Lucian Beer

Abstract: Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.

PURPOSE: PET/MRI has recently been introduced into clinical practice. We prospectively investigated the clinical impact of PET/MRI compared with PET/CT, in a mixed population of cancer patients, and performed an economic evaluation of PET/MRI. METHODS: F]FDOPA, depending on tumor histology. PET/MRI and PET/CT were rated separately, and lesions were assessed per anatomic region; based on regions, per-examination and per-patient accuracies were determined. A simulated, multidisciplinary team meeting served as reference standard and determined whether differences between PET/CT and PET/MRI affected patient management. The McNemar tests were used to compare accuracies, and incremental cost-effectiveness ratios (ICERs) for PET/MRI were calculated. RESULTS: Two hundred sixty-three patients (330 same-day PET/CT and PET/MRI examinations) were included. PET/MRI was accurate in 319/330 examinations and PET/CT in 277/330 examinations; the respective accuracies of 97.3% and 83.9% differed significantly (P < 0.001). The additional findings on PET/MRI-mainly liver and brain metastases-had implications for patient management in 21/263 patients (8.0%). The per-examination cost was 596.97 EUR for PET/MRI and 405.95 EUR for PET/CT. ICERs for PET/MRI were 14.26 EUR per percent of diagnostic accuracy and 23.88 EUR per percent of correctly managed patients. CONCLUSIONS: PET/MRI enables more appropriate management than PET/CT in a nonnegligible fraction of cancer patients. Since the per-examination cost is about 50% higher for PET/MRI than for PET/CT, a histology-based triage of patients to either PET/MRI or PET/CT may be meaningful.

OBJECTIVES: (1) To assess the methodological quality of radiomics studies investigating histological subtypes, therapy response, and survival in patients with renal cell carcinoma (RCC) and (2) to determine the risk of bias in these radiomics studies. METHODS: In this systematic review, literature published since 2000 on radiomics in RCC was included and assessed for methodological quality using the Radiomics Quality Score. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool and a meta-analysis of radiomics studies focusing on differentiating between angiomyolipoma without visible fat and RCC was performed. RESULTS: Fifty-seven studies investigating the use of radiomics in renal cancer were identified, including 4590 patients in total. The average Radiomics Quality Score was 3.41 (9.4% of total) with good inter-rater agreement (ICC 0.96, 95% CI 0.93-0.98). Three studies validated results with an independent dataset, one used a publically available validation dataset. None of the studies shared the code, images, or regions of interest. The meta-analysis showed moderate heterogeneity among the included studies and an odds ratio of 6.24 (95% CI 4.27-9.12; p < 0.001) for the differentiation of angiomyolipoma without visible fat from RCC. CONCLUSIONS: Radiomics algorithms show promise for answering clinical questions where subjective interpretation is challenging or not established. However, the generalizability of findings to prospective cohorts needs to be demonstrated in future trials for progression towards clinical translation. Improved sharing of methods including code and images could facilitate independent validation of radiomics signatures. KEY POINTS: • Studies achieved an average Radiomics Quality Score of 10.8%. Common reasons for low Radiomics Quality Scores were unvalidated results, retrospective study design, absence of open science, and insufficient control for multiple comparisons. • A previous training phase allowed reaching almost perfect inter-rater agreement in the application of the Radiomics Quality Score. • Meta-analysis of radiomics studies distinguishing angiomyolipoma without visible fat from renal cell carcinoma show moderate diagnostic odds ratios of 6.24 and moderate methodological diversity.

We previously showed that, when peripheral blood mononuclear cells (PBMCs) were stressed with ionizing radiation, they released paracrine factors that showed regenerative capacity in vitro and in vivo. This study aimed to characterize the secretome of PBMCs and to investigate its biologically active components in vitro and vivo. Bioinformatics analysis revealed that irradiated PBMCs differentially expressed genes that encoded secreted proteins. These genes were primarily involved in (a) pro-angiogenic and regenerative pathways and (b) the generation of oxidized phospholipids with known pro-angiogenic and inflammation-modulating properties. Subsequently, in vitro assays showed that the exosome and protein fractions of irradiated and non-irradiated PBMC secretome were the major biological components that enhanced cell mobility; conversely, secreted lipids and microparticles had no effects. We tested a viral-cleared PBMC secretome, prepared according to good manufacturing practice (GMP), in a porcine model of closed chest, acute myocardial infarction. We found that the potency for preventing ventricular remodeling was similar with the GMP-compliant and experimentally-prepared PBMC secretomes. Our results indicate that irradiation modulates the release of proteins, lipid-mediators and extracellular vesicles from human PBMCs. In addition our findings implicate the use of secretome fractions as valuable material for the development of cell-free therapies in regenerative medicine.

“Regenerative medicine” or “tissue regeneration” had become to an inspired term recently since it has been realized in the last decade that many organs such as the skin display morphological plasticity and possess healing capacity instead of being a post-mitotic terminally developed organ (1,2).