Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Hepatic arterial oxaliplatin plus intravenous 5-fluorouracil and cetuximab for first-line treatment of colorectal liver metastases: A multicenter phase II trial.

BACKGROUND: The efficacy and tolerability of hepatic arterial infusion (HAI) oxaliplatin plus systemic 5-fluorouracil and cetuximab as frontline treatment in patients with colorectal liver metastases (CRLM) are unknown. METHODS: In this multicenter, single-arm phase II study, patients with CRLM not amenable to curative-intent resection or requiring complex/major liver resection, and no prior chemotherapy for metastatic disease, received HAI oxaliplatin and intravenous 5-fluorouracil, leucovorin and cetuximab, every two weeks until disease progression, limiting toxicity or at least 3 months after complete response or curative-intent resection/ablation. The primary endpoint was overall response rate (ORR). RESULTS: 35 patients, mostly with bilateral (89%), multiple CRLM (>4, 86%; >10, 46%) were enrolled in eight centers. The ORR was 88% (95% CI, 71%-96%) among evaluable patients (n = 32), and 95% (95% CI 70-100%) among the 22 wild-type RAS/BRAF evaluable patients. After a median follow-up of 8.8 years (95% CI, 8.7-not reached), median progression-free survival was 17.9 months (95% CI, 15-23) and median overall survival (OS) was 46.3 months (95% CI, 40.0-not reached). 23 of the 35 patients (66%), including 22 (79%) of the 25 patients with wild-type RAS tumor, underwent curative-intent surgical resection and/or ablation of CRLM. HAI catheter remained patent in 86% of patients, allowing for a median of eight oxaliplatin infusions (range, 1-19). Treatment toxicity was manageable, without toxic death. CONCLUSION: HAI oxaliplatin plus systemic 5-fluorouracil and cetuximab appears highly effective in the frontline treatment of patients with unresectable CRLM and should be investigated further.

Designing clinical trials based on modern imaging and metastasis-directed treatments in patients with oligometastatic breast cancer: a consensus recommendation from the EORTC Imaging and Breast Cancer Groups.

Breast cancer remains the most common cause of cancer death among women. Despite its considerable histological and molecular heterogeneity, those characteristics are not distinguished in most definitions of oligometastatic disease and clinical trials of oligometastatic breast cancer. After an exhaustive review of the literature covering all aspects of oligometastatic breast cancer, 35 experts from the European Organisation for Research and Treatment of Cancer Imaging and Breast Cancer Groups elaborated a Delphi questionnaire aimed at offering consensus recommendations, including oligometastatic breast cancer definition, optimal diagnostic pathways, and clinical trials required to evaluate the effect of diagnostic imaging strategies and metastasis-directed therapies. The main recommendations are the introduction of modern imaging methods in metastatic screening for an earlier diagnosis of oligometastatic breast cancer and the development of prospective trials also considering the histological and molecular complexity of breast cancer. Strategies for the randomisation of imaging methods and therapeutic approaches in different subsets of patients are also addressed.

Detection and quantification of pulmonary embolism with artificial intelligence: The SFR 2022 artificial intelligence data challenge.

PURPOSE: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence. MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks. RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784. CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.

A Patient-Centered Model of Fast-Track Lung Cancer Diagnosis.

