Deep-active-learning approach towards accurate right ventricular segmentation using a two-level uncertainty estimation.

The Right Ventricle (RV) is currently recognised to be a significant and important prognostic factor for various pathologies. Its assessment is made possible using Magnetic Resonance Imaging (CMRI) short-axis slices. Yet, due to the challenging issues of this cavity, radiologists still perform its delineation manually, which is tedious, laborious, and time-consuming. Therefore, to automatically tackle the RV segmentation issues, Deep-Learning (DL) techniques seem to be the axis of the most recent promising approaches. Along with its potential at dealing with shape variations, DL techniques highly requires a large number of labelled images to avoid over-fitting. Subsequently, with the produced large amounts of data in the medical industry, preparing annotated datasets manually is still time-consuming, and requires high skills to be accomplished. To benefit from a significant number of labelled and unlabelled CMRI images, a Deep-Active-Learning (DAL) approach is proposed in this paper to segment the RV. Thus, three main steps are distinguished. First, a personalised labelled dataset is gathered and augmented to allow initial learning. Secondly, a U-Net based architecture is modified towards efficient initial accuracy. Finally, a two-level uncertainty estimation technique is settled to enable the selection of complementary unlabelled data. The proposed pipeline is enhanced with a customised postprocessing step, in which epistemic uncertainty and Dense Conditional Random Fields are used. The proposed approach is tested on 791 images gathered from 32 public patients and 1230 images of 50 custom subjects. The obtained results show an increased dice coefficient from 0.86 to 0.91 with a decreased Hausdorff distance from 7.55 to 7.45.

SARS-CoV-2 diagnosis using medical imaging techniques and artificial intelligence: A review.

OBJECTIVE: SARS-CoV-2 is a worldwide health emergency with unrecognized clinical features. This paper aims to review the most recent medical imaging techniques used for the diagnosis of SARS-CoV-2 and their potential contributions to attenuate the pandemic. Recent researches, including artificial intelligence tools, will be described. METHODS: We review the main clinical features of SARS-CoV-2 revealed by different medical imaging techniques. First, we present the clinical findings of each technique. Then, we describe several artificial intelligence approaches introduced for the SARS-CoV-2 diagnosis. RESULTS: CT is the most accurate diagnostic modality of SARS-CoV-2. Additionally, ground-glass opacities and consolidation are the most common signs of SARS-CoV-2 in CT images. However, other findings such as reticular pattern, and crazy paving could be observed. We also found that pleural effusion and pneumothorax features are less common in SARS-CoV-2. According to the literature, the B lines artifacts and pleural line irregularities are the common signs of SARS-CoV-2 in ultrasound images. We have also stated the different studies, focusing on artificial intelligence tools, to evaluate the SARS-CoV-2 severity. We found that most of the reported works based on deep learning focused on the detection of SARS-CoV-2 from medical images while the challenge for the radiologists is how to differentiate between SARS-CoV-2 and other viral infections with the same clinical features. CONCLUSION: The identification of SARS-CoV-2 manifestations on medical images is a key step in radiological workflow for the diagnosis of the virus and could be useful for researchers working on computer-aided diagnosis of pulmonary infections.

Chest CT-scan finding of asymptomatic COVID-19 pneumonia: a prospective 542 patients' single center study.

Since asymptomatic infections as "covert transmitter", and some patients can progress rapidly in the short term, it is essential to pay attention to the diagnosis and surveillance of asymptomatic patients with SARS-COV2 infection. CT scan has great value in screening and detecting patients with COVID-19 pneumonia, especially in the highly suspected or probable asymptomatic cases with negative RT-PCR for SARS-COV2. This study aimed to detect incidentally COVID-19 pneumonia on medical imaging for patients consulting for other reasons.

Temporal choroidal fissure cyst: a rare cause of temporal lobe epilepsy.

Only a few cases of temporal choroidal fissure cyst are reported. We describe a new case of an 8 years old girl who manifested complex partial seizure. The diagnosis was made by magnetic resonance imagining (MRI). The signal intensity of the cyst was identical to the cerebrospinal fluid (CSF), and the underlying hippocampus was compressed by the cyst. The seizures were medically controlled. The value of MRI in the diagnosis and medical treatment will be discussed.

A Spatiotemporal exploration and 3D modeling of blood flow in healthy carotid artery bifurcation from two modalities: Ultrasound-Doppler and phase contrast MRI.

In the present study, we investigated the velocity profile over the carotid bifurcation in ten healthy volunteers by combining velocity measurements from two imaging modalities (PC-MRI and US-Doppler) and hemodynamic modeling in order to determine the optimal combination for the most realistic velocity estimation. The workflow includes data acquisition, velocity profile extraction at three sites (CCA, ECA and ICA), the arterial geometrical model reconstruction, a mesh generation and a rheological modeling. The results showed that US-Doppler measurements yielded higher velocity values as compared to PC-MRI (about 26% shift in CCA, 52% in ECA and 53% in ICA). This implies higher simulated velocities based on US-Doppler inlet as compared to simulated velocities based on PC-MRI inlet. Overall, PC-MRI inlet based simulations are closer to measurements than US-Doppler inlet based simulations. Moreover, the measured velocities showed that blood flow keeps a parabolic sectional profile distal from CCA, ECA and ICA, while being quite disturbed in the carotid sinus with a significant decrease in magnitude making this site very prone to atherosclerosis.

