A Novel Deep Learning Network and Its Application for Pulmonary Nodule Segmentation.

Pulmonary nodules are the early manifestation of lung cancer, which appear as circular shadow of no more than 3 cm on the computed tomography (CT) image. Accurate segmentation of the contours of pulmonary nodules can help doctors improve the efficiency of diagnosis. Deep learning has achieved great success in computer vision. In this study, we propose a novel network for pulmonary nodule segmentation from CT images based on U-NET. The proposed network has two merits: one is that it introduces dense connection to transfer and utilize features. Additionally, the problem of gradient disappearance can be avoided. The second is that it introduces a new loss function which is tolerance on the pixels near the borders of the nodule. Experimental results show that the proposed network at least achieves 1% improvement compared with other state-of-art networks in terms of different criteria.

Hyperthyroidism Presenting with Coronary Vasospasm.

Hyperthyroidism is associated with a number of heart diseases, and it may aggravate previous cardiac problems or cause new ones, such as hyperthyroid cardiopathy. Cases of hyperthyroidism presenting with coronary vasospasm are rarely reported. Herein, we present a case of a 54-year male patient with recurrent left chest pain for 2 months. Coronary angiography showed no obvious coronary artery stenosis, and coronary vasospasm was suspected. After admission, the patient's thyroid function and TSH-receptor antibody (TRAb) were abnormal. However, there was no obvious palpitation, hyperhidrosis, or weight loss, and the diagnosis of Graves' disease was rendered, which seemed to be the cause of coronary vasospasm. The patient did not experience chest pain after treatment with methimazole. Patients with coronary vasospasm should be investigated for the possibility of hyperthyroidism. Key Words: Hyperthyroidism, Chest pain, Coronary angiography, Coronary vasospasm.