INTRODUCTION: Despite the increasing importance of digital resources in modern life over the past decades, little is known about the impact of internet-based solutions on patient's health. We aimed to study the potential benefit of a digital platform helping patients to deal with abnormal chest CT scan revealing possible lung cancer. METHODS: We set up a fast-track lung cancer diagnosis pathway through a secure online platform. Patient-generated information combined with online review of their imaging enables preplanning of further investigations ahead of clinical assessment. We compared outcomes of "self-referred" patients (patient group), who directly fill out the online questionnaire, to general practitioner-driven patients (GP group), who were referred by their GP. RESULTS: From June 2021 to June 2022, we included 125 patients (61% males, median age 67 years, IQR 56.9-72.5): 41% in the patient group and 59% in the GP group. No difference was found between groups in terms of time from contact to first appointment (median 5 days in both groups, P = .6), percentage of pathways including prebooked tests (94% vs. 92%, P = .6), number of scheduled invasive procedures (median 1, IQR 1-2 vs. 2, IQR 1-2, P = .4) and in final cancer diagnosis (76% vs. 78%, P = .4). CONCLUSION: A lung cancer diagnosis pathway directly accessible by patients through a secure online platform was feasible and as efficient as the usual general practitioner pathway. It demonstrated the benefit of leaning on new digital tools in order to answer to the new challenges of a patient-centered health care system.

Epidemiological Study to Assess the Prevalence of Lung Cancer in patients with smoking-associated atherosclerotic cardiovascular diseases: PREVALUNG study protocol.

INTRODUCTION: Eligibility criteria definition for a lung cancer screening (LCS) is an unmet need. We hypothesised that patients with a history of atheromatous cardiovascular disease (ACVD) associated with tobacco consumption are at risk of lung cancer (LC). The main objective is to assess LC prevalence among patients with ACVD and history of tobacco consumption by using low-dose chest CT scan. Secondary objectives include the evaluation LCS in this population and the constitution of a biological biobank to stratify risk of LC. METHODS AND ANALYSIS: We are performing a monocentric 'single-centre' prospective study among patients followed up in adult cardiovascular programmes of vascular surgery, cardiology and cardiac surgery recruited from 18 November 2019 to 18 May 2021. The inclusion criteria are (1) age 45-75 years old, (2) history of ACVD and (3) history of daily tobacco consumption for 10 years prior to onset of ACVD. Exclusion criteria are symptoms of LC, existing follow-up for pulmonary nodule, fibrosis, pulmonary hypertension, resting dyspnoea and active pulmonary infectious disease. We targeted the inclusion of 500 patients. After inclusion (V0), patients are scheduled for a low-dose chest CT and blood and faeces harvesting within 7 months (V1). Each patient is scheduled for a follow-up by telephonic visits at month 3 (V2), month 6 (V3) and month 12 (V4) after V1. Each patient is followed up until 1 year after V1 (14 February 2023). We measure LC prevalence and quantify the National Lung Screening Trial and Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON) trial eligibility criteria, radiation, positive screening, false positivity, rate of localised LC diagnosis, quality of life with the Short Form 12 (SF-12) and anxiety with the Spielberger State-Trait Anxiety Inventory A and B (STAI-YA and STAI-YB, respectively), smoking cessation and onset of cardiovascular and oncological events within 1 year of follow-up. A case-control study nested in the cohort is performed to identify clinical or biological candidate biomarkers of LC. ETHICS AND DISSEMINATION: The study was approved according the French Jardé law; the study is referenced at the French 'Agence Nationale de Sécurité du Médicament et des Produits de Santé' (reference ID RCB: 2019-A00262-55) and registered on clinicaltrial.gov. The results of the study will be presented after the closure of the follow-up scheduled on 14 February 2023 and disseminated through peer-reviewed journals and national and international conferences. TRIAL REGISTRATION NUMBER: NCT03976804.

Standardised lesion segmentation for imaging biomarker quantitation: a consensus recommendation from ESR and EORTC.

