Evaluation of mediastinal lymph node segmentation of heterogeneous CT data with full and weak supervision.

Accurate lymph node size estimation is critical for staging cancer patients, initial therapeutic management, and assessing response to therapy. Current standard practice for quantifying lymph node size is based on a variety of criteria that use uni-directional or bi-directional measurements. Segmentation in 3D can provide more accurate evaluations of the lymph node size. Fully convolutional neural networks (FCNs) have achieved state-of-the-art results in segmentation for numerous medical imaging applications, including lymph node segmentation. Adoption of deep learning segmentation models in clinical trials often faces numerous challenges. These include lack of pixel-level ground truth annotations for training, generalizability of the models on unseen test domains due to the heterogeneity of test cases and variation of imaging parameters. In this paper, we studied and evaluated the performance of lymph node segmentation models on a dataset that was completely independent of the one used to create the models. We analyzed the generalizability of the models in the face of a heterogeneous dataset and assessed the potential effects of different disease conditions and imaging parameters. Furthermore, we systematically compared fully-supervised and weakly-supervised methods in this context. We evaluated the proposed methods using an independent dataset comprising 806 mediastinal lymph nodes from 540 unique patients. The results show that performance achieved on the independent test set is comparable to that on the training set. Furthermore, neither the underlying disease nor the heterogeneous imaging parameters impacted the performance of the models. Finally, the results indicate that our weakly-supervised method attains 90%- 91% of the performance achieved by the fully supervised training.

Correlation of Radiomics with Treatment Response in Liver Metastases.

RATIONALE AND OBJECTIVES: To assess differences in radiomics derived from semi-automatic segmentation of liver metastases for stable disease (SD), partial response (PR), and progressive disease (PD) based on RECIST1.1 and to assess if radiomics alone at baseline can predict response. MATERIALS AND METHODS: Our IRB-approved study included 203 women (mean age 54 ± 11 years) with metastatic liver disease from breast cancer. All patients underwent contrast abdomen-pelvis CT in the portal venous phase at two points: baseline (pre-treatment) and follow-up (between 3 and 12 months following treatment). Patients were subcategorized into three subgroups based on RECIST 1.1 criteria (Response Evaluation Criteria in Solid Tumors version 1.1): 66 with SD, 69 with PR, and 68 with PD on follow-up CT. The deidentified baseline and follow-up CT images were exported to the radiomics prototype. The prototype enabled semi-automatic segmentation of the target liver lesions for the extraction of first and high order radiomics. Statistical analyses with logistic regression and random forest classifiers were performed to differentiate SD from PD and PR. RESULTS: There was no significant difference between the radiomics on the baseline and follow-up CT images of patients with SD (area under the curve (AUC): 0.3). Random forest classifier differentiated patients with PR with an AUC of 0.845. The most relevant feature was the large dependence emphasis's high and low pass wavelet filter (derived gray level dependence matrix features). Random forest classifier differentiated PD with an AUC of 0.731, with the most relevant feature being the surface-to-volume ratio. There was no difference in radiomics among the three groups at baseline; therefore, a response could not be predicted. CONCLUSION: Radiomics of liver metastases with semi-automatic segmentation demonstrate differences between SD from PR and PD. SUMMARY STATEMENT: Semiautomatic segmentation and radiomics of metastatic liver disease demonstrate differences in SD from the PR and progressive metastatic on the baseline and follow-up CT. Despite substantial variations in the scanners, acquisition, and reconstruction parameters, radiomics had an AUC of 0.84-0.89 for differentiating stable hepatic metastases from decreasing and increasing metastatic disease.

Ten-Year Follow-up of Internal Neurofibroma Growth Behavior in Adult Patients With Neurofibromatosis Type 1 Using Whole-Body MRI.

