Breast tumor segmentation in medical images is a decisive step for diagnosis and treatment follow-up. Automating this challenging task helps radiologists to reduce the high manual workload of breast cancer analysis. In this paper, we propose two deep learning approaches to automate the breast tumor segmentation in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) by building two fully convolutional neural networks (CNN) based on SegNet and U-Net. The obtained models can handle both detection and segmentation on each single DCE-MRI slice. In this study, we used a dataset of 86 DCE-MRIs, acquired before and after two cycles of chemotherapy, of 43 patients with local advanced breast cancer, a total of 5452 slices were used to train and validate the proposed models. The data were annotated manually by an experienced radiologist. To reduce the training time, a high-performance architecture composed of graphic processing units was used. The model was trained and validated, respectively, on 85% and 15% of the data. A mean intersection over union (IoU) of 68.88 was achieved using SegNet and 76.14% using U-Net architecture.

No abstract

No abstract

Mycobacterium marinum is the cause of opportunistic infections in man. Although its clinical presentation is usually cutaneous, osteoarticular infections are not rare and should be rapidly diagnosed. Orthopaedic surgeons may have to manage a patient with this mycobacterial infection and should be able to make this diagnosis based on information about the patient's history and clinical criteria. Lesions develop from a skin wound, with a single nodule or a bright purplish-red patch with papules; they also may be inflamed or may abscess. Secondary lesions may develop as the disease progresses. Aquatic exposure is the most important factor to look for. We report three cases of this infection with a delayed diagnosis. Response to treatment and an absence of complications are correlated with an early diagnosis.

Internet of Things is becoming widely present in our daily life. In fact, more and more devices able to interact together have been recently designed and launched in the market. Learning Internet of Things technologies is becoming unavoidable in education. In this paper, we propose a practical approach allowing to progressively learn, by practice the, essential concepts of Internet of Things applied to Smart Homes. From basic knowledge of C++ language and the use of Arduino or its derived, students can develop skills and also smart applications in the field of Internet of Things.