Inter- and Intra-Patient Repeatability of Radiomic Features from Multiparametric Whole-Body MRI in Patients with Metastatic Prostate Cancer.

(1) Background: We assessed the test-re-test repeatability of radiomics in metastatic castration-resistant prostate cancer (mCPRC) bone disease on whole-body diffusion-weighted (DWI) and T1-weighted Dixon MRI. (2) Methods: In 10 mCRPC patients, 1.5 T MRI, including DWI and T1-weighted gradient-echo Dixon sequences, was performed twice on the same day. Apparent diffusion coefficient (ADC) and relative fat-fraction-percentage (rFF%) maps were calculated. Per study, up to 10 target bone metastases were manually delineated on DWI and Dixon images. All 106 radiomic features included in the Pyradiomics toolbox were derived for each target volume from the ADC and rFF% maps. To account for inter- and intra-patient measurement repeatability, the log-transformed individual target measurements were fitted to a hierarchical model, represented as a Bayesian network. Repeatability measurements, including the intraclass correlation coefficient (ICC), were derived. Feature ICCs were compared with mean ADC and rFF ICCs. (3) Results: A total of 65 DWI and 47 rFF% targets were analysed. There was no significant bias for any features. Pairwise correlation revealed fifteen ADC and fourteen rFF% feature sub-groups, without specific patterns between feature classes. The median intra-patient ICC was generally higher than the inter-patient ICC. Features that describe extremes in voxel values (minimum, maximum, range, skewness, and kurtosis) showed generally lower ICCs. Several mostly shape-based texture features were identified, which showed high inter- and intra-patient ICCs when compared with the mean ADC or mean rFF%, respectively. (4) Conclusions: Pyradiomics texture features of mCRPC bone metastases varied greatly in inter- and intra-patient repeatability. Several features demonstrated good repeatability, allowing for further exploration as diagnostic parameters in mCRPC bone disease.

Validated machine learning tools to distinguish immune checkpoint inhibitor, radiotherapy, COVID-19 and other infective pneumonitis.

BACKGROUND: Pneumonitis is a well-described, potentially disabling, or fatal adverse effect associated with both immune checkpoint inhibitors (ICI) and thoracic radiotherapy. Accurate differentiation between checkpoint inhibitor pneumonitis (CIP) radiation pneumonitis (RP), and infective pneumonitis (IP) is crucial for swift, appropriate, and tailored management to achieve optimal patient outcomes. However, correct diagnosis is often challenging, owing to overlapping clinical presentations and radiological patterns. METHODS: In this multi-centre study of 455 patients, we used machine learning with radiomic features extracted from chest CT imaging to develop and validate five models to distinguish CIP and RP from COVID-19, non-COVID-19 infective pneumonitis, and each other. Model performance was compared to that of two radiologists. RESULTS: Models to distinguish RP from COVID-19, CIP from COVID-19 and CIP from non-COVID-19 IP out-performed radiologists (test set AUCs of 0.92 vs 0.8 and 0.8; 0.68 vs 0.43 and 0.4; 0.71 vs 0.55 and 0.63 respectively). Models to distinguish RP from non-COVID-19 IP and CIP from RP were not superior to radiologists but demonstrated modest performance, with test set AUCs of 0.81 and 0.8 respectively. The CIP vs RP model performed less well on patients with prior exposure to both ICI and radiotherapy (AUC 0.54), though the radiologists also had difficulty distinguishing this test cohort (AUC values 0.6 and 0.6). CONCLUSION: Our results demonstrate the potential utility of such tools as a second or concurrent reader to support oncologists, radiologists, and chest physicians in cases of diagnostic uncertainty. Further research is required for patients with exposure to both ICI and thoracic radiotherapy.

Predicting cervical cancer target motion using a multivariate regression model to enable patient selection for adaptive external beam radiotherapy.