BACKGROUND AND OBJECTIVES: Internal neurofibromas, including plexiform neurofibromas (PNF), can cause significant morbidity in patients with neurofibromatosis type 1 (NF1). PNF growth is most pronounced in children and young adults, with more rapid growth thought to occur in a subset of PNF termed distinct nodular lesions (DNL). Growth behavior of internal neurofibromas and DNL in older adults is not well documented; yet knowledge thereof is important for patient risk stratification and clinical trial design. The primary objective of this study was to evaluate the long-term growth behavior of internal neurofibromas in adults with NF1. Secondary objectives were to correlate tumor growth behavior with patient-specific, tumor-specific, and patient-reported variables. METHODS: In this prospective cohort study, internal neurofibromas were identified on coronal short TI inversion recovery sequences on baseline and follow-up whole-body MRIs (WBMRIs). Tumor growth and shrinkage were defined as a volume change ≥20%. The association between tumor growth and patient-specific (baseline age, sex, and genotype), tumor-specific (morphology, location, DNL presence on baseline WBMRI, and maximum standardized uptake value on baseline PET imaging), and patient-reported variables (endogenous and exogenous hormone exposure, pain intensity, and quality of life) was assessed using the Spearman correlation coefficient and Kruskal-Wallis test. RESULTS: Of 106 patients with a baseline WBMRI obtained as part of a previous research study, 44 had a follow-up WBMRI. Three additional patients with WBMRIs acquired for clinical care were included, generating 47 adults for this study. The median age during baseline WBMRI was 42 years (range 18-70). The median time between WBMRIs was 10.4 years. Among 324 internal neurofibromas, 62.8% (56% of PNF and 62.1% of DNL) shrank spontaneously without treatment and 17.1% (17.9% of PNF and 13.8% of DNL) grew. Growth patterns were heterogeneous within participants. Patient-specific, tumor-specific, and patient-reported variables (including endogenous and exogenous hormone exposure) were not strong predictors of tumor growth. DISCUSSION: Internal neurofibroma growth behavior in older adults differs fundamentally from that in children and young adults, with most tumors, including DNL, demonstrating spontaneous shrinkage. Better growth models are needed to understand factors that influence tumor growth. These results will inform clinical trial design for internal neurofibromas.

Management of neurofibromatosis type 1-associated plexiform neurofibromas.

Plexiform Neurofibromas (PN) are a common manifestation of the genetic disorder neurofibromatosis type 1 (NF1). These benign nerve sheath tumors often cause significant morbidity, with treatment options limited historically to surgery. There have been tremendous advances over the past two decades in our understanding of PN, and the recent regulatory approvals of the MEK inhibitor selumetinib are reshaping the landscape for PN management. At present, there is no agreed upon PN definition, diagnostic evaluation, surveillance strategy, or clear indications for when to initiate treatment and selection of treatment modality. In this review, we address these questions via consensus recommendations from a panel of multidisciplinary NF1 experts.

DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI.

Neurofibromatosis type 1 (NF1) is an autosomal dominant tumor predisposition syndrome that involves the central and peripheral nervous systems. Accurate detection and segmentation of neurofibromas are essential for assessing tumor burden and longitudinal tumor size changes. Automatic convolutional neural networks (CNNs) are sensitive and vulnerable as tumors' variable anatomical location and heterogeneous appearance on MRI. In this study, wepropose deep interactive networks (DINs) to address the above limitations. User interactions guide the model to recognize complicated tumors and quickly adapt to heterogeneous tumors. We introduce a simple but effective Exponential Distance Transform (ExpDT) that converts user interactions into guide maps regarded as the spatial and appearance prior. Comparing with popular Euclidean and geodesic distances, ExpDT is more robust to various image sizes, which reserves the distribution of interactive inputs. Furthermore, to enhance the tumor-related features, we design a deep interactive module to propagate the guides into deeper layers. We train and evaluate DINs on three MRI data sets from NF1 patients. The experiment results yield significant improvements of 44% and 14% in DSC comparing with automated and other interactive methods, respectively. We also experimentally demonstrate the efficiency of DINs in reducing user burden when comparing with conventional interactive methods.

