Automatic Staging of Cancer Tumors Using AIM Image Annotations and Ontologies.

A second opinion about cancer stage is crucial when clinicians assess patient treatment progress. Staging is a process that takes into account description, location, characteristics, and possible metastasis of tumors in a patient. It should follow standards, such as the TNM Classification of Malignant Tumors. However, in clinical practice, the implementation of this process can be tedious and error prone. In order to alleviate these problems, we intend to assist radiologists by providing a second opinion in the evaluation of cancer stage. For doing this, we developed a TNM classifier based on semantic annotations, made by radiologists, using the ePAD tool. It transforms the annotations (stored using the AIM format), using axioms and rules, into AIM4-O ontology instances. From then, it automatically calculates the liver TNM cancer stage. The AIM4-O ontology was developed, as part of this work, to represent annotations in the Web Ontology Language (OWL). A dataset of 51 liver radiology reports with staging data, from NCI's Genomic Data Commons (GDC), were used to evaluate our classifier. When compared with the stages attributed by physicians, the classifier stages had a precision of 85.7% and recall of 81.0%. In addition, 3 radiologists from 2 different institutions manually reviewed a random sample of 4 of the 51 records and agreed with the tool staging. AIM4-O was also evaluated with good results. Our classifier can be integrated into AIM aware imaging tools, such as ePAD, to offer a second opinion about staging as part of the cancer treatment workflow.

Computational Identification of Tumor Anatomic Location Associated with Survival in 2 Large Cohorts of Human Primary Glioblastomas.

BACKGROUND AND PURPOSE: Tumor location has been shown to be a significant prognostic factor in patients with glioblastoma. The purpose of this study was to characterize glioblastoma lesions by identifying MR imaging voxel-based tumor location features that are associated with tumor molecular profiles, patient characteristics, and clinical outcomes. MATERIALS AND METHODS: Preoperative T1 anatomic MR images of 384 patients with glioblastomas were obtained from 2 independent cohorts (n = 253 from the Stanford University Medical Center for training and n = 131 from The Cancer Genome Atlas for validation). An automated computational image-analysis pipeline was developed to determine the anatomic locations of tumor in each patient. Voxel-based differences in tumor location between good (overall survival of >17 months) and poor (overall survival of <11 months) survival groups identified in the training cohort were used to classify patients in The Cancer Genome Atlas cohort into 2 brain-location groups, for which clinical features, messenger RNA expression, and copy number changes were compared to elucidate the biologic basis of tumors located in different brain regions. RESULTS: Tumors in the right occipitotemporal periventricular white matter were significantly associated with poor survival in both training and test cohorts (both, log-rank P < .05) and had larger tumor volume compared with tumors in other locations. Tumors in the right periatrial location were associated with hypoxia pathway enrichment and PDGFRA amplification, making them potential targets for subgroup-specific therapies. CONCLUSIONS: Voxel-based location in glioblastoma is associated with patient outcome and may have a potential role for guiding personalized treatment.

Formative evaluation of ontology learning methods for entity discovery by using existing ontologies as reference standards.

OBJECTIVE: Developing a two-step method for formative evaluation of statistical Ontology Learning (OL) algorithms that leverages existing biomedical ontologies as reference standards. METHODS: In the first step optimum parameters are established. A 'gap list' of entities is generated by finding the set of entities present in a later version of the ontology that are not present in an earlier version of the ontology. A named entity recognition system is used to identify entities in a corpus of biomedical documents that are present in the 'gap list', generating a reference standard. The output of the algorithm (new entity candidates), produced by statistical methods, is subsequently compared against this reference standard. An OL method that performs perfectly will be able to learn all of the terms in this reference standard. Using evaluation metrics and precision-recall curves for different thresholds and parameters, we compute the optimum parameters for each method. In the second step, human judges with expertise in ontology development evaluate each candidate suggested by the algorithm configured with the optimum parameters previously established. These judgments are used to compute two performance metrics developed from our previous work: Entity Suggestion Rate (ESR) and Entity Acceptance Rate (EAR). RESULTS: Using this method, we evaluated two statistical OL methods for OL in two medical domains. For the pathology domain, we obtained 49% ESR, 28% EAR with the Lin method and 52% ESR, 39% EAR with the Church method. For the radiology domain, we obtain 87% ESA, 9% EAR using Lin method and 96% ESR, 16% EAR using Church method. CONCLUSION: This method is sufficiently general and flexible enough to permit comparison of any OL method for a specific corpus and ontology of interest.

