Curation of myeloma observational study MALIMAR using XNAT: solving the challenges posed by real-world data.

OBJECTIVES: MAchine Learning In MyelomA Response (MALIMAR) is an observational clinical study combining "real-world" and clinical trial data, both retrospective and prospective. Images were acquired on three MRI scanners over a 10-year window at two institutions, leading to a need for extensive curation. METHODS: Curation involved image aggregation, pseudonymisation, allocation between project phases, data cleaning, upload to an XNAT repository visible from multiple sites, annotation, incorporation of machine learning research outputs and quality assurance using programmatic methods. RESULTS: A total of 796 whole-body MR imaging sessions from 462 subjects were curated. A major change in scan protocol part way through the retrospective window meant that approximately 30% of available imaging sessions had properties that differed significantly from the remainder of the data. Issues were found with a vendor-supplied clinical algorithm for "composing" whole-body images from multiple imaging stations. Historic weaknesses in a digital video disk (DVD) research archive (already addressed by the mid-2010s) were highlighted by incomplete datasets, some of which could not be completely recovered. The final dataset contained 736 imaging sessions for 432 subjects. Software was written to clean and harmonise data. Implications for the subsequent machine learning activity are considered. CONCLUSIONS: MALIMAR exemplifies the vital role that curation plays in machine learning studies that use real-world data. A research repository such as XNAT facilitates day-to-day management, ensures robustness and consistency and enhances the value of the final dataset. The types of process described here will be vital for future large-scale multi-institutional and multi-national imaging projects. CRITICAL RELEVANCE STATEMENT: This article showcases innovative data curation methods using a state-of-the-art image repository platform; such tools will be vital for managing the large multi-institutional datasets required to train and validate generalisable ML algorithms and future foundation models in medical imaging. KEY POINTS: • Heterogeneous data in the MALIMAR study required the development of novel curation strategies. • Correction of multiple problems affecting the real-world data was successful, but implications for machine learning are still being evaluated. • Modern image repositories have rich application programming interfaces enabling data enrichment and programmatic QA, making them much more than simple "image marts".

A Subset of Non-Small Cell Lung Cancer Patients Treated with Pemetrexed Show 18F-Fluorothymidine "Flare" on Positron Emission Tomography.

Thymidylate synthase (TS) remains a major target for cancer therapy. TS inhibition elicits increases in DNA salvage pathway activity, detected as a transient compensatory "flare" in 3'-deoxy-3'-[18F]fluorothymidine positron emission tomography (18F-FLT PET). We determined the magnitude of the 18F-FLT flare in non-small cell lung cancer (NSCLC) patients treated with the antifolate pemetrexed in relation to clinical outcome. METHOD: Twenty-one patients with advanced/metastatic non-small cell lung cancer (NSCLC) scheduled to receive palliative pemetrexed ± platinum-based chemotherapy underwent 18F-FLT PET at baseline and 4 h after initiating single-agent pemetrexed. Plasma deoxyuridine (dUrd) levels and thymidine kinase 1 (TK1) activity were measured before each scan. Patients were then treated with the combination therapy. The 18F-FLT PET variables were compared to RECIST 1.1 and overall survival (OS). RESULTS: Nineteen patients had evaluable PET scans at both time points. A total of 32% (6/19) of patients showed 18F-FLT flares (>20% change in SUVmax-wsum). At the lesion level, only one patient had an FLT flare in all the lesions above (test-retest borders). The remaining had varied uptake. An 18F-FLT flare occurred in all lesions in 1 patient, while another patient had an 18F-FLT reduction in all lesions; 17 patients showed varied lesion uptake. All patients showed global TS inhibition reflected in plasma dUrd levels (p < 0.001) and 18F-FLT flares of TS-responsive normal tissues including small bowel and bone marrow (p = 0.004 each). Notably, 83% (5/6) of patients who exhibited 18F-FLT flares were also RECIST responders with a median OS of 31 m, unlike patients who did not exhibit 18F-FLT flares (15 m). Baseline plasma TK1 was prognostic of survival but its activity remained unchanged following treatment. CONCLUSIONS: The better radiological response and longer survival observed in patients with an 18F-FLT flare suggest the efficacy of the tracer as an indicator of the early therapeutic response to pemetrexed in NSCLC.

Development and Evaluation of Machine Learning in Whole-Body Magnetic Resonance Imaging for Detecting Metastases in Patients With Lung or Colon Cancer: A Diagnostic Test Accuracy Study.

