Multicentre validation of CT grey-level co-occurrence matrix features for overall survival in primary oesophageal adenocarcinoma.

BACKGROUND: Personalising management of primary oesophageal adenocarcinoma requires better risk stratification. Lack of independent validation of proposed imaging biomarkers has hampered clinical translation. We aimed to prospectively validate previously identified prognostic grey-level co-occurrence matrix (GLCM) CT features for 3-year overall survival. METHODS: Following ethical approval, clinical and contrast-enhanced CT data were acquired from participants from five institutions. Data from three institutions were used for training and two for testing. Survival classifiers were modelled on prespecified variables ('Clinical' model: age, clinical T-stage, clinical N-stage; 'ClinVol' model: clinical features + CT tumour volume; 'ClinRad' model: ClinVol features + GLCM_Correlation and GLCM_Contrast). To reflect current clinical practice, baseline stage was also modelled as a univariate predictor ('Stage'). Discrimination was assessed by area under the receiver operating curve (AUC) analysis; calibration by Brier scores; and clinical relevance by thresholding risk scores to achieve 90% sensitivity for 3-year mortality. RESULTS: A total of 162 participants were included (144 male; median 67 years [IQR 59, 72]; training, 95 participants; testing, 67 participants). Median survival was 998 days [IQR 486, 1594]. The ClinRad model yielded the greatest test discrimination (AUC, 0.68 [95% CI 0.54, 0.81]) that outperformed Stage (ΔAUC, 0.12 [95% CI 0.01, 0.23]; p = .04). The Clinical and ClinVol models yielded comparable test discrimination (AUC, 0.66 [95% CI 0.51, 0.80] vs. 0.65 [95% CI 0.50, 0.79]; p > .05). Test sensitivity of 90% was achieved by ClinRad and Stage models only. CONCLUSIONS: Compared to Stage, multivariable models of prespecified clinical and radiomic variables yielded improved prediction of 3-year overall survival. CLINICAL RELEVANCE STATEMENT: Previously identified radiomic features are prognostic but may not substantially improve risk stratification on their own. KEY POINTS: • Better risk stratification is needed in primary oesophageal cancer to personalise management. • Previously identified CT features-GLCM_Correlation and GLCM_Contrast-contain incremental prognostic information to age and clinical stage. • Compared to staging, multivariable clinicoradiomic models improve discrimination of 3-year overall survival.

The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Predicting programmed death-ligand 1 (PD-L1) expression with fluorine-18 fluorodeoxyglucose ([18F]FDG) positron emission tomography/computed tomography (PET/CT) metabolic parameters in resectable non-small cell lung cancer.

BACKGROUND: Programmed death-ligand 1 (PD-L1) expression is a predictive biomarker for immunotherapy in non-small cell lung cancer (NSCLC). PD-L1 and glucose transporter 1 expression are closely associated, and studies demonstrate correlation of PD-L1 with glucose metabolism. AIM: The aim of this study was to investigate the association of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography ([18F]FDG-PET/CT) metabolic parameters with PD-L1 expression in primary lung tumour and lymph node metastases in resected NSCLC. METHODS: We conducted a retrospective analysis of 210 patients with node-positive resectable stage IIB-IIIB NSCLC. PD-L1 tumour proportion score (TPS) was determined using the DAKO 22C3 immunohistochemical assay. Semi-automated techniques were used to analyse pre-operative [18F]FDG-PET/CT images to determine primary and nodal metabolic parameter scores (including max, mean, peak and peak adjusted for lean body mass standardised uptake values (SUV), metabolic tumour volume (MTV), total lesional glycolysis (TLG) and SUV heterogeneity index (HISUV)). RESULTS: Patients were predominantly male (57%), median age 70 years with non-squamous NSCLC (68%). A majority had negative primary tumour PD-L1 (TPS < 1%; 53%). Mean SUVmax, SUVmean, SUVpeak and SULpeak values were significantly higher (p < 0.05) in those with TPS ≥ 1% in primary tumour (n = 210) or lymph nodes (n = 91). However, ROC analysis demonstrated only moderate separability at the 1% PD-L1 TPS threshold (AUCs 0.58-0.73). There was no association of MTV, TLG and HISUV with PD-L1 TPS. CONCLUSION: This study demonstrated the association of SUV-based [18F]FDG-PET/CT metabolic parameters with PD-L1 expression in primary tumour or lymph node metastasis in resectable NSCLC, but with poor sensitivity and specificity for predicting PD-L1 positivity ≥ 1%. CLINICAL RELEVANCE STATEMENT: Whilst SUV-based fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography metabolic parameters may not predict programmed death-ligand 1 positivity ≥ 1% in the primary tumour and lymph nodes of resectable non-small cell lung cancer independently, there is a clear association which warrants further investigation in prospective studies. TRIAL REGISTRATION: Non-applicable KEY POINTS: • Programmed death-ligand 1 immunohistochemistry has a predictive role in non-small cell lung cancer immunotherapy; however, it is both heterogenous and dynamic. • SUV-based fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography ([18F]FDG-PET/CT) metabolic parameters were significantly higher in primary tumour or lymph node metastases with positive programmed death-ligand 1 expression. • These SUV-based parameters could potentially play an additive role along with other multi-modal biomarkers in selecting patients within a predictive nomogram.