Age estimation at death by the study of chest plate radiographs: establishing a Tunisian male score.

We aim to establish a Tunisian score for age estimation through the study of chest plate's radiographs of a Tunisian male sample. We have focused on the study of 128 chest plate radiographs of Tunisian male individuals. We have established a score of eight criteria. The total score ranges from 8 to 32. Three observers scored double-blind the X-ray films. We studied the correlation of each criterion as well as the total score with chronological age for each observer. We also tested the reproducibility and the repeatability of criteria and total score. We calculated the estimated age for each score. We studied the relationship between the estimated age and the chronological age. The correlation between the total score and the chronological age has been good for the three observers (0.746, 0.756 and 0.742). The total score gives an estimation of age with a standard deviation of ± 5.88 years and a confidence interval of 95%, the interval's width increases gradually from 6.9 years to 23 years.

The role of imaging in the management of sinonasal mucoceles.

Mucoceles are slow-growing paranasal sinus cystic masses whose clinical presentation varies according to the affected sinus. Diagnosis is often radiological, based essentially on CT scan. The aim of this work was to study the radiologic characteristics of mucoceles on CT scan and MRI. We conducted a retrospective study of patients with mucoceles explored by imaging and operated on in our department. In our series, fronto-ethmoidal sinuses were the most frequently affected (81%). Facial scan confirmed the diagnosis in the majority of cases. Magnetic resonance imaging (MRI) was performed in 4 cases. Eleven patients were operated on by endonasal approach, three by external approach and one by combined surgical approach. Recurrence was observed in two patients after an average delay of 24 months. CT scan is considered the method of choice in the investigation of mucoceles. MRI is indicated in some cases to assess any orbital or intracranial extension.

Case Report: Coronary artery stent infection with mycotic aneurysm secondary to tricuspid valve infective endocarditis.

Coronary artery stent infection with mycotic aneurysm is a rare life-threatening complication following coronary angioplasty, usually requiring surgical intervention. Reaching and confirming the diagnosis remains the most challenging aspect of this complication. We describe an unusual case of bare metal stent infection and coronary artery aneurysm in the setting of tricuspid valve infective endocarditis, resulting in ST elevation myocardial infarction, with a favorable outcome after primary angioplasty and antibiotic therapy. In the current era of growth of coronary stent implantation, it's important for clinicians to consider and to prevent such potentially fatal events. The diagnosis process remains difficult and requires the association of multiple clinical, biological and imaging parameters. Although treatment modalities tend to favor surgery, we showed that coronary angioplasty could be a successful alternative solution.

Strangulated obturator hernia: a case report with literature review.

Obturator hernia is rare. It occurs when part of the pelvic contents protrude through the obturator foramen. It is a diagnostic challenge in the emergency department since the signs and symptoms are non-specific. It often occurs in elderly, emaciated and chronically ill women. The clinical picture include intestinal obstruction with abdominal pain, nausea and vomiting. The treatment is only surgical. Delayed diagnosis of this condition usually leads to a high mortality rate. We report the case of an 83-year-old woman with a strangulated obturator hernia. The hernia was discovered early by computed tomography and was treated by emergency laparotomy. We emphasize on the rule of CT scan to establishing a prompt preoperative diagnosis of an obturator hernia, appropriate planning of surgical intervention and thus optimizing the outcome.

Orbital varix: rare cause of blepharospasm.

Orbital varix (or varicose) is an exceptional pathology with poor clinical sign. The blepharospasm can be a revealing cause. The long-term risk is optic atrophy and blindness. Magnetic resonance imaging is the best diagnostic tools. The rise of lesion dimensions by Valsalva maneuvers and prone position is characteristic. We report the observation of a 42-year-old young man, consulting for a blepharospasm of the left eye evolving for two years. Imaging investigations made the diagnosis of orbital varicose.

Postpartum sacral stress fracture associated with mechanical sacroiliac joint disease: A case report.

RATIONALE: Stress fractures of the sacrum and mechanical sacroiliac joint disease can occur not only during pregnancy but also postpartum. Mechanical sacroiliac joint disease is common in patients with low back pain but often misdiagnosed by practitioners. The association of the 2 conditions has not been studied yet. PATIENT CONCERNS: A 37-year-old woman physiatrist presented with 8-week history of persistent low back and left buttock pain that started in the third trimester of her pregnancy. DIAGNOSES: Laboratory investigation, dual-energy x-ray absorptiometry, magnetic resonance imaging, and CT of the pelvic region were performed. The patient was diagnosed with postpartum sacral stress fracture associated with mechanical sacroiliac joint disease. INTERVENTIONS: Treatment consisted in pain killers and tailored to a nonweight-bearing period of 3 months. OUTCOMES: Painful symptoms disappeared and the patient was able to walk and perform other daily activities normally. LESSONS: Clinician should be aware of the clinical context and the possible association of these 2 conditions in order to undertake an early and appropriate treatment.

Posttraumatic Uncal Herniation in a Conscious Patient.

The incidence of primary traumatic oculomotor nerve palsies in craniocerebral trauma is approximately 1.2% and is usually persistent and associated with loss of consciousness, other neurologic deficits, and skull base or orbital fractures. This case is a rare demonstration of complete left third nerve palsy from uncal herniation after trauma without any loss of consciousness.