Background and purpose: Interfraction motion during cervical cancer radiotherapy is substantial in some patients, minimal in others. Non-adaptive plans may miss the target and/or unnecessarily irradiate normal tissue. Adaptive radiotherapy leads to superior dose-volume metrics but is resource-intensive. The aim of this study was to predict target motion, enabling patient selection and efficient resource allocation. Materials and methods: Forty cervical cancer patients had CT with full-bladder (CT-FB) and empty-bladder (CT-EB) at planning, and daily cone-beam CTs (CBCTs). The low-risk clinical target volume (CTVLR) was contoured. Mean coverage of the daily CTVLR by the CT-FB CTVLR was calculated for each patient. Eighty-three investigated variables included measures of organ geometry, patient, tumour and treatment characteristics. Models were trained on 29 patients (171 fractions). The Two-CT multivariate model could use all available data. The Single-CT multivariate model excluded data from the CT-EB. A univariate model was trained using the distance moved by the uterine fundus tip between CTs, the only method of patient selection found in published cervix plan-of-the-day studies. Models were tested on 11 patients (68 fractions). Accuracy in predicting mean coverage was reported as mean absolute error (MAE), mean squared error (MSE) and R2. Results: The Two-CT model was based upon rectal volume, dice similarity coefficient between CT-FB and CT-EB CTVLR, and uterine thickness. The Single-CT model was based upon rectal volume, uterine thickness and tumour size. Both performed better than the univariate model in predicting mean coverage (MAE 7 %, 7 % and 8 %; MSE 82 %2, 65 %2, 110 %2; R2 0.2, 0.4, -0.1). Conclusion: Uterocervix motion is complex and multifactorial. We present two multivariate models which predicted motion with reasonable accuracy using pre-treatment information, and outperformed the only published method.

Deep Learning for Delineation of the Spinal Canal in Whole-Body Diffusion-Weighted Imaging: Normalising Inter- and Intra-Patient Intensity Signal in Multi-Centre Datasets.

BACKGROUND: Whole-Body Diffusion-Weighted Imaging (WBDWI) is an established technique for staging and evaluating treatment response in patients with multiple myeloma (MM) and advanced prostate cancer (APC). However, WBDWI scans show inter- and intra-patient intensity signal variability. This variability poses challenges in accurately quantifying bone disease, tracking changes over follow-up scans, and developing automated tools for bone lesion delineation. Here, we propose a novel automated pipeline for inter-station, inter-scan image signal standardisation on WBDWI that utilizes robust segmentation of the spinal canal through deep learning. METHODS: We trained and validated a supervised 2D U-Net model to automatically delineate the spinal canal (both the spinal cord and surrounding cerebrospinal fluid, CSF) in an initial cohort of 40 patients who underwent WBDWI for treatment response evaluation (80 scans in total). Expert-validated contours were used as the target standard. The algorithm was further semi-quantitatively validated on four additional datasets (three internal, one external, 207 scans total) by comparing the distributions of average apparent diffusion coefficient (ADC) and volume of the spinal cord derived from a two-component Gaussian mixture model of segmented regions. Our pipeline subsequently standardises WBDWI signal intensity through two stages: (i) normalisation of signal between imaging stations within each patient through histogram equalisation of slices acquired on either side of the station gap, and (ii) inter-scan normalisation through histogram equalisation of the signal derived within segmented spinal canal regions. This approach was semi-quantitatively validated in all scans available to the study (N = 287). RESULTS: The test dice score, precision, and recall of the spinal canal segmentation model were all above 0.87 when compared to manual delineation. The average ADC for the spinal cord (1.7 × 10-3 mm2/s) showed no significant difference from the manual contours. Furthermore, no significant differences were found between the average ADC values of the spinal cord across the additional four datasets. The signal-normalised, high-b-value images were visualised using a fixed contrast window level and demonstrated qualitatively better signal homogeneity across scans than scans that were not signal-normalised. CONCLUSION: Our proposed intensity signal WBDWI normalisation pipeline successfully harmonises intensity values across multi-centre cohorts. The computational time required is less than 10 s, preserving contrast-to-noise and signal-to-noise ratios in axial diffusion-weighted images. Importantly, no changes to the clinical MRI protocol are expected, and there is no need for additional reference MRI data or follow-up scans.

