Multicentric development and evaluation of 18F-FDG PET/CT and MRI radiomics models to predict para-aortic lymph node involvement in locally advanced cervical cancer.

PURPOSE: To develop machine learning models to predict para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using 18F-FDG PET/CT and MRI radiomics combined with clinical parameters. METHODS: We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital 18F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared. RESULTS: In the training set (n = 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (n = 76) and external testing sets (n = 30 and n = 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively. CONCLUSIONS: Radiomic features extracted from pre-CRT analog and digital 18F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. Prospective validation of our models should now be carried out.

Tumor-immune landscape patterns before and after chemoradiation in resectable esophageal adenocarcinomas.

Immunotherapy is a new anti-cancer treatment option, showing promising results in clinical trials. To investigate potential immune biomarkers in esophageal adenocarcinoma (EAC), we explored immune landscape patterns in the tumor microenvironment before and after neoadjuvant chemoradiation (nCRT). Sections from matched pretreatment biopsies and post-nCRT resection specimens (n = 188) were stained for (1) programmed death-ligand 1 (PD-L1, CD274); (2) programmed cell death protein 1 (PD-1, CD279), forkhead box P3 (FOXP3), CD8, pan-cytokeratin multiplex; and (3) an MHC class I, II duplex. The densities of tumor-associated immune cells (TAICs) were calculated using digital image analyses and correlated to histopathological nCRT response [tumor regression grade (TRG)], survival, and post-nCRT immune patterns. PD-L1 positivity defined by a combined positive score of >1 was associated with a better response post-nCRT (TRG 1-3 versus 4, 5, p = 0.010). In addition, high combined mean densities of CD8+ , FOXP3+ , and PD-1+ TAICs in the tumor epithelium and stroma of biopsies were associated with a better response (TRG 1-3 versus 4, 5, p = 0.025 and p = 0.044, respectively). Heterogeneous TAIC density patterns were observed post-nCRT, with significantly higher CD8+ and PD-1+ TAIC mean densities compared with biopsies (both p = 0.000). Three immune landscape patterns were defined post-nCRT: 'inflamed', 'invasive margin', and 'desert', of which 'inflamed' was the most frequent (57%). Compared with matched biopsies, resection specimens with 'inflamed' tumors showed a significantly higher increase in CD8+ density compared with non-inflamed tumors post-nCRT (p = 0.000). In this cohort of EAC patients, higher TAIC densities in pretreatment biopsies were associated with response to nCRT. This warrants future research into the potential of the tumor-immune landscape for patient stratification and novel (immune) therapeutic strategies. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd on behalf of The Pathological Society of Great Britain and Ireland.

A review in radiomics: Making personalized medicine a reality via routine imaging.

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

ACE2 Protein Expression During Childhood, Adolescence, and Early Adulthood.

Purpose and context. Angiotensin-converting enzyme 2 is the entry receptor for SARS-CoV and SARS-CoV-2. Variations in ACE2 expression might explain age-related symptomatology of COVID-19, that is, more gastro-intestinal symptoms and less pulmonary complaints. This study qualitatively investigated ACE2 protein expression in various organs from the fetal to the young adolescent stage. Method. Autopsy samples from lung, heart, liver, stomach, small intestine, pancreas, kidney, adrenals, and brain (when available) were obtained from twenty subjects aged 24 weeks gestational age through 28 years. Formalin-fixed paraffin-embedded 4-um-thick tissue sections were stained against ACE2. Key results. We showed that the extent of ACE2 expression is age-related. With age, expression increases in lungs and decreases in intestines. In the other examined organs, ACE2 protein expression did not change with age. In brain tissue, ACE2 was expressed in astrocytes and endothelial cells. Conclusions. Age-related ACE2 expression differences could be one substrate of the selective clinical vulnerability of the respiratory and gastro-intestinal system to SARS-CoV-2 infection during infancy.

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions.

Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.

Comparison of CT-based Lobar Ventilation with 3He MR Imaging Ventilation Measurements.

