The Impact of an Artificial Intelligence Certificate Program on Radiology Resident Education.

RATIONALE AND OBJECTIVES: The objective of this study was to evaluate the effectiveness of a pilot artificial intelligence (AI) certificate program in aiding radiology trainees to develop an understanding of the evolving role and application of artificial intelligence in radiology. A secondary objective was set to determine the background of residents that would most benefit from such training. MATERIALS AND METHODS: This was a prospective pilot study involving 42 radiology residents at two separate residency programs who participated in the Radiological Society of North America Imaging AI Foundational Certificate course over a four-month period. The course consisted of 6 online modules that contained didactic lectures followed by end-of-module quizzes to assess knowledge gained from these lectures. Pre- and post-course assessments were conducted to evaluate the residents' knowledge and skills in AI. Additionally, a post-course survey was performed to assess participants' overall satisfaction with the course. RESULTS: All participating residents completed the certificate program. The mean pre-course assessment score was 37 %, which increased to 73 % after completing the modules (p < 0.001). 74 % (31/42) endorsed the belief the course improved familiarity with artificial intelligence in radiology. Residency program, residency year, and reported prior familiarity with AI were not found to influence pre-course score, post-course score, nor score improvement. 57 % (24/42) endorsed interest in pursuing further certification in AI. CONCLUSION: Our pilot study suggests that a certificate course can effectively enhance the knowledge and skills of radiology residents in the application of AI in radiology. The benefits of such a course can be found regardless of program, resident year, and self-reported prior resident understanding of radiology in AI.

New Frontiers in Breast Cancer Imaging: The Rise of AI.

Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist in the diagnosis and treatment of patients. AI implementation in radiology, more specifically for breast imaging, has advanced considerably. Breast cancer is one of the most important causes of cancer mortality among women, and there has been increased attention towards creating more efficacious methods for breast cancer detection utilizing AI to improve radiologist accuracy and efficiency to meet the increasing demand of our patients. AI can be applied to imaging studies to improve image quality, increase interpretation accuracy, and improve time efficiency and cost efficiency. AI applied to mammography, ultrasound, and MRI allows for improved cancer detection and diagnosis while decreasing intra- and interobserver variability. The synergistic effect between a radiologist and AI has the potential to improve patient care in underserved populations with the intention of providing quality and equitable care for all. Additionally, AI has allowed for improved risk stratification. Further, AI application can have treatment implications as well by identifying upstage risk of ductal carcinoma in situ (DCIS) to invasive carcinoma and by better predicting individualized patient response to neoadjuvant chemotherapy. AI has potential for advancement in pre-operative 3-dimensional models of the breast as well as improved viability of reconstructive grafts.

Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation.

Purpose: Breast ultrasound suffers from low positive predictive value and specificity. Artificial intelligence (AI) proposes to improve accuracy, reduce false negatives, reduce inter- and intra-observer variability and decrease the rate of benign biopsies. Perpetuating racial/ethnic disparities in healthcare and patient outcome is a potential risk when incorporating AI-based models into clinical practice; therefore, it is necessary to validate its non-bias before clinical use. Approach: Our retrospective review assesses whether our AI decision support (DS) system demonstrates racial/ethnic bias by evaluating its performance on 1810 biopsy proven cases from nine breast imaging facilities within our health system from January 1, 2018 to October 28, 2021. Patient age, gender, race/ethnicity, AI DS output, and pathology results were obtained. Results: Significant differences in breast pathology incidence were seen across different racial and ethnic groups. Stratified analysis showed that the difference in output by our AI DS system was due to underlying differences in pathology incidence for our specific cohort and did not demonstrate statistically significant bias in output among race/ethnic groups, suggesting similar effectiveness of our AI DS system among different races (p>0.05 for all). Conclusions: Our study shows promise that an AI DS system may serve as a valuable second opinion in the detection of breast cancer on diagnostic ultrasound without significant racial or ethnic bias. AI tools are not meant to replace the radiologist, but rather to aid in screening and diagnosis without perpetuating racial/ethnic disparities.

The RSNA ImageShare - Enabling Secure, Transparent, and Easy Image Exchange.

