Machine Learning Applied to Pre-Operative Computed-Tomography-Based Radiomic Features Can Accurately Differentiate Uterine Leiomyoma from Leiomyosarcoma: A Pilot Study.

BACKGROUND: The accurate discrimination of uterine leiomyosarcomas and leiomyomas in a pre-operative setting remains a current challenge. To date, the diagnosis is made by a pathologist on the excised tumor. The aim of this study was to develop a machine learning algorithm using radiomic data extracted from contrast-enhanced computed tomography (CECT) images that could accurately distinguish leiomyosarcomas from leiomyomas. METHODS: Pre-operative CECT images from patients submitted to surgery with a histological diagnosis of leiomyoma or leiomyosarcoma were used for the region of interest identification and radiomic feature extraction. Feature extraction was conducted using the PyRadiomics library, and three feature selection methods combined with the general linear model (GLM), random forest (RF), and support vector machine (SVM) classifiers were built, trained, and tested for the binary classification task (malignant vs. benign). In parallel, radiologists assessed the diagnosis with or without clinical data. RESULTS: A total of 30 patients with leiomyosarcoma (mean age 59 years) and 35 patients with leiomyoma (mean age 48 years) were included in the study, comprising 30 and 51 lesions, respectively. Out of nine machine learning models, the three feature selection methods combined with the GLM and RF classifiers showed good performances, with predicted area under the curve (AUC), sensitivity, and specificity ranging from 0.78 to 0.97, from 0.78 to 1.00, and from 0.67 to 0.93, respectively, when compared to the results obtained from experienced radiologists when blinded to the clinical profile (AUC = 0.73 95%CI = 0.62-0.84), as well as when the clinical data were consulted (AUC = 0.75 95%CI = 0.65-0.85). CONCLUSIONS: CECT images integrated with radiomics have great potential in differentiating uterine leiomyomas from leiomyosarcomas. Such a tool can be used to mitigate the risks of eventual surgical spread in the case of leiomyosarcoma and allow for safer fertility-sparing treatment in patients with benign uterine lesions.

A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study.

BACKGROUND: Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed to investigate the potential of radiomic features extracted from pre-surgical CT scans to accurately predict disease-free survival (DFS) among EC patients. METHODS: Contrast-Enhanced CT (CE-CT) scans from 81 EC cases were used to extract the radiomic features from semi-automatically contoured volumes of interest. We employed a 10-fold cross-validation approach with a 6:4 training to test set and utilized data augmentation and balancing techniques. Univariate analysis was applied for feature reduction leading to the development of three distinct machine learning (ML) models for the prediction of DFS: LASSO-Cox, CoxBoost and Random Forest (RFsrc). RESULTS: In the training set, the ML models demonstrated AUCs ranging from 0.92 to 0.93, sensitivities from 0.96 to 1.00 and specificities from 0.77 to 0.89. In the test set, AUCs ranged from 0.86 to 0.90, sensitivities from 0.89 to 1.00 and specificities from 0.73 to 0.90. Patients classified as having a high recurrence risk prediction by ML models exhibited significantly worse DSF (p-value < 0.001) across all models. CONCLUSIONS: Our findings demonstrate the potential of radiomics in predicting EC recurrence. While further validation studies are needed, our results underscore the promising role of radiomics in forecasting EC outcomes.

Co-Infections and Superinfections in COVID-19 Critically Ill Patients Are Associated with CT Imaging Abnormalities and the Worst Outcomes.

Background: Bacterial and fungal co-infections and superinfections have a critical role in the outcome of the COVID-19 patients admitted to the Intensive Care Unit (ICU). Methods: The present study is a retrospective analysis of 95 patients admitted to the ICU for COVID-19-related ARDS during the first (February−May 2020) and second waves of the pandemic (October 2020−January 2021). Demographic and clinical data, CT imaging features, and pulmonary and extra-pulmonary complications were recorded, as well as the temporal evolution of CT findings when more than one scan was available. The presence of co-infections and superinfections was registered, reporting the culprit pathogens and the specimen type for culture. A comparison between patients with and without bacterial and/or co-infections/superinfections was performed. Results: Sixty-three patients (66.3%) developed at least one confirmed co-infection/superinfection, with 52 (82.5%) developing pneumonia and 43 (68.3%) bloodstream infection. Gram-negative bacteria were the most common co-pathogens identified and Aspergillus spp. was the most frequent pulmonary microorganism. Consolidations, cavitations, and bronchiectasis were significantly associated with the presence of co-infections/superinfections (p = 0.009, p = 0.010 and p = 0.009, respectively); when considering only patients with pulmonary co-pathogens, only consolidations remained statistically significative (p = 0.004). Invasive pulmonary aspergillosis was significantly associated with the presence of cavitations and bronchiectasis (p < 0.001). Patients with co-infections/superinfections presented a significantly higher mortality rate compared to patients with COVID-19 only (52.4% vs. 25%, p = 0.016). Conclusions: Bacterial and fungal co-infections and superinfections are frequent in COVID-19 patients admitted to ICU and are associated with worse outcomes. Imaging plays an important role in monitoring critically ill COVID-19 patients and may help detect these complications, suggesting further laboratory investigations.