BACKGROUND: Lesion/tissue segmentation on digital medical images enables biomarker extraction, image-guided therapy delivery, treatment response measurement, and training/validation for developing artificial intelligence algorithms and workflows. To ensure data reproducibility, criteria for standardised segmentation are critical but currently unavailable. METHODS: A modified Delphi process initiated by the European Imaging Biomarker Alliance (EIBALL) of the European Society of Radiology (ESR) and the European Organisation for Research and Treatment of Cancer (EORTC) Imaging Group was undertaken. Three multidisciplinary task forces addressed modality and image acquisition, segmentation methodology itself, and standards and logistics. Devised survey questions were fed via a facilitator to expert participants. The 58 respondents to Round 1 were invited to participate in Rounds 2-4. Subsequent rounds were informed by responses of previous rounds. RESULTS/CONCLUSIONS: Items with ≥ 75% consensus are considered a recommendation. These include system performance certification, thresholds for image signal-to-noise, contrast-to-noise and tumour-to-background ratios, spatial resolution, and artefact levels. Direct, iterative, and machine or deep learning reconstruction methods, use of a mixture of CE marked and verified research tools were agreed and use of specified reference standards and validation processes considered essential. Operator training and refreshment were considered mandatory for clinical trials and clinical research. Items with a 60-74% agreement require reporting (site-specific accreditation for clinical research, minimal pixel number within lesion segmented, use of post-reconstruction algorithms, operator training refreshment for clinical practice). Items with ≤ 60% agreement are outside current recommendations for segmentation (frequency of system performance tests, use of only CE-marked tools, board certification of operators, frequency of operator refresher training). Recommendations by anatomical area are also specified.

Imaging standardisation in metastatic colorectal cancer: A joint EORTC-ESOI-ESGAR expert consensus recommendation.

BACKGROUND: Treatment monitoring in metastatic colorectal cancer (mCRC) relies on imaging to evaluate the tumour burden. Response Evaluation Criteria in Solid Tumors provide a framework on reporting and interpretation of imaging findings yet offer no guidance on a standardised imaging protocol tailored to patients with mCRC. Imaging protocol heterogeneity remains a challenge for the reproducibility of conventional imaging end-points and is an obstacle for research on novel imaging end-points. PATIENTS AND METHODS: Acknowledging the recently highlighted potential of radiomics and artificial intelligence tools as decision support for patient care in mCRC, a multidisciplinary, international and expert panel of imaging specialists was formed to find consensus on mCRC imaging protocols using the Delphi method. RESULTS: Under the guidance of the European Organisation for Research and Treatment of Cancer (EORTC) Imaging and Gastrointestinal Tract Cancer Groups, the European Society of Oncologic Imaging (ESOI) and the European Society of Gastrointestinal and Abdominal Radiology (ESGAR), the EORTC-ESOI-ESGAR core imaging protocol was identified. CONCLUSION: This consensus protocol attempts to promote standardisation and to diminish variations in patient preparation, scan acquisition and scan reconstruction. We anticipate that this standardisation will increase reproducibility of radiomics and artificial intelligence studies and serve as a catalyst for future research on imaging end-points. For ongoing and future mCRC trials, we encourage principal investigators to support the dissemination of these imaging standards across recruiting centres.

Quantification and reduction of cross-vendor variation in multicenter DWI MR imaging: results of the Cancer Core Europe imaging task force.

OBJECTIVES: In the Cancer Core Europe Consortium (CCE), standardized biomarkers are required for therapy monitoring oncologic multicenter clinical trials. Multiparametric functional MRI and particularly diffusion-weighted MRI offer evident advantages for noninvasive characterization of tumor viability compared to CT and RECIST. A quantification of the inter- and intraindividual variation occurring in this setting using different hardware is missing. In this study, the MRI protocol including DWI was standardized and the residual variability of measurement parameters quantified. METHODS: Phantom and volunteer measurements (single-shot T2w and DW-EPI) were performed at the seven CCE sites using the MR hardware produced by three different vendors. Repeated measurements were performed at the sites and across the sites including a traveling volunteer, comparing qualitative and quantitative ROI-based results including an explorative radiomics analysis. RESULTS: For DWI/ADC phantom measurements using a central post-processing algorithm, the maximum deviation could be decreased to 2%. However, there is no significant difference compared to a decentralized ADC value calculation at the respective MRI devices. In volunteers, the measurement variation in 2 repeated scans did not exceed 11% for ADC and is below 20% for single-shot T2w in systematic liver ROIs. The measurement variation between sites amounted to 20% for ADC and < 25% for single-shot T2w. Explorative radiomics classification experiments yield better results for ADC than for single-shot T2w. CONCLUSION: Harmonization of MR acquisition and post-processing parameters results in acceptable standard deviations for MR/DW imaging. MRI could be the tool in oncologic multicenter trials to overcome the limitations of RECIST-based response evaluation. KEY POINTS: • Harmonizing acquisition parameters and post-processing homogenization, standardized protocols result in acceptable standard deviations for multicenter MR-DWI studies. • Total measurement variation does not to exceed 11% for ADC in repeated measurements in repeated MR acquisitions, and below 20% for an identical volunteer travelling between sites. • Radiomic classification experiments were able to identify stable features allowing for reliable discrimination of different physiological tissue samples, even when using heterogeneous imaging data.