Perceptions of radiologists on structured reporting for cancer imaging-a survey by the European Society of Oncologic Imaging (ESOI).

OBJECTIVES: To assess radiologists' current use of, and opinions on, structured reporting (SR) in oncologic imaging, and to provide recommendations for a structured report template. MATERIALS AND METHODS: An online survey with 28 questions was sent to European Society of Oncologic Imaging (ESOI) members. The questionnaire had four main parts: (1) participant information, e.g., country, workplace, experience, and current SR use; (2) SR design, e.g., numbers of sections and fields, and template use; (3) clinical impact of SR, e.g., on report quality and length, workload, and communication with clinicians; and (4) preferences for an oncology-focused structured CT report. Data analysis comprised descriptive statistics, chi-square tests, and Spearman correlation coefficients. RESULTS: A total of 200 radiologists from 51 countries completed the survey: 57.0% currently utilized SR (57%), with a lower proportion within than outside of Europe (51.0 vs. 72.7%; p = 0.006). Among SR users, the majority observed markedly increased report quality (62.3%) and easier comparison to previous exams (53.5%), a slightly lower error rate (50.9%), and fewer calls/emails by clinicians (78.9%) due to SR. The perceived impact of SR on communication with clinicians (i.e., frequency of calls/emails) differed with radiologists' experience (p < 0.001), and experience also showed low but significant correlations with communication with clinicians (r = - 0.27, p = 0.003), report quality (r = 0.19, p = 0.043), and error rate (r = - 0.22, p = 0.016). Template use also affected the perceived impact of SR on report quality (p = 0.036). CONCLUSION: Radiologists regard SR in oncologic imaging favorably, with perceived positive effects on report quality, error rate, comparison of serial exams, and communication with clinicians. CLINICAL RELEVANCE STATEMENT: Radiologists believe that structured reporting in oncologic imaging improves report quality, decreases the error rate, and enables better communication with clinicians. Implementation of structured reporting in Europe is currently below the international level and needs society endorsement. KEY POINTS: • The majority of oncologic imaging specialists (57% overall; 51% in Europe) use structured reporting in clinical practice. • The vast majority of oncologic imaging specialists use templates (92.1%), which are typically cancer-specific (76.2%). • Structured reporting is perceived to markedly improve report quality, communication with clinicians, and comparison to prior scans.

Development and validation of open-source deep neural networks for comprehensive chest x-ray reading: a retrospective, multicentre study.