An Imaging Overview of COVID-19 ARDS in ICU Patients and Its Complications: A Pictorial Review.

A significant proportion of patients with COVID-19 pneumonia could develop acute respiratory distress syndrome (ARDS), thus requiring mechanical ventilation, and resulting in a high rate of intensive care unit (ICU) admission. Several complications can arise during an ICU stay, from both COVID-19 infection and the respiratory supporting system, including barotraumas (pneumothorax and pneumomediastinum), superimposed pneumonia, coagulation disorders (pulmonary embolism, venous thromboembolism, hemorrhages and acute ischemic stroke), abdominal involvement (acute mesenteric ischemia, pancreatitis and acute kidney injury) and sarcopenia. Imaging plays a pivotal role in the detection and monitoring of ICU complications and is expanding even to prognosis prediction. The present pictorial review describes the clinicopathological and radiological findings of COVID-19 ARDS in ICU patients and discusses the imaging features of complications related to invasive ventilation support, as well as those of COVID-19 itself in this particularly fragile population. Radiologists need to be familiar with COVID-19's possible extra-pulmonary complications and, through reliable and constant monitoring, guide therapeutic decisions. Moreover, as more research is pursued and the pathophysiology of COVID-19 is increasingly understood, the role of imaging must evolve accordingly, expanding from the diagnosis and subsequent management of patients to prognosis prediction.

Spontaneous Evolution of COVID-19 Lung Sequelae: Results from a Double-Step Follow-Up.

BACKGROUND: Few studies have reported a double-step follow-up of patients after hospitalization for COVID-19. OBJECTIVES: We designed an observational double-step follow-up study with a clinical, functional, and radiological evaluation at 2 and 6 months after COVID-19. The primary outcome was to describe symptoms, spirometry, and 6-minute walking test (6MWT) at 2 and 6 months. Secondary outcomes were to identify if the lowest PaO2/FiO2 during hospitalization is related with functional and radiological evolution and to assess the correlation between radiological and functional abnormalities at 6 months. METHODS: Symptoms, spirometry, and 6MWT were assessed at 2 and 6 months; arterial blood gas, chest x-ray, and lung ultrasound were performed at 2 months; body plethysmography, diffusing capacity for carbon monoxide (DLCO), and CT scan were performed at 6 months. RESULTS: Sixty-four per cent and 42% of patients reported at least one symptom at 2 and 6 months, respectively. The most common 6-month functional alteration was DLCO impairment (57% of patients). An improvement of FEV1, FVC, and 6MWT was observed between 2 and 6 months (p < 0.001). Patients with PaO2/FiO2 <200 during hospitalization performed worse at 6MWT at 2 and 6 months (p < 0.05) and reported more extended radiological abnormalities at 6 months (p < 0.001) compared with patients with PaO2/FiO2>200. At 6 months, more extended radiological abnormalities were related with worse 6MWT, DLCO, and total lung capacity (p < 0.05). DISCUSSION: DLCO and 6MWT impairment seem to be the functional hallmark of COVID-19 and are related with the severity of acute pneumonia. At 6 months, radiological abnormalities were related to functional impairment.

The triple rule out CT in acute chest pain: a challenge for emergency radiologists?