PURPOSE: To compare lobar lung ventilation computed from expiratory and inspiratory computed tomographic (CT) data with direct measurements of ventilation at hyperpolarized helium 3 ((3)He) magnetic resonance (MR) imaging by using same-breath hydrogen 1 ((1)H) MR imaging examinations to coregister the multimodality images. MATERIALS AND METHODS: The study was approved by the national research ethics committee, and written patient consent was obtained. Thirty patients with asthma underwent breath-hold CT at total lung capacity and functional residual capacity. (3)He and (1)H MR images were acquired during the same breath hold at a lung volume of functional residual capacity plus 1 L. Lobar segmentations delineated by major fissures on both CT scans were used to calculate the percentage of ventilation per lobe from the change in inspiratory and expiratory lobar volumes. CT-based ventilation was compared with (3)He MR imaging ventilation by using diffeomorphic image registration of (1)H MR imaging to CT, which enabled indirect registration of (3)He MR imaging to CT. Statistical analysis was performed by using the Wilcoxon signed-rank test, Pearson correlation coefficient, and Bland-Altman analysis. RESULTS: The mean ± standard deviation absolute difference between the CT and (3)He MR imaging percentage of ventilation volume in all lobes was 4.0% (right upper and right middle lobes, 5.4% ± 3.3; right lower lobe, 3.7% ± 3.9; left upper lobe, 2.8% ± 2.7; left lower lobe, 3.9% ± 2.6; Wilcoxon signed-rank test, P < .05). The Pearson correlation coefficient between the two techniques in all lobes was 0.65 (P < .001). Greater percentage of ventilation was seen in the upper lobes with (3)He MR imaging and in the lower lobes with CT. This was confirmed with Bland-Altman analysis, with 95% limits of agreement for right upper and middle lobes, -2.4, 12.7; right lower lobe, -11.7, 4.6; left upper lobe, -4.9, 8.7; and left lower lobe, -9.8, 2.8. CONCLUSION: The percentage of regional ventilation per lobe calculated at CT was comparable to a direct measurement of lung ventilation at hyperpolarized (3)He MR imaging. This work provides evidence for the validity of the CT model, and same-breath (1)H MR imaging enables regional interpretation of (3)He ventilation MR imaging on the underlying lung anatomy at thin-section CT.

Granulomatous foreign-body reactions to permanent fillers: detection of CD123+ plasmacytoid dendritic cells.

BACKGROUND: Soft-tissue augmentation with permanent fillers can lead to severe granulomatous foreign-body reactions (GFBRs), but the immune pathomechanism of this complication is still unknown. We performed conventional histologic examination and immunostaining for plasmacytoid dendritic cells (pDCs) in skin sections from patients with GFBR to 4 permanent filler agents, which have been widely used in recent decades. METHODS: Twenty-one skin biopsies were studied from 19 patients with GFBR to polyalkylimide 4% gel (PAIG, n = 10), polyacrylamide 2.5% gel (PAAG, n = 2), hydroxyethyl methacrylate/ethyl methacrylate in hyaluronic acid (HEMA/EMA, n = 4), or liquid injectable silicone (n = 5). GFBRs were analyzed in hematoxylin and eosin stained sections and pDCs detected using CD123 antibodies. Anti-CD11c immunostaining was performed for comparison. RESULTS: Grading of the inflammatory infiltrates observed histologically did not correlate with the clinical features of inflammation. Immunostaining for CD123 did not detect pDCs in 8 of 10 polyalkylimide gel, 1 of 2 polyacrylamide gel, and the 5 liquid injectable silicone biopsies. In contrast, all 4 HEMA/EMA biopsies contained collections of pDCs in lymphocytic infiltrates close to filler particles and adjacent sarcoidal granulomas. CONCLUSIONS: Our data suggest that pDCs contribute to the sarcoidal granulomas associated with injected HEMA/EMA. Recruited pDCs may exert their pro-inflammatory effects by the release of interferon-α at the site of these filler deposits.

Using artificial intelligence and predictive modelling to enable learning healthcare systems (LHS) for pandemic preparedness.