Monitoring tumor growth rate to predict immune checkpoint inhibitors' treatment outcome in advanced NSCLC.

INTRODUCTION: Radiological response assessment to immune checkpoint inhibitor is challenging due to atypical pattern of response and commonly used RECIST 1.1 criteria do not take into account the kinetics of tumor behavior. Our study aimed at evaluating the tumor growth rate (TGR) in addition to RECIST 1.1 criteria to assess the benefit of immune checkpoint inhibitors (ICIs). METHODS: Tumor real volume was calculated with a dedicated computed tomography (CT) software that semi-automatically assess tumor volume. Target lesions were identified according to RECIST 1.1. For each patient, we had 3 measurement of tumor volume. CT-1 was performed 8-12 weeks before ICI start, the CT at baseline for ICI was CT0, while CT + 1 was the first assessment after ICI. We calculated the percentage increase in tumor volume before (TGR1) and after immunotherapy (TGR2). Finally, we compared TGR1 and TGR2. If no progressive disease (PD), the group was disease control (DC). If PD but TGR2 < TGR1, it was called LvPD and if TGR2 ⩾ TGR1, HvPD. RESULTS: A total of 61 patients who received ICIs and 33 treated with chemotherapy (ChT) were included. In ICI group, 18 patients were HvPD, 22 LvPD, 21 DC. Median OS was 4.4 months (95% CI: 2.0-6.8, reference) for HvPD, 7.1 months (95% CI 5.4-8.8) for LvPD, p = 0.018, and 20.9 months (95% CI: 12.5-29.3) for DC, p < 0.001. In ChT group, 7 were categorized as HvPD, 17 as LvPD and 9 as DC. No difference in OS was observed in the ChT group (p = 0.786). CONCLUSION: In the presence of PD, a decrease in TGR may result in a clinical benefit in patients treated with ICI but not with chemotherapy. Monitoring TGR changes after ICIs administration can help physician in deciding to treat beyond PD.

CD8+PD-1+ to CD4+PD-1+ ratio (PERLS) is associated with prognosis of patients with advanced NSCLC treated with PD-(L)1 blockers.