PURPOSE: To evaluate the feasibility of triple rule out computed tomography (TRO-CT) in an emergency radiology workflow by comparing the diagnostic performance of cardiovascular and general radiologists in the interpretation of emergency TRO-CT studies in patients with acute and atypical chest pain. METHODS: Between July 2017 and December 2019, 350 adult patients underwent TRO-CT studies for the assessment of atypical chest pain. Three radiologists with different fields and years of expertise (a cardioradiologist-CR, an emergency senior radiologist-SER, and an emergency junior radiologist-JER) retrospectively and independently reviewed all TRO-CT studies, by trans-axial and multiplanar reconstruction only. Concordance rates were then calculated using as reference blinded results from a different senior cardioradiologist, who previously evaluated studies using all available analysis software. RESULTS: Concordance rate was 100% for acute aortic syndrome (AAS) and pulmonary embolism (PE). About coronary stenosis (CS) for non-obstructive (<50%), CS concordance rates were 97.98%, 90.91%, and 97.18%, respectively, for CR, SER, and JER; for obstructive CS (>50%), concordance rates were respectively 88%, 85.7%, and 71.43%. Moreover, it was globally observed a better performance in the evaluation of last half of examinations compared with the first one. CONCLUSIONS: Our study confirm the feasibility of the TRO-CT even in an Emergency Radiology department that cannot rely on a 24/7 availability of a dedicated skilled cardiovascular radiologist. The "undedicated" radiologists could exclude with good diagnostic accuracy the presence of obstructive stenosis, those with a clinical impact on patient management, without needing time-consuming software and/or reconstructions.

Thoracic manifestation of Eisenmenger's syndrome in adult patients: a MDCT review.

Eisenmenger's syndrome (ES) is the most advanced form of pulmonary arterial hypertension (PAH) associated with congenital heart diseases (CHD). It is caused by simple or complex CHD with a large systemic-to-pulmonary shunt. When the pulmonary pressure exceeds the systemic pressure, the shunt reverses and central cyanosis appears. ES is a progressive and fatal condition, and it is accompanied by an increased risk of a range of potentially life-threatening complications. Patients with ES are both at risk for bleeding, due to damaged capillaries and high pressure, and for in situ pulmonary thrombosis, related to hyper-viscosity and slow blood flow in dilated pulmonary arteries. Moreover, the enlarged main pulmonary arteries and cardiac chambers may determine displacement or extrinsic compression on airways, pulmonary veins, coronary arteries, and other mediastinal structures. The clinical effects may be diverse, such as respiratory difficulties, localized pulmonary edema, cardiac dysfunction, or sudden death. Multidetector computed tomography (MDCT) allows to accurately assess in a single examination, pulmonary parenchyma and vessels, coronary artery origin, and heart chambers. The aim of this review was to illustrate the thoracic MDCT angiography findings and complications of adult patients with PAH-CHD and in particular of those with ES.

Pulmonary veno-occlusive disease: the role of CT.

OBJECTIVE: The authors sought to evaluate the diagnostic accuracy of high-resolution computed tomography (HRCT) in the detection of pulmonary veno-occlusive disease (PVOD) in patients with pre-capillary pulmonary arterial hypertension (PAH) of unknown aetiology, and to identify the role of CT in diagnosis and therapy. MATERIALS AND METHODS: The CT scans of 96 patients were retrospectively reviewed and assessed for specific HRCT findings: ground-glass opacities, septal lines and mediastinal lymph nodal enlargement (short diameter ≥1 cm). According to the HRCT findings, patients were divided into PVOD-suspicious and not PVOD-suspicious. Subsequently, a clinical-instrumental evaluation was performed, and the response to therapy and histopathological reports were evaluated. RESULTS: Radiological evaluation based on HRCT findings revealed 29 patients as PVOD-suspicious and 67 as not PVOD-suspicious. The final diagnosis was PVOD in 22 patients and idiopathic PAH in 74 patients. The CT scan showed 95.5 % sensitivity, 89% specificity, 72.5% positive predictive value, and 98.5% negative predictive value, with a diagnostic accuracy of 90.5% in identifying patients with PVOD. CONCLUSIONS: Chest CT can be considered a screening test in the assessment of patients with PAH of unknown aetiology, and the radiologist can help the clinician to identify patients with CT findings that make PVOD highly probable.

A foreign body aspiration in a preschool child mimicking a multitrigger wheezing: a case report and review of the literature.