In anticipation of potential future pandemics, we examined the challenges and opportunities presented by the COVID-19 outbreak. This analysis highlights how artificial intelligence (AI) and predictive models can support both patients and clinicians in managing subsequent infectious diseases, and how legislators and policymakers could support these efforts, to bring learning healthcare system (LHS) from guidelines to real-world implementation. This report chronicles the trajectory of the COVID-19 pandemic, emphasizing the diverse data sets generated throughout its course. We propose strategies for harnessing this data via AI and predictive modelling to enhance the functioning of LHS. The challenges faced by patients and healthcare systems around the world during this unprecedented crisis could have been mitigated with an informed and timely adoption of the three pillars of the LHS: Knowledge, Data and Practice. By harnessing AI and predictive analytics, we can develop tools that not only detect potential pandemic-prone diseases early on but also assist in patient management, provide decision support, offer treatment recommendations, deliver patient outcome triage, predict post-recovery long-term disease impacts, monitor viral mutations and variant emergence, and assess vaccine and treatment efficacy in real-time. A patient-centric approach remains paramount, ensuring patients are both informed and actively involved in disease mitigation strategies.

Viral presence and immunopathology in a kidney transplant recipient with fatal COVID-19: a clinical autopsy report.

COVID-19 is of special concern to immunocompromised individuals, including organ transplant recipients. However, the exact implications of COVID-19 for the immunocompromised host remain unclear. Existing theories regarding this matter are controversial and mainly based on clinical observations. Here, the postmortem histopathology, immunopathology, and viral presence in various tissues of a kidney transplant recipient with COVID-19 were compared to those of 2 nontransplanted patients with COVID-19 matched for age, sex, length of intensive care unit stay, and admission period in the pandemic. None of the tissues of the kidney transplant recipient demonstrated the presence of SARS-CoV-2. In lung tissues of both controls, some samples showed viral positivity with high Ct values with quantitative reverse transcription polymerase chain reaction. The lungs of the kidney transplant recipient and controls demonstrated similar pathology, consisting of acute fibrinous and organizing pneumonia with thrombosis and an inflammatory response with T cells, B cells, and macrophages. The kidney allograft and control kidneys showed a similar pattern of interstitial lymphoplasmacytic infiltration. No myocarditis could be observed in the hearts of the kidney transplant recipient and controls, although all cases contained scattered lymphoplasmacytic infiltrates in the myocardium, pericardium, and atria. The brainstems of the kidney transplant recipient and controls showed a similar pattern of lymphocytic inflammation with microgliosis. This research report highlights the possibility that, based on the results obtained from this single case, at time of death, the immune response in kidney transplant recipients with long-term antirejection immunosuppression use prior to severe illness is similar to nontransplanted deceased COVID-19 patients.

Novel functional imaging of changes in small airways of patients treated with extrafine beclomethasone/formoterol.

BACKGROUND: Inhaled formulations using extrafine particles of long-acting ß2-agonists and corticosteroids were developed to optimize asthma treatment. Findings that these combinations reach and treat smaller airways more effectively are predominantly based on general non-specific outcomes with little information on regional characteristics. OBJECTIVES: This study aims to assess long-term effects of extrafine beclomethasone/formoterol on small airways of asthmatic patients using novel functional imaging methods. METHODS: Twenty-four stable asthma patients were subdivided into three groups (steroid naive, n = 7; partially controlled, n = 6; well controlled, n = 11). Current treatment was switched to a fixed combination of extrafine beclomethasone/formoterol (Foster®; Chiesi Pharmaceuticals, Parma, Italy). Patients underwent lung function evaluation and thorax high-resolution computerized tomography (HRCT) scan. Local airway resistance was obtained from computational fluid dynamics (CFD). RESULTS: After 6 months, the entire population showed improvement in pre-bronchodilation imaging parameters, including small airway volume (p = 0.0007), resistance (p = 0.011), and asthma control score (p = 0.016). Changes in small airway volume correlated with changes in asthma control score (p = 0.004). Forced expiratory volume in 1 s (p = 0.044) and exhaled nitric oxide (p = 0.040) also improved. Functional imaging provided more detail and clinical relevance compared to lung function tests, especially in the well-controlled group where only functional imaging parameters showed significant improvement, while the correlation with asthma control score remained. CONCLUSIONS: Extrafine beclomethasone/formoterol results in a significant reduction of small airway obstruction, detectable by functional imaging (HRCT/CFD). Changes in imaging parameters correlated significantly with clinically relevant improvements. This indicates that functional imaging is a useful tool for sensitive assessment of changes in the respiratory system after asthma treatment.

Radiomics and Delta-Radiomics Signatures to Predict Response and Survival in Patients with Non-Small-Cell Lung Cancer Treated with Immune Checkpoint Inhibitors.