The value of baseline 18F-sodium fluoride and 18F-choline PET activity for identifying responders to radium-223 treatment in castration-resistant prostate cancer bone metastases.

OBJECTIVES: To investigate whether baseline 18F-sodium fluoride (NaF) and 18F-choline PET activity is associated with metastatic castration-resistant prostate cancer (mCRPC) global and individual bone metastases' DWI MR imaging response to radium-223 treatment. METHODS: Thirty-six bone-only mCRPC patients were prospectively recruited from three centers. Whole-body (WB)-MRI with DWI and 18F-NaF and 18F-choline PET/CT were performed at therapy baseline and 8-week intervals. In each patient, bone disease median global (g)ADC change between baseline and follow-up was calculated. Additionally, up to five bone target lesions per patient were delineated and individual median ADC change recorded. An ADC increase > 30% defined response per-patient and per-lesion. For the same targets, baseline 18F-NaF and 18F-choline PET SUVmax were recorded. Mean SUVmax across patient targets was correlated with gADC change and lesion SUVmax with per-lesion ADC change. RESULTS: A total of 133 lesions in 36 patients (14 responders) were analyzed. 18F-NaF PET per-patient mean SUVmax was significantly higher in responders (median = 56.0 versus 38.7 in non-responders; p = 0.008), with positive correlation between SUVmax and gADC increase (rho = 0.42; p = 0.015). A 48.7 SUVmax threshold identified responders with 77% sensitivity and 75% specificity. Baseline 18F-NaF PET per-lesion SUVmax was higher in responding metastases (median = 51.6 versus 31.8 in non-responding metastases; p = 0.001), with positive correlation between baseline lesion SUVmax and ADC increase (rho = 0.39; p < 0.001). A 36.8 SUVmax threshold yielded 72% sensitivity and 63% specificity. No significant association was found between baseline 18F-choline PET SUVmax and ADC response on a per-patient (p = 0.164) or per-lesion basis (p = 0.921). CONCLUSION: 18F-NaF PET baseline SUVmax of target mCRPC bone disease showed significant association with response to radium-223 defined by ADC change. CLINICAL RELEVANCE STATEMENT: 18F-sodium fluoride PET/CT baseline maximum SUV of castration-resistant prostate cancer bone metastases could be used as a predictive biomarker for response to radium-223 therapy. KEY POINTS: • 18F-sodium fluoride PET baseline SUVmax of castration-resistant prostate cancer bone metastases showed significant association with response to radium-223. • Baseline 18F-sodium fluoride PET can improve patient selection for radium-223 therapy. • Change in whole-body DWI parameters can be used for response correlation with baseline 18F-sodium fluoride PET SUVmax in castration-resistant prostate cancer bone metastases.

Deep Learning Framework with Multi-Head Dilated Encoders for Enhanced Segmentation of Cervical Cancer on Multiparametric Magnetic Resonance Imaging.

T2-weighted magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) are essential components of cervical cancer diagnosis. However, combining these channels for the training of deep learning models is challenging due to image misalignment. Here, we propose a novel multi-head framework that uses dilated convolutions and shared residual connections for the separate encoding of multiparametric MRI images. We employ a residual U-Net model as a baseline, and perform a series of architectural experiments to evaluate the tumor segmentation performance based on multiparametric input channels and different feature encoding configurations. All experiments were performed on a cohort of 207 patients with locally advanced cervical cancer. Our proposed multi-head model using separate dilated encoding for T2W MRI and combined b1000 DWI and apparent diffusion coefficient (ADC) maps achieved the best median Dice similarity coefficient (DSC) score, 0.823 (confidence interval (CI), 0.595-0.797), outperforming the conventional multi-channel model, DSC 0.788 (95% CI, 0.568-0.776), although the difference was not statistically significant (p > 0.05). We investigated channel sensitivity using 3D GRAD-CAM and channel dropout, and highlighted the critical importance of T2W and ADC channels for accurate tumor segmentation. However, our results showed that b1000 DWI had a minor impact on the overall segmentation performance. We demonstrated that the use of separate dilated feature extractors and independent contextual learning improved the model's ability to reduce the boundary effects and distortion of DWI, leading to improved segmentation performance. Our findings could have significant implications for the development of robust and generalizable models that can extend to other multi-modal segmentation applications.

