Search

The purpose of this study was to evaluate and compare the diagnostic performances of the deep convolutional neural network (CNN) and expert radiologists for differentiating thyroid nodules on ultrasonography (US), and to validate the results in multicenter data sets. This multicenter retrospective study collected 15,375 US images of thyroid nodules for algorithm development (n = 13,560, Severance Hospital, SH training set), the internal test (n = 634, SH test set), and the external test (n = 781, Samsung Medical Center, SMC set; n = 200, CHA Bundang Medical Center, CBMC set; n = 200, Kyung Hee University Hospital, KUH set). Two individual CNNs and two classification ensembles (CNNE1 and CNNE2) were tested to differentiate malignant and benign thyroid nodules. CNNs demonstrated high area under the curves (AUCs) to diagnose malignant thyroid nodules (0.898-0.937 for the internal test set and 0.821-0.885 for the external test sets). AUC was significantly higher for CNNE2 than radiologists in the SH test set (0.932 vs. 0.840, P < 0.001). AUC was not significantly different between CNNE2 and radiologists in the external test sets (P = 0.113, 0.126, and 0.690). CNN showed diagnostic performances comparable to expert radiologists for differentiating thyroid nodules on US in both the internal and external test sets.

Background The distally extended muscle belly of the flexor digitorum (MB-FD) within the carpal tunnel has been suggested as a plausible cause for carpal tunnel syndrome (CTS) based on cadaveric studies. Purpose To evaluate whether MB-FD within the carpal tunnel is a risk factor for CTS by comparing asymptomatic volunteers and patients with CTS. Material and Methods Presence, length, and cross-sectional area of MB-FD within the carpal tunnel were evaluated in 63 wrists of 32 asymptomatic volunteers and 52 wrists of 33 patients with CTS using ultrasonography. Length of MB-FD within the carpal tunnel was measured as the distance between the distal end of MB-FD and the palmar margin of the distal radius longitudinally. On a transverse scan, the cross-sectional area of MB-FD at the proximal limit of the carpal tunnel was measured. Results MB-FD in the carpal tunnel was found in 39 (62%) asymptomatic volunteers and 35 (67%) patients with CTS ( P = 0.549). There was a female preponderancy of MB-FD within the carpal tunnel in asymptomatic volunteers ( P = 0.044), but not in patients. Length and cross-sectional area of MB-FD within the carpal tunnel were significantly greater in male-CTS patients than in male volunteers ( P = 0.022 and 0.012, respectively). These qualities were risk factors for CTS in men, though not in women. Conclusion The presence of distally extended MB-FD within the carpal tunnel was not a risk factor for CTS. In men, a longer and thicker MB-FD within the carpal tunnel increased the risk for CTS.

Background: No previous study has employed the frequency and interval of follow-up ultrasonography (US) during the first 10 years after total thyroidectomy in patients with papillary thyroid carcinoma (PTC). The aim of this study was to determine the appropriate frequency and interval of follow-up US during the first 10 years in patients who have undergone total thyroidectomy for PTC. Methods: Two hundred seventy-two patients underwent total thyroidectomy for PTC at our institution from January 2006 to December 2007. Nineteen patients were excluded because of lack of US follow-up data for the neck. Follow-up US was performed by one of two radiologists in all patients. Tumor recurrence/persistence was confirmed by histopathology. Results: The mean interval between surgery and the final follow-up US examination was 79.0 months, and the mean number of follow-up US sessions was 5.9 in the 253 evaluable patients. Eleven patients (4.3%) developed tumor recurrence/persistence, which was detected on follow-up US within 5 years after total thyroidectomy in all cases. T and N stages were independently associated with tumor recurrence/persistence. The interval between surgery and first suspicion of tumor recurrence/persistence on follow-up US was ≤12 months in six patients and 20, 35, 41, 53, and 60 months in the remaining five patients. Conclusion: For detection of tumor recurrence/persistence after total thyroidectomy in patients with PTC, one or two sessions of follow-up US during the first 2 years, depending on T and N stages and one session of follow-up US in every second year during the following 8 years may be appropriate. [ABSTRACT FROM AUTHOR]

Purpose No previous study using follow-up ultrasonography for evaluating the factors associated with the successful regression of congenital muscular torticollis in young infants has been published. This study aimed to assess clinical factors and sonographic features potentially influencing regression in patients with congenital muscular torticollis. Methods From January 2010 to December 2012, 80 infants underwent neck ultrasonography because of clinical suspicion of congenital muscular torticollis. We statistically analysed the correlation between complete resolution and clinicosonographic findings when complete resolution was defined as no visible lesion on follow-up ultrasonography. Results Of the 80 infants, 61 had congenital muscular torticollis and all were followed up by ultrasonography: 1) 34 underwent physiotherapy, and 27 of them (79.4%) revealed complete resolution in follow-up; 2) 27 did not undergo physiotherapy, and 15 of them (55.6%) showed complete resolution. A statistically significant correlation was found between physiotherapy and complete resolution, but not between complete resolution and patient sex; size, volume, and echogenicity of the lesion; and thickness ratio. Conclusions Physiotherapy was the only factor influencing complete resolution in young infants with congenital muscular torticollis. [ABSTRACT FROM AUTHOR]