Identification of CT radiomic features robust to acquisition and segmentation variations for improved prediction of radiotherapy-treated lung cancer patient recurrence.

The primary objective of the present study was to identify a subset of radiomic features extracted from primary tumor imaged by computed tomography of early-stage non-small cell lung cancer patients, which remain unaffected by variations in segmentation quality and in computed tomography image acquisition protocol. The robustness of these features to segmentation variations was assessed by analyzing the correlation of feature values extracted from lesion volumes delineated by two annotators. The robustness to variations in acquisition protocol was evaluated by examining the correlation of features extracted from high-dose and low-dose computed tomography scans, both of which were acquired for each patient as part of the stereotactic body radiotherapy planning process. Among 106 radiomic features considered, 21 were identified as robust. An analysis including univariate and multivariate assessments was subsequently conducted to estimate the predictive performance of these robust features on the outcome of early-stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. The univariate predictive analysis revealed that robust features demonstrated superior predictive potential compared to non-robust features. The multivariate analysis indicated that linear regression models built with robust features displayed greater generalization capabilities by outperforming other models in predicting the outcomes of an external validation dataset.

Predictive clinical and dosimetric parameters for risk of relapse in early-stage non-small cell lung cancer treated by SBRT: A large single institution experience.

Purpose: To evaluate the impact of dosimetric parameters on efficacy of stereotactic body radiation therapy (SBRT) in early-stage non-small cell lung cancer (ES-NSCLC), using Hypofractionated Treatment Effects in the Clinic (HyTEC) reporting standards. Methods: From April 2010 to December 2020, 497 patients who received SBRT for ES-NSCLC at the University Hospital of Liège were retrospectively enrolled. A total dose of 40 to 60 Gy in 3-5 fractions (72-180 Gy biologically effective dose with an α/ß ratio of 10 (BED10)) was prescribed to the 80 % isodose line of the PTV. Potential clinical and dosimetric predictors of recurrence, overall survival (OS) and disease specific survival (DSS) were evaluated using univariate and multivariate analyses. Results: After a median follow-up of 32 months (range 3-143 months), the local control and disease-free survival (DFS) rates at 3 years were 91 % (95 % CI: 90 %-93 %) and 75 % (95 % CI: 73 %-77 %), respectively. The median OS was 41.6 months and the median DSS was not reached. On multivariate analysis, a higher gross tumor volume (GTV) Dmax (BED10) (cut-off 198 Gy) and a larger percent of the GTV receiving ≥110 % of the prescribed dose were predictive of a better local control, only GTV volume was correlated with DSS and no parameter was correlated with OS and regional or distant recurrences. Conclusion: Lung SBRT for ES-NSCLC in 3 to 5 fractions resulted in high local control rates. A higher percent of GTV receiving ≥110 % of the prescribed dose and a higher GTV Dmax (BED10) seem to allow a better local control.

Multicentric development and evaluation of [18F]FDG PET/CT and CT radiomic models to predict regional and/or distant recurrence in early-stage non-small cell lung cancer treated by stereotactic body radiation therapy.

PURPOSE: To develop machine learning models to predict regional and/or distant recurrence in patients with early-stage non-small cell lung cancer (ES-NSCLC) after stereotactic body radiation therapy (SBRT) using [18F]FDG PET/CT and CT radiomics combined with clinical and dosimetric parameters. METHODS: We retrospectively collected 464 patients (60% for training and 40% for testing) from University Hospital of Liège and 63 patients from University Hospital of Brest (external testing set) with ES-NSCLC treated with SBRT between 2010 and 2020 and who had undergone pretreatment [18F]FDG PET/CT and planning CT. Radiomic features were extracted using the PyRadiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Clinical, radiomic, and combined models were trained and tested using a neural network approach to predict regional and/or distant recurrence. RESULTS: In the training (n = 273) and testing sets (n = 191 and n = 63), the clinical model achieved moderate performances to predict regional and/or distant recurrence with C-statistics from 0.53 to 0.59 (95% CI, 0.41, 0.67). The radiomic (original_firstorder_Entropy, original_gldm_LowGrayLevelEmphasis and original_glcm_DifferenceAverage) model achieved higher predictive ability in the training set and kept the same performance in the testing sets, with C-statistics from 0.70 to 0.78 (95% CI, 0.63, 0.88) while the combined model performs moderately well with C-statistics from 0.50 to 0.62 (95% CI, 0.37, 0.69). CONCLUSION: Radiomic features extracted from pre-SBRT analog and digital [18F]FDG PET/CT outperform clinical parameters in the prediction of regional and/or distant recurrence and to discuss an adjuvant systemic treatment in ES-NSCLC. Prospective validation of our models should now be carried out.