BACKGROUND: Artificial intelligence (AI) systems for automated chest x-ray interpretation hold promise for standardising reporting and reducing delays in health systems with shortages of trained radiologists. Yet, there are few freely accessible AI systems trained on large datasets for practitioners to use with their own data with a view to accelerating clinical deployment of AI systems in radiology. We aimed to contribute an AI system for comprehensive chest x-ray abnormality detection. METHODS: In this retrospective cohort study, we developed open-source neural networks, X-Raydar and X-Raydar-NLP, for classifying common chest x-ray findings from images and their free-text reports. Our networks were developed using data from six UK hospitals from three National Health Service (NHS) Trusts (University Hospitals Coventry and Warwickshire NHS Trust, University Hospitals Birmingham NHS Foundation Trust, and University Hospitals Leicester NHS Trust) collectively contributing 2 513 546 chest x-ray studies taken from a 13-year period (2006-19), which yielded 1 940 508 usable free-text radiological reports written by the contemporary assessing radiologist (collectively referred to as the "historic reporters") and 1 896 034 frontal images. Chest x-rays were labelled using a taxonomy of 37 findings by a custom-trained natural language processing (NLP) algorithm, X-Raydar-NLP, from the original free-text reports. X-Raydar-NLP was trained on 23 230 manually annotated reports and tested on 4551 reports from all hospitals. 1 694 921 labelled images from the training set and 89 238 from the validation set were then used to train a multi-label image classifier. Our algorithms were evaluated on three retrospective datasets: a set of exams sampled randomly from the full NHS dataset reported during clinical practice and annotated using NLP (n=103 328); a consensus set sampled from all six hospitals annotated by three expert radiologists (two independent annotators for each image and a third consultant to facilitate disagreement resolution) under research conditions (n=1427); and an independent dataset, MIMIC-CXR, consisting of NLP-annotated exams (n=252 374). FINDINGS: X-Raydar achieved a mean AUC of 0·919 (SD 0·039) on the auto-labelled set, 0·864 (0·102) on the consensus set, and 0·842 (0·074) on the MIMIC-CXR test, demonstrating similar performance to the historic clinical radiologist reporters, as assessed on the consensus set, for multiple clinically important findings, including pneumothorax, parenchymal opacification, and parenchymal mass or nodules. On the consensus set, X-Raydar outperformed historical reporter balanced accuracy with significance on 27 of 37 findings, was non-inferior on nine, and inferior on one finding, resulting in an average improvement of 13·3% (SD 13·1) to 0·763 (0·110), including a mean 5·6% (13·2) improvement in critical findings to 0·826 (0·119). INTERPRETATION: Our study shows that automated classification of chest x-rays under a comprehensive taxonomy can achieve performance levels similar to those of historical reporters and exhibit robust generalisation to external data. The open-sourced neural networks can serve as foundation models for further research and are freely available to the research community. FUNDING: Wellcome Trust.

Patient Reidentification from Chest Radiographs: An Interpretable Deep Metric Learning Approach and Its Applications.

Purpose: To train an explainable deep learning model for patient reidentification in chest radiograph datasets and assess changes in model-perceived patient identity as a marker for emerging radiologic abnormalities in longitudinal image sets. Materials and Methods: This retrospective study used a set of 1 094 537 frontal chest radiographs and free-text reports from 259 152 patients obtained from six hospitals between 2006 and 2019, with validation on the public ChestX-ray14, CheXpert, and MIMIC-CXR datasets. A deep learning model was trained for patient reidentification and assessed on patient identity confirmation, retrieval of patient images from a database based on a query image, and radiologic abnormality prediction in longitudinal image sets. The representation learned was incorporated into a generative adversarial network, allowing visual explanations of the relevant features. Performance was evaluated with sensitivity, specificity, F1 score, Precision at 1, R-Precision, and area under the receiver operating characteristic curve (AUC) for normal and abnormal prediction. Results: Patient reidentification was achieved with a mean F1 score of 0.996 ± 0.001 (2 SD) on the internal test set (26 152 patients) and F1 scores of 0.947-0.993 on the external test data. Database retrieval yielded a mean Precision at 1 score of 0.976 ± 0.005 at 299 × 299 resolution on the internal test set and Precision at 1 scores between 0.868 and 0.950 on the external datasets. Patient sex, age, weight, and other factors were identified as key model features. The model achieved an AUC of 0.73 ± 0.01 for abnormality prediction versus an AUC of 0.58 ± 0.01 for age prediction error. Conclusion: The image features used by a deep learning patient reidentification model for chest radiographs corresponded to intuitive human-interpretable characteristics, and changes in these identifying features over time may act as markers for an emerging abnormality.Keywords: Conventional Radiography, Thorax, Feature Detection, Supervised Learning, Convolutional Neural Network, Principal Component Analysis Supplemental material is available for this article. © RSNA, 2023See also the commentary by Raghu and Lu in this issue.

Weakly supervised segmentation models as explainable radiological classifiers for lung tumour detection on CT images.