The aim of our study was to determine the potential role of CT-based radiomics in predicting treatment response and survival in patients with advanced NSCLC treated with immune checkpoint inhibitors. We retrospectively included 188 patients with NSCLC treated with PD-1/PD-L1 inhibitors from two independent centers. Radiomics analysis was performed on pre-treatment contrast-enhanced CT. A delta-radiomics analysis was also conducted on a subset of 160 patients who underwent a follow-up contrast-enhanced CT after 2 to 4 treatment cycles. Linear and random forest (RF) models were tested to predict response at 6 months and overall survival. Models based on clinical parameters only and combined clinical and radiomics models were also tested and compared to the radiomics and delta-radiomics models. The RF delta-radiomics model showed the best performance for response prediction with an AUC of 0.8 (95% CI: 0.65-0.95) on the external test dataset. The Cox regression delta-radiomics model was the most accurate at predicting survival with a concordance index of 0.68 (95% CI: 0.56-0.80) (p = 0.02). The baseline CT radiomics signatures did not show any significant results for treatment response prediction or survival. In conclusion, our results demonstrated the ability of a CT-based delta-radiomics signature to identify early on patients with NSCLC who were more likely to benefit from immunotherapy.

External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients.

The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

Deep learning based identification of bone scintigraphies containing metastatic bone disease foci.

PURPOSE: Metastatic bone disease (MBD) is the most common form of metastases, most frequently deriving from prostate cancer. MBD is screened with bone scintigraphy (BS), which have high sensitivity but low specificity for the diagnosis of MBD, often requiring further investigations. Deep learning (DL) - a machine learning technique designed to mimic human neuronal interactions- has shown promise in the field of medical imaging analysis for different purposes, including segmentation and classification of lesions. In this study, we aim to develop a DL algorithm that can classify areas of increased uptake on bone scintigraphy scans. METHODS: We collected 2365 BS from three European medical centres. The model was trained and validated on 1203 and 164 BS scans respectively. Furthermore we evaluated its performance on an external testing set composed of 998 BS scans. We further aimed to enhance the explainability of our developed algorithm, using activation maps. We compared the performance of our algorithm to that of 6 nuclear medicine physicians. RESULTS: The developed DL based algorithm is able to detect MBD on BSs, with high specificity and sensitivity (0.80 and 0.82 respectively on the external test set), in a shorter time compared to the nuclear medicine physicians (2.5 min for AI and 30 min for nuclear medicine physicians to classify 134 BSs). Further prospective validation is required before the algorithm can be used in the clinic.

The acute effect of budesonide/formoterol in COPD: a multi-slice computed tomography and lung function study.

The Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification of chronic obstructive pulmonary disease (COPD) does not always match with other clinical disease descriptors such as exacerbation frequency and quality of life, indicating that forced expiratory volume in 1 s (FEV(1)) is not a perfect descriptor of the disease. The aim of this study was to find out whether changes in airway geometry after inhalation of the most commonly used inhalation therapy in severe COPD can more adequately be described with an image-based approach than with spirometry. 10 COPD GOLD stage III patients were assessed in a double-blind crossover study. Airway volumes were analysed using segmentation of multi-slice computed tomography (MSCT) images; airway resistance was determined using computational fluid dynamics (CFD). Distal airway volume significantly increased (p=0.011) in patients 4 h after receiving a budesonide/formoterol combination from 9.6±4.67 cm(3) to 10.14±4.81 cm(3). Also CFD-determined airway resistance significantly decreased (p=0.047) from 0.051±0.021 kPa·s·L(-1) to 0.043±0.019 kPa·s·L(-1). None of the lung function parameters showed a significant change. Only functional residual capacity (FRC) showed a trend to decline (p=0.056). Only the image-based parameters were able to predict the visit at which the combination product was administered. This study showed that imaging is a sensitive, complementary tool to describe changes in airway structure.

Particle deposition in airways of chronic respiratory patients exposed to an urban aerosol.