Imaging informatics: toward capturing and processing semantic information in radiology images.

OBJECTIVES: To identify challenges and opportunities in imaging informatics that can lead to the use of images for discovery, and that can potentially improve the diagnostic accuracy of imaging professionals. METHODS: Recent articles on imaging informatics and related articles from PubMed were reviewed and analyzed. Some new developments and challenges that recent research in imaging informatics will meet are identified and discussed. RESULTS: While much literature continues to be devoted to traditional imaging informatics topics of image processing, visualization, and computerized detection, three new trends are emerging: (1) development of ontologies to describe radiology reports and images, (2) structured reporting and image annotation methods to make image semantics explicit and machine-accessible, and (3) applications that use semantic image information for decision support to improve radiologist interpretation performance. The informatics methods being developed have similarities and synergies with recent work in the biomedical informatics community that leverage large high-throughput data sets, and future research in imaging informatics will build on these advances to enable discovery by mining large image databases. CONCLUSIONS: Imaging informatics is beginning to develop and apply knowledge representation and analysis methods to image datasets. This type of work, already commonplace in biomedical research with large scale molecular and clinical datasets, will lead to new ways for computers to work with image data. The new advances hold promise for integrating imaging with the rest of the patient record as well as molecular data, for new data-driven discoveries in imaging analogous to that in bioinformatics, and for improved quality of radiology practice.

Knowledge representation and tool support for critiquing clinical trial protocols.

The increasing complexities of clinical trials have led to increasing costs for investigators and organizations that author and administer those trials. The process of authoring a clinical trial protocol, the document that specifies the details of the study, is usually a manual task, and thus authors may introduce subtle errors in medical and procedural content. We have created a protocol inspection and critiquing tool (PICASSO) that evaluates the procedural aspects of a clinical trial protocol. To implement this tool, we developed a knowledge base for clinical trials that contains knowledge of the medical domain (diseases, drugs, lab tests, etc.) and of specific requirements for clinical trial protocols (eligibility criteria, patient treatments, and monitoring activities). We also developed a set of constraints, expressed in a formal language, that describe appropriate practices for authoring clinical trials. If a clinical trial designed with PICASSO violates any of these constraints, PICASSO generates a message to the user and a list of inconsistencies for each violated constraint. To test our methodology, we encoded portions of a hypothetical protocol and implemented designs consistent and inconsistent with known clinical trial practice. Our hope is that this methodology will be useful for standardizing new protocols and improving their quality.

Efficacy and safety of mangafodipir trisodium (MnDPDP) injection for hepatic MRI in adults: results of the U.S. Multicenter phase III clinical trials. Efficacy of early imaging.

The efficacy of contrast-enhanced magnetic resonance imaging (MRI) for detecting and characterizing, or excluding, hepatic masses was assessed in 404 patients, following the intravenous administration of mangafodipir trisodium (MnDPDP) injection, a hepatic MRI contrast agent. An initial contrast-enhanced computed tomography (CT) examination was followed by unenhanced MRI, injection of MnDPDP (5 micromol/kg IV), and enhanced MRI at 15 minutes post injection. Agreement of the radiologic diagnoses with the patients' final diagnoses was higher for enhanced MRI and for the combined unenhanced and enhanced MRI evaluations than for unenhanced MRI alone or enhanced CT using the clinical diagnosis as the gold standard. Mangafodipir-enhanced MRI uniquely provided additional diagnostic information in 48% of the patients, and patient management was consequently altered in 6% of the patients. MnDPDP-enhanced MRI was comparable or superior to unenhanced MRI and enhanced CT for the detection, classification, and diagnosis of focal liver lesions in patients with known or suspected focal liver disease.

Safety and efficacy of mangafodipir trisodium (MnDPDP) injection for hepatic MRI in adults: results of the U.S. multicenter phase III clinical trials (safety).

