Cystic adventitial disease of the popliteal artery with unusual spontaneous regression: A case report with literature review.

This report highlights the case of cystic adventitial disease of the left popliteal artery in a 45-year-old male patient. Imaging modalities confirmed the diagnosis and high resolution MRI found a cystic connection to the adjacent knee joint. The evolution was unusual with spontaneous regression of the symptoms.

Distance education in times of covid 19: a leap into the future?

INTRODUCTION: Online education has grown a lot in recent months in our country during the global health crisis (COVID19). It has been widely used at all levels and fields of education ranging from elementary school to graduate and postgraduate studies. The aim of this study is to evaluate this teaching method compared to classical face-to-face teaching by referring to the learner's point of view. METHODS: It was a prospective and descriptive cross-sectional study targeting residents in medical imaging (all levels approximately 200 people) It was based on an online questionnaire sent to all residents after attending synchronous online teaching sessions at the College of Medical Imaging and Nuclear Medicine. The assessment was done by the learners using a 5 points Likert scale. RESULTS:    Ninety-seven residents answered the questionnaire. Sixty percent of our learners were satisfied with this new way of teaching. 73% of the students found the logistical means suitable for this course. The main advantages noted by our residents were accessibility to sessions from any location and the ability to replay lessons later. The weaknesses put forward were the lack of interaction with the teacher compared to face-to-face teaching and the occurrence of technical problems which could sometimes hamper the smooth running of the sessions. CONCLUSION: Our study allowed us to get feedback from our learners on this teaching. The multiplication of learning means, in particular a hybrid education should be considered to overcome the shortcomings of exclusive online teaching.

A bilinear convolutional neural network for lung nodules classification on CT images.

PURPOSE: Lung cancer is the most frequent cancer worldwide and is the leading cause of cancer-related deaths. Its early detection and treatment at the stage of a lung nodule improve the prognosis. In this study was proposed a new classification approach named bilinear convolutional neural network (BCNN) for the classification of lung nodules on CT images. METHODS: Convolutional neural network (CNN) is considered as the leading model in deep learning and is highly recommended for the design of computer-aided diagnosis systems thanks to its promising results on medical image analysis. The proposed BCNN scheme consists of two-stream CNNs (VGG16 and VGG19) as feature extractors followed by a support vector machine (SVM) classifier for false positive reduction. Series of experiments are performed by introducing the bilinear vector features extracted from three BCNN combinations into various types of SVMs that we adopted instead of the original softmax to determine the most suitable classifier for our study. RESULTS: The method performance was evaluated on 3186 images from the public LUNA16 database. We found that the BCNN [VGG16, VGG19] combination with and without SVM surpassed the [VGG16]2 and [VGG19]2 architectures, achieved an accuracy rate of 91.99% against 91.84% and 90.58%, respectively, and an area under the curve (AUC) rate of 95.9% against 94.8% and 94%, respectively. CONCLUSION: The proposed method improved the outcomes of conventional CNN-based architectures and showed promising and satisfying results, compared to other works, with an affordable complexity. We believe that the proposed BCNN can be used as an assessment tool for radiologists to make a precise analysis of lung nodules and an early diagnosis of lung cancers.

Deep learning-based CAD schemes for the detection and classification of lung nodules from CT images: A survey.

BACKGROUND: Lung cancer is the most common cancer in the world. Computed tomography (CT) is the standard medical imaging modality for early lung nodule detection and diagnosis that improves patient's survival rate. Recently, deep learning algorithms, especially convolutional neural networks (CNNs), have become a preferred methodology for developing computer-aided detection and diagnosis (CAD) schemes of lung CT images. OBJECTIVE: Several CNN-based research projects have been initiated to design robust and efficient CAD schemes for the detection and classification of lung nodules. This paper reviews the recent works in this area and gives an insight into technical progress. METHODS: First, a brief overview of CNN models and their basic structures is presented in this investigation. Then, we provide an analytic comparison of the existing approaches to discover recent trend and upcoming challenges. We also introduce an objective description of both handcrafted and deep learning features, as well as the types of nodules, the medical imaging modalities, the widely used databases, and related works in the last three years. The articles presented in this work were selected from various databases. About 57% of reviewed articles published in the last year. RESULTS: Our analysis reveals that several methods achieved promising performance with high sensitivity rates ranging from 66% to 100% under the false-positive rates ranging from 1 to 15 per CT scan. It can be noted that CNN models have contributed to the accurate detection and early diagnosis of lung nodules. CONCLUSIONS: From the critical discussion and an outline for prospective directions, this survey provide researchers valuable information to master the deep learning concepts and to deepen their knowledge of the trend and latest techniques in developing CAD schemes of lung CT images.

Interstitial lung diseases: Imaging contribution to diagnosis and elementary radiological lesions.