PURPOSE: Interpretability is essential for reliable convolutional neural network (CNN) image classifiers in radiological applications. We describe a weakly supervised segmentation model that learns to delineate the target object, trained with only image-level labels ("image contains object" or "image does not contain object"), presenting a different approach towards explainable object detectors for radiological imaging tasks. METHODS: A weakly supervised Unet architecture (WSUnet) was trained to learn lung tumour segmentation from image-level labelled data. WSUnet generates voxel probability maps with a Unet and then constructs an image-level prediction by global max-pooling, thereby facilitating image-level training. WSUnet's voxel-level predictions were compared to traditional model interpretation techniques (class activation mapping, integrated gradients and occlusion sensitivity) in CT data from three institutions (training/validation: n = 412; testing: n = 142). Methods were compared using voxel-level discrimination metrics and clinical value was assessed with a clinician preference survey on data from external institutions. RESULTS: Despite the absence of voxel-level labels in training, WSUnet's voxel-level predictions localised tumours precisely in both validation (precision: 0.77, 95% CI: [0.76-0.80]; dice: 0.43, 95% CI: [0.39-0.46]), and external testing (precision: 0.78, 95% CI: [0.76-0.81]; dice: 0.33, 95% CI: [0.32-0.35]). WSUnet's voxel-level discrimination outperformed the best comparator in validation (area under precision recall curve (AUPR): 0.55, 95% CI: [0.49-0.56] vs. 0.23, 95% CI: [0.21-0.25]) and testing (AUPR: 0.40, 95% CI: [0.38-0.41] vs. 0.36, 95% CI: [0.34-0.37]). Clinicians preferred WSUnet predictions in most instances (clinician preference rate: 0.72 95% CI: [0.68-0.77]). CONCLUSION: Weakly supervised segmentation is a viable approach by which explainable object detection models may be developed for medical imaging. CRITICAL RELEVANCE STATEMENT: WSUnet learns to segment images at voxel level, training only with image-level labels. A Unet backbone first generates a voxel-level probability map and then extracts the maximum voxel prediction as the image-level prediction. Thus, training uses only image-level annotations, reducing human workload. WSUnet's voxel-level predictions provide a causally verifiable explanation for its image-level prediction, improving interpretability. KEY POINTS: • Explainability and interpretability are essential for reliable medical image classifiers. • This study applies weakly supervised segmentation to generate explainable image classifiers. • The weakly supervised Unet inherently explains its image-level predictions at voxel level.

Diffusion-weighted imaging complements T2-weighted MRI for tumour response assessment in squamous anal carcinoma.

OBJECTIVES: A published tumour regression grade (TRG) score for squamous anal carcinoma treated with definitive chemoradiotherapy based on T2-weighted MRI yields a high proportion of indeterminate responses (TRG-3). We investigate whether the addition of diffusion-weighted imaging (DWI) improves tumour response assessment in the early post treatment period. MATERIALS AND METHODS: This retrospective observational study included squamous anal carcinoma patients undergoing MRI before and within 3 months of completing chemoradiotherapy from 2009 to 2020. Four independent radiologists (1-20 years' experience) scored MRI studies using a 5-point TRG system (1 = complete response; 5 = no response) based on T2-weighted sequences alone, and then after a 12-week washout period, using a 5-point DWI-TRG system based on T2-weighted and DWI. Scoring confidence was recorded on a 5-point scale (1 = low; 5 = high) for each reading and compared using the Wilcoxon test. Indeterminate scores (TRG-3) from each reading session were compared using the McNemar test. Interobserver agreement was assessed using kappa statistics. RESULTS: Eighty-five patients were included (mean age, 59 years ± 12 [SD]; 55 women). T2-weighted TRG-3 scores from all readers combined halved from 24% (82/340) to 12% (41/340) with DWI (p < 0.001). TRG-3 scores changed most frequently (41%, 34/82) to DWI-TRG-2 (excellent response). Complete tumour response was recorded clinically in 77/85 patients (91%). Scoring confidence increased using DWI (p < 0.001), with scores of 4 or 5 in 84% (287/340). Interobserver agreement remained fair to moderate (kappa range, 0.28-0.58). CONCLUSION: DWI complements T2-weighted MRI by reducing the number of indeterminate tumour responses (TRG-3). DWI increases radiologist's scoring confidence. CLINICAL RELEVANCE STATEMENT: Diffusion-weighted imaging improves T2-weighted tumour response assessment in squamous anal cancer, halving the number of indeterminate responses in the early post treatment period, and increases radiologists' confidence. KEY POINTS: Tumour response based on T2-weighted MRI is often indeterminate in squamous anal carcinoma. Diffusion-weighted imaging alongside T2-weighted MRI halved indeterminate tumour regression grade scores assigned by four radiologists from 24 to 12%. Scoring confidence of expert and non-expert radiologists increased with the inclusion of diffusion-weighted imaging.

