% were confirmed true associations via manual review of a list of sampled pairs. Compared to the manual curated annotation, OARD is 100% data driven and its pipeline can be shared across different institutions. By supporting privacy-preserving sharing of aggregated summary statistics, such as term frequencies and disease-phenotype associations, it fills an important gap to facilitate data-driven research in the rare disease community.

Leveraging electronic health record data for clinical trial planning by assessing eligibility criteria's impact on patient count and safety.

OBJECTIVE: To present an approach on using electronic health record (EHR) data that assesses how different eligibility criteria, either individually or in combination, can impact patient count and safety (exemplified by all-cause hospitalization risk) and further assist with criteria selection for prospective clinical trials. MATERIALS AND METHODS: Trials in three disease domains - relapsed/refractory (r/r) lymphoma/leukemia; hepatitis C virus (HCV); stages 3 and 4 chronic kidney disease (CKD) - were analyzed as case studies for this approach. For each disease domain, criteria were identified and all criteria combinations were used to create EHR cohorts. Per combination, two values were derived: (1) number of eligible patients meeting the selected criteria; (2) hospitalization risk, measured as the hazard ratio between those that qualified and those that did not. From these values, k-means clustering was applied to derive which criteria combinations maximized patient counts but minimized hospitalization risk. RESULTS: Criteria combinations that reduced hospitalization risk without substantial reductions on patient counts were as follows: for r/r lymphoma/leukemia (23 trials; 9 criteria; 623 patients), applying no infection and adequate absolute neutrophil count while forgoing no prior malignancy; for HCV (15; 7; 751), applying no human immunodeficiency virus and no hepatocellular carcinoma while forgoing no decompensated liver disease/cirrhosis; for CKD (10; 9; 23893), applying no congestive heart failure. CONCLUSIONS: Within each disease domain, the more drastic effects were generally driven by a few criteria. Similar criteria across different disease domains introduce different changes. Although results are contingent on the trial sample and the EHR data used, this approach demonstrates how EHR data can inform the impact on safety and available patients when exploring different criteria combinations for designing clinical trials.

Ensembles of natural language processing systems for portable phenotyping solutions.

BACKGROUND: Manually curating standardized phenotypic concepts such as Human Phenotype Ontology (HPO) terms from narrative text in electronic health records (EHRs) is time consuming and error prone. Natural language processing (NLP) techniques can facilitate automated phenotype extraction and thus improve the efficiency of curating clinical phenotypes from clinical texts. While individual NLP systems can perform well for a single cohort, an ensemble-based method might shed light on increasing the portability of NLP pipelines across different cohorts. METHODS: We compared four NLP systems, MetaMapLite, MedLEE, ClinPhen and cTAKES, and four ensemble techniques, including intersection, union, majority-voting and machine learning, for extracting generic phenotypic concepts. We addressed two important research questions regarding automated phenotype recognition. First, we evaluated the performance of different approaches in identifying generic phenotypic concepts. Second, we compared the performance of different methods to identify patient-specific phenotypic concepts. To better quantify the effects caused by concept granularity differences on performance, we developed a novel evaluation metric that considered concept hierarchies and frequencies. Each of the approaches was evaluated on a gold standard set of clinical documents annotated by clinical experts. One dataset containing 1,609 concepts derived from 50 clinical notes from two different institutions was used in both evaluations, and an additional dataset of 608 concepts derived from 50 case report abstracts obtained from PubMed was used for evaluation of identifying generic phenotypic concepts only. RESULTS: For generic phenotypic concept recognition, the top three performers in the NYP/CUIMC dataset are union ensemble (F1, 0.634), training-based ensemble (F1, 0.632), and majority vote-based ensemble (F1, 0.622). In the Mayo dataset, the top three are majority vote-based ensemble (F1, 0.642), cTAKES (F1, 0.615), and MedLEE (F1, 0.559). In the PubMed dataset, the top three are majority vote-based ensemble (F1, 0.719), training-based (F1, 0.696) and MetaMapLite (F1, 0.694). For identifying patient specific phenotypes, the top three performers in the NYP/CUIMC dataset are majority vote-based ensemble (F1, 0.610), MedLEE (F1, 0.609), and training-based ensemble (F1, 0.585). In the Mayo dataset, the top three are majority vote-based ensemble (F1, 0.604), cTAKES (F1, 0.531) and MedLEE (F1, 0.527). CONCLUSIONS: Our study demonstrates that ensembles of natural language processing can improve both generic phenotypic concept recognition and patient specific phenotypic concept identification over individual systems. Among the individual NLP systems, each individual system performed best when they were applied in the dataset that they were primary designed for. However, combining multiple NLP systems to create an ensemble can generally improve the performance. Specifically, the ensemble can increase the results reproducibility across different cohorts and tasks, and thus provide a more portable phenotyping solution compared to individual NLP systems.