Standardized 4-point scoring scale of [18F]-FDG PET/CT imaging helps in the diagnosis of renal and hepatic cyst infections in patients with autosomal dominant polycystic kidney disease: a validation cohort.

Background: Autosomal dominant polycystic kidney disease (ADPKD) is prone to multiple complications, including cyst infection (CyI). 2-Deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography ([18F]-FDG PET/CT) imaging has proved useful in the diagnosis of renal and hepatic CyI. A 4-point scale comparing the uptake of [18F]-FDG in the suspected infected cyst versus the hepatic physiological background has been recently proposed. We performed an independent validation of this semi-quantitative scoring system. Methods: All ADPKD patients hospitalized between January 2009 and November 2019 who underwent an [18F]-FDG PET/CT for suspected CyI were retrospectively identified using computer-based databases. Medical files were reviewed. CyI was conventionally defined by the combination of fever (≥38°C), abdominal pain, increased plasma C-reactive protein levels (≥70 mg/L), absence of any other cause of inflammation and favourable outcome after ≥21 days of antibiotics. [18F]-FDG uptake of the suspected CyI was evaluated using a 4-point scale comparing the uptake of [18F]-FDG around the infected cysts with the uptake in the hepatic parenchyma. Statistics were performed using SAS version 9.4. Results: Fifty-one [18F]-FDG PET/CT scans in 51 patients were included, of which 11 were cases of CyI. The agreement between the 4-point scale and the gold-standard criteria of CyI was significant [odds ratio of 6.03 for CyI in case of a score ≥3 (P = .014)]. The corresponding sensitivity, specificity, and positive and negative predictive values of [18F]-FDG PET/CT using the 4-point scale were 64% [Clopper-Pearson 95% confidence interval (CI) 30%-89%], 78% (95% CI 62%-89%), 44% (95% CI 20%-70%) and 89% (95% CI 73%-97%), respectively. Conclusions: Our independent validation cohort confirms the use of a semi-quantitative 4-point scoring system of [18F]-FDG PET/CT imaging in the diagnosis of CyI in patients with ADPKD. Considering its performance metrics with high specificity and negative predictive value, the scoring system is particularly useful to distinguish other causes of clinical inflammation than CyI and as such avoid unnecessarily long antibiotic treatment.

Genetic diversity of Echinococcus multilocularis specimens isolated from Belgian patients with alveolar echinococcosis using EmsB microsatellites analysis.

The genetic diversity of Echinococcus multilocularis (E. multilocularis) specimens isolated from patients with alveolar echinococcosis (AE), is a major field of investigation to correlate with sources of infection, clinical manifestations and prognosis of the disease. Molecular markers able to distinguish samples are commonly used worldwide, including the EmsB microsatellite. Here, we report the use of the EmsB microsatellite polymorphism data mining for the retrospective typing of Belgian specimens of E. multilocularis infecting humans. A total of 18 samples from 16 AE patients treated between 2006 and 2021 were analyzed through the EmsB polymorphism. Classification of specimens was performed through a dendrogram construction in order to compare the similarity among Belgian samples, some human referenced specimens on the EWET database (EmsB Website for the Echinococcus Typing) and previously published EmsB profiles from red foxes circulating in/near Belgium. According to a comparison with human European specimens previously genotyped in profiles, the 18 Belgian ones were classified into three EmsB profiles. Four specimens could not be assigned to an already known profile but some are near to EWET referenced samples. This study also highlights that some specimens share the same EmsB profile with profiles characterized in red foxes from north Belgium, the Netherlands, Luxembourg and French department near to the Belgian border. Furthermore, Belgian specimens present a genetic diversity and include one profile that don't share similarities with the ones referenced in the EWET database. However, at this geographical scale, there is no clear correlation between EmsB profiles and geographical location. Further studies including additional clinical samples and isolates from foxes and rodents of south Belgium are necessary to better understand the spatial and temporal circumstances of human infections but also a potential correlation between EmsB profiles and parasite virulence.