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.

Association of dynamic contrast-enhanced MRI and 18F-Fluorodeoxyglucose PET/CT parameters with neoadjuvant therapy response and survival in esophagogastric cancer.

INTRODUCTION: Better predictive markers are needed to deliver individualized care for patients with primary esophagogastric cancer. This exploratory study aimed to assess whether pre-treatment imaging parameters from dynamic contrast-enhanced MRI and 18F-fluorodeoxyglucose (18F-FDG) PET/CT are associated with response to neoadjuvant therapy or outcome. MATERIALS AND METHODS: Following ethical approval and informed consent, prospective participants underwent dynamic contrast-enhanced MRI and 18F-FDG PET/CT prior to neoadjuvant chemotherapy/chemoradiotherapy ± surgery. Vascular dynamic contrast-enhanced MRI and metabolic 18F-FDG PET parameters were compared by tumor characteristics using Mann Whitney U test and with pathological response (Mandard tumor regression grade), recurrence-free and overall survival using logistic regression modelling, adjusting for predefined clinical variables. RESULTS: 39 of 47 recruited participants (30 males; median age 65 years, IQR: 54, 72 years) were included in the final analysis. The tumor vascular-metabolic ratio was higher in patients remaining node positive following neoadjuvant therapy (median tumor peak enhancement/SUVmax ratio: 0.052 vs. 0.023, p = 0.02). In multivariable analysis adjusted for age, gender, pre-treatment tumor and nodal stage, peak enhancement (highest gadolinium concentration value prior to contrast washout) was associated with pathological tumor regression grade. The odds of response decreased by 5% for each 0.01 unit increase (OR 0.95; 95% CI: 0.90, 1.00, p = 0.04). No 18F-FDG PET/CT parameters were predictive of pathological tumor response. No relationships between pre-treatment imaging and survival were identified. CONCLUSION: Pre-treatment esophagogastric tumor vascular and metabolic parameters may provide additional information in assessing response to neoadjuvant therapy.

Inter-rater and intra-rater agreement of [99mTc]-labelled NM-01, a single-domain programmed death-ligand 1 (PD-L1) antibody, using quantitative SPECT/CT in non-small cell lung cancer.

BACKGROUND: Immune checkpoint inhibitors, including those against programmed cell death protein-1 (PD-1) or its ligand (PD-L1), are routinely used to treat non-small cell lung cancer (NSCLC). PD-L1 is a validated prognostic and predictive immunohistochemical biomarker of anti-PD-1/PD-L1 therapy but displays temporospatial heterogeneity of expression. Non-invasive radiopharmaceutical techniques, including technetium-99m [99mTc]-labelled anti-PD-L1 single-domain antibody (NM-01) SPECT/CT, have the potential to improve the predictive value of PD-L1 assessment. This study aims to determine the inter- and intra-rater agreement of the quantitative measurement of [99mTc]NM-01 SPECT/CT in NSCLC. METHODS: Participants (n = 14) with untreated advanced NSCLC underwent [99mTc]NM-01 SPECT/CT at baseline (n = 3) or at baseline plus 9-week follow-up (n = 11). [99mTc]NM-01 uptake (of primary lung, lymph node, thoracic and distant metastases, and healthy reference tissues) was measured using SUVmax and malignant lesion-to-blood pool ratios with Siemens xSPECT Broad Quantification software by three independent raters. Intraclass correlation coefficients (ICC) were calculated and Bland-Altman plot analysis performed to determine inter- and intra-rater agreement. RESULTS: There was excellent inter-rater agreement of manual freehand SUVmax scores of primary lung tumour (T; n = 25; ICC 1.00; 95% CI 0.99-1.00), individual lymph node metastases (LN; n = 56; ICC 0.97; 95% CI 0.95-0.98), thoracic metastases (ThMet; n = 9; ICC 0.94; 95% CI 0.83-0.99) and distant metastases (DisMet; n = 21; ICC 0.91; 95% CI 0.83-0.96). The inter-rater ICCs of tumour-to-blood pool (T:BP), LN:BP, ThMet:BP and DisMet:BP measures of [99mTc]NM-01 uptake also demonstrated good or excellent agreement. Manual freehand scoring of T, LN, ThMet, DisMet and their ratios using [99mTc]NM-01 SPECT/CT following a 28-day interval was consistent for all raters with good or excellent intra-rater agreement demonstrated (ICCs range 0.86-1.00). CONCLUSION: Quantitative assessment of [99mTc]NM-01 SPECT/CT in NSCLC, using SUVmax of malignant primary or metastatic lesions and their ratios with healthy reference tissues, demonstrated good or excellent inter- and intra-rater agreement in this study. Further validation with ongoing and future larger cohort studies is now warranted. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov identifier no. NCT04436406 (registered 18th June 2020; available at https://clinicaltrials.gov/ct2/show/NCT04436406 ) and NCT04992715 (registered 5th August 2021; available at https://clinicaltrials.gov/ct2/show/NCT04992715 ).