In the early 2000s, the radiology community was awakened to the limitations of electronic media (CDs, DVDs) for exchanging imaging exams. Clinicians frustrated by the time-consuming task of opening discs, while Internet-based exchange of music, photos, and videos were becoming more widespread. The RSNA, which had extensive experience working on interoperability issues in medical imaging, began to look for opportunities to address the issue. In 2007, in the wake of the financial crisis, the National Institute of Biomedical Imaging and Bioengineering (NIBIB) issued an RFP to address Internet-based exchange of medical images. The RFP defined requirements for the network, including that it needed to be patient controlled and standards based. The RSNA was awarded funding for what came to be known as RSNA ImageShare. Over the next 8 years, the RSNA worked in partnership with several vendors and academic institutions to create a network for sharing image-enabled personal health records (PHR). The foundation of interoperability standards used in ImageShare was provided by Integrating the Healthcare Enterprise (IHE), a standards-development organization with which RSNA has had a long association. In 2018 and 2019, the RSNA looked at what had been accomplished and asked if we could take that next step at a national level and promote a solution by which any standards-compliant party could exchange imaging exams through an HIE mechanism.

Predicting Patient Demographics From Chest Radiographs With Deep Learning.

BACKGROUND: Deep learning models are increasingly informing medical decision making, for instance, in the detection of acute intracranial hemorrhage and pulmonary embolism. However, many models are trained on medical image databases that poorly represent the diversity of the patients they serve. In turn, many artificial intelligence models may not perform as well on assisting providers with important medical decisions for underrepresented populations. PURPOSE: Assessment of the ability of deep learning models to classify the self-reported gender, age, self-reported ethnicity, and insurance status of an individual patient from a given chest radiograph. METHODS: Models were trained and tested with 55,174 radiographs in the MIMIC Chest X-ray (MIMIC-CXR) database. External validation data came from two separate databases, one from CheXpert and another from a multihospital urban health care system after institutional review board approval. Macro-averaged area under the curve (AUC) values were used to evaluate performance of models. Code used for this study is open-source and available at https://github.com/ai-bias/cxr-bias, and pixelstopatients.com/models/demographics. RESULTS: Accuracy of models to predict gender was nearly perfect, with 0.999 (95% confidence interval: 0.99-0.99) AUC on held-out test data and 0.994 (0.99-0.99) and 0.997 (0.99-0.99) on external validation data. There was high accuracy to predict age and ethnicity, ranging from 0.854 (0.80-0.91) to 0.911 (0.88-0.94) AUC, and moderate accuracy to predict insurance status, with AUC ranging from 0.705 (0.60-0.81) on held-out test data to 0.675 (0.54-0.79) on external validation data. CONCLUSIONS: Deep learning models can predict the age, self-reported gender, self-reported ethnicity, and insurance status of a patient from a chest radiograph. Visualization techniques are useful to ensure deep learning models function as intended and to demonstrate anatomical regions of interest. These models can be used to ensure that training data are diverse, thereby ensuring artificial intelligence models that work on diverse populations.

Moving Toward Seamless Interinstitutional Electronic Image Transfer.

The fact that medical images are still predominately exchanged between institutions via physical media is unacceptable in the era of value-driven health care. Although better solutions are technically possible, problems of coordination and market dynamics may be inhibiting progress more than technical factors. We provide a macrosystem analysis of the problem of interinstitutional medical image exchange and propose a strategy for nudging the market toward a patient-friendly solution. The system can be viewed as a network, with autonomous nodes interconnected by links through which information is exchanged. A variety of potential network configurations include those that depend on individual carriers, peer-to-peer links, one or multiple hubs, or a hybrid of models. We find the linked multihub model, in which individual institutions are connected to other institutions via image exchange companies, to be the configuration most likely to create a patient-friendly electronic image exchange system. To achieve this configuration, image exchange companies, which operate in a competitive marketplace, must exchange images with each other. We call on these vendors to immediately commit to coordinating in this manner. We call on all other stakeholders, including local care provider institutions, medical societies, payers, and regulators, to actively encourage and facilitate this behavior. Specifically, we call on institutions to create appropriate market incentives by only contracting with image exchange vendors who are committed to begin vendor-to-vendor image exchange by no later than 2024.