Imaging Evaluation of Plexiform Neurofibromas in Neurofibromatosis Type 1: A Survey-Based Assessment.

OBJECTIVE: To assess imaging utilization practices across clinical specialists in neurofibromatosis type 1 (NF1) for the evaluation of symptomatic and asymptomatic children and adults with or without plexiform neurofibromas (PN). METHODS: An institutional review board-exempt survey was administered to medical practitioners caring for individuals with NF1 at the Response Evaluation in Neurofibromatosis and Schwannomatosis (REiNS) meeting in September 2019. The survey included questions on respondent demographic data (9 questions), type of imaging obtained for asymptomatic (4 questions) and symptomatic (4 questions) people with and without PN, and utilization of diffusion-weighted imaging (2 questions). RESULTS: Thirty practitioners participated in the survey. Most were academic neuro-oncologists at high-volume (>10 patients/week) NF1 centers. Of 30 respondents, 26 had access to whole-body MRI (WB-MRI). The most common approach to an asymptomatic person without PN was no imaging (adults: 57% [17/30]; children: 50% [15/30]), followed by a screening WB-MRI (adults: 20% [6/30]; children: 26.7% [8/30]). The most common approach to a person with symptoms or known PN was regional MRI (adults: 90% [27/30]; children: 93% [28/30]), followed by WB-MRI (adults: 20% [6/30]; children: 36.7% [11/30]). WB-MRI was most often obtained to evaluate a symptomatic child with PN (37% [11/30]). CONCLUSIONS: More than 90% of practitioners indicated they would obtain a regional MRI in a symptomatic patient without known or visible PN. Otherwise, there was little consensus on imaging practices. Given the high prevalence of PN and risk of malignant conversion in this patient population, there is a need to define imaging-based guidelines for optimal clinical care and the design of future clinical trials.

Phase II trial of carboplatin and bevacizumab in patients with breast cancer brain metastases.

BACKGROUND: We aimed to examine the safety and efficacy of bevacizumab and carboplatin in patients with breast cancer brain metastases. METHODS: We enrolled patients with breast cancer and > 1 measurable new or progressive brain metastasis. Patients received bevacizumab 15 mg/kg intravenously (IV) on cycle 1 day 1 and carboplatin IV AUC = 5 on cycle 1 day 8. Patients with HER2-positive disease also received trastuzumab. In subsequent cycles, all drugs were administered on day 1 of each cycle. Contrast-enhanced brain MRI was performed at baseline, 24-96 h after the first bevacizumab dose (day + 1), and every 2 cycles. The primary endpoint was objective response rate in the central nervous system (CNS ORR) by composite criteria. Associations between germline VEGF single nucleotide polymorphisms (rs699947, rs2019063, rs1570360, rs833061) and progression-free survival (PFS) and overall survival (OS) were explored, as were associations between early (day + 1) MRI changes and outcomes. RESULTS: Thirty-eight patients were enrolled (29 HER2-positive, 9 HER2-negative); all were evaluable for response. The CNS ORR was 63% (95% CI, 46-78). Median PFS was 5.62 months and median OS was 14.10 months. As compared with an Eastern Cooperative Oncology Group performance status (ECOG PS) of 0, patients with ECOG PS 1-2 had significantly worse PFS and OS (all P < 0.01). No significant associations between VEGF genotypes or early MRI changes and clinical outcomes were observed. CONCLUSIONS: The combination of bevacizumab and carboplatin results in a high rate of durable objective response in patients with brain metastases from breast cancer. This regimen warrants further investigation. TRIAL REGISTRATION: NCT01004172 . Registered 28 October 2009.

Comparative analysis of three-dimensional volume rendering and maximum intensity projection for preoperative planning in liver cancer.