Image quality in whole-body MRI using the MY-RADS protocol in a prospective multi-centre multiple myeloma study.

BACKGROUND: The Myeloma Response Assessment and Diagnosis System (MY-RADS) guidelines establish a standardised acquisition and analysis pipeline for whole-body MRI (WB-MRI) in patients with myeloma. This is the first study to assess image quality in a multi-centre prospective trial using MY-RADS. METHODS: The cohort consisted of 121 examinations acquired across ten sites with a range of prior WB-MRI experience, three scanner manufacturers and two field strengths. Image quality was evaluated qualitatively by a radiologist and quantitatively using a semi-automated pipeline to quantify common artefacts and image quality issues. The intra- and inter-rater repeatability of qualitative and quantitative scoring was also assessed. RESULTS: Qualitative radiological scoring found that the image quality was generally good, with 94% of examinations rated as good or excellent and only one examination rated as non-diagnostic. There was a significant correlation between radiological and quantitative scoring for most measures, and intra- and inter-rater repeatability were generally good. When the quality of an overall examination was low, this was often due to low quality diffusion-weighted imaging (DWI), where signal to noise ratio (SNR), anterior thoracic signal loss and brain geometric distortion were found as significant predictors of examination quality. CONCLUSIONS: It is possible to successfully deliver a multi-centre WB-MRI study using the MY-RADS protocol involving scanners with a range of manufacturers, models and field strengths. Quantitative measures of image quality were developed and shown to be significantly correlated with radiological assessment. The SNR of DW images was identified as a significant factor affecting overall examination quality. TRIAL REGISTRATION: ClinicalTrials.gov, NCT03188172 , Registered on 15 June 2017. CRITICAL RELEVANCE STATEMENT: Good overall image quality, assessed both qualitatively and quantitatively, can be achieved in a multi-centre whole-body MRI study using the MY-RADS guidelines. KEY POINTS: • A prospective multi-centre WB-MRI study using MY-RADS can be successfully delivered. • Quantitative image quality metrics were developed and correlated with radiological assessment. • SNR in DWI was identified as a significant predictor of quality, allowing for rapid quality adjustment.

Radium-223 in metastatic castration-resistant prostate cancer: whole-body diffusion-weighted magnetic resonance imaging scanning to assess response.

BACKGROUND: Radium-223 is a bone-seeking, ɑ-emitting radionuclide used to treat men with bone metastases from castration-resistant prostate cancer. Sclerotic bone lesions cannot be evaluated using Response Evaluation Criteria in Solid Tumors. Therefore, imaging response biomarkers are needed. METHODS: We conducted a phase 2 randomized trial to assess disease response to radium-223. Men with metastatic castration-resistant prostate cancer and bone metastases were randomly allocated to 55 or 88 kBq/kg radium-223 every 4 weeks for 6 cycles. Whole-body diffusion-weighted magnetic resonance imaging (DWI) was performed at baseline, at cycles 2 and 4, and after treatment. The primary endpoint was defined as a 30% increase in global median apparent diffusion coefficient. RESULTS: Disease response on DWI was seen in 14 of 36 evaluable patients (39%; 95% confidence interval = 23% to 56%), with marked interpatient and intrapatient heterogeneity of response. There was an association between prostate-specific antigen response and MRI response (odds ratio = 18.5, 95% confidence interval = 1.32 to 258, P = .013). Mean administered activity of radium-223 per cycle was not associated with global MRI response (P = .216) but was associated with DWI response using a 5-target-lesion evaluation (P = .007). In 26 of 36 (72%) patients, new bone metastases, not present at baseline, were seen on DWI scans during radium-223 treatment. CONCLUSIONS: DWI is useful for assessment of disease response in bone. Response to radium-223 is heterogeneous, both between patients and between different metastases in the same patient. New bone metastases appear during radium-223 treatment.The REASURE trial is registered under ISRCTN17805587.