An Interview with the Carequality Imaging Use Case Implementers.

Imagine you had a cell phone plan that only allowed you to call other customers within the same carrier network. That is the situation most healthcare providers experience when joining a data sharing network. Carequality is a network-to-network trust framework that brings together the entire healthcare industry to overcome this challenge by providing a national-level, consensus built, common interoperability framework to enable health information exchange between and among health data sharing networks. The RSNA partnered with Carequality in 2019 to develop an implementation guide to enable the Imaging Exchange Use Case. The implementation guide was published in December 2019 for early adopters to sign up as implementers to the Carequality framework. Exchange standards must be clearly laid out so that all implementers can easily follow and be held accountable to enable interoperability of medical imaging. The guide was reviewed and tested by implementers and approved for production use in March 2021. Since the launch of the implementation guide, five Carequality Implementers have participated in Carequality's Image Exchange Use Case: Ambra Health, Hyland, Life Image, Nuance, and Philips. These implementers recognized a gap in image interoperability and the need for change and collaboration. Carequality has asked each of the implementers to share their thoughts on issues pertinent to becoming an implementer and imaging interoperability with the hope that the reader will gain insight as to the evolution of network-based image exchange.

Automated detection of critical findings in multi-parametric brain MRI using a system of 3D neural networks.

With the rapid growth and increasing use of brain MRI, there is an interest in automated image classification to aid human interpretation and improve workflow. We aimed to train a deep convolutional neural network and assess its performance in identifying abnormal brain MRIs and critical intracranial findings including acute infarction, acute hemorrhage and mass effect. A total of 13,215 clinical brain MRI studies were categorized to training (74%), validation (9%), internal testing (8%) and external testing (8%) datasets. Up to eight contrasts were included from each brain MRI and each image volume was reformatted to common resolution to accommodate for differences between scanners. Following reviewing the radiology reports, three neuroradiologists assigned each study to abnormal vs normal, and identified three critical findings including acute infarction, acute hemorrhage, and mass effect. A deep convolutional neural network was constructed by a combination of localization feature extraction (LFE) modules and global classifiers to identify the presence of 4 variables in brain MRIs including abnormal, acute infarction, acute hemorrhage and mass effect. Training, validation and testing sets were randomly defined on a patient basis. Training was performed on 9845 studies using balanced sampling to address class imbalance. Receiver operating characteristic (ROC) analysis was performed. The ROC analysis of our models for 1050 studies within our internal test data showed AUC/sensitivity/specificity of 0.91/83%/86% for normal versus abnormal brain MRI, 0.95/92%/88% for acute infarction, 0.90/89%/81% for acute hemorrhage, and 0.93/93%/85% for mass effect. For 1072 studies within our external test data, it showed AUC/sensitivity/specificity of 0.88/80%/80% for normal versus abnormal brain MRI, 0.97/90%/97% for acute infarction, 0.83/72%/88% for acute hemorrhage, and 0.87/79%/81% for mass effect. Our proposed deep convolutional network can accurately identify abnormal and critical intracranial findings on individual brain MRIs, while addressing the fact that some MR contrasts might not be available in individual studies.

Initial Management of Noncastrate Advanced, Recurrent, or Metastatic Prostate Cancer: ASCO Guideline Update.