Temporary treatment cessation versus continuation of first-line tyrosine kinase inhibitor in patients with advanced clear cell renal cell carcinoma (STAR): an open-label, non-inferiority, randomised, controlled, phase 2/3 trial.

BACKGROUND: Temporary drug treatment cessation might alleviate toxicity without substantially compromising efficacy in patients with cancer. We aimed to determine if a tyrosine kinase inhibitor drug-free interval strategy was non-inferior to a conventional continuation strategy for first-line treatment of advanced clear cell renal cell carcinoma. METHODS: This open-label, non-inferiority, randomised, controlled, phase 2/3 trial was done at 60 hospital sites in the UK. Eligible patients (aged ≥18 years) had histologically confirmed clear cell renal cell carcinoma, inoperable loco-regional or metastatic disease, no previous systemic therapy for advanced disease, uni-dimensionally assessed Response Evaluation Criteria in Solid Tumours-defined measurable disease, and an Eastern Cooperative Oncology Group performance status of 0-1. Patients were randomly assigned (1:1) at baseline to a conventional continuation strategy or drug-free interval strategy using a central computer-generated minimisation programme incorporating a random element. Stratification factors were Memorial Sloan Kettering Cancer Center prognostic group risk factor, sex, trial site, age, disease status, tyrosine kinase inhibitor, and previous nephrectomy. All patients received standard dosing schedules of oral sunitinib (50 mg per day) or oral pazopanib (800 mg per day) for 24 weeks before moving into their randomly allocated group. Patients allocated to the drug-free interval strategy group then had a treatment break until disease progression, when treatment was re-instated. Patients in the conventional continuation strategy group continued treatment. Patients, treating clinicians, and the study team were aware of treatment allocation. The co-primary endpoints were overall survival and quality-adjusted life-years (QALYs); non-inferiority was shown if the lower limit of the two-sided 95% CI for the overall survival hazard ratio (HR) was 0·812 or higher and if the lower limit of the two-sided 95% CI of the marginal difference in mean QALYs was -0·156 or higher. The co-primary endpoints were assessed in the intention-to-treat (ITT) population, which included all randomly assigned patients, and the per-protocol population, which excluded patients in the ITT population with major protocol violations and who did not begin their randomisation allocation as per the protocol. Non-inferiority was to be concluded if it was met for both endpoints in both analysis populations. Safety was assessed in all participants who received a tyrosine kinase inhibitor. The trial was registered with ISRCTN, 06473203, and EudraCT, 2011-001098-16. FINDINGS: Between Jan 13, 2012, and Sept 12, 2017, 2197 patients were screened for eligibility, of whom 920 were randomly assigned to the conventional continuation strategy (n=461) or the drug-free interval strategy (n=459; 668 [73%] male and 251 [27%] female; 885 [96%] White and 23 [3%] non-White). The median follow-up time was 58 months (IQR 46-73 months) in the ITT population and 58 months (46-72) in the per-protocol population. 488 patients continued on the trial after week 24. For overall survival, non-inferiority was demonstrated in the ITT population only (adjusted HR 0·97 [95% CI 0·83 to 1·12] in the ITT population; 0·94 [0·80 to 1·09] in the per-protocol population). Non-inferiority was demonstrated for QALYs in the ITT population (n=919) and per-protocol (n=871) population (marginal effect difference 0·06 [95% CI -0·11 to 0·23] for the ITT population; 0·04 [-0·14 to 0·21] for the per-protocol population). The most common grade 3 or worse adverse events were hypertension (124 [26%] of 485 patients in the conventional continuation strategy group vs 127 [29%] of 431 patients in the drug-free interval strategy group); hepatotoxicity (55 [11%] vs 48 [11%]); and fatigue (39 [8%] vs 63 [15%]). 192 (21%) of 920 participants had a serious adverse reaction. 12 treatment-related deaths were reported (three patients in the conventional continuation strategy group; nine patients in the drug-free interval strategy group) due to vascular (n=3), cardiac (n=3), hepatobiliary (n=3), gastrointestinal (n=1), or nervous system (n=1) disorders, and from infections and infestations (n=1). INTERPRETATION: Overall, non-inferiority between groups could not be concluded. However, there seemed to be no clinically meaningful reduction in life expectancy between the drug-free interval strategy and conventional continuation strategy groups and treatment breaks might be a feasible and cost-effective option with lifestyle benefits for patients during tyrosine kinase inhibitor therapy in patients with renal cell carcinoma. FUNDING: UK National Institute for Health and Care Research.