[Lung disease associated with rheumatoid arthritis]. / La pathologie pulmonaire associée à la polyarthrite rhumatoïde.

Rheumatoid arthritis is a chronic inflammatory systemic disease. Pulmonary manifestations are the most common extra-articular involvements and can impact all components of the respiratory system: parenchyma, pleura, vessels and airways, all complications that are briefly described in this article. Interstitial lung disease is the most common of these and is associated with significant morbidity and mortality. Its detection and monitoring are based on spirometry and thoracic imaging. Specific treatments are initiated in order to reduce the risk of disease flare up but may themselves in case of toxicity be associated with respiratory manifestations, either directly or by promoting infectious complications.

La polyarthrite rhumatoïde est une pathologie systémique inflammatoire chronique. Les manifestations pulmonaires représentent l'atteinte extra-articulaire la plus fréquente et peuvent affecter tous les composants du système respiratoire : le parenchyme, la plèvre, les vaisseaux et les voies aériennes, complications décrites brièvement dans cet article. La pneumopathie interstitielle diffuse en est la plus commune et associée à une morbi-mortalité importante. Son dépistage et son suivi reposent sur les épreuves fonctionnelles et l'imagerie thoracique. Des traitements spécifiques sont initiés afin de limiter au mieux l'évolution pulmonaire, mais peuvent eux-mêmes être associés à des manifestations respiratoires, soit directement, soit en favorisant des complications infectieuses.

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.

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.

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.

Outcome analysis of HDR compared to PDR IGABT in locally advanced cervical cancer: a single-center cohort analysis.

PURPOSE: This monocentric study aimed to assess the impact of technical advancement in brachytherapy (BT) on local control (LC) and cancer-specific survival (CSS) in locally advanced cervical cancer (LACC). METHODS: Since 2010, 211 patients with LACC have been treated with 45/50.4 Gy or 60 Gy radiochemotherapy (RTCT) followed by image-guided adaptive brachytherapy (IGABT) at the authors' institution. In 2013, combined intracavitary and interstitial brachytherapy (BT IC/IS) was implemented and in 2018, pulsed-dose-rate BT (PDR-BT) was replaced by high-dose-rate BT (HDR-BT). LC, CSS, and morbidity according to the RTOG/EORTC scoring system were analyzed. Dose-volume parameters for the high-risk clinical target volume (HRCTV) and organs at risk (OAR) were reported. RESULTS: While 27 (12.8%) patients died of LACC, complete local remission was achieved in 199 (94.3%). Local relapse decreases with a high D95 in the HRCTV (hazard ratio, HR = 0.85, p = 0.0024). D95 in the HRCTV is lower after 60 Gy even if interstitial BT is used. Mean D95 in the HRCTV is 78.2 Gy, 83.3 Gy, and 83.4 Gy with PDR-BT IC, PDR-BT IC/IS, and HDR-BT IC/IS, respectively, after 45/50.4 Gy. D2 cc of OARs is significantly reduced by using interstitial BT. The mean rectum and sigmoid D2 cc are about 61.5 Gy with PDR-BT IC/IS and significantly decreased with HDR-BT IC/IS. This translates into a low fistula incidence. A very low rate of severe gastrointestinal (3.4%) and genitourinary (2.3%) toxicity was observed with HDR-BT IC/IS. CONCLUSION: This large monocentric study provides further evidence that implementation of BT IC/IS has an impact on D95 in the HRCTV, LC, and CSS. There are no differences between HDR and PDR in terms of efficacy, D95 in the HRCTV, and toxicity grade ≥ 3.

The role of PET imaging in inflammatory bowel diseases: state-of-the-art review.

Inflammatory bowel diseases (IBD), i.e. Crohn disease and ulcerative colitis, are autoimmune processes of undetermined origin characterized by the chronic inflammation of the digestive tract. There is no single gold-standard to diagnose IBD which is therefore carried out through the combination of endoscopy, biopsy, radiological and biological investigations; and the development of non-invasive technique allowing the assessment and monitoring of these diseases is necessary. In this state-of-the-art review of the literature, we present the results of PET imaging studies for the diagnosis and staging of IBD (suspected or known), response evaluation to treatment and evaluation of one the main complication, i.e. strictures; explain the reasons why this examination is currently not considered in the IBD guidelines, e.g. radiation exposure, lack of standardization and not validated performances; and finally discuss the perspectives that could possibly allow it to find a place in the future, e.g. digital PET-CT, dynamic PET images acquisition, new radiopharmaceuticals, use of radiomics and use of artificial intelligence for automatically characterize and quantify digestive [18F]FDG uptake.