The short-term safety of mangafodipir trisodium (MnDPDP) injection was studied in 546 adults with known or suspected focal liver lesions. An initial contrast-enhanced computed tomography examination was followed by unenhanced magnetic resonance imaging (MRI), injection of MnDPDP (5 micromol/kg), and enhanced MRI. Adverse events were reported for 23% of the patients; most were mild to moderate in intensity, did not require treatment, and were not drug related. The most commonly reported adverse events were nausea (7%) and headache (4%). The incidence of serious adverse events was low (nine events in six patients) and not drug related. Injection-associated discomfort was reported for 69% of the patients, and the most commonly reported discomforts included heat (49%) and flushing (33%). Changes in laboratory values and vital signs were generally transient, were not clinically significant, and did not require treatment. There were no clinically significant short-term risks from exposure to MnDPDP.

Targeting adolescent risk-taking behaviors: the contributions of egocentrism and sensation-seeking.

Tremendous resources are spent each year developing programs and messages targeting adolescent risk behavior. Adolescents are often reasonably well educated about methods for health promotion such as preventing HIV infection, yet they fail to act accordingly. One widely used individual difference variable, sensation-seeking, has been incorporated in health message design to some extent, but it fails to take development into account. Research on adolescent egocentrism suggests adolescents experience personal fable which can lead to an exaggerated sense of invulnerability. The present study sampled adolescents and college students to examine relative contributions of egocentrism and sensation-seeking to risk-taking behavior. Results indicate a latent factor labeled risk-seeking (primarily indicated by disinhibition and risk-taking personality, and to a lesser degree by invulnerability, experience-seeking, boredom susceptibility, and thrill and adventure-seeking) indeed predicted a latent factor labeled delinquent behavior (primarily indicated by alcohol consumption and delinquency, and to a lesser degree by drug use, drinking and driving, and risky driving). Other results indicate consistently high personal fable combined with high sensation-seeking explained most risk-taking behavior. Implications and directions for future research are discussed.

Magnetic resonance imaging in patients with central nervous system pathology: a comparison of OptiMARK (Gd-DTPA-BMEA) and Magnevist (Gd-DTPA).

RATIONALE AND OBJECTIVES: The objective of the two pivotal phase 3 studies was to evaluate the safety and efficacy of OptiMARK (Gd-DTPA-bis(methoxyethylamide) [Gd-DTPA-BMEA]) compared with Magnevist (Gd-DTPA) in magnetic resonance imaging of the central nervous system. METHODS: Two multicenter, randomized, double-blind, parallel group studies were conducted in 395 patients with known or suspected central nervous system pathology. Subjects were randomized to receive a single 0.1 mmol/kg intravenous injection of either Gd-DTPA-BMEA or Gd-DTPA. The safety of Gd-DTPA-BMEA and Gd-DTPA was monitored for up to 72 hours after study drug administration. Precontrast and postcontrast administration magnetic resonance scans were acquired using identical imaging planes and techniques. RESULTS: No deaths or unexpected adverse events were reported in either group. A comparison of adverse events by intensity and relation demonstrated no statistically significant differences between the two groups. Gd-DTPA-BMEA and Gd-DTPA were equivalent with respect to confidence in diagnosis, conspicuity, and border delineation. CONCLUSIONS: Gd-DTPA-BMEA and Gd-DTPA demonstrated comparable efficacy profiles, and the safety profiles were considered similar.

Tool support for authoring eligibility criteria for cancer trials.

A critical component of authoring new clinical trial protocols is assembling a set of eligibility criteria for patient enrollment. We found that clinical protocols in three different cancer domains can be categorized according to a set of clinical states that describe various clinical scenarios for that domain. Classifying protocols in this manner revealed similarities among the eligibility criteria and permitted some standardization of criteria based on clinical state. We have developed an eligibility criteria authoring tool which uses a standard set of eligibility criteria and a diagram of the clinical states to present the relevant eligibility criteria to the protocol author. We demonstrate our ideas with phase-3 protocols from breast cancer, prostate cancer, and non-small cell lung cancer. Based on measurements of redundancy and percentage coverage of criteria included in our tool, we conclude that our model reduces redundancy in the number of criteria needed to author multiple protocols, and it allows some eligibility criteria to be authored automatically based on the clinical state of interest for a protocol.