PURPOSE: Update all preceding ASCO guidelines on initial hormonal management of noncastrate advanced, recurrent, or metastatic prostate cancer. METHODS: The Expert Panel based recommendations on a systematic literature review. Recommendations were approved by the Expert Panel and the ASCO Clinical Practice Guidelines Committee. RESULTS: Four clinical practice guidelines, one clinical practice guidelines endorsement, 19 systematic reviews with or without meta-analyses, 47 phase III randomized controlled trials, nine cohort studies, and two review papers informed the guideline update. RECOMMENDATIONS: Docetaxel, abiraterone, enzalutamide, or apalutamide, each when administered with androgen deprivation therapy (ADT), represent four separate standards of care for noncastrate metastatic prostate cancer. Currently, the use of any of these agents in any particular combination or series cannot be recommended. ADT plus docetaxel, abiraterone, enzalutamide, or apalutamide should be offered to men with metastatic noncastrate prostate cancer, including those who received prior therapies, but have not yet progressed. The combination of ADT plus abiraterone and prednisolone should be considered for men with noncastrate locally advanced nonmetastatic prostate cancer who have undergone radiotherapy, rather than castration monotherapy. Immediate ADT may be offered to men who initially present with noncastrate locally advanced nonmetastatic disease who have not undergone previous local treatment and are unwilling or unable to undergo radiotherapy. Intermittent ADT may be offered to men with high-risk biochemically recurrent nonmetastatic prostate cancer. Active surveillance may be offered to men with low-risk biochemically recurrent nonmetastatic prostate cancer. The panel does not support use of either micronized abiraterone acetate or the 250 mg dose of abiraterone with a low-fat breakfast in the noncastrate setting at this time.Additional information is available at www.asco.org/genitourinary-cancer-guidelines.

Diaphragmatic excursion: Quantitative measure to assess adequacy of expiratory phase CT chest images.

OBJECTIVE: To evaluate diaphragmatic excursion as a quantitative metric for change in lung volume between inspiratory and expiratory chest computed tomography (CT) images. METHODS: A 12-month retrospective review identified 226 chest CT exams with inspiratory and expiratory phase imaging, 63 in individuals referred with diagnosis of asthma by ICD9/10 code. Exams acquired in the supine position at 1.25 mm slice thickness in each phase were included (n = 30, mean age = 62, M = 15, F = 15). Diaphragmatic excursion was calculated as the difference between axial slices through the lungs on inspiration and expiration, using the lung apex as the cranial bound, and the hemidiaphragm caudally. Inspiratory and expiratory lung and tracheal volumes were calculated through volumetric segmentation. Tracheal morphology was assessed at 1 cm above the level of the aortic arch, and 1 cm above the carina. RESULTS: Inspiratory and expiratory lung volumes were higher in men (mean I = 5 + 1.6 L, E = 3.1 + 1.2 L) than women (mean I = 3.6 + 0.8 L, E = 2.4 + 0.7 L), p = .005 and p = .047, respectively. Average inspiratory and expiratory tracheal volumes were higher in men (I = 61 + 17 mL, E = 43 + 14) than women (I = 44 + 14, E = 30 + 8), p = .006 and p = .005. Average change in lung and tracheal volume between inspiratory and expiratory scans did not significantly differ between men and women. Average diaphragmatic excursion was 2.5 cm between inspiratory and expiratory scans (2.7 cm in men, 2.3 cm in women; p = .5). There was a strong positive correlation between diaphragmatic excursion and change in lung (r = .84) and tracheal volume (r = .79). A moderate correlation was also found between change in tracheal volume and change in lung volume (r = 0.67). Change in tracheal morphology between inspiratory and expiratory imaging was associated with change in tracheal volume at both 1 cm above the aortic arch (p = .04) and 1 cm above the carina (p = .008); there was no association with diaphragmatic excursion or lung volume. CONCLUSIONS: Diaphragmatic excursion is a quantitative measure of expiratory effort as validated by both lung and tracheal volumes in asthma patients, and may be more accurate than qualitative assessment based on tracheal morphology.

Advancing Semantic Interoperability of Image Annotations: Automated Conversion of Non-standard Image Annotations in a Commercial PACS to the Annotation and Image Markup.

Sharing radiologic image annotations among multiple institutions is important in many clinical scenarios; however, interoperability is prevented because different vendors' PACS store annotations in non-standardized formats that lack semantic interoperability. Our goal was to develop software to automate the conversion of image annotations in a commercial PACS to the Annotation and Image Markup (AIM) standardized format and demonstrate the utility of this conversion for automated matching of lesion measurements across time points for cancer lesion tracking. We created a software module in Java to parse the DICOM presentation state (DICOM-PS) objects (that contain the image annotations) for imaging studies exported from a commercial PACS (GE Centricity v3.x). Our software identifies line annotations encoded within the DICOM-PS objects and exports the annotations in the AIM format. A separate Python script processes the AIM annotation files to match line measurements (on lesions) across time points by tracking the 3D coordinates of annotated lesions. To validate the interoperability of our approach, we exported annotations from Centricity PACS into ePAD (http://epad.stanford.edu) (Rubin et al., Transl Oncol 7(1):23-35, 2014), a freely available AIM-compliant workstation, and the lesion measurement annotations were correctly linked by ePAD across sequential imaging studies. As quantitative imaging becomes more prevalent in radiology, interoperability of image annotations gains increasing importance. Our work demonstrates that image annotations in a vendor system lacking standard semantics can be automatically converted to a standardized metadata format such as AIM, enabling interoperability and potentially facilitating large-scale analysis of image annotations and the generation of high-quality labels for deep learning initiatives. This effort could be extended for use with other vendors' PACS.