Urban atmospheres in modern cities carry characteristic mixtures of particulate pollution which are potentially aggravating for chronic respiratory patients (CRP). Although air quality surveys can be detailed, the obtained information is not always useful to evaluate human health effects. This paper presents a novel approach to estimate particle deposition rates in airways of CRP, based on real air pollution data. By combining computational fluid dynamics with physical-chemical characteristics of particulate pollution, deposition rates are estimated for particles of different toxicological relevance, that is, minerals, iron oxides, sea salts, ammonium salts, and carbonaceous particles. Also, it enables some qualitative evaluation of the spatial, temporal, and patient specific effects on the particle dose upon exposure to the urban atmosphere. Results show how heavy traffic conditions increases the deposition of anthropogenic particles in the trachea and lungs of respiratory patients (here, +0.28 and +1.5 µg·h(-1), respectively). In addition, local and synoptic meteorological conditions were found to have a strong effect on the overall dose. However, the pathology and age of the patient was found to be more crucial, with highest deposition rates for toxic particles in adults with a mild anomaly, followed by mild asthmatic children and adults with severe respiratory dysfunctions (7, 5, and 3 µg·h(-1), respectively).

A case series on lung deposition analysis of inhaled medication using functional imaging based computational fluid dynamics in asthmatic patients: effect of upper airway morphology and comparison with in vivo data.

CONTEXT: Asthma affects 20 million Americans resulting in an economic burden of approximately $18 billion in the US alone (Allergies and Asthma Foundation 2000; National Center for Environmental Health (NCEH) 1999). Research studies based on differences in patient-specific airway morphology for asthma and the associated effect on deposition of inhaled aerosols are currently not available in the literature. Therefore, the role of morphological variations such as upper airway (extrathoracic) occlusion is not well documented. OBJECTIVE: Functional imaging based computational fluid dynamics (CFD) of the respiratory airways for five asthmatic subjects is performed in this study using computed tomography (CT) based patient-specific airway models and boundary conditions. METHODS: CT scans for 5 asthma patients were used to reconstruct 3D lung models using segmentation software. An averaged inhalation profile and patient-specific lobar flow distribution were used to perform the simulation. The simulations were used to obtain deposition for BDP/Formoterol® HFA pMDI in the patient-specific airway models. RESULTS: The lung deposition obtained using CFD was in excellent agreement with available in vivo data using the same product. Specifically, CFD resulted in 30% lung deposition, whereas in vivo lung deposition was reported to be approximately 31%. CONCLUSION: It was concluded that a combination of patient-specific airway models and lobar boundary conditions can be used to obtain accurate lung deposition estimates. Lower lung deposition can be expected for patients with higher extrathoracic resistance. Novel respiratory drug delivery devices need to accommodate population sub-groups based on these morphological and anatomical differences in addition to subject age.

An externally validated fully automated deep learning algorithm to classify COVID-19 and other pneumonias on chest computed tomography.

Purpose: In this study, we propose an artificial intelligence (AI) framework based on three-dimensional convolutional neural networks to classify computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19), influenza/community-acquired pneumonia (CAP), and no infection, after automatic segmentation of the lungs and lung abnormalities. Methods: The AI classification model is based on inflated three-dimensional Inception architecture and was trained and validated on retrospective data of CT images of 667 adult patients (no infection n=188, COVID-19 n=230, influenza/CAP n=249) and 210 adult patients (no infection n=70, COVID-19 n=70, influenza/CAP n=70), respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients (no infection n=55, COVID-19 n= 94, influenza/CAP n=124) and an external validation set from a different centre (305 adult patients: COVID-19 n=169, no infection n=76, influenza/CAP n=60). Results: The model showed excellent performance in the external validation set with area under the curve of 0.90, 0.92 and 0.92 for COVID-19, influenza/CAP and no infection, respectively. The selection of the input slices based on automatic segmentation of the abnormalities in the lung reduces analysis time (56 s per scan) and computational burden of the model. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score of the proposed model is 47% (15 out of 32 TRIPOD items). Conclusion: This AI solution provides rapid and accurate diagnosis in patients suspected of COVID-19 infection and influenza.

Distinction of Lymphoma from Sarcoidosis on 18F-FDG PET/CT: Evaluation of Radiomics-Feature-Guided Machine Learning Versus Human Reader Performance.