OBJECTIVES: Whole-body magnetic resonance imaging (WB-MRI) has been demonstrated to be efficient and cost-effective for cancer staging. The study aim was to develop a machine learning (ML) algorithm to improve radiologists' sensitivity and specificity for metastasis detection and reduce reading times. MATERIALS AND METHODS: A retrospective analysis of 438 prospectively collected WB-MRI scans from multicenter Streamline studies (February 2013-September 2016) was undertaken. Disease sites were manually labeled using Streamline reference standard. Whole-body MRI scans were randomly allocated to training and testing sets. A model for malignant lesion detection was developed based on convolutional neural networks and a 2-stage training strategy. The final algorithm generated lesion probability heat maps. Using a concurrent reader paradigm, 25 radiologists (18 experienced, 7 inexperienced in WB-/MRI) were randomly allocated WB-MRI scans with or without ML support to detect malignant lesions over 2 or 3 reading rounds. Reads were undertaken in the setting of a diagnostic radiology reading room between November 2019 and March 2020. Reading times were recorded by a scribe. Prespecified analysis included sensitivity, specificity, interobserver agreement, and reading time of radiology readers to detect metastases with or without ML support. Reader performance for detection of the primary tumor was also evaluated. RESULTS: Four hundred thirty-three evaluable WB-MRI scans were allocated to algorithm training (245) or radiology testing (50 patients with metastases, from primary 117 colon [n = 117] or lung [n = 71] cancer). Among a total 562 reads by experienced radiologists over 2 reading rounds, per-patient specificity was 86.2% (ML) and 87.7% (non-ML) (-1.5% difference; 95% confidence interval [CI], -6.4%, 3.5%; P = 0.39). Sensitivity was 66.0% (ML) and 70.0% (non-ML) (-4.0% difference; 95% CI, -13.5%, 5.5%; P = 0.344). Among 161 reads by inexperienced readers, per-patient specificity in both groups was 76.3% (0% difference; 95% CI, -15.0%, 15.0%; P = 0.613), with sensitivity of 73.3% (ML) and 60.0% (non-ML) (13.3% difference; 95% CI, -7.9%, 34.5%; P = 0.313). Per-site specificity was high (>90%) for all metastatic sites and experience levels. There was high sensitivity for the detection of primary tumors (lung cancer detection rate of 98.6% with and without ML [0.0% difference; 95% CI, -2.0%, 2.0%; P = 1.00], colon cancer detection rate of 89.0% with and 90.6% without ML [-1.7% difference; 95% CI, -5.6%, 2.2%; P = 0.65]). When combining all reads from rounds 1 and 2, reading times fell by 6.2% (95% CI, -22.8%, 10.0%) when using ML. Round 2 read-times fell by 32% (95% CI, 20.8%, 42.8%) compared with round 1. Within round 2, there was a significant decrease in read-time when using ML support, estimated as 286 seconds (or 11%) quicker ( P = 0.0281), using regression analysis to account for reader experience, read round, and tumor type. Interobserver variance suggests moderate agreement, Cohen κ = 0.64; 95% CI, 0.47, 0.81 (with ML), and Cohen κ = 0.66; 95% CI, 0.47, 0.81 (without ML). CONCLUSIONS: There was no evidence of a significant difference in per-patient sensitivity and specificity for detecting metastases or the primary tumor using concurrent ML compared with standard WB-MRI. Radiology read-times with or without ML support fell for round 2 reads compared with round 1, suggesting that readers familiarized themselves with the study reading method. During the second reading round, there was a significant reduction in reading time when using ML support.

Does the addition of whole-body MRI to routine imaging influence real-world treatment decisions in metastatic breast cancer?

