Enhancing physicians' radiology diagnostics of COVID-19's effects on lung health by leveraging artificial intelligence.

Introduction: This study aimed to develop an individualized artificial intelligence model to help radiologists assess the severity of COVID-19's effects on patients' lung health. Methods: Data was collected from medical records of 1103 patients diagnosed with COVID-19 using RT- qPCR between March and June 2020, in Hospital Madrid-Group (HM-Group, Spain). By using Convolutional Neural Networks, we determine the effects of COVID-19 in terms of lung area, opacities, and pulmonary air density. We then combine these variables with age and sex in a regression model to assess the severity of these conditions with respect to fatality risk (death or ICU). Results: Our model can predict high effect with an AUC of 0.736. Finally, we compare the performance of the model with respect to six physicians' diagnosis, and test for improvements on physicians' performance when using the prediction algorithm. Discussion: We find that the algorithm outperforms physicians (39.5% less error), and thus, physicians can significantly benefit from the information provided by the algorithm by reducing error by almost 30%.

Biomechanical modelling of the pelvic system: improving the accuracy of the location of neoplasms in MRI-TRUS fusion prostate biopsy.

BACKGROUND: An accurate knowledge of the relocation of prostate neoplasms during biopsy is of great importance to reduce the number of false negative results. Prostate neoplasms are visible in magnetic resonance images (MRI) but it is difficult for the practitioner to locate them at the time of performing a transrectal ultrasound (TRUS) guided biopsy. In this study, we present a new methodology, based on simulation, that predicts both prostate deformation and lesion migration during the biopsy. METHODS: A three-dimensional (3-D) anatomy model of the pelvic region, based on medical images, is constructed. A finite element (FE) numerical simulation of the organs motion and deformation as a result of the pressure exerted by the TRUS probe is carried out using the Code-Aster open-source computer software. Initial positions of potential prostate lesions prior to biopsy are taken into consideration and the final location of each lesion is targeted in the FE simulation output. RESULTS: Our 3-D FE simulations show that the effect of the pressure exerted by the TRUS probe is twofold as the prostate experiences both a motion and a deformation of its original shape. We targeted the relocation of five small prostate lesions when the TRUS probe exerts a force of 30 N on the rectum inner wall. The distance travelled by these lesions ranged between 5.6 and 13.9 mm. CONCLUSIONS: Our new methodology can help to predict the location of neoplasms during a prostate biopsy but further studies are needed to validate our results. Moreover, the new methodology is completely developed on open-source software, which means that its implementation would be affordable to all healthcare providers.

Effects of walking in deep venous thrombosis: a new integrated solid and fluid mechanics model.

Deep venous thrombosis (DVT) is a common disease. Large thrombi in venous vessels cause bad blood circulation and pain; and when a blood clot detaches from a vein wall, it causes an embolism whose consequences range from mild to fatal. Walking is recommended to DVT patients as a therapeutical complement. In this study the mechanical effects of walking on a specific patient of DVT were simulated by means of an unprecedented integration of 3 elements: a real geometry, a biomechanical model of body tissues, and a computational fluid dynamics study. A set of computed tomography images of a patient's leg with a thrombus in the popliteal vein was employed to reconstruct a geometry model. Then a biomechanical model was used to compute the new deformed geometry of the vein as a function of the fiber stretch level of the semimembranosus muscle. Finally, a computational fluid dynamics study was performed to compute the blood flow and the wall shear stress (WSS) at the vein and thrombus walls. Calculations showed that either a lengthening or shortening of the semimembranosus muscle led to a decrease of WSS levels up to 10%. Notwithstanding, changes in blood viscosity properties or blood flow rate may easily have a greater impact in WSS.

Traducción de artículos al inglés / English translation of manuscripts

No disponible

Effect of anticoagulant treatment in deep vein thrombosis: A patient-specific computational fluid dynamics study.

A methodology that might help physicians to establish a diagnostic and treatment tailored for each specific patient with a pathological thrombus is presented. A realistic model for the geometry of a popliteal vein with a thrombus just above the knee was reconstructed from in vivo computed tomography images acquired from one specific patient and then it was used to perform computational fluid dynamics (CFD) simulations. The wall shear stress (WSS) response to the administration of anticoagulant drugs and the influence of viscosity on the shape of the velocity distribution were investigated. Both a Newtonian and a non-Newtonian viscosity model were implemented for different blood flow rates in the range 3-7 cm(3)/s. The effect of anticoagulants on the blood was simulated by setting three different levels of viscosity in the Newtonian model (µ/µ∞=0.60, 0.80 and 1 with µ∞=3.45×10(-3) Pas). A reduction of µ by a given amount always led to a more modest reduction, typically by a factor of two, of the resulting WSS levels. Moreover, for a given flow rate the calculation with the non-Newtonian viscosity model yielded WSS levels between 20% and 40% larger than those obtained in the corresponding Newtonian fluid simulation. It was also found that blood moves slowly in the region between the thrombus and the vein wall, a fact that will favor the growth of the thrombotic mass. Both the mean WSS levels and the degree of sluggishness of the blood flow can be described by functions of the Reynolds number.

Focal splenic FDG uptake in a patient with Kala-Azar (visceral leishmaniasis).

We present a woman with a history of Gaucher disease and secondary portal hypertension. She went to hospital for treatment of resistant fever without apparent cause. A conventional study of fever of unknown origin did not show any pathology. For this reason, she was referred to our department for a PET/CT, which did not demonstrate a cause for the fever. Two months after, she was admitted again in hospital for fever recurrence. A new PET/CT showed FDG avid hypodense splenic lesions, suspicious for infection. Splenectomy was performed and histopathologic analysis demonstrated intracellular organisms compatible with Leishmania.

Soft tissue solitary fibrous tumor. Imaging findings in a series of nine cases.

OBJECTIVE: Few articles have been published regarding the imaging characteristics of soft tissue solitary fibrous tumors (SFT). The aim of this study is to describe the radiological features in a series of nine patients and to compare these results with pathological and clinical outcome. SUBJECTS AND METHODS: Nine cases of soft tissue SFT, confirmed by an experienced tumor pathologist, were studied with imaging techniques (US and MRI). Tumor location, size, morphology, local invasion, vascularity, MRI signal intensities, and dynamic contrast-enhancement patterns were recorded. Tumors were subclassified into cellular, fibrous, and giant cell forms histologically. RESULTS: The most common findings were a well-defined, polylobulated mass that tended to displace adjacent structures. The extremities were the most frequent site of presentation. The tumors showed high vascularity in all imaging studies. The radiological features that correlated better with malignant criteria were tumor size, heterogeneous signal intensity, and heterogeneous uptake of contrast on MRI. On dynamic contrast-enhanced (DCE) sequences, three tumors showed a biphasic curve (type IV) and one a progressive uptake curve (type II). The latter recurred twice after extensive local surgery and was classified as a giant cell variant. CONCLUSION: In this study a retrospective review of nine new cases of soft tissue SFT was carried out. The presence of a large solid, highly vascularized mass with a prominent vascular pedicle that displaces adjacent structures may suggest the diagnosis of an SFT. DCE sequences might help identify those tumors with worse clinical outcome, but a study with a larger series of patients is needed.