Making work visible for electronic phenotype implementation: Lessons learned from the eMERGE network.

BACKGROUND: Implementation of phenotype algorithms requires phenotype engineers to interpret human-readable algorithms and translate the description (text and flowcharts) into computable phenotypes - a process that can be labor intensive and error prone. To address the critical need for reducing the implementation efforts, it is important to develop portable algorithms. METHODS: We conducted a retrospective analysis of phenotype algorithms developed in the Electronic Medical Records and Genomics (eMERGE) network and identified common customization tasks required for implementation. A novel scoring system was developed to quantify portability from three aspects: Knowledge conversion, clause Interpretation, and Programming (KIP). Tasks were grouped into twenty representative categories. Experienced phenotype engineers were asked to estimate the average time spent on each category and evaluate time saving enabled by a common data model (CDM), specifically the Observational Medical Outcomes Partnership (OMOP) model, for each category. RESULTS: A total of 485 distinct clauses (phenotype criteria) were identified from 55 phenotype algorithms, corresponding to 1153 customization tasks. In addition to 25 non-phenotype-specific tasks, 46 tasks are related to interpretation, 613 tasks are related to knowledge conversion, and 469 tasks are related to programming. A score between 0 and 2 (0 for easy, 1 for moderate, and 2 for difficult portability) is assigned for each aspect, yielding a total KIP score range of 0 to 6. The average clause-wise KIP score to reflect portability is 1.37 ±â€¯1.38. Specifically, the average knowledge (K) score is 0.64 ±â€¯0.66, interpretation (I) score is 0.33 ±â€¯0.55, and programming (P) score is 0.40 ±â€¯0.64. 5% of the categories can be completed within one hour (median). 70% of the categories take from days to months to complete. The OMOP model can assist with vocabulary mapping tasks. CONCLUSION: This study presents firsthand knowledge of the substantial implementation efforts in phenotyping and introduces a novel metric (KIP) to measure portability of phenotype algorithms for quantifying such efforts across the eMERGE Network. Phenotype developers are encouraged to analyze and optimize the portability in regards to knowledge, interpretation and programming. CDMs can be used to improve the portability for some 'knowledge-oriented' tasks.

Focal Liver Lesions: Computer-aided Diagnosis by Using Contrast-enhanced US Cine Recordings.