BACKGROUND: The assessment of metastatic breast cancer (MBC) can be limited with routine imaging such as computed tomography (CT) especially in bone-only or bone-predominant disease. This analysis investigates the effects of the use of WBMRI in addition to the use of routine CT, bone scintigraphy (BS) and fluorine-18-fluorodeoxyglucose positron emission tomography with computed tomography (FDG-PET/CT) on influencing systemic anti-cancer treatment (SACT) decisions in patients with known MBC. METHODS: MBC patients undergoing SACT who had WBMRI undertaken within 8 weeks of either a routine CT, BS or FDG-PET/CT were reviewed retrospectively. The clinical indications for undertaking the WBMRI examinations were recorded. Data on the extent and distribution of the disease were collected and discordance/concordance of disease status across the imaging modalities were compared. SACT decisions at each time point were also evaluated. RESULTS: There were 105 MBC patients with 148 WBMRI studies paired with CT, BS or FDG-PET/CT. 50 pairs (33.8%) showed differences in the extent of disease, with 44 pairs due to additional sites (AS) reported on WBMRI alone. 81 patients (Group 1) had one WBMRI paired with routine imaging due to a variety of indications, with clinical symptoms (such as bone pain) being the most common (24.7%). 24 patients (Group 2) had more than one WBMRI study paired with routine imaging comprising 67 pairs. 13/67 pairs (19.4%) showed discordance in assessments. 10/13 pairs had progressive disease (PD) reported on WBMRI alone. SACT change due to AS reported on WBMRI alone occurred in 21/23 pairs (91.3%) in Group 1. SACT change due to PD reported on WBMRI alone in Group 2 occurred in 6/14 pairs (42.9%). SACT change due to AS/PD in both groups occurred in 11/102 pairs (10.8%) with known invasive ductal carcinoma (IDC) and 13/28 pairs (46.4%) with invasive lobular carcinoma (ILC). CONCLUSIONS: The use of WBMRI in MBC led to earlier recognition of PD and SACT change compared with the other imaging modalities. A higher proportion of discordant response assessments and SACT changes were observed in ILC compared with IDC in our patient group, although larger-scale studies are required to investigate this further.

Detection and staging of radio-recurrent prostate cancer using multiparametric MRI.

OBJECTIVE: We determined the sensitivity and specificity of multiparametric magnetic resonance imaging (MP-MRI) in detection of locally recurrent prostate cancer and extra prostatic extension in the post-radical radiotherapy setting. Histopathological reference standard was whole-mount prostatectomy specimens. We also assessed for any added value of the dynamic contrast enhancement (DCE) sequence in detection and staging of local recurrence. METHODS: This was a single centre retrospective study. Participants were selected from a database of males treated with salvage prostatectomy for locally recurrent prostate cancer following radiotherapy. All underwent pre-operative prostate-specific antigen assay, positron emission tomography CT, MP-MRI and transperineal template prostate mapping biopsy prior to salvage prostatectomy. MP-MRI performance was assessed using both Prostate Imaging-Reporting and Data System v. 2 and a modified scoring system for the post-treatment setting. RESULTS: 24 patients were enrolled. Using Prostate Imaging-Reporting and Data System v. 2, sensitivity, specificity, positive predictive value and negative predictive value was 64%, 94%, 98% and 36%. MP-MRI under staged recurrent cancer in 63%. A modified scoring system in which DCE was used as a co-dominant sequence resulted in improved diagnostic sensitivity (61%-76%) following subgroup analysis. CONCLUSION: Our results show MP-MRI has moderate sensitivity (64%) and high specificity (94%) in detecting radio-recurrent intraprostatic disease, though disease tends to be under quantified and under staged. Greater emphasis on dynamic contrast images in overall scoring can improve diagnostic sensitivity. ADVANCES IN KNOWLEDGE: MP-MRI tends to under quantify and under stage radio-recurrent prostate cancer. DCE has a potentially augmented role in detecting recurrent tumour compared with the de novo setting. This has relevance in the event of any future modified MP-MRI scoring system for the irradiated gland.

Pictorial review of whole body MRI in myeloma: emphasis on diffusion-weighted imaging.

There have been major advances in myeloma imaging over the past few years with focal lesions on imaging now forming part of the disease defining criteria. Whole body diffusion-weighted MRI (WB-MRI) is considered the most sensitive technique for the detection of focal active lesions. This pictorial review will focus on imaging the spectrum of myelomatous disorders on WB-MRI including diffusion and Dixon sequences. The typical imaging patterns of disease are demonstrated including in the contexts of staging, presumed solitary plasmacytoma, smouldering myeloma and examples of paramedullary and extramedullary disease. The utility of diffusion-weighted imaging in response assessment is a major advantage and this will be exemplified here.

Lung Parenchymal and Tracheal CT Morphology: Evaluation before and after Bariatric Surgery.