Research should remain a priority in 21st century radiology recruitment to training.

Research drives innovation, however, recently Clinical Radiology has been overwhelmed by increased clinical demand, workforce shortages and lack of funding/protected research time. The newly released 2023 radiology speciality application process gives research a lower priority compared to other domains such as audit which is concerning given the current lack of research culture within the speciality. It is vital for the future radiology workforce to engage with research and in order to fulfil the Royal College of Radiologist's new curriculum aims of strengthening research within training, we must continue attracting the brightest and best candidates and ensure research remains a priority.

Role of 3'-Deoxy-3'-[18F] Fluorothymidine Positron Emission Tomography-Computed Tomography as a Predictive Biomarker in Argininosuccinate Synthetase 1-Deficient Thoracic Cancers Treated With Pegargiminase.

Introduction: Pegargiminase (ADI-PEG 20I) degrades arginine in patients with argininosuccinate synthetase 1-deficient malignant pleural mesothelioma (MPM) and NSCLC. Imaging with proliferation biomarker 3'-deoxy-3'-[18F] fluorothymidine (18F-FLT) positron emission tomography (PET)-computed tomography (CT) was performed in a phase 1 study of pegargiminase with pemetrexed and cisplatin (ADIPemCis). The aim was to determine whether FLT PET-CT predicts treatment response earlier than CT. Methods: A total of 18 patients with thoracic malignancies (10 MPM; eight NSCLC) underwent imaging. FLT PET-CT was performed at baseline (PET1), 24 hours post-pegargiminase monotherapy (PET2), post one cycle of ADIPemCis (PET3), and at end of treatment (EOT, PET4). CT was performed at baseline (CT1) and EOT (CT4). CT4 (modified) Response Evaluation Criteria in Solid Tumors (RECIST) response was compared with treatment response on PET (changes in maximum standardized uptake value [SUVmax] on European Organisation for Research and Treatment of Cancer-based criteria). Categorical responses (progression, partial response, and stable disease) for PET2, PET3, and PET4 were compared against CT using Cohen's kappa. Results: ADIPemCis treatment response resulted in 22% mean decrease in size between CT1 and CT4 and 37% mean decrease in SUVmax between PET1 and PET4. PET2 agreed with CT4 response in 62% (8 of 13) of patients (p = 0.043), although decrease in proliferation (SUVmax) did not precede decrease in size (RECIST). Partial responses on FLT PET-CT were detected in 20% (3 of 15) of participants at PET2 and 69% (9 of 13) at PET4 with good agreement between modalities in MPM at EOT. Conclusions: Early FLT imaging (PET2) agrees with EOT CT results in nearly two-thirds of patients. Both early and late FLT PET-CT provide evidence of response to ADIPemCis therapy in MPM and NSCLC. We provide first-in-human FLT PET-CT data in MPM, indicating it is comparable with modified RECIST.