Purpose To assess the performance of computer-aided diagnosis (CAD) systems and to determine the dominant ultrasonographic (US) features when classifying benign versus malignant focal liver lesions (FLLs) by using contrast material-enhanced US cine clips. Materials and Methods One hundred six US data sets in all subjects enrolled by three centers from a multicenter trial that included 54 malignant, 51 benign, and one indeterminate FLL were retrospectively analyzed. The 105 benign or malignant lesions were confirmed at histologic examination, contrast-enhanced computed tomography (CT), dynamic contrast-enhanced magnetic resonance (MR) imaging, and/or 6 or more months of clinical follow-up. Data sets included 3-minute cine clips that were automatically corrected for in-plane motion and automatically filtered out frames acquired off plane. B-mode and contrast-specific features were automatically extracted on a pixel-by-pixel basis and analyzed by using an artificial neural network (ANN) and a support vector machine (SVM). Areas under the receiver operating characteristic curve (AUCs) for CAD were compared with those for one experienced and one inexperienced blinded reader. A third observer graded cine quality to assess its effects on CAD performance. Results CAD, the inexperienced observer, and the experienced observer were able to analyze 95, 100, and 102 cine clips, respectively. The AUCs for the SVM, ANN, and experienced and inexperienced observers were 0.883 (95% confidence interval [CI]: 0.793, 0.940), 0.829 (95% CI: 0.724, 0.901), 0.843 (95% CI: 0.756, 0.903), and 0.702 (95% CI: 0.586, 0.782), respectively; only the difference between SVM and the inexperienced observer was statistically significant. Accuracy improved from 71.3% (67 of 94; 95% CI: 60.6%, 79.8%) to 87.7% (57 of 65; 95% CI: 78.5%, 93.8%) and from 80.9% (76 of 94; 95% CI: 72.3%, 88.3%) to 90.3% (65 of 72; 95% CI: 80.6%, 95.8%) when CAD was in agreement with the inexperienced reader and when it was in agreement with the experienced reader, respectively. B-mode heterogeneity and contrast material washout were the most discriminating features selected by CAD for all iterations. CAD selected time-based time-intensity curve (TIC) features 99.0% (207 of 209) of the time to classify FLLs, versus 1.0% (two of 209) of the time for intensity-based features. None of the 15 video-quality criteria had a statistically significant effect on CAD accuracy-all P values were greater than the Holm-Sidak α-level correction for multiple comparisons. Conclusion CAD systems classified benign and malignant FLLs with an accuracy similar to that of an expert reader. CAD improved the accuracy of both readers. Time-based features of TIC were more discriminating than intensity-based features. © RSNA, 2017 Online supplemental material is available for this article.

Applying unsupervised machine learning approaches to characterize autologous breast reconstruction patient subgroups: an NSQIP analysis of 14,274 patients.

BACKGROUND: Autologous breast reconstruction is composed of diverse techniques and results in a variety of outcome trajectories. We propose employing an unsupervised machine learning method to characterize such heterogeneous patterns in large-scale datasets. METHODS: A retrospective cohort study of autologous breast reconstruction patients was conducted through the National Surgical Quality Improvement Program database. Patient characteristics, intraoperative variables, and occurrences of acute postoperative complications were collected. The cohort was classified into patient subgroups via the K-means clustering algorithm, a similarity-based unsupervised learning approach. The characteristics of each cluster were compared for differences from the complementary sample (p < 2 ×10-4) and validated with a test set. RESULTS: A total of 14,274 female patients were included in the final study cohort. Clustering identified seven optimal subgroups, ordered by increasing rate of postoperative complication. Cluster 1 (2027 patients) featured breast reconstruction with free flaps (50%) and latissimus dorsi flaps (40%). In addition to its low rate of complications (14%, p < 2 ×10-4), its patient population was younger and with lower comorbidities when compared with the whole cohort. In the other extreme, cluster 7 (1112 patients) almost exclusively featured breast reconstruction with free flaps (94%) and possessed the highest rates of unplanned reoperations, readmissions, and dehiscence (p < 2 ×10-4). The reoperation profile of cluster 3 was also significantly different from the general cohort and featured lower proportions of vascular repair procedures (p < 8 ×10-4). CONCLUSIONS: This study presents a novel, generalizable application of an unsupervised learning model to organize patient subgroups with associations between comorbidities, modality of breast reconstruction, and postoperative outcomes.

Clinical and temporal characterization of COVID-19 subgroups using patient vector embeddings of electronic health records.