Interoperability and Considerations for Standards-Based Exchange of Medical Images: HIMSS-SIIM Collaborative White Paper.

This white paper explores the considerations of standards-based interoperability of medical images between organizations, patients, and providers. In this paper, we will look at three different standards-based image exchange implementations that have been deployed to facilitate exchange of images between provider organizations. The paper will describe how each implementation uses applicable technology and standards; the image types that are included; and the governance policies that define participation, access, and trust. Limitations of the solution or non-standard approaches to solve challenges will also be identified. Much can be learned from successes elsewhere, and those learnings will point to recommendations of best practices to facilitate the adoption of image exchange.

A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop.

Imaging research laboratories are rapidly creating machine learning systems that achieve expert human performance using open-source methods and tools. These artificial intelligence systems are being developed to improve medical image reconstruction, noise reduction, quality assurance, triage, segmentation, computer-aided detection, computer-aided classification, and radiogenomics. In August 2018, a meeting was held in Bethesda, Maryland, at the National Institutes of Health to discuss the current state of the art and knowledge gaps and to develop a roadmap for future research initiatives. Key research priorities include: 1, new image reconstruction methods that efficiently produce images suitable for human interpretation from source data; 2, automated image labeling and annotation methods, including information extraction from the imaging report, electronic phenotyping, and prospective structured image reporting; 3, new machine learning methods for clinical imaging data, such as tailored, pretrained model architectures, and federated machine learning methods; 4, machine learning methods that can explain the advice they provide to human users (so-called explainable artificial intelligence); and 5, validated methods for image de-identification and data sharing to facilitate wide availability of clinical imaging data sets. This research roadmap is intended to identify and prioritize these needs for academic research laboratories, funding agencies, professional societies, and industry.

Effect of Clinical Decision Support on Appropriateness of Advanced Imaging Use Among Physicians-in-Training.

OBJECTIVE: Clinical decision support (CDS) tools have been shown to reduce inappropriate imaging orders. We hypothesized that CDS may be especially effective for house staff physicians who are prone to overuse of resources. MATERIALS AND METHODS: Our hospital implemented CDS for CT and MRI orders in the emergency department with scores based on the American College of Radiology's Appropriateness Criteria (range, 1-9; higher scores represent more-appropriate orders). Data on CT and MRI orders from April 2013 through June 2016 were categorized as pre-CDS or baseline, post-CDS period 1 (i.e., intervention with active feedback for scores of ≤ 4), and post-CDS period 2 (i.e., intervention with active feedback for scores of ≤ 6). Segmented regression analysis with interrupted time series data estimated changes in scores stratified by house staff and non-house staff. Generalized linear models further estimated the modifying effect of the house staff variable. RESULTS: Mean scores were 6.2, 6.2, and 6.7 in the pre-CDS, post-CDS 1, and post-CDS 2 periods, respectively (p < 0.05). In the segmented regression analysis, mean scores significantly (p < 0.05) increased when comparing pre-CDS versus post-CDS 2 periods for both house staff (baseline increase, 0.41; 95% CI, 0.17-0.64) and non-house staff (baseline increase, 0.58; 95% CI, 0.34-0.81), showing no differences in effect between the cohorts. The generalized linear model showed significantly higher scores, particularly in the post-CDS 2 period compared with the pre-CDS period (0.44 increase in scores; p < 0.05). The house staff variable did not significantly change estimates in the post-CDS 2 period. CONCLUSION: Implementation of active CDS increased overall scores of CT and MRI orders. However, there was no significant difference in effect on scores between house staff and non-house staff.