BACKGROUND: Programmed cell death protein-1 (PD-1) expression has been associated with activation and exhaustion of both the CD4 and CD8 populations in advanced non-small cell lung cancer (aNSCLC). Nevertheless, the impact of the balance between circulating CD8+PD-1+ and CD4+PD-1+ in patients treated with immune checkpoint blockers (ICB) is unknown. METHODS: The CD8+PD-1+ to CD4+PD-1+ ratio (PD-1-Expressing Ratio on Lymphocytes in a Systemic blood sample, or 'PERLS') was determined by cytometry in fresh whole blood from patients with aNSCLC before treatment with single-agent ICB targeting PD-1 or programmed cell death-ligand 1 (PD-L1 (discovery cohort). A PERLS cut-off was identified by log-rank maximization. Patients treated with ICB (validation cohort) or polychemotherapy (control cohort) were classified as PERLS+/- (above/below cut-off). Circulating immune cell phenotype and function were correlated with PERLS. A composite score (good, intermediate and poor) was determined using the combination of PERLS and senescent immune phenotype as previously described in aNSCLC. RESULTS: In the discovery cohort (N=75), the PERLS cut-off was 1.91, and 11% of patients were PERLS+. PERLS + correlated significantly with median progression-free survival (PFS) of 9.63 months (95% CI 7.82 to not reached (NR)) versus 2.69 months (95% CI 1.81 to 5.52; p=0.03). In an independent validation cohort (N=36), median PFS was NR (95% CI 7.9 to NR) versus 2.00 months (95% CI 1.3 to 4.5; p=0.04) for PERLS + and PERLS-, respectively; overall survival (OS) followed a similar but non-significant trend. In the pooled cohort (N=111), PERLS + correlated significantly with PFS and OS. PERLS did not correlate with outcome in the polychemotherapy cohort. PERLS did not correlate with clinical characteristics but was significantly associated with baseline circulating naïve CD4+ T cells and the increase of memory T cells post-ICB treatment. Accumulation of memory T cells during treatment was linked to CD4+ T cell polyfunctionality. The composite score was evaluated in the pooled cohort (N=68). The median OS for good, intermediate and poor composite scores was NR (95% CI NR to NR), 8.54 months (95% CI 4.96 to NR) and 2.42 months (95% CI 1.97 to 15.5; p=0.001), respectively. The median PFS was 12.60 months (95% CI 9.63 to NR), 2.58 months (95% CI 1.74 to 7.29) and 1.76 months (95% CI 1.31 to 4.57; p<0.0001), respectively. CONCLUSIONS: Elevated PERLS, determined from a blood sample before immunotherapy, was correlated with benefit from PD-(L)1 blockers in aNSCLC.

Tumour burden and efficacy of immune-checkpoint inhibitors.

Accumulating evidence suggests that a high tumour burden has a negative effect on anticancer immunity. The concept of tumour burden, simply defined as the total amount of cancer in the body, in contrast to molecular tumour burden, is often poorly understood by the wider medical community; nonetheless, a possible role exists in defining the optimal treatment strategy for many patients. Historically, tumour burden has been assessed using imaging. In particular, CT scans have been used to evaluate both the number and size of metastases as well as the number of organs involved. These methods are now often complemented by metabolic tumour burden, measured using the more recently developed 2-deoxy-2-[18F]-fluoro-D-glucose (FDG)-PET/CT. Serum-based biomarkers, such as lactate dehydrogenase, can also reflect tumour burden and are often also correlated with a poor response to immune-checkpoint inhibitors. Other circulating markers (such as circulating free tumour DNA and/or circulating tumour cells) are also attracting research interest as surrogate markers of tumour burden. In this Review, we summarize evidence supporting the utility of tumour burden as a biomarker to guide the use of immune-checkpoint inhibitors. We also describe data and provide perspective on the various tools used for tumour burden assessment, with a particular emphasis on future therapeutic strategies that might address the issue of inferior outcomes among patients with cancer with a high tumour burden.

Can MRI differentiate surrounding vertebral invasion from reactive inflammatory changes in superior sulcus tumor?