Three-dimensional imaging is a useful tool to evaluate liver structure and surrounding vessels for preoperative planning. In this study, we compared two methods of visualizing vascular maps on computed tomography including maximum intensity projection (MIP) and 3D volume rendered (VR) imaging. We compiled important imaging components of pre-surgical planning, and developed criteria for comparison. The imaging techniques were compared based on colorization, volume quantification, rotation, vessel delineation, small vessel clarity, and segmental liver isolation. MIP had more overall limitations due to reduced differentiation of superimposed structures, motion artifact, and interference from calcifications. We determined that because 3D quantitative volume rendered imaging can provide more detail and perspective than MIP imaging, it may be more useful in preoperative planning for patients with liver malignancy. Advanced 3D imaging is a useful tool that can have profound clinical implications on cancer detection and surgical planning.

Open Health Imaging Foundation Viewer: An Extensible Open-Source Framework for Building Web-Based Imaging Applications to Support Cancer Research.

PURPOSE: Zero-footprint Web architecture enables imaging applications to be deployed on premise or in the cloud without requiring installation of custom software on the user's computer. Benefits include decreased costs and information technology support requirements, as well as improved accessibility across sites. The Open Health Imaging Foundation (OHIF) Viewer is an extensible platform developed to leverage these benefits and address the demand for open-source Web-based imaging applications. The platform can be modified to support site-specific workflows and accommodate evolving research requirements. MATERIALS AND METHODS: The OHIF Viewer provides basic image review functionality (eg, image manipulation and measurement) as well as advanced visualization (eg, multiplanar reformatting). It is written as a client-only, single-page Web application that can easily be embedded into third-party applications or hosted as a standalone Web site. The platform provides extension points for software developers to include custom tools and adapt the system for their workflows. It is standards compliant and relies on DICOMweb for data exchange and OpenID Connect for authentication, but it can be configured to use any data source or authentication flow. Additionally, the user interface components are provided in a standalone component library so that developers can create custom extensions. RESULTS: The OHIF Viewer and its underlying components have been widely adopted and integrated into multiple clinical research platforms (e,g Precision Imaging Metrics, XNAT, LabCAS, ISB-CGC) and commercial applications (eg, Osirix). It has also been used to build custom imaging applications (eg, ProstateCancer.ai, Crowds Cure Cancer [presented as a case study]). CONCLUSION: The OHIF Viewer provides a flexible framework for building applications to support imaging research. Its adoption could reduce redundancies in software development for National Cancer Institute-funded projects, including Informatics Technology for Cancer Research and the Quantitative Imaging Network.

Correlation between NF1 genotype and imaging phenotype on whole-body MRI: NF1 radiogenomics.

OBJECTIVE: To investigate the genotype-phenotype correlation between neurofibromatosis 1 (NF1) germline mutations and imaging features of neurofibromas on whole-body MRI (WBMRI) by using radiomics image analysis techniques. MATERIALS AND METHODS: Twenty-nine patients with NF1 who had known germline mutations determined by targeted next-generation sequencing were selected from a previous WBMRI study using coronal short tau inversion recovery sequence. Each tumor was segmented in WBMRI and a set of 59 imaging features was calculated using our in-house volumetric image analysis platform, 3DQI. A radiomics heatmap of 59 imaging features was analyzed to investigate the per-tumor and per-patient associations between the imaging features and mutation domains and mutation types. Linear mixed-effect models and one-way analysis of variance tests were performed to assess the similarity of tumor imaging features within mutation groups, between mutation groups, and between randomly selected groups. RESULTS: A total of 218 neurofibromas (97 discrete neurofibromas and 121 plexiform neurofibromas) were identified in 19 of the 29 patients. The unsupervised hierarchical clustering in heatmap analysis revealed 6 major image feature patterns that were significantly correlated with gene mutation domains and types with strong to very strong associations of genotype-phenotype correlations in both per-tumor and per-patient studies (p < 0.05, Cramer V > 0.5), whereas tumor size and locations showed no correlations with imaging features (p = 0.79 and p = 0.42, respectively). The statistical analyses revealed that the number of significantly different features (SDFs) within mutation groups were significantly lower than those between mutation groups (mutation domains: 10.9 ± 9.5% vs 31.9 ± 23.8% and mutation types: 31.8 ± 30.7% vs 52.6 ± 29.3%). The first and second quartile p values of within-patient groups were more than 2 times higher than those between-patient groups. However, the numbers of SDFs between randomly selected groups were much lower (approximately 5.2%). CONCLUSION: This preliminary study identified the NF1 radiogenomics linkage between NF1 causative mutations and MRI radiomic features, i.e., the correlation between NF1 genotype and imaging phenotype on WBMRI.