A first-in-human phase 1a study of the bispecific anti-DLL4/anti-VEGF antibody navicixizumab (OMP-305B83) in patients with previously treated solid tumors.

Purpose Navicixizumab (OMP-305B83) is a bispecific antibody that inhibits delta-like ligand 4 and vascular endothelial growth factor. This Phase 1a trial assessed escalating doses of navicixizumab in refractory solid tumors patients. Design A 3 + 3 dose escalation design was used followed by the treatment of additional patients in an expansion cohort. Study objectives were determination of the maximum tolerated dose, safety, pharmacokinetics, pharmacodynamics, immunogenicity and efficacy. Results Sixty-six patients were treated once every 3 weeks in 8 dose-escalation cohorts (0.5, 1, 2.5, 3.5, 5, 7.5, 10, and 12.5 mg/kg) and an expansion cohort (7.5 mg/kg). The median age was 60 years and 68% of the patients were female. The most commonly enrolled tumor types were ovarian (12), colorectal (11) and breast, pancreatic, uterine and endometrial (4 each) cancers. As only 1 dose limiting toxicity occurred, the maximum tolerated dose was not reached, but 7.5 mg/kg was chosen as the dose for the expansion cohort. The treatment related adverse events (≥15% of patients) were hypertension (57.6%), headache (28.8%), fatigue (25.8%), and pulmonary hypertension (18.2%). Pulmonary hypertension was mostly asymptomatic at doses ≤5 mg/kg (6 Gr1, 1 Gr2), but was more severe at higher doses (4 Gr2, 1 Gr3). Navicixizumab's half-life was 11.4 days and there was a moderate (29%) incidence of anti-drug antibody formation. Four patients (3 ovarian cancer, 1 uterine carcinosarcoma) had a partial response and 17 patients had stable disease. Nineteen patients had a reduction in the size of their target lesions including 7/11 patients with ovarian cancer. Four patients remained on study for >300 days and 2 of these patients were on study for >500 days. Conclusions Navicixizumab can be safely administered with manageable toxicities and these data showed preliminary signs of antitumor activity in multiple tumor types, but was most promising in ovarian cancer. As a result these data justify its continued development in combination Phase 1b clinical trials.

Causative factors, imaging findings, and CT course of round atelectasis.

OBJECTIVE: To assess causative factors, associated imaging findings, and CT course of round atelectasis (RA). MATERIALS AND METHODS: We retrospectively reviewed CT reports for "round" or "rounded atelectasis" over a 5-year time frame. Patients with at least 2 CT scans a minimum of 6 months apart were included. Electronic medical records and clinical and imaging follow-up was reviewed for all cases. RESULTS: Study population included 50 individuals with mean age of 63 years, and 59 unique instances of RA. The most commonly associated etiologies were hepatic hydrothorax (26%, n = 13) and asbestos exposure (26%), followed by post-infectious pleural inflammation (22%), congestive heart failure (12%), and end stage renal disease (8%). RA was found in the right lower lobe in over half of cases (n = 30). Association with one or more pleural abnormality was identified in all cases, including thickening (88%), fluid (60%), or calcification (40%). Nearly one third (n = 19) demonstrated intra-lesional calcification. In those who underwent PET/CT (20%), lesions demonstrated an average SUV of 2.2 (range 0-7.8). CT course over mean follow up of 32 months (range 6-126 months), demonstrated RA to remain stable (n = 26) or decrease (n = 26) in size in the majority (88%) of cases. CONCLUSION: Round atelectasis may arise from diverse etiologies beyond asbestos, and will most often decrease or remain stable in size over serial exams. Accurate identification may obviate the need for added diagnostic interventions.

A First-in-Human Phase I Study of the Anticancer Stem Cell Agent Ipafricept (OMP-54F28), a Decoy Receptor for Wnt Ligands, in Patients with Advanced Solid Tumors.