Safety and efficacy of a new oral contrast agent for sonography: a phase II trial.

OBJECTIVE: Our purpose was to study the safety and efficacy of a new orally administered sonographic contrast agent in patients with suspected upper abdominal disorders. SUBJECTS AND METHODS: Ninety-nine patients with signs or symptoms suggestive of upper abdominal disorders were enrolled in a prospective range-of-dose phase II clinical trial at six sites; sonograms of 93 patients were evaluated for efficacy. Patients underwent upper abdominal sonography before and after receiving a randomized dose of the contrast agent (200, 400, 600, 800, or 1000 ml). Safety was monitored by physical examination and laboratory testing. The primary efficacy parameter was additional information provided by the contrast agent when comparing unenhanced and contrast-enhanced sonography. RESULTS: Of the 14 adverse events in 11 patients, only five, which included mild diarrhea and nausea, were considered related to the contrast agent. In 83 of 93 patients, additional information was obtained from the contrast-enhanced images. Visualization of anatomy was improved as follows: the stomach, in 82% of patients; the duodenum, in 63% of patients; the pancreatic head and body, in 61% of patients; and the pancreatic tail, in 67% of patients. CONCLUSION: SonoRx is a safe and well-tolerated contrast agent that improves the sonographic evaluation of the upper abdomen, with significant improvement in imaging the stomach, duodenum, and pancreas.

A multisite phase III study of the safety and efficacy of a new manganese chloride-based gastrointestinal contrast agent for MRI of the abdomen and pelvis.

The purpose of this study was to evaluate the safety and efficacy of a manganese chloride-based oral magnetic resonance (MR) contrast agent during a Phase III multisite clinical trial. Two hundred seventeen patients were enrolled who were already scheduled for MRI of the abdomen and/or pelvis. In this group of patients, it was postulated that the use of an oral agent would better allow discrimination of pathology from bowel. Patients with known gastrointestinal pathology including peptic ulcer disease, inflammatory bowel disease, obstruction, or perforation were excluded to minimize confounding variables that could affect the safety assessment. Of these 217 patients, 18 received up to 900 mL of placebo, and 199 patients were given up to 900 mL of a manganese chloride-based oral contrast agent, LumenHance (Bracco Diagnostics, Inc.). Safety was determined by comparing pre- and post-dose physical examinations, vital signs, and laboratory examinations and by documenting adverse events. Efficacy was assessed by unblinded site investigators and two blinded reviewers who compared pre- and post-dose T1- and T2-weighted MRI scans of the abdomen and/or pelvis. In 111 (57%) of the 195 cases evaluated for efficacy by site investigators (unblinded readers), MRI after LumenHance provided additional diagnostic information. Increased information was found by two blinded readers in 52% and 51% of patients, respectively. In 44/195 cases (23%) unblinded readers felt the additional information would have changed patient diagnosis and in 50 patients (26%), it would have changed management and/or therapy. Potential changes in patient diagnosis or management/therapy were seen by the two blinded readers in 8-20% of patients. No clinically significant post-dose laboratory changes were seen. Forty-eight patients (24%) receiving LumenHance and four patients (22%) receiving placebo experienced one or more adverse events. Gastrointestinal tract side effects were most common, seen in 29 (15%) of LumenHance patients and in 3 (17%) of the placebo patients. LumenHance is a safe and efficacious oral gastrointestinal contrast agent for MRI of the abdomen and pelvis.

Polymeric gadolinium chelate magnetic resonance imaging contrast agents: design, synthesis, and properties.

We have synthesized and evaluated five series of polymeric gadolinium chelates which are of interest as potential MRI blood pool contrast agents. The polymers were designed so that important physical properties including molecular weight, relaxivity, metal content, viscosity, and chelate stability could be varied. We have shown that, by selecting polymers of the appropriate MW, extended blood pool retention can be achieved. In addition, relaxivity can be manipulated by changing the polymer rigidity, metal content affected by monomer selection, viscosity by polymer shape, and chelate stability by chelator selection.