OBJECTIVE: To identify and characterize clinical subgroups of hospitalized Coronavirus Disease 2019 (COVID-19) patients. MATERIALS AND METHODS: Electronic health records of hospitalized COVID-19 patients at NewYork-Presbyterian/Columbia University Irving Medical Center were temporally sequenced and transformed into patient vector representations using Paragraph Vector models. K-means clustering was performed to identify subgroups. RESULTS: A diverse cohort of 11 313 patients with COVID-19 and hospitalizations between March 2, 2020 and December 1, 2021 were identified; median [IQR] age: 61.2 [40.3-74.3]; 51.5% female. Twenty subgroups of hospitalized COVID-19 patients, labeled by increasing severity, were characterized by their demographics, conditions, outcomes, and severity (mild-moderate/severe/critical). Subgroup temporal patterns were characterized by the durations in each subgroup, transitions between subgroups, and the complete paths throughout the course of hospitalization. DISCUSSION: Several subgroups had mild-moderate severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections but were hospitalized for underlying conditions (pregnancy, cardiovascular disease [CVD], etc.). Subgroup 7 included solid organ transplant recipients who mostly developed mild-moderate or severe disease. Subgroup 9 had a history of type-2 diabetes, kidney and CVD, and suffered the highest rates of heart failure (45.2%) and end-stage renal disease (80.6%). Subgroup 13 was the oldest (median: 82.7 years) and had mixed severity but high mortality (33.3%). Subgroup 17 had critical disease and the highest mortality (64.6%), with age (median: 68.1 years) being the only notable risk factor. Subgroups 18-20 had critical disease with high complication rates and long hospitalizations (median: 40+ days). All subgroups are detailed in the full text. A chord diagram depicts the most common transitions, and paths with the highest prevalence, longest hospitalizations, lowest and highest mortalities are presented. Understanding these subgroups and their pathways may aid clinicians in their decisions for better management and earlier intervention for patients.

A machine learning approach to identifying delirium from electronic health records.

The identification of delirium in electronic health records (EHRs) remains difficult due to inadequate assessment or under-documentation. The purpose of this research is to present a classification model that identifies delirium using retrospective EHR data. Delirium was confirmed with the Confusion Assessment Method for the Intensive Care Unit. Age, sex, Elixhauser comorbidity index, drug exposures, and diagnoses were used as features. The model was developed based on the Columbia University Irving Medical Center EHR data and further validated with the Medical Information Mart for Intensive Care III dataset. Seventy-six patients from Surgical/Cardiothoracic ICU were included in the model. The logistic regression model achieved the best performance in identifying delirium; mean AUC of 0.874 ± 0.033. The mean positive predictive value of the logistic regression model was 0.80. The model promises to identify delirium cases with EHR data, thereby enable a sustainable infrastructure to build a retrospective cohort of delirium.

Quantitative automated image analysis system with automated debris filtering for the detection of breast carcinoma cells.

OBJECTIVE: To develop an intraoperative method for margin status evaluation during breast conservation therapy (BCT) using an automated analysis of imprint cytology specimens. STUDY DESIGN: Imprint cytology samples were prospectively taken from 47 patients undergoing either BCT or breast reduction surgery. Touch preparations from BCT patients were taken on cut sections through the tumor to generate positive margin controls. For breast reduction patients, slide imprints were taken at cuts through the center of excised tissue. Analysis results from the presented technique were compared against standard pathologic diagnosis. Slides were stained with cytokeratin and Hoechst, imaged with an automated fluorescent microscope, and analyzed with a fast algorithm to automate discrimination between epithelial cells and noncellular debris. RESULTS: The accuracy of the automated analysis was 95% for identifying invasive cancers compared against final pathologic diagnosis. The overall sensitivity was 87% while specificity was 100% (no false positives). This is comparable to the best reported results from manual examination of intraoperative imprint cytology slides while reducing the need for direct input from a cytopathologist. CONCLUSION: This work demonstrates a proof of concept for developing a highly accurate and automated system for the intraoperative evaluation of margin status to guide surgical decisions and lower positive margin rates.

From clinical trials to clinical practice: How long are drugs tested and then used by patients?