Measurement of Glenoid Bone Loss With 3-Dimensional Magnetic Resonance Imaging: A Matched Computed Tomography Analysis.

PURPOSE: To compare the measurement of glenoid bone surface area (GBSA) and glenoid bone loss (GBL) between 3-dimensional computed tomography (3D CT) and an autosegmentation approach for 3D magnetic resonance imaging (MRI) of patients with recurrent shoulder instability. METHODS: Eight subjects (2 women and 6 men; age range, 15-72 years [mean, 44 ± 19 years]) were consecutively enrolled who had both CT and MRI of the shoulder for clinical shoulder instability. Inclusion criteria were patients with shoulder instability or other shoulder injury who had both a CT scan and MRI performed of the same shoulder. All patients underwent a 3D CT scan and a 3-Tesla 3D MRI with additional volumetric and autosegmented sequences. En face views of the glenoid for both CT and MRI were auto- and manually measured for overall GBSA and GBL using best-fit circle technique; the amount of GBL was compared with loss of GBSA and was expressed as a percentage of bone loss. RESULTS: There were no differences in GBL measured by 3D CT (41 mm2, 6.6%) vs 3D MRI (40 mm2, 6.5%, P = .852). The mean GBSA was not different among the manual- and autocalculated 3D CT (644 mm2 vs 640 mm2, P = .482). In addition, the manual MRI scan glenoid area was similar to the autocalculated 3D MRI (622 mm2 vs 618 mm2, respectively; P = .482). Overall regression analysis demonstrated excellent correlation between CT and MRI for both GBSA and GBL calculations (R2 = 0.84-0.90). CONCLUSIONS: 3D MRI of the glenoid is nearly identical to 3D CT scans for measurement of GBSA and GBL, making 3D MRI a reliable alternative to a CT scan for a preoperative shoulder evaluation of the glenoid pathology. This study shows that a 3D MRI could be a radiation-free and reliable alternative to a preoperative CT shoulder scan. LEVEL OF EVIDENCE: Level III, case-control study.

2016 Children's Tumor Foundation conference on neurofibromatosis type 1, neurofibromatosis type 2, and schwannomatosis.

Organized and hosted by the Children's Tumor Foundation (CTF), the Neurofibromatosis (NF) conference is the premier annual gathering for clinicians and researchers interested in neurofibromatosis type 1 (NF1), neurofibromatosis type 2 (NF2), and schwannomatosis (SWN). The 2016 edition constituted a blend of clinical and basic aspects of NF research that helped in clarifying different advances in the field. The incorporation of next generation sequencing is changing the way genetic diagnostics is performed for NF and related disorders, providing solutions to problems like genetic heterogeneity, overlapping clinical manifestations, or the presence of mosaicism. The transformation from plexiform neurofibroma (PNF) to malignant peripheral nerve sheath tumor (MPNST) is being clarified, along with new management and treatments for benign and premalignant tumors. Promising new cellular and in vivo models for understanding the musculoskeletal abnormalities in NF1, the development of NF2 or SWN associated schwannomas, and clarifying the cells that give rise to NF1-associated optic pathway glioma were presented. The interaction of neurofibromin and SPRED1 was described comprehensively, providing functional insight that will help in the interpretation of pathogenicity of certain missense variants identified in NF1 and Legius syndrome patients. Novel promising imaging techniques are being developed, as well as new integrative and holistic management models for patients that take into account psychological, social, and biological factors. Importantly, new therapeutic approaches for schwannomas, meningiomas, ependymomas, PNF, and MPNST are being pursued. This report highlights the major advances that were presented at the 2016 CTF NF conference.