Repeatability of quantitative individual lesion and total disease multiparametric whole-body MRI measurements in prostate cancer bone metastases.

OBJECTIVES: To assess the repeatability of quantitative multiparametric whole-body MRI (mpWB-MRI) parameters in advanced prostate cancer (APC) bone metastases. METHODS: 1.5T MRI was performed twice on the same day in 10 APC patients. MpWB-MRI-included diffusion weighted imaging (DWI) and T1-weighted gradient-echo 2-point Dixon sequences. ADC and relative fat-fraction percentage (rFF%) maps were calculated, respectively. A radiologist delineated up to 10 target bone metastases per study. Means of ADC, b900 signal intensity(SI), normalised b900 SI, rFF% and maximum diameter (MD) for each target lesion and overall parameter averages across all targets per patient were recorded. The total disease volume (tDV in ml) was manually delineated on b900 images and mean global (g)ADC was derived. Bland-Altman analyses were performed with calculation of 95% repeatability coefficients (RC). RESULTS: Seventy-three individual targets (median MD 26 mm) were included. Lesion mean ADC RC was 12.5%, mean b900 SI RC 137%, normalised mean b900 SI RC 110%, rFF% RC 3.2 and target MD RC 5.5 mm (16.3%). Patient target lesion average mean ADC RC was 6.4%, b900 SI RC 104% and normalised mean b900 SI RC 39.6%. Target average rFF% RC was 1.8, average MD RC 1.3 mm (4.8%). tDV segmentation RC was 6.4% and mean gADC RC 5.3%. CONCLUSIONS: APC bone metastases' ADC, rFF% and maximum diameter, tDV and gADC show good repeatability. ADVANCES IN KNOWLEDGE: APC bone metastases' mean ADC and rFF% measurements of single lesions and global disease volumes are repeatable, supporting their potential role as quantitative biomarkers in metastatic bone disease.

Pseudoprogression in patients with uterine leiomyosarcoma treated with first-line single-agent doxorubicin.

AIM: To evaluate the incidence of pseudoprogression in patients with metastatic or inoperable uterine leiomyosarcoma (LMS) treated with first-line single-agent doxorubicin. METHODS: The Royal Marsden NHS Foundation Trust Sarcoma Unit database was searched to identify all patients with metastatic or inoperable LMS treated with first-line doxorubicin from January 2006 to January 2022. Patients with available computed tomography scans performed at baseline and during doxorubicin therapy were included. Response evaluation criteria in solid tumours v1.1 and Choi criteria were applied. Any increase in the sum of the longest diameter that decreased on the subsequent scan was labelled as pseudoprogression. RESULTS: The total number of patients evaluated was 52. In total, 19% (n = 10) of patients treated with doxorubicin showed pseudoprogression. However, pseudoprogression at the time of the second scan was not associated with time to doxorubicin failure. Choi criteria identified 30% (n = 3) of pseudoprogressors as responding. CONCLUSION: Despite the use of doxorubicin as first-line therapy for soft-tissue sarcomas for over 40 years, pseudoprogression has not been described. This retrospective study shows that pseudoprogression occurs in 19% of patients with metastatic/inoperable uterine LMS treated with first-line doxorubicin. Choi criteria were not consistently able to differentiate pseudoprogression from true progression. It is imperative that oncologists and radiologists are aware of this as symptomatically stable/improving patients may benefit from continued treatment despite initial radiological growth in tumour size.

Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and deep learning in the era of COVID-19.

Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications.

Optimisation of b-values for the accurate estimation of the apparent diffusion coefficient (ADC) in whole-body diffusion-weighted MRI in patients with metastatic melanoma.