OBJECTIVE: Evidence is scarce regarding the safety of long-term drug use, especially for drugs treating chronic diseases. To bridge this knowledge gap, this research investigated the differences in drug exposure between clinical trials and clinical practice. MATERIALS AND METHODS: We extracted drug follow-up times from clinical trials in ClinicalTrials.gov and compared the difference between clinical trials and real-world usage data for 914 drugs taken by 96 645 927 patients. RESULTS: A total of 17.5% of drugs had longer median exposure in practice than in trials, 6% of patients had extended exposure to at least 1 drug, and drugs treating nervous system disorders and cardiovascular diseases were the most common among drugs with high rates of extended exposure. CONCLUSIONS: For most of patients, the drug use length is shorter than the tested length in clinical trials. Still, a remarkable number of patients experienced extended drug exposure, particularly for drugs treating nervous system disorders or cardiovascular disorders.

The potential role of EHR data in optimizing eligibility criteria definition for cardiovascular outcome trials.

BACKGROUND: Cardiovascular outcome trials (CVOTs) include patients with high risks for cardiovascular events based on specific inclusion criteria. Little is known about the impact of such inclusion criteria on patient accrual and the incidence rate of cardiovascular events. MATERIALS AND METHODS: We evaluated the impact of criteria on the accrual and the number of cardiovascular events in a cohort of 1544 diabetes patients identified from the clinical data warehouse of New York Presbyterian Hospital / Columbia University Irving Medical Center. RESULTS: The highest incidence rate of the composite events (i.e., cardiovascular mortality, stroke, and myocardial infarction) was observed when the inclusion criteria seek patients with underlying cardiovascular diseases or age ≥ 60 with at least two of the risk factors including duration of diabetes, hypertension, dyslipidemia, smoking status, and albuminuria. CONCLUSION: Our study shows that the electronic health records could be utilized to optimize the inclusion criteria while balancing study inclusiveness and number of events.

Towards clinical data-driven eligibility criteria optimization for interventional COVID-19 clinical trials.

OBJECTIVE: This research aims to evaluate the impact of eligibility criteria on recruitment and observable clinical outcomes of COVID-19 clinical trials using electronic health record (EHR) data. MATERIALS AND METHODS: On June 18, 2020, we identified frequently used eligibility criteria from all the interventional COVID-19 trials in ClinicalTrials.gov (n = 288), including age, pregnancy, oxygen saturation, alanine/aspartate aminotransferase, platelets, and estimated glomerular filtration rate. We applied the frequently used criteria to the EHR data of COVID-19 patients in Columbia University Irving Medical Center (CUIMC) (March 2020-June 2020) and evaluated their impact on patient accrual and the occurrence of a composite endpoint of mechanical ventilation, tracheostomy, and in-hospital death. RESULTS: There were 3251 patients diagnosed with COVID-19 from the CUIMC EHR included in the analysis. The median follow-up period was 10 days (interquartile range 4-28 days). The composite events occurred in 18.1% (n = 587) of the COVID-19 cohort during the follow-up. In a hypothetical trial with common eligibility criteria, 33.6% (690/2051) were eligible among patients with evaluable data and 22.2% (153/690) had the composite event. DISCUSSION: By adjusting the thresholds of common eligibility criteria based on the characteristics of COVID-19 patients, we could observe more composite events from fewer patients. CONCLUSIONS: This research demonstrated the potential of using the EHR data of COVID-19 patients to inform the selection of eligibility criteria and their thresholds, supporting data-driven optimization of participant selection towards improved statistical power of COVID-19 trials.

Detecting Systemic Data Quality Issues in Electronic Health Records.

Secondary analysis of electronic health records for clinical research faces significant challenges due to known data quality issues in health data observationally collected for clinical care and the data biases caused by standard healthcare processes. In this manuscript, we contribute methodology for data quality assessment by plotting domain-level (conditions (diagnoses), drugs, and procedures) aggregate statistics and concept-level temporal frequencies (i.e., annual prevalence rates of clinical concepts). We detect common temporal patterns in concept frequencies by normalizing and clustering annual concept frequencies using K-means clustering. We apply these methods to the Columbia University Irving Medical Center Observational Medical Outcomes Partnership database. The resulting domain-aggregate and cluster plots show a variety of patterns. We review the patterns found in the condition domain and investigate the processes that shape them. We find that these patterns suggest data quality issues influenced by system-wide factors that affect individual concept frequencies.