Background There is significant pulmonary functional deficit related to obesity, but no prospective CT studies have evaluated the effects of obesity on the lungs and trachea. Purpose To evaluate lung parenchymal and tracheal CT morphology before and 6 months after bariatric surgery, with functional and symptomatic correlation. Materials and Methods A prospective longitudinal study of 51 consecutive individuals referred for bariatric surgery was performed (from November 2011 to November 2013). All individuals had undergone limited (three-location) inspiratory and end-expiratory thoracic CT before and after surgery, with concurrent pulmonary function testing, body mass index calculation, and modified Medical Research Council (mMRC) dyspnea scale and Epworth scoring. Two thoracic radiologists scored the CT extent of mosaic attenuation, end-expiratory air trapping, and tracheal shape. The inspiratory and end-expiratory cross-sectional areas of the trachea were measured. The paired t test or Wilcoxon signed-rank test was used for pre- and postsurgical comparisons. Spearman correlation and logistic regression were used to evaluate correlations between CT findings and functional and symptom indexes. Results A total of 51 participants (mean age, 52 years ± 8 [standard deviation]; 20 men) were evaluated. Before surgery, air trapping extent correlated most strongly with decreased total lung capacity (Spearman rank correlation coefficient [rs] = -0.40, P = .004). After surgery, there were decreases in percentage mosaic attenuation (0% [interquartile range {IQR}: 0%-2.5%] vs 0% [IQR: 0%-0%], P < .001), air trapping (9.6% [IQR: 5.8%-15.8%] vs 2.5% [IQR: 0%-6.7%], P < .001), and tracheal collapse (201 mm2 [IQR: 181-239 mm2] vs 229 mm2 [186-284 mm2], P < .001). After surgery, mMRC dyspnea score change correlated positively with air trapping extent change (rs = 0.46, P = .001) and end-expiratory tracheal shape change (rs = 0.40, P = .01). At multivariable analysis, air trapping was the main determinant for decreased dyspnea after surgery (odds ratio, 1.2; 95% confidence interval: 1.1, 1.2; P = .03). Conclusion Dyspnea improved in obese participants after weight reduction, which correlated with less tracheal collapse and air trapping at end-expiration chest CT. © RSNA, 2020 Online supplemental material is available for this article.

Interobserver agreement of the visual Herder scale for the assessment of solitary pulmonary nodules on 18F Fluorodeoxyglucose PET/computed tomography.

BACKGROUND: British Thoracic Society guidelines recommend 18F Fluorodeoxyglucose (F-FDG) PET/computed tomography (CT) for solitary pulmonary nodule (SPN) follow-up in high-risk individuals or if the CT Brock score is >10%. Nodule tracer uptake is assessed visually in comparison to the surrounding lung tissue and mediastinal blood pool (Herder score). This score is used to calculate the risk of malignancy and guide patient management. Despite its widespread use, there have been no studies to date looking at interobserver agreement using the Herder scale. PATIENTS AND METHODS: F-FDG PET/CT studies of 100 consecutive patients imaged for the evaluation of SPN were retrospectively analysed. Anonymized images were reviewed independently by three Consultant Nuclear Medicine Radiologists and the Herder score was documented, along with a confidence score graded 1-3, where 1 indicated 'not at all confident' and 3 indicated 'very confident'. Interobserver agreement was assessed using interclass correlation coefficient modelling. RESULTS: There was complete reviewer agreement in 81% cases, and interclass correlation with Cronbach's alpha was excellent at 0.973 (95% confidence interval, 0.962-0.981). The agreement between pairs of reviewers was good and confidence scores using the Herder scale were high, with reviewers giving a confidence score of 3 in an average of 78% of cases. CONCLUSION: Our study suggests excellent interobserver agreement for use of the Herder scale in evaluating SPNs. Reviewer confidence scores were high reflecting high confidence in the use of the Herder scale for evaluating SPN.

Post-Radiation Therapy Imaging Appearances in Cervical Carcinoma.