Sarcoidosis and lymphoma often share common features on 18F-FDG PET/CT, such as intense hypermetabolic lesions in lymph nodes and multiple organs. We aimed at developing and validating radiomics signatures to differentiate sarcoidosis from Hodgkin lymphoma (HL) and diffuse large B-cell lymphoma (DLBCL). Methods: We retrospectively collected 420 patients (169 sarcoidosis, 140 HL, and 111 DLBCL) who underwent pretreatment 18F-FDG PET/CT at the University Hospital of Liege. The studies were randomly distributed to 4 physicians, who gave their diagnostic suggestion among the 3 diseases. The individual and pooled performance of the physicians was then calculated. Interobserver variability was evaluated using a sample of 34 studies interpreted by all physicians. Volumes of interest were delineated over the lesions and the liver using MIM software, and 215 radiomics features were extracted using the RadiomiX Toolbox. Models were developed combining clinical data (age, sex, and weight) and radiomics (original and tumor-to-liver TLR radiomics), with 7 different feature selection approaches and 4 different machine-learning (ML) classifiers, to differentiate sarcoidosis and lymphomas on both lesion-based and patient-based approaches. Results: For identifying lymphoma versus sarcoidosis, physicians' pooled sensitivity, specificity, area under the receiver-operating-characteristic curve (AUC), and accuracy were 0.99 (95% CI, 0.97-1.00), 0.75 (95% CI, 0.68-0.81), 0.87 (95% CI, 0.84-0.90), and 89.3%, respectively, whereas for identifying HL in the tumor population, it was 0.58 (95% CI, 0.49-0.66), 0.82 (95% CI, 0.74-0.89), 0.70 (95% CI, 0.64-0.75) and 68.5%, respectively. Moderate agreement was found among observers for the diagnosis of lymphoma versus sarcoidosis and HL versus DLBCL, with Fleiss κ-values of 0.66 (95% CI, 0.45-0.87) and 0.69 (95% CI, 0.45-0.93), respectively. The best ML models for identifying lymphoma versus sarcoidosis showed an AUC of 0.94 (95% CI, 0.93-0.95) and 0.85 (95% CI, 0.82-0.88) in lesion- and patient-based approaches, respectively, using TLR radiomics (plus age for the second). To differentiate HL from DLBCL, we obtained an AUC of 0.95 (95% CI, 0.93-0.96) in the lesion-based approach using TLR radiomics and 0.86 (95% CI, 0.80-0.91) in the patient-based approach using original radiomics and age. Conclusion: Characterization of sarcoidosis and lymphoma lesions is feasible using ML and radiomics, with very good to excellent performance, equivalent to or better than that of physicians, who showed significant interobserver variability in their assessment.

The Role of Imaging in the Detection of Non-COVID-19 Pathologies during the Massive Screening of the First Pandemic Wave.

During the COVID-19 pandemic induced by the SARS-CoV-2, numerous chest scans were carried out in order to establish the diagnosis, quantify the extension of lesions but also identify the occurrence of potential pulmonary embolisms. In this perspective, the performed chest scans provided a varied database for a retrospective analysis of non-COVID-19 chest pathologies discovered de novo. The fortuitous discovery of de novo non-COVID-19 lesions was generally not detected by the automated systems for COVID-19 pneumonia developed in parallel during the pandemic and was thus identified on chest CT by the radiologist. The objective is to use the study of the occurrence of non-COVID-19-related chest abnormalities (known and unknown) in a large cohort of patients having suffered from confirmed COVID-19 infection and statistically correlate the clinical data and the occurrence of these abnormalities in order to assess the potential of increased early detection of lesions/alterations. This study was performed on a group of 362 COVID-19-positive patients who were prescribed a CT scan in order to diagnose and predict COVID-19-associated lung disease. Statistical analysis using mean, standard deviation (SD) or median and interquartile range (IQR), logistic regression models and linear regression models were used for data analysis. Results were considered significant at the 5% critical level (p < 0.05). These de novo non-COVID-19 thoracic lesions detected on chest CT showed a significant prevalence in cardiovascular pathologies, with calcifying atheromatous anomalies approaching nearly 35.4% in patients over 65 years of age. The detection of non-COVID-19 pathologies was mostly already known, except for suspicious nodule, thyroid goiter and the ascending thoracic aortic aneurysm. The presence of vertebral compression or signs of pulmonary fibrosis has shown a significant impact on inpatient length of stay. The characteristics of the patients in this sample, both from a demographic and a tomodensitometric point of view on non-COVID-19 pathologies, influenced the length of hospital stay as well as the risk of intra-hospital death. This retrospective study showed that the potential importance of the detection of these non-COVID-19 lesions by the radiologist was essential in the management and the intra-hospital course of the patients.