OBJECTIVE: To establish optimised diffusion weightings ('b-values') for acquisition of whole-body diffusion-weighted MRI (WB-DWI) for estimation of the apparent diffusion coefficient (ADC) in patients with metastatic melanoma (MM). Existing recommendations for WB-DWI have not been optimised for the tumour properties in MM; therefore, evaluation of acquisition parameters is essential before embarking on larger studies. METHODS: Retrospective clinical data and phantom experiments were used. Clinical data comprised 125 lesions from 14 examinations in 11 patients with multifocal MM, imaged before and/or after treatment with immunotherapy at a single institution. ADC estimates from these data were applied to a model to estimate the optimum b-value. A large non-diffusing phantom was used to assess eddy current-induced geometric distortion. RESULTS: Considering all tumour sites from pre- and post-treatment examinations together, metastases exhibited a large range of mean ADC values, [0.67-1.49] × 10-3 mm2/s, and the optimum high b-value (bhigh) for ADC estimation was 1100 (10th-90th percentile: 740-1790) s/mm2. At higher b-values, geometric distortion increased, and longer echo times were required, leading to reduced signal. CONCLUSIONS: Theoretical optimisation gave an optimum bhigh of 1100 (10th-90th percentile: 740-1790) s/mm2 for ADC estimation in MM, with the large range of optimum b-values reflecting the wide range of ADC values in these tumours. Geometric distortion and minimum echo time increase at higher b-values and are not included in the theoretical optimisation; bhigh in the range 750-1100 s/mm2 should be adopted to maintain acceptable image quality but performance should be evaluated for a specific scanner. KEY POINTS: • Theoretical optimisation gave an optimum high b-value of 1100 (10th-90th percentile: 740-1790) s/mm2 for ADC estimation in metastatic melanoma. • Considering geometric distortion and minimum echo time (TE), a b-value in the range 750-1100 s/mm2 is recommended. • Sites should evaluate the performance of specific scanners to assess the effect of geometric distortion and minimum TE.

A radiomics-based decision support tool improves lung cancer diagnosis in combination with the Herder score in large lung nodules.

BACKGROUND: Large lung nodules (≥15 mm) have the highest risk of malignancy, and may exhibit important differences in phenotypic or clinical characteristics to their smaller counterparts. Existing risk models do not stratify large nodules well. We aimed to develop and validate an integrated segmentation and classification pipeline, incorporating deep-learning and traditional radiomics, to classify large lung nodules according to cancer risk. METHODS: 502 patients from five U.K. centres were recruited to the large-nodule arm of the retrospective LIBRA study between July 2020 and April 2022. 838 CT scans were used for model development, split into training and test sets (70% and 30% respectively). An nnUNet model was trained to automate lung nodule segmentation. A radiomics signature was developed to classify nodules according to malignancy risk. Performance of the radiomics model, termed the large-nodule radiomics predictive vector (LN-RPV), was compared to three radiologists and the Brock and Herder scores. FINDINGS: 499 patients had technically evaluable scans (mean age 69 ± 11, 257 men, 242 women). In the test set of 252 scans, the nnUNet achieved a DICE score of 0.86, and the LN-RPV achieved an AUC of 0.83 (95% CI 0.77-0.88) for malignancy classification. Performance was higher than the median radiologist (AUC 0.75 [95% CI 0.70-0.81], DeLong p = 0.03). LN-RPV was robust to auto-segmentation (ICC 0.94). For baseline solid nodules in the test set (117 patients), LN-RPV had an AUC of 0.87 (95% CI 0.80-0.93) compared to 0.67 (95% CI 0.55-0.76, DeLong p = 0.002) for the Brock score and 0.83 (95% CI 0.75-0.90, DeLong p = 0.4) for the Herder score. In the international external test set (n = 151), LN-RPV maintained an AUC of 0.75 (95% CI 0.63-0.85). 18 out of 22 (82%) malignant nodules in the Herder 10-70% category in the test set were identified as high risk by the decision-support tool, and may have been referred for earlier intervention. INTERPRETATION: The model accurately segments and classifies large lung nodules, and may improve upon existing clinical models. FUNDING: This project represents independent research funded by: 1) Royal Marsden Partners Cancer Alliance, 2) the Royal Marsden Cancer Charity, 3) the National Institute for Health Research (NIHR) Biomedical Research Centre at the Royal Marsden NHS Foundation Trust and The Institute of Cancer Research, London, 4) the National Institute for Health Research (NIHR) Biomedical Research Centre at Imperial College London, 5) Cancer Research UK (C309/A31316).