Purpose: Wnt signaling is implicated in tumor cell dedifferentiation and cancer stem cell function. Ipafricept (OMP-54F28) is a first-in-class recombinant fusion protein with the extracellular part of human frizzled 8 receptor fused to a human IgG1 Fc fragment that binds Wnt ligands. This trial evaluated ipafricept in patients with solid tumors.Experimental design: A 3+3 design was used; ipafricept was given intravenously every 3 weeks. The objectives were determination of dose-limiting toxicities (DLTs), recommended phase 2 dose (RP2D), safety, pharmacokinetics (PK), immunogenicity, pharmacodynamics (PD), and preliminary efficacy.Results: 26 patients were treated in seven dose-escalation cohorts (0.5, 1, 2.5, 5, 10, 15, and 20 mg/kg). No further dose escalation was pursued as PK modeling indicated that the target efficacious dose was reached at 10 mg/kg, and fragility fractures occurred at 20 mg/kg. Most common related grade 1 and 2 adverse events (AEs; ≥20% of patients) were dysgeusia, decreased appetite, fatigue, and muscle spasms. Ipafricept-related grade 3 TEAEs included hypophosphatemia and weight decrease (1 subject each, 3.8%). Ipafricept half-life was ∼4 days and had low incidence of antidrug antibody formation (7.69%) with no impact on drug exposure. Six patients had ß-C-terminal telopeptide (ß-CTX) doubling from baseline, which was reversible. PD modulation of Wnt pathway genes in hair follicles occurred ≥2.5 mg/kg. Two desmoid tumor and a germ cell cancer patient experienced stable disease for >6 months.Conclusions: Ipafricept was well tolerated, with RP2D of 15 mg/kg Q3W. Prolonged SD was noted in desmoid tumor and germ cell cancer patients. Clin Cancer Res; 23(24); 7490-7. ©2017 AACR.

A first-in-human dose-escalation study of the oral proteasome inhibitor oprozomib in patients with advanced solid tumors.

PURPOSE: To determine the dose-limiting toxicities (DLTs), maximum tolerated dose (MTD), safety, and pharmacokinetic and pharmacodynamic profiles of the tripeptide epoxyketone proteasome inhibitor oprozomib in patients with advanced refractory or recurrent solid tumors. METHODS: Patients received escalating once daily (QD) or split doses of oprozomib on days 1-5 of 14-day cycles (C). The split-dose arm was implemented and compared in fasted (C1) and fed (C2) states. Pharmacokinetic samples were collected during C1 and C2. Proteasome inhibition was evaluated in red blood cells and peripheral blood mononuclear cells. RESULTS: Forty-four patients (QD, n = 25; split dose, n = 19) were enrolled. The most common primary tumor types were non-small cell lung cancer (18%) and colorectal cancer (16%). In the 180-mg QD cohort, two patients experienced DLTs: grade 3 vomiting and dehydration; grade 3 hypophosphatemia (n = 1 each). In the split-dose group, three DLTs were observed (180-mg cohort: grade 3 hypophosphatemia; 210-mg cohort: grade 5 gastrointestinal hemorrhage and grade 3 hallucinations (n = 1 each). In the QD and split-dose groups, the MTD was 150 and 180 mg, respectively. Common adverse events (all grades) included nausea (91%), vomiting (86%), and diarrhea (61%). Peak concentrations and total exposure of oprozomib generally increased with the increasing dose. Oprozomib induced dose-dependent proteasome inhibition. Best response was stable disease. CONCLUSIONS: While generally low-grade, clinically relevant gastrointestinal toxicities occurred frequently with this oprozomib formulation. Despite dose-dependent increases in pharmacokinetics and pharmacodynamics, single-agent oprozomib had minimal antitumor activity in this patient population with advanced solid tumors.

Breast Imaging in the Era of Big Data: Structured Reporting and Data Mining.

OBJECTIVE: The purpose of this article is to describe structured reporting and the development of large databases for use in data mining in breast imaging. CONCLUSION: The results of millions of breast imaging examinations are reported with structured tools based on the BI-RADS lexicon. Much of these data are stored in accessible media. Robust computing power creates great opportunity for data scientists and breast imagers to collaborate to improve breast cancer detection and optimize screening algorithms. Data mining can create knowledge, but the questions asked and their complexity require extremely powerful and agile databases. New data technologies can facilitate outcomes research and precision medicine.