OBJECTIVES: Vertebral invasion is a key prognostic factor and a critical aspect of surgical planning for superior sulcus tumors. This study aims to further evaluate MRI features of vertebral invasion in order to distinguish it from reactive inflammatory changes. METHODS: Between 2000 and 2016, a retrospective study was performed at a single institution. All patients with superior sulcus tumors undergoing surgery, including at least two partial vertebrectomies, were included. An expert radiologist evaluated qualitative and quantitative MRI signal intensity characteristics (contrast-to-noise ratio [CNR]) of suspected involved and non-involved vertebrae. A comparison of CNR of invaded and sane vertebrae was performed using non-parametric tests. Imaging data were correlated with pathological findings. RESULTS: A total of 92 surgical samples of vertebrectomy were analyzed. The most specific sequences for invasion were T1 and T2 weighted (92% and 97%, respectively). The most sensitive sequences were contrast enhanced T1 weighted fat suppressed and T2 weighted fat suppressed (100% and 80%). Loss of extrapleural paravertebral fat on the T1-weighted sequence was highly sensitive (100%) but not specific (63%). Using quantitative analysis, the optimum cut-off (p < 0.05) to distinguish invasion from reactive inflammatory changes was CNR > 11 for the T2-weighted fat-sat sequence (sensitivity 100%), CNR > 9 for contrast-enhanced T1-weighted fat-suppressed sequence (sensitivity 100%), and CNR < - 30 for the T1-weighted sequence (specificity 97%). Combining these criteria, 23 partial vertebrectomies could have been avoided in our cohort. CONCLUSION: Qualitative and quantitative MRI analyses are useful to discriminate vertebral invasion from reactive inflammatory changes. KEY POINTS: • Abnormal signal intensity in a vertebral body adjacent to a superior sulcus tumor may be secondary to direct invasion or reactive inflammatory changes. • Accurate differentiation between invasion and reactive inflammatory changes significantly impacts surgical planning. T1w and T2w are the best sequences to differentiate malignant versus benign bone marrow changes. The use of quantitative analysis improves MRI specificity. • Using contrast media improves the sensitivity for the detection of tumor invasion.

Dual-energy CT angiography reveals high prevalence of perfusion defects unrelated to pulmonary embolism in COVID-19 lesions.

BACKGROUND: Lung perfusion defects (PDs) have been described in COVID-19 using dual-energy computed tomography pulmonary angiography (DE-CTPA). We assessed the prevalence and characteristics of PDs in COVID-19 patients with suspected pulmonary embolism (PE) and negative CTPA. METHODS: This retrospective study included COVID-19 and non-COVID-19 pneumonia groups of patients with DE-CTPA negative for PE. Two radiologists rated the presence of PD within the lung opacities and analyzed the type of lung opacities and PD pattern (i.e. homogeneous or heterogeneous). The clinical, biological, radiological characteristics including time from first symptoms and admission to DE-CTPA, oxygen requirements, CRP, D-dimer levels, duration of hospital admission and death were compared within the COVID-19 group between patients with (PD +) or without PD (PD-). RESULTS: 67 COVID-19 and 79 non-COVID-19 patients were included. PDs were more frequent in the COVID-19 than in the non-COVID-19 group (59.7% and 26.6% respectively, p < 0.001). Patterns of PDs were different, with COVID-19 patients exhibiting heterogenous PDs (38/40, 95%) whereas non-COVID-19 patients showed mostly homogeneous perfusion defects (7/21 heterogeneous PDs, 33%), p < 0.001. In COVID-19 patients, most consolidations (9/10, 90%) exhibited PDs while less than a third of consolidations (19/67, 28%) had PDs in non-COVID-19 patients. D-dimer, oxygen levels and outcome were similar between COVID-19 PD + and PD- patients; however, time between admission and DE-CTPA was longer in PD + patients (median [IQR], 1 [0-7] and 0 [0-2]; p = 0.045). CONCLUSION: Unlike in bacterial pneumonia, heterogeneous PDs within lung opacities are a frequent feature of COVID-19 pneumonia in PE-suspected patients.

Tumour-infiltrating lymphocyte density is associated with favourable outcome in patients with advanced non-small cell lung cancer treated with immunotherapy.