DQueST: dynamic questionnaire for search of clinical trials.

OBJECTIVE: Information overload remains a challenge for patients seeking clinical trials. We present a novel system (DQueST) that reduces information overload for trial seekers using dynamic questionnaires. MATERIALS AND METHODS: DQueST first performs information extraction and criteria library curation. DQueST transforms criteria narratives in the ClinicalTrials.gov repository into a structured format, normalizes clinical entities using standard concepts, clusters related criteria, and stores the resulting curated library. DQueST then implements a real-time dynamic question generation algorithm. During user interaction, the initial search is similar to a standard search engine, and then DQueST performs real-time dynamic question generation to select criteria from the library 1 at a time by maximizing its relevance score that reflects its ability to rule out ineligible trials. DQueST dynamically updates the remaining trial set by removing ineligible trials based on user responses to corresponding questions. The process iterates until users decide to stop and begin manually reviewing the remaining trials. RESULTS: In simulation experiments initiated by 10 diseases, DQueST reduced information overload by filtering out 60%-80% of initial trials after 50 questions. Reviewing the generated questions against previous answers, on average, 79.7% of the questions were relevant to the queried conditions. By examining the eligibility of random samples of trials ruled out by DQueST, we estimate the accuracy of the filtering procedure is 63.7%. In a study using 5 mock patient profiles, DQueST on average retrieved trials with a 1.465 times higher density of eligible trials than an existing search engine. In a patient-centered usability evaluation, patients found DQueST useful, easy to use, and returning relevant results. CONCLUSION: DQueST contributes a novel framework for transforming free-text eligibility criteria to questions and filtering out clinical trials based on user answers to questions dynamically. It promises to augment keyword-based methods to improve clinical trial search.

Columbia Open Health Data, clinical concept prevalence and co-occurrence from electronic health records.

Columbia Open Health Data (COHD) is a publicly accessible database of electronic health record (EHR) prevalence and co-occurrence frequencies between conditions, drugs, procedures, and demographics. COHD was derived from Columbia University Irving Medical Center's Observational Health Data Sciences and Informatics (OHDSI) database. The lifetime dataset, derived from all records, contains 36,578 single concepts (11,952 conditions, 12,334 drugs, and 10,816 procedures) and 32,788,901 concept pairs from 5,364,781 patients. The 5-year dataset, derived from records from 2013-2017, contains 29,964 single concepts (10,159 conditions, 10,264 drugs, and 8,270 procedures) and 15,927,195 concept pairs from 1,790,431 patients. Exclusion of rare concepts (count ≤ 10) and Poisson randomization enable data sharing by eliminating risks to patient privacy. EHR prevalences are informative of healthcare consumption rates. Analysis of co-occurrence frequencies via relative frequency analysis and observed-expected frequency ratio are informative of associations between clinical concepts, useful for biomedical research tasks such as drug repurposing and pharmacovigilance. COHD is publicly accessible through a web application-programming interface (API) and downloadable from the Figshare repository. The code is available on GitHub.

Extended Lifetime In Vivo Pulse Stimulated Ultrasound Imaging.

An on-demand long-lived ultrasound contrast agent that can be activated with single pulse stimulated imaging (SPSI) has been developed using hard shell liquid perfluoropentane filled silica 500-nm nanoparticles for tumor ultrasound imaging. SPSI was tested on LnCAP prostate tumor models in mice; tumor localization was observed after intravenous (IV) injection of the contrast agent. Consistent with enhanced permeability and retention, the silica nanoparticles displayed an extended imaging lifetime of 3.3±1 days (mean±standard deviation). With added tumor specific folate functionalization, the useful lifetime was extended to 12 ± 2 days; in contrast to ligand-based tumor targeting, the effect of the ligands in this application is enhanced nanoparticle retention by the tumor. This paper demonstrates for the first time that IV injected functionalized silica contrast agents can be imaged with an in vivo lifetime ~500 times longer than current microbubble-based contrast agents. Such functionalized long-lived contrast agents may lead to new applications in tumor monitoring and therapy.

