Attention deficit/hyperactivity disorder (ADHD) is a behavioral disorder syndrome found mainly in school-age population. At present, the diagnosis of ADHD mainly depends on the subjective methods, leading to the high rate of misdiagnosis and missed-diagnosis. To solve these problems, we proposed an algorithm for classifying ADHD objectively based on convolutional neural network. At first, preprocessing steps, including skull stripping, Gaussian kernel smoothing, et al., were applied to brain magnetic resonance imaging (MRI). Then, coarse segmentation was used for selecting the right caudate nucleus, left precuneus, and left superior frontal gyrus region. Finally, a 3 level convolutional neural network was used for classification. Experimental results showed that the proposed algorithm was capable of classifying ADHD and normal groups effectively, the classification accuracies obtained by the right caudate nucleus and the left precuneus brain regions were greater than the highest classification accuracy (62.52%) in the ADHD-200 competition, and among 3 brain regions in ADHD and the normal groups, the classification accuracy from the right caudate nucleus was the highest. It is well concluded that the method for classification of ADHD and normal groups proposed in this paper utilizing the coarse segmentation and deep learning is a useful method for the purpose. The classification accuracy of the proposed method is high, and the calculation is simple. And the method is able to extract the unobvious image features better, and can overcome the shortcomings of traditional methods of MRI brain area segmentation, which are time-consuming and highly complicate. The method provides an objective diagnosis approach for ADHD.
Objective To assess clinical value of thyroidectomy by meticulous capsular dissection technique through neck incision approach in treatment of 75 patients with type Ⅰ substernal goiter. Methods The clinical data of 75 patients with type Ⅰ substernal goiter in the Department of General Surgery of the Central Hospital of Xiaogan from April 2013 to April 2017 were retrospectively analyzed. These patients received the surgical resection by the meticulous capsular dissection technique with an ultrasonic scalpel and a bipolar coagulation forcep through neck incision approach. Results There were 12 Hashimoto thyroiditis, 10 thyroid adenoma, 41 nodular goiter, and 12 thyroid carcinoma in the 75 patients with type Ⅰ substernal goiter. Five cases underwent the unilateral total thyroidectomy. Fifty-eight cases underwent the bilateral total thyroidectomy. The bilateral total thyroidectomy plus central lymph node dissection were performed in the 9 patients with thyroid carcinoma, the bilateral total thyroidectomy plus central lymph node dissection plus affected ipsilateral neck lymph node dissection were performed in the 3 patients with thyroid carcinoma. The average operative time was 100 min, the average intraoperative blood loss was 50 mL, the average postoperative hospital stay was 5 d. The rate of parathyroid injury was 2.7% (2/75), the rate of hypocalcemia caused by parathyroid injury was 2.7% (2/75). There were 3 cases (4.0%) of unilateral recurrent laryngeal nerve injury, 1 case (1.3%) of the outer branch of the upper laryngeal nerve injury. There were 2 cases of tracheal partial softening in the 75 patients. None of postoperative bleeding and seroma happened. No death and the tumor recurrence and metastasis of patients happened during follow-up period. Conclusions Preliminary results in this study show that operation of meticulous capsular dissection technique with an ultrasonic scalpel and a bipolar coagulation forcep through neck incision approach in treatment of type Ⅰ substernal goiter is safe and feasible, it could effectively reduce postoperative complications of thyroidectomy, and protect parathyroid and it’s function, recurrent laryngeal nerve, and superior laryngeal nerve.