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.

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.

Radiomics in Lung Diseases Imaging: State-of-the-Art for Clinicians.

Artificial intelligence (AI) has increasingly been serving the field of radiology over the last 50 years. As modern medicine is evolving towards precision medicine, offering personalized patient care and treatment, the requirement for robust imaging biomarkers has gradually increased. Radiomics, a specific method generating high-throughput extraction of a tremendous amount of quantitative imaging data using data-characterization algorithms, has shown great potential in individuating imaging biomarkers. Radiomic analysis can be implemented through the following two methods: hand-crafted radiomic features extraction or deep learning algorithm. Its application in lung diseases can be used in clinical decision support systems, regarding its ability to develop descriptive and predictive models in many respiratory pathologies. The aim of this article is to review the recent literature on the topic, and briefly summarize the interest of radiomics in chest Computed Tomography (CT) and its pertinence in the field of pulmonary diseases, from a clinician's perspective.

Can predicting COVID-19 mortality in a European cohort using only demographic and comorbidity data surpass age-based prediction: An externally validated study.

OBJECTIVE: To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a precursor to implementing smart lockdowns and vaccine distribution strategies. METHODS: The training cohort comprised 2337 COVID-19 inpatients from nine hospitals in The Netherlands. The clinical outcome was death within 21 days of being discharged. The features were derived from electronic health records collected during admission. Three feature selection methods were used: LASSO, univariate using a novel metric, and pairwise (age being half of each pair). 478 patients from Belgium were used to test the model. All modeling attempts were compared against an age-only model. RESULTS: In the training cohort, the mortality group's median age was 77 years (interquartile range = 70-83), higher than the non-mortality group (median = 65, IQR = 55-75). The incidence of former/active smokers, male gender, hypertension, diabetes, dementia, cancer, chronic obstructive pulmonary disease, chronic cardiac disease, chronic neurological disease, and chronic kidney disease was higher in the mortality group. All stated differences were statistically significant after Bonferroni correction. LASSO selected eight features, novel univariate chose five, and pairwise chose none. No model was able to surpass an age-only model in the external validation set, where age had an AUC of 0.85 and a balanced accuracy of 0.77. CONCLUSION: When applied to an external validation set, we found that an age-only mortality model outperformed all modeling attempts (curated on www.covid19risk.ai) using three feature selection methods on 22 demographic and comorbid features.

[18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation.

PURPOSE: To test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[18F] fluoro-2-deoxy-D-glucose ([18F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC). METHODS: One hundred fifty-eight patients with LACC from multiple centers were retrospectively included in the study. Tumours were segmented using the Fuzzy Local Adaptive Bayesian (FLAB) algorithm. Radiomic features were extracted from the tumours and from regions drawn over the normal liver. Cox proportional hazard model was used to test statistical significance of clinical and radiomic features. Fivefold cross validation was used to tune the number of features. Seven different feature selection methods and four classifiers were tested. The models with the selected features were trained using bootstrapping and tested in data from each scanner independently. Reproducibility of radiomics features, clinical data added value and effect of ComBat-based harmonisation were evaluated across scanners. RESULTS: After a median follow-up of 23 months, 29% of the patients recurred. No individual radiomic or clinical features were significantly associated with cancer recurrence. The best model was obtained using 10 TLR features combined with clinical information. The area under the curve (AUC), F1-score, precision and recall were respectively 0.78 (0.67-0.88), 0.49 (0.25-0.67), 0.42 (0.25-0.60) and 0.63 (0.20-0.80). ComBat did not improve the predictive performance of the best models. Both the TLR and the native models performance varied across scanners used in the test set. CONCLUSION: [18F]FDG PET radiomic features combined with ML add relevant information to the standard clinical parameters in terms of LACC patient's outcome but remain subject to variability across PET/CT devices.