Pain correlates with germline mutation in schwannomatosis.

Schwannomatosis has been linked to germline mutations in the SMARCB1 and LZTR1 genes, and is frequently associated with pain.In a cohort study, we assessed the mutation status of 37 patients with clinically diagnosed schwannomatosis and compared to clinical data, whole body MRI (WBMRI), visual analog pain scale, and Short Form 36 (SF-36) bodily pain subscale.We identified a germline mutation in LZTR1 in 5 patients (13.5%) and SMARCB1 in 15 patients (40.5%), but found no germline mutation in 17 patients (45.9%). Peripheral schwannomas were detected in 3 LZTR1-mutant (60%) and 10 SMARCB1-mutant subjects (66.7%). Among those with peripheral tumors, the median tumor number was 4 in the LZTR1 group (median total body tumor volume 30 cc) and 10 in the SMARCB1 group (median volume 85cc), (P=.2915 for tumor number and P = .2289 for volume). mutation was associated with an increased prevalence of spinal schwannomas (100% vs 41%, P = .0197). The median pain score was 3.9/10 in the LZTR1 group and 0.5/10 in the SMARCB1 group (P = .0414), and SF-36 pain-associated quality of life was significantly worse in the LZTR1 group (P = .0106). Pain scores correlated with total body tumor volume (rho = 0.32471, P = .0499), but not with number of tumors (rho = 0.23065, P = .1696).We found no significant difference in quantitative tumor burden between mutational groups, but spinal schwannomas were more common in LZTR1-mutant patients. Pain was significantly higher in LZTR1-mutant than in SMARCB1-mutant patients, though spinal tumor location did not significantly correlate with pain. This suggests a possible genetic association with schwannomatosis-associated pain.

Clinical trial design for systemic agents in patients with brain metastases from solid tumours: a guideline by the Response Assessment in Neuro-Oncology Brain Metastases working group.

Patients with active CNS disease are often excluded from clinical trials, and data regarding the CNS efficacy of systemic agents are usually obtained late in the drug development process or not at all. In this guideline from the Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) working group, we provide detailed recommendations on when patients with brain metastases from solid tumours should be included or excluded in clinical trials of systemic agents. We also discuss the limitations of retrospective studies in determining the CNS efficacy of systemic drugs. Inclusion of patients with brain metastases early on in the clinical development of a drug or a regimen is needed to generate appropriate CNS efficacy or non-efficacy signals. We consider how to optimally incorporate or exclude such patients in systemic therapy trials depending on the likelihood of CNS activity of the agent by considering three scenarios: drugs that are considered very unlikely to have CNS antitumour activity or efficacy; drugs that are considered very likely to have CNS activity or efficacy; and drugs with minimal baseline information on CNS activity or efficacy. We also address trial design issues unique to patients with brain metastases, including the selection of appropriate CNS endpoints in systemic therapy trials.

Immune-related tumour response assessment criteria: a comprehensive review.