Locally advanced and node-positive cervical cancers are usually treated with external beam radiation therapy and intracavitary brachytherapy with concomitant chemotherapy. In patients with locally advanced cervical cancer, imaging plays a vital role in pretreatment planning, assessment of primary tumor response to treatment, follow-up, and evaluation of treatment-related complications. Radiation therapy planning is crucial to successful local and regional control of disease. Patient selection criteria for radiation therapy with concomitant chemotherapy are described, as is assessment of treatment response of the primary cervical tumor at magnetic resonance (MR) imaging. Image interpretation can be challenging because of radiation therapy-related changes in the pelvic organs. Expected changes in the bladder, bowel, and bone marrow after radiation therapy are described, and multimodality imaging findings at computed tomography, MR imaging, and fluorine 18 fluorodeoxyglucose positron emission tomography are illustrated. Complications after radiation therapy have declined over recent years because of targeted radiation therapy. These complications can be divided into acute and chronic effects, where acute toxic effects occur within weeks of treatment. Chronic complications include cervical stenosis, small bowel stricture, fistula formation, and insufficiency fractures. Imaging is an essential tool in the care of patients with cervical cancer treated with chemotherapy and radiation therapy. The reporting radiologist should be familiar with the expected imaging appearances of the pelvic organs after radiation therapy, as well as potential complications, to avoid pitfalls in image interpretation.

Clinical and angiographic findings in Moya Moya.

PATIENT: Female, 40 FINAL DIAGNOSIS: Moya-Moya Disease Symptoms: Blurred vision • headache • lethargy MEDICATION: - Clinical Procedure: - Specialty: Neurology. OBJECTIVE: Rare disease. BACKGROUND: Moya Moya is a cerebrovasculopathy of the terminal internal carotid arteries and the proximal anterior and middle cerebral arteries. It is comparatively more common in Japan compared to Western countries. CASE REPORT: We present a patient of South-East Asian origin diagnosed with Moya Moya, confirmed on magnetic resonance angiography and later computerized tomography angiography. She was managed conservatively through medical management and lifestyle advice, and has now been enlisted into the national Moya Moya database in the UK. CONCLUSIONS: We believe this report will help advance our understanding on Moya Moya and help to elucidate the importance of a combined medical and radiological approach to this condition.

68Ga DOTATATE PET/CT uptake in spinal lesions and MRI correlation on a patient with neuroendocrine tumor: potential pitfalls.

A 62-year-old female patient with suspected insulinoma underwent 68Ga DOTA-TATE PET/CT for characterization and staging. This demonstrated a focus of uptake in the pancreas and 3 foci of uptake in the spine. An MRI of the spine performed to further characterize the lesions revealed the presence of a meningioma and degenerative changes, both of which showed 68Ga DOTA-TATE uptake. A vertebral metastasis seen on PET was occult on CT and MRI. A vertebral hemangioma had no discrete tracer uptake. Awareness of sources of error in interpreting 68Ga DOTA-TATE scans is important in order to avoid pitfalls.

Nasu-hakola syndrome: an unusual cause of pathological fractures.

Nasu-Hakola syndrome is a hereditary cause of pathological fractures. Uniquely, patients also develop neuropsychiatric symptoms and signs. The disease is ultimately fatal. We propose a management strategy for pathological fractures in sufferers based on the stage of the disease.

Effects of cannabinoids on capsaicin receptor activity following exposure of primary sensory neurons to inflammatory mediators.

AIMS: Activation of the cannabinoid 1 (CB1) receptor in cultured primary sensory neurons reduces responses mediated through the transient receptor potential vanilloid type 1 receptor (TRPV1), which plays a pivotal role in the development of heat hyperalgesia and visceral hyper-reflexia in inflammatory conditions. Here, we studied the effect of cannabinoid-evoked inhibitory effect on TRPV1 in inflammatory conditions. MAIN METHODS: The effect of anandamide (1 nM-30 nM) and 1,1-dimethylheptyl-11-hydroxytetrahydrocannabinol (HU210; 1 microM-10 microM) was assessed on capsaicin (10 nM or 100 nM)-evoked cobalt uptake in rat cultured primary sensory neurons following the incubation of the cells in an "inflammatory environment" created by the major inflammatory mediators, bradykinin (5 microM), prostaglandin E(2) (5 microM) and nerve growth factor (100 ng/ml) for 10 min. KEY FINDINGS: 1 nM and 10 nM anandamide significantly reduced the 10 nM but not the 100 nM capsaicin-evoked responses. HU210 did not produce a significant change in responses evoked by capsaicin at either of its concentrations. The anandamide-induced inhibitory effect could not be reversed by the CB1 receptor antagonist, rimonabant (200 nM) or the membrane-permeable cAMP analogue, 8Br-cAMP (100 microM). SIGNIFICANCE: These findings suggest that anandamide may inhibit TRPV1-mediated responses in a non-CB1/non-cannabinoid 2 receptor-dependent manner in primary sensory neurons in inflammatory conditions.