We report a child with a history of recurrent episodes of wheezing. At 3 months of age, the frequency of these episodes began to increase. Wheezing was associated with persistent cough and dyspnea with nocturnal awakening. The skin prick test was positive for pollen and pet dander. Airway endoscopy revealed the presence of a peanut, which obstructed the left main bronchus. Chronic cough and recurrent wheezing with symptoms between acute exacerbations could be signs not only of asthma but also of other disorders. Therefore, coexisting conditions should be evaluated whenever symptoms seem to be unusually severe or frequent.

Lung neovascularity in pulmonary arterial hypertension associated with congenital heart defects and idiopathic pulmonary arterial hypertension: study of 198 patients.

OBJECTIVES: To correlate the severity of lung neovascularity (Sheehan vessels) with the cause and haemodynamic severity of pulmonary arterial hypertension (PAH), pulmonary artery (PA) size and heart disease type in patients with PH associated with congenital heart diseases (PAH-CHD) and idiopathic PH (IPAH). METHODS: We reviewed the HRCT and CT pulmonary angiography studies of 87 patients with PAH-CHD and 111 with IPAH; all had undergone right heart catheterisation. We evaluated the PA size and severity of neovascularity on CT. RESULTS: Neovascularity, which was found in 72% of PAH-CHD (56% with Eisenmenger's syndrome) and in 22% of IPAH patients, is significantly related to the severity of PH and all patients with severe neovascularity had intermediate or high PH. All PAH-CHD patients had a dilated PA with a greater risk of developing severe dilatation (diameter >5 cm). The neovascularity correlated with the PA size only in IPAH. CONCLUSIONS: Neovascularity even if not pathognomonic for PAH-CHD, is significantly more common in these patients, especially in Eisenmenger's syndrome. It is often the first CT sign to indicate the severity of PH in PAH-CHD and IPAH. A neovascularity ≥5 on CT indicates a intermediate or high PH. KEY POINTS: • Large retrospective studying specific lung disorders in patients with pulmonary arterial hypertension. • Neovascularity is often the first CT sign indicating the severity of pulmonary hypertension Alterations of lung parenchyma on CT in pulmonary hypertension are described • The first study to assess the severity of pulmonary hypertension by CT • If substantiated, CT might eventually replace some cardiac catheterisation for evaluating PH.

Incidental vertebral compression fractures in imaging studies: Lessons not learned by radiologists.

AIM: To assess radiologists reporting rates of incidental vertebral compression fractures in imaging studies. METHODS: We performed a review of the current literature on the prevalence and reporting rates of incidental vertebral compression fractures in radiologic examinations. RESULTS: The bibliographic search revealed 12 studies: 7 studies using conventional radiology and 5 using multidetector computed tomography (MDCT). The loss of height cut-off to define a vertebral fracture varied from 15% to 25%. Fracture prevalence was high (mean 21.1%; range 9.5%-35%) in both radiographic and MDCT studies (mean 21.6% and 20.2%, respectively). Reporting rates were low with a mean value of 27.4% (range 0%-66.3%) and were significantly lower in MDCT than in radiographic studies (mean 8.1% vs 41.1%). Notably, recent studies showed lower reporting rates than older studies. CONCLUSION: Many scientific studies have confirmed a high prevalence of vertebral compression fractures as incidental findings on imaging studies. However, the underreporting of these fractures, as determined in our study, may negatively affect patient care.

DISH of the cervical spine causing epiglottis impingement.

Diffuse idiopathic skeletal hyperostosis (DISH) is a condition characterized by calcification and ossification of ligaments and entheses; it mainly affects the vertebral column. We report the case of a patient with pharyngeal dysphagia and episodic aspiration secondary to DISH involvement of the cervical spine, which had caused alteration in the epiglottic tilt mechanism during deglutition.

Emergency ultrasound and gallstone ileus.

Gallstone ileus is an uncommon cause of mechanical obstruction due to a biliary stone that wedges the intestinal lumen. It is a surgical emergency representing a clinical and diagnostic challenge: the clinical manifestations are rarely specific, often causing diagnostic delay that can adversely affect the prognosis. Emergency ultrasound could be useful in assessing the level and identifying the cause of bowel obstruction. We report a case of a 74-year-old patient with a 6-day history of constipation and crampy abdominal pain without previous history of abdominal diseases. Emergency ultrasound led to an early diagnosis showing dilated small bowel loops with a shadowing mass inside consistent with an ileal stone, in the absence of aberrant located stone on plain abdominal film.