BACKGROUND: The established role of morphological evaluation of tumour-infiltrating lymphocytes (TILs) with immune checkpoint inhibitors (ICIs) in non-small cell lung cancer (NSCLC) is unknown. We aimed to determine TIL association with the outcome for ICIs and for chemotherapy in advanced NSCLC. METHODS: This is a multicenter retrospective study of a nivolumab cohort of 221 patients treated between November 2012 and February 2017 and a chemotherapy cohort of 189 patients treated between June 2009 and October 2016. Patients with available tissue for stromal TIL evaluation were analysed. The presence of a high TIL count (high-TIL) was defined as ≥10% density. The primary end-point was overall survival (OS). RESULTS: Among the nivolumab cohort, 64% were male, with median age of 63 years, 82.3% were smokers, 77% had performance status ≤1 and 63% had adenocarcinoma histology. High-TIL was observed in 22% patients and associated with OS (hazard ratio [HR] 0.48; 95% confidence interval [95% CI]: 0.28-0.81) and progression-free survival [PFS] (HR = 0.40; 95% CI: 0.25-0.64). Median PFS was 13.0 months (95% CI: 5.0-not reached) with high-TIL versus 2.2 months (95% CI: 1.7-3.0) with the presence of a low TIL count (low-TIL). Median OS for high-TIL was not reached (95% CI: 12.2-not reached) versus 8.4 months (95% CI: 5.0-11.6) in the low-TIL group. High-TIL was associated with the overall response rate (ORR) and disease control rate (DCR) (both, P < .0001). Among the chemotherapy cohort, 69% were male, 89% were smokers, 86% had performance status ≤1 and 90% had adenocarcinoma histology. High-TIL was seen in 37%. Median PFS and OS were 5.7 months (95% CI: 4.9-6.7) and 11.7 months (95% CI: 9.3-13.0), respectively, with no association with TILs. CONCLUSIONS: High-TIL was associated with favourable outcomes in a real-world immunotherapy cohort of patients with NSCLC, but not with chemotherapy, suggesting that TILs may be useful in selecting patients for immunotherapy.

Incorporating radiomics into clinical trials: expert consensus endorsed by the European Society of Radiology on considerations for data-driven compared to biologically driven quantitative biomarkers.

Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. KEY POINTS: • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

Twenty Years On: RECIST as a Biomarker of Response in Solid Tumours an EORTC Imaging Group - ESOI Joint Paper.

Response evaluation criteria in solid tumours (RECIST) v1.1 are currently the reference standard for evaluating efficacy of therapies in patients with solid tumours who are included in clinical trials, and they are widely used and accepted by regulatory agencies. This expert statement discusses the principles underlying RECIST, as well as their reproducibility and limitations. While the RECIST framework may not be perfect, the scientific bases for the anticancer drugs that have been approved using a RECIST-based surrogate endpoint remain valid. Importantly, changes in measurement have to meet thresholds defined by RECIST for response classification within thus partly circumventing the problems of measurement variability. The RECIST framework also applies to clinical patients in individual settings even though the relationship between tumour size changes and outcome from cohort studies is not necessarily translatable to individual cases. As reproducibility of RECIST measurements is impacted by reader experience, choice of target lesions and detection/interpretation of new lesions, it can result in patients changing response categories when measurements are near threshold values or if new lesions are missed or incorrectly interpreted. There are several situations where RECIST will fail to evaluate treatment-induced changes correctly; knowledge and understanding of these is crucial for correct interpretation. Also, some patterns of response/progression cannot be correctly documented by RECIST, particularly in relation to organ-site (e.g. bone without associated soft-tissue lesion) and treatment type (e.g. focal therapies). These require specialist reader experience and communication with oncologists to determine the actual impact of the therapy and best evaluation strategy. In such situations, alternative imaging markers for tumour response may be used but the sources of variability of individual imaging techniques need to be known and accounted for. Communication between imaging experts and oncologists regarding the level of confidence in a biomarker is essential for the correct interpretation of a biomarker and its application to clinical decision-making. Though measurement automation is desirable and potentially reduces the variability of results, associated technical difficulties must be overcome, and human adjudications may be required.