Gross tumour volume radiomics for prognostication of recurrence & death following radical radiotherapy for NSCLC.

Recurrence occurs in up to 36% of patients treated with curative-intent radiotherapy for NSCLC. Identifying patients at higher risk of recurrence for more intensive surveillance may facilitate the earlier introduction of the next line of treatment. We aimed to use radiotherapy planning CT scans to develop radiomic classification models that predict overall survival (OS), recurrence-free survival (RFS) and recurrence two years post-treatment for risk-stratification. A retrospective multi-centre study of >900 patients receiving curative-intent radiotherapy for stage I-III NSCLC was undertaken. Models using radiomic and/or clinical features were developed, compared with 10-fold cross-validation and an external test set, and benchmarked against TNM-stage. Respective validation and test set AUCs (with 95% confidence intervals) for the radiomic-only models were: (1) OS: 0.712 (0.592-0.832) and 0.685 (0.585-0.784), (2) RFS: 0.825 (0.733-0.916) and 0.750 (0.665-0.835), (3) Recurrence: 0.678 (0.554-0.801) and 0.673 (0.577-0.77). For the combined models: (1) OS: 0.702 (0.583-0.822) and 0.683 (0.586-0.78), (2) RFS: 0.805 (0.707-0.903) and 0·755 (0.672-0.838), (3) Recurrence: 0·637 (0.51-0.·765) and 0·738 (0.649-0.826). Kaplan-Meier analyses demonstrate OS and RFS difference of >300 and >400 days respectively between low and high-risk groups. We have developed validated and externally tested radiomic-based prediction models. Such models could be integrated into the routine radiotherapy workflow, thus informing a personalised surveillance strategy at the point of treatment. Our work lays the foundations for future prospective clinical trials for quantitative personalised risk-stratification for surveillance following curative-intent radiotherapy for NSCLC.

Deep-learned estimation of uncertainty in measurements of apparent diffusion coefficient from whole-body diffusion-weighted MRI.

PURPOSE: To use deep learning to calculate the uncertainty in apparent diffusion coefficient (σADC) voxel-wise measurements to clinically impact the monitoring of treatment response and improve the quality of ADC maps. MATERIALS AND METHODS: We use a uniquely designed diffusion-weighted imaging (DWI) acquisition protocol that provides gold-standard measurements of σADC to train a deep learning model on two separate cohorts: 16 patients with prostate cancer and 28 patients with mesothelioma. Our network was trained with a novel cost function, which incorporates a perception metric and a b-value regularisation term, on ADC maps calculated by combinations of 2 or 3 b-values (e.g. 50/600/900, 50/900, 50/600, 600/900 s/mm2). We compare the accuracy of the deep-learning based approach for estimation of σADC with gold-standard measurements. RESULTS: The model accurately predicted the σADC for every b-value combination in both cohorts. Mean values of σADC within areas of active disease deviated from those measured by the gold-standard by 4.3% (range, 2.87-6.13%) for the prostate and 3.7% (range, 3.06-4.54%) for the mesothelioma cohort. We also showed that the model can easily be adapted for a different DWI protocol and field-of-view with only a few images (as little as a single patient) using transfer learning. CONCLUSION: Deep learning produces maps of σADC from standard clinical diffusion-weighted images (DWI) when 2 or more b-values are available.

Radiomic Features From Diffusion-Weighted MRI of Retroperitoneal Soft-Tissue Sarcomas Are Repeatable and Exhibit Change After Radiotherapy.