Ultrasound Responsive Macrophase-Segregated Microcomposite Films for in Vivo Biosensing.

Ultrasound imaging is a safe, low-cost, and in situ method for detecting in vivo medical devices. A poly(methyl-2-cyanoacrylate) film containing 2 µm boron-doped, calcined, porous silica microshells was developed as an ultrasound imaging marker for multiple medical devices. A macrophase separation drove the gas-filled porous silica microshells to the top surface of the polymer film by controlled curing of the cyanoacrylate glue and the amount of microshell loading. A thin film of polymer blocked the wall pores of the microshells to seal air in their hollow core, which served as an ultrasound contrast agent. The ultrasound activity disappeared when curing conditions were modified to prevent the macrophase segregation. Phase segregated films were attached to multiple surgical tools and needles and gave strong color Doppler signals in vitro and in vivo with the use of a clinical ultrasound imaging instrument. Postprocessing of the simultaneous color Doppler and B-mode images can be used for autonomous identification of implanted surgical items by correlating the two images. The thin films were also hydrophobic, thereby extending the lifetime of ultrasound signals to hours of imaging in tissues by preventing liquid penetration. This technology can be used as a coating to guide the placement of implantable medical devices or used to image and help remove retained surgical items.

2-tier in-plane motion correction and out-of-plane motion filtering for contrast-enhanced ultrasound.

OBJECTIVES: Contrast-enhanced ultrasound (CEUS) cines of focal liver lesions (FLLs) can be quantitatively analyzed to measure tumor perfusion on a pixel-by-pixel basis for diagnostic indication. However, CEUS cines acquired freehand and during free breathing cause nonuniform in-plane and out-of-plane motion from frame to frame. These motions create fluctuations in the time-intensity curves (TICs), reducing the accuracy of quantitative measurements. Out-of-plane motion cannot be corrected by image registration in 2-dimensional CEUS and degrades the quality of in-plane motion correction (IPMC). A 2-tier IPMC strategy and adaptive out-of-plane motion filter (OPMF) are proposed to provide a stable correction of nonuniform motion to reduce the impact of motion on quantitative analyses. MATERIALS AND METHODS: A total of 22 cines of FLLs were imaged with dual B-mode and contrast specific imaging to acquire a 3-minute TIC. B-mode images were analyzed for motion, and the motion correction was applied to both B-mode and contrast images. For IPMC, the main reference frame was automatically selected for each cine, and subreference frames were selected in each respiratory cycle and sequentially registered toward the main reference frame. All other frames were sequentially registered toward the local subreference frame. Four OPMFs were developed and tested: subsample normalized correlation (NC), subsample sum of absolute differences, mean frame NC, and histogram. The frames that were most dissimilar to the OPMF reference frame using 1 of the 4 above criteria in each respiratory cycle were adaptively removed by thresholding against the low-pass filter of the similarity curve. Out-of-plane motion filter was quantitatively evaluated by an out-of-plane motion metric (OPMM) that measured normalized variance in the high-pass filtered TIC within the tumor region-of-interest with low OPMM being the goal. Results for IPMC and OPMF were qualitatively evaluated by 2 blinded observers who ranked the motion in the cines before and after various combinations of motion correction steps. RESULTS: Quantitative measurements showed that 2-tier IPMC and OPMF improved imaging stability. With IPMC, the NC B-mode metric increased from 0.504 ± 0.149 to 0.585 ± 0.145 over all cines (P < 0.001). Two-tier IPMC also produced better fits on the contrast-specific TIC than industry standard IPMC techniques did (P < 0.02). In-plane motion correction and OPMF were shown to improve goodness of fit for pixel-by-pixel analysis (P < 0.001). Out-of-plane motion filter reduced variance in the contrast-specific signal as shown by a median decrease of 49.8% in the OPMM. Two-tier IPMC and OPMF were also shown to qualitatively reduce motion. Observers consistently ranked cines with IPMC higher than the same cine before IPMC (P < 0.001) as well as ranked cines with OPMF higher than when they were uncorrected. CONCLUSION: The 2-tier sequential IPMC and adaptive OPMF significantly reduced motion in 3-minute CEUS cines of FLLs, thereby overcoming the challenges of drift and irregular breathing motion in long cines. The 2-tier IPMC strategy provided stable motion correction tolerant of out-of-plane motion throughout the cine by sequentially registering subreference frames that bypassed the motion cycles, thereby overcoming the lack of a nearly stationary reference point in long cines. Out-of-plane motion filter reduced apparent motion by adaptively removing frames imaged off-plane from the automatically selected OPMF reference frame, thereby tolerating nonuniform breathing motion. Selection of the best OPMF by minimizing OPMM effectively reduced motion under a wide variety of motion patterns applicable to clinical CEUS. These semiautomated processes only required user input for region-of-interest selection and can improve the accuracy of quantitative perfusion measurements.