Growing emphasis on precision medicine in oncology has led to increasing use of targeted therapies that encompass a spectrum of drug classes including angiogenesis inhibitors, immune modulators, signal transduction inhibitors, DNA damage modulators, hormonal agents etc. Immune therapeutic drugs constitute a unique group among the novel therapeutic agents that are transforming cancer treatment, and their use is rising. The imaging manifestations in patients on immune therapies appear to be distinct from those typically seen with conventional cytotoxic therapies. Patients on immune therapies may demonstrate a delayed response, transient tumour enlargement followed by shrinkage, stable size, or initial appearance of new lesions followed by stability or response. These newer patterns of response to treatment have rendered conventional criteria such as World Health Organization and response evaluation criteria in solid tumours suboptimal in monitoring changes in tumour burden. As a consequence, newer imaging response criteria such as immune-related response evaluation criteria in solid tumours and immune-related response criteria are being implemented in many trials to effectively monitor patients on immune therapies. In this review, we discuss the traditional and new imaging response criteria for evaluation of solid tumours, review the outcomes of various articles which compared traditional criteria with the new immune-related criteria and discuss pseudo-progression and immune-related adverse events.

Volumetric MRI Analysis of Plexiform Neurofibromas in Neurofibromatosis Type 1: Comparison of Two Methods.

OBJECTIVES: Plexiform neurofibromas (PNs) are complex, histologically benign peripheral nerve sheath tumors that are challenging to measure by simple line measurements. Computer-aided volumetric segmentation of PN has become the recommended method to assess response in clinical trials directed at PN. Different methods for volumetric analysis of PN have been developed. The goal of this study is to test the level of agreement in volume measurements and in interval changes using two separate methods of volumetric magnetic resonance imaging analysis. METHODS: Three independent volume measurements were performed on 15 PN imaged at three time-points using 3DQI software at Massachusetts General Hospital (MGH) and National Cancer Institute (NCI) and MEDx software at NCI. RESULTS: Median volume differences at each time-point comparing MGH-3DQI and NCI-3DQI were -0.5, -4.2, and -19.9 mL; comparing NCI-3DQI and NCI-MEDx were -21.0, -47.0, and -21.0 mL; comparing MGH-3DQI and NCI-MEDx were -10.0, -70.3, and -29.9 mL. Median differences in percentage change over time comparing MGH-3DQI and NCI-3DQI were -1.7, 1.1, and -1.0%; comparing NCI-3DQI and NCI-MEDx were -2.3, 3.3, and -1.1%; comparing MGH-3DQI and NCI-MEDx were -0.4, 2.0, and -1.5%. Volume differences were <20% of the mean of the two measurements in 117 of 135 comparisons (86.7%). Difference in interval change was <20% in 120 of the 135 comparisons (88.9%), while disease status classification was concordant in 115 of 135 comparisons (85.2%). CONCLUSIONS: The volumes, interval changes, and progression status classifications were in good agreement. The comparison of two volumetric analysis methods suggests no systematic differences in tumor assessment. A prospective comparison of the two methods is planned.

LesionTracker: Extensible Open-Source Zero-Footprint Web Viewer for Cancer Imaging Research and Clinical Trials.

Oncology clinical trials have become increasingly dependent upon image-based surrogate endpoints for determining patient eligibility and treatment efficacy. As therapeutics have evolved and multiplied in number, the tumor metrics criteria used to characterize therapeutic response have become progressively more varied and complex. The growing intricacies of image-based response evaluation, together with rising expectations for rapid and consistent results reporting, make it difficult for site radiologists to adequately address local and multicenter imaging demands. These challenges demonstrate the need for advanced cancer imaging informatics tools that can help ensure protocol-compliant image evaluation while simultaneously promoting reviewer efficiency. LesionTracker is a quantitative imaging package optimized for oncology clinical trial workflows. The goal of the project is to create an open source zero-footprint viewer for image analysis that is designed to be extensible as well as capable of being integrated into third-party systems for advanced imaging tools and clinical trials informatics platforms. Cancer Res; 77(21); e119-22. ©2017 AACR.

Current whole-body MRI applications in the neurofibromatoses: NF1, NF2, and schwannomatosis.