Interstitial pneumonias comprise a heterogeneous group of disorders in which a multidisciplinary approach is important for accuracy in diagnosis; indeed, one might say, even mandatory. The team of collaborators should include radiologists, because high resolution computed tomography (HRCT) of the thorax is the first, and most of times, the only imaging examination to be prescribed after chest X-ray. Elementary lesions of the interstitium can be accurately described with HRCT, inasmuch as lung windowing with sharp filtering in this technique reproduces the microscopic features of the lung. Guidance of bronchoalveolar lavage and biopsy procedures is also possible with HRCT.

Posterior mediastinal angiomyxolipoma with spinal canal extension.

BACKGROUND: Angiomyxolipoma is a benign tumor considered as a variant of lipoma and that occurs mainly in the subcutis. The mediastinal location hasn't been previously reported. AIM: To describe the radiological features of this tumor in its posterior mediastinal location and to confront them to the pathological features. CASE REPORT: We report the case of a 49-year-old woman who was admitted for chest wall pain and neurologic disturbance of her two lower limbs. The chest X-ray showed a posterior mediastinal opacity. On CT examination, this mass contained some small areas of fat and enhanced intensely. Microscopic examination of the excised mass confirmed the diagnosis of posterior mediastinal angiomyxolipoma. CONCLUSION: Mediastinal location of angiomyxolipoma hasn't been previously reported. Clinicians and radiologists should be aware that this diagnosis should be suggested, among others, when there is a posterior mediastinal mass that contains fat and that intensely enhances with a possible spinal cord extension.

Imaging of thoracic textiloma.

OBJECTIVE: Intrathoracic textiloma or gossypiboma, a retained surgical sponge in the thoracic cavity, is an exceptional but serious complication following thoracic or abdominal surgery. The purpose of this work is to highlight the topographic features of thoracic textiloma and to describe imaging aspects, and, particularly, computed tomography (CT) features. METHODS: Eight patients have been operated in our thoracic surgery department for thoracic gossypiboma. In the past, three patients had undergone hepatic surgery and the five others had a history of thoracic surgery. All the patients had a chest radiograph, five of them had a thoracic ultrasonography, all had a chest CT, and one patient had a chest magnetic resonance imaging (MRI). RESULTS: In patients with a history of abdominal surgery, the foreign body was located in the parenchyma of the right lower lobe. In the other patients, the foreign body was either intrapleural or mediastinal. Ultrasonography suggested the diagnosis of textiloma in three of the five patients by demonstrating a non-calcified hyperechoic mass with acoustic shadow. At CT, the gossypiboma was a low-attenuating mass containing trapped gas lucencies in six patients and it was a high-attenuating mass in two patients. MRI showed a diaphragmatic defect in one patient with an intrapulmonary gossypiboma that migrated from the abdomen. CONCLUSIONS: The CT aspect of thoracic gossypiboma may be different according to pleural or parenchymal location. The spongiform appearance, characteristic in abdominal gossypiboma, is not the only CT presentation of thoracic gossypiboma. The confrontation of the surgical history with the CT signs helps to have a preoperative diagnosis.

Acute pulmonary embolism: epidemiologic and tomodensitometric study.

BACKGROUND: Acute pulmonary embolism is a common disease with substantial morbidity and mortality in untreated patients. It requires an urgent positive diagnosis. AIM: To assess the prevalence of acute pulmonary embolism and calculate the sensitivity and specificity of multidetector CT for the diagnosis of acute pulmonary embolism in a hospital specialized in cardio-thoracic diseases. METHODS: This is a prospective study conducted at Abderrahmen Mami Hospital, which included 200 consecutive patients suspected of acute pulmonary embolism and explored by a multidetector CT pulmonary angiography (16 slices). RESULTS: Prevalence of acute pulmonary embolism was calculated at 37.5%. The multidetector CT has enabled an alternative diagnosis in 46 patients (40%). The sensitivity and specificity of multidetector CT were calculated respectively 89.6% and 100%. CONCLUSION: The prevalence of acute pulmonary embolism, in a hospital specialized in cardio-thoracic diseases, is higher than that found in general hospitals. High sensitivity and specificity of multidetector CT makes it the gold standard for the diagnosis of pulmonary embolism.

Castleman's disease: an intrapulmonary form with intrafissural development.

Castleman's disease (CD) is an uncommon, mainly benign, lymphoproliferative disorder of unknown etiology, mostly involving the mediastinum. Parenchymal lung involvement of the disease is exceedingly rare. We describe a case of CD in a 23-year-old woman with a 4-year history of recurring dyspnea and nonproductive cough, whose chest X-ray showed an abnormal shadow of the right hilum. Chest computed tomography confirmed the presence of a tissue-density mass of the right lower lobe, demonstrating poor contrast enhancement, associated with multiple laterotracheal and mediastinal lymphadenopathies. The patient underwent curative surgery, revealing a right hilar compressive mass, with an intrafissural development between the superior and middle lobes. Pneumonectomy was performed due to profuse bleeding. This case of CD is particular because of its unusual intrapulmonary location and its intrafissural development. Poor contrast enhancement is atypical in CD.