Automating tumor classification with pixel-by-pixel contrast-enhanced ultrasound perfusion kinetics.

Contrast-enhanced ultrasound (CEUS) enables highly specific time-resolved imaging of vasculature by intravenous injection of ∼2 µm gas filled microbubbles. To develop a quantitative automated diagnosis of breast tumors with CEUS, breast tumors were induced in rats by administration of N-ethyl-N-nitrosourea. A bolus injection of microbubbles was administered and CEUS videos of each tumor were acquired for at least 3 min. The time-intensity curve of each pixel within a region of interest (ROI) was analyzed to measure kinetic parameters associated with the wash-in, peak enhancement, and wash-out phases of microbubble bolus injections since it was expected that the aberrant vascularity of malignant tumors will result in faster and more diverse perfusion kinetics versus those of benign lesions. Parameters were classified using linear discriminant analysis to differentiate between benign and malignant tumors and improve diagnostic accuracy. Preliminary results with a small dataset (10 tumors, 19 videos) show 100% accuracy with fivefold cross-validation testing using as few as two choice variables for training and validation. Several of the parameters which provided the best differentiation between malignant and benign tumors employed comparative analysis of all the pixels in the ROI including enhancement coverage, fractional enhancement coverage times, and the standard deviation of the envelope curve difference normalized to the mean of the peak frame. Analysis of combinations of five variables demonstrated that pixel-by-pixel analysis produced the most robust information for tumor diagnostics and achieved 5 times greater separation of benign and malignant cases than ROI-based analysis.

Integrated processing of contrast pulse sequencing ultrasound imaging for enhanced active contrast of hollow gas filled silica nanoshells and microshells.

In recent years, there have been increasing developments in the field of contrast-enhanced ultrasound both in the creation of new contrast agents and in imaging modalities. These contrast agents have been employed to study tumor vasculature in order to improve cancer detection and diagnosis. An in vivo study is presented of ultrasound imaging of gas filled hollow silica microshells and nanoshells which have been delivered intraperitoneally to an IGROV-1 tumor bearing mouse. In contrast to microbubbles, this formulation of microshells provided strong ultrasound imaging signals by shell disruption and release of gas. Imaging of the microshells in an animal model was facilitated by novel image processing. Although the particle signal could be identified by eye under live imaging, high background obfuscated the particle signal in still images and near the borders of the tumor with live images. Image processing techniques were developed that employed the transient nature of the particle signal to selectively filter out the background signal. By applying image registration, high-pass, median, threshold, and motion filtering, a short video clip of the particle signal was compressed into a single image, thereby resolving the silica shells within the tumor. © 2012 American Vacuum Society.