Background: Size-based assessments are inaccurate indicators of tumor response in soft-tissue sarcoma (STS), motivating the requirement for new response imaging biomarkers for this rare and heterogeneous disease. In this study, we assess the test-retest repeatability of radiomic features from MR diffusion-weighted imaging (DWI) and derived maps of apparent diffusion coefficient (ADC) in retroperitoneal STS and compare baseline repeatability with changes in radiomic features following radiotherapy (RT). Materials and Methods: Thirty patients with retroperitoneal STS received an MR examination prior to treatment, of whom 23/30 were investigated in our repeatability analysis having received repeat baseline examinations and 14/30 patients were investigated in our post-treatment analysis having received an MR examination after completing pre-operative RT. One hundred and seven radiomic features were extracted from the full manually delineated tumor region using PyRadiomics. Test-retest repeatability was assessed using an intraclass correlation coefficient (baseline ICC), and post-radiotherapy variance analysis (post-RT-IMS) was used to compare the change in radiomic feature value to baseline repeatability. Results: For the ADC maps and DWI images, 101 and 102 features demonstrated good baseline repeatability (baseline ICC > 0.85), respectively. Forty-three and 2 features demonstrated both good baseline repeatability and a high post-RT-IMS (>0.85), respectively. Pearson correlation between the baseline ICC and post-RT-IMS was weak (0.432 and 0.133, respectively). Conclusions: The ADC-based radiomic analysis shows better test-retest repeatability compared with features derived from DWI images in STS, and some of these features are sensitive to post-treatment change. However, good repeatability at baseline does not imply sensitivity to post-treatment change.

Virtual Biopsy in Soft Tissue Sarcoma. How Close Are We?

A shift in radiology to a data-driven specialty has been unlocked by synergistic developments in imaging biomarkers (IB) and computational science. This is advancing the capability to deliver "virtual biopsies" within oncology. The ability to non-invasively probe tumour biology both spatially and temporally would fulfil the potential of imaging to inform management of complex tumours; improving diagnostic accuracy, providing new insights into inter- and intra-tumoral heterogeneity and individualised treatment planning and monitoring. Soft tissue sarcomas (STS) are rare tumours of mesenchymal origin with over 150 histological subtypes and notorious heterogeneity. The combination of inter- and intra-tumoural heterogeneity and the rarity of the disease remain major barriers to effective treatments. We provide an overview of the process of successful IB development, the key imaging and computational advancements in STS including quantitative magnetic resonance imaging, radiomics and artificial intelligence, and the studies to date that have explored the potential biological surrogates to imaging metrics. We discuss the promising future directions of IBs in STS and illustrate how the routine clinical implementation of a virtual biopsy has the potential to revolutionise the management of this group of complex cancers and improve clinical outcomes.

Implementation of Whole-Body MRI (MY-RADS) within the OPTIMUM/MUKnine multi-centre clinical trial for patients with myeloma.

BACKGROUND: Whole-body (WB) MRI, which includes diffusion-weighted imaging (DWI) and T1-w Dixon, permits sensitive detection of marrow disease in addition to qualitative and quantitative measurements of disease and response to treatment of bone marrow. We report on the first study to embed standardised WB-MRI within a prospective, multi-centre myeloma clinical trial (IMAGIMM trial, sub-study of OPTIMUM/MUKnine) to explore the use of WB-MRI to detect minimal residual disease after treatment. METHODS: The standardised MY-RADS WB-MRI protocol was set up on a local 1.5 T scanner. An imaging manual describing the MR protocol, quality assurance/control procedures and data transfer was produced and provided to sites. For non-identical scanners (different vendor or magnet strength), site visits from our physics team were organised to support protocol optimisation. The site qualification process included review of phantom and volunteer data acquired at each site and a teleconference to brief the multidisciplinary team. Image quality of initial patients at each site was assessed. RESULTS: WB-MRI was successfully set up at 12 UK sites involving 3 vendor systems and two field strengths. Four main protocols (1.5 T Siemens, 3 T Siemens, 1.5 T Philips and 3 T GE scanners) were generated. Scanner limitations (hardware and software) and scanning time constraint required protocol modifications for 4 sites. Nevertheless, shared methodology and imaging protocols enabled other centres to obtain images suitable for qualitative and quantitative analysis. CONCLUSIONS: Standardised WB-MRI protocols can be implemented and supported in prospective multi-centre clinical trials. Trial registration NCT03188172 clinicaltrials.gov; registration date 15th June 2017 https://clinicaltrials.gov/ct2/show/study/NCT03188172.