OBJECTIVES: The Response Evaluation in Neurofibromatosis and Schwannomatosis (REiNS) International Collaboration Whole-Body MRI (WB-MRI) Working Group reviewed the existing literature on WB-MRI, an emerging technology for assessing disease in patients with neurofibromatosis type 1 (NF1), neurofibromatosis type 2 (NF2), and schwannomatosis (SWN), to recommend optimal image acquisition and analysis methods to enable WB-MRI as an endpoint in NF clinical trials. METHODS: A systematic process was used to review all published data about WB-MRI in NF syndromes to assess diagnostic accuracy, feasibility and reproducibility, and data about specific techniques for assessment of tumor burden, characterization of neoplasms, and response to therapy. RESULTS: WB-MRI at 1.5T or 3.0T is feasible for image acquisition. Short tau inversion recovery (STIR) sequence is used in all investigations to date, suggesting consensus about the utility of this sequence for detection of WB tumor burden in people with NF. There are insufficient data to support a consensus statement about the optimal imaging planes (axial vs coronal) or 2D vs 3D approaches. Functional imaging, although used in some NF studies, has not been systematically applied or evaluated. There are no comparative studies between regional vs WB-MRI or evaluations of WB-MRI reproducibility. CONCLUSIONS: WB-MRI is feasible for identifying tumors using both 1.5T and 3.0T systems. The STIR sequence is a core sequence. Additional investigation is needed to define the optimal approach for volumetric analysis, the reproducibility of WB-MRI in NF, and the diagnostic performance of WB-MRI vs regional MRI.

Cancer Imaging at the Crossroads of Precision Medicine: Perspective From an Academic Imaging Department in a Comprehensive Cancer Center.

The authors propose one possible vision for the transformative role that cancer imaging in an academic setting can play in the current era of personalized and precision medicine by sharing a conceptual model that is based on experience and lessons learned designing a multidisciplinary, integrated clinical and research practice at their institution. The authors' practice and focus are disease-centric rather than imaging-centric. A "wall-less" infrastructure has been developed, with bidirectional integration of preclinical and clinical cancer imaging research platforms, enabling rapid translation of novel cancer drugs from discovery to clinical trial evaluation. The talents and expertise of medical professionals, scientists, and staff members have been coordinated in a horizontal and vertical fashion through the creation of Cancer Imaging Consultation Services and the "Adopt-a-Radiologist" campaign. Subspecialized imaging consultation services at the hub of an outpatient cancer center facilitate patient decision support and management at the point of care. The Adopt-a-Radiologist campaign has led to the creation of a novel generation of imaging clinician-scientists, fostered new collaborations, increased clinical and academic productivity, and improved employee satisfaction. Translational cancer research is supported, with a focus on early in vivo testing of novel cancer drugs, co-clinical trials, and longitudinal tumor imaging metrics through the imaging research core laboratory. Finally, a dedicated cancer imaging fellowship has been developed, promoting the future generation of cancer imaging specialists as multidisciplinary, multitalented professionals who are trained to effectively communicate with clinical colleagues and positively influence patient care.

Response assessment criteria for brain metastases: proposal from the RANO group.

CNS metastases are the most common cause of malignant brain tumours in adults. Historically, patients with brain metastases have been excluded from most clinical trials, but their inclusion is now becoming more common. The medical literature is difficult to interpret because of substantial variation in the response and progression criteria used across clinical trials. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) working group is an international, multidisciplinary effort to develop standard response and progression criteria for use in clinical trials of treatment for brain metastases. Previous efforts have focused on aspects of trial design, such as patient population, variations in existing response and progression criteria, and challenges when incorporating neurological, neuro-cognitive, and quality-of-life endpoints into trials of patients with brain metastases. Here, we present our recommendations for standard response and progression criteria for the assessment of brain metastases in clinical trials. The proposed criteria will hopefully facilitate the development of novel approaches to this difficult problem by providing more uniformity in the assessment of CNS metastases across trials.