• Journal of the Korean Society of Radiology
• /
• v.81 no.5
• /
• pp.1164-1174
• /
• 2020

Purpose To evaluate a deep learning model to predict recurrence of thyroid tumor using preoperative ultrasonography (US). Materials and Methods We included representative images from 229 US-based patients (male:female = 42:187; mean age, 49.6 years) who had been diagnosed with thyroid cancer on preoperative US and subsequently underwent thyroid surgery. After selecting each representative transverse or longitudinal US image, we created a data set from the resulting database of 898 images after augmentation. The Python 2.7.6 and Keras 2.1.5 framework for neural networks were used for deep learning with a convolutional neural network. We compared the clinical and histological features between patients with and without recurrence. The predictive performance of the deep learning model between groups was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve served as a summary of the prognostic performance of the deep learning model to predict recurrent thyroid cancer. Results Tumor recurrence was noted in 49 (21.4%) among the 229 patients. Tumor size and multifocality varied significantly between the groups with and without recurrence (p < 0.05). The overall mean area under the curve (AUC) value of the deep learning model for prediction of recurrent thyroid cancer was 0.9 ± 0.06. The mean AUC value was 0.87 ± 0.03 in macrocarcinoma and 0.79 ± 0.16 in microcarcinoma. Conclusion A deep learning model for analysis of US images of thyroid cancer showed the possibility of predicting recurrence of thyroid cancer.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.670-683
• /
• 2020

Objective: The presence of coagulative necrosis (CN) in clear cell renal cell carcinoma (ccRCC) indicates a poor prognosis, while the absence of CN indicates a good prognosis. The purpose of this study was to build and validate a radiomics signature based on preoperative CT imaging data to estimate CN status in ccRCC. Materials and Methods: Altogether, 105 patients with pathologically confirmed ccRCC were retrospectively enrolled in this study and then divided into training (n = 72) and validation (n = 33) sets. Thereafter, 385 radiomics features were extracted from the three-dimensional volumes of interest of each tumor, and 10 traditional features were assessed by two experienced radiologists using triple-phase CT-enhanced images. A multivariate logistic regression algorithm was used to build the radiomics score and traditional predictors in the training set, and their performance was assessed and then tested in the validation set. The radiomics signature to distinguish CN status was then developed by incorporating the radiomics score and the selected traditional predictors. The receiver operating characteristic (ROC) curve was plotted to evaluate the predictive performance. Results: The area under the ROC curve (AUC) of the radiomics score, which consisted of 7 radiomics features, was 0.855 in the training set and 0.885 in the validation set. The AUC of the traditional predictor, which consisted of 2 traditional features, was 0.843 in the training set and 0.858 in the validation set. The radiomics signature showed the best performance with an AUC of 0.942 in the training set, which was then confirmed with an AUC of 0.969 in the validation set. Conclusion: The CT-based radiomics signature that incorporated radiomics and traditional features has the potential to be used as a non-invasive tool for preoperative prediction of CN in ccRCC.

• Journal of Trauma and Injury
• /
• v.18 no.2
• /
• pp.141-147
• /
• 2005

Purpose: Recently, The new Injury Severity Score (NISS) has become a more accurate predictor of mortality than the traditional Injury Severity Score (ISS) in the trauma population. Trauma Score Injury Severity Score (TRISS) method, regarded as the gold standard for mortality prediction in trauma patients, still contains the ISS as an essential factor within its formula. The purpose of this study was to determine whether a simple modification of the TRISS by replacing the ISS with the NISS would improve the prediction of in-hospital mortality in a trauma population with blunt head and neck trauma. Objects and Methods: The study population consisted of 641 patients from a regional emergency medical center in Kyoungsangnam-do. Demographic data, clinical information, the final diagnosis, and the outcome for each patient were collected in a retrospective manner. the ISS, NISS, TRISS, and modified TRISS were calculated for each patients. The discrimination and the calibration of the ISS, NISS, modified TRISS and conventional TRISS models were compared using receiver operator characteristic (ROC) curves, areas under the ROC curve (AUC) and Hosmer-Lemeshow statistics. Results: The AUC of the ISS, NISS, modified TRISS, and conventional TRISS were 0.885, 0.941, 0.971, and 0.918 respectively. Statistical differences were found between the ISS and the NISS (p=0.008) and between the modified TRISS and the conventional TRISS (p=0.009). Hosmer-Lemeshow chi square values were 13.2, 2.3, 50.1, and 13.8, respectively; only the conventional TRISS failed to achieve the level of and an excellent calibration model (p<0.001). Conclusion: The modified TRISS is a more accurate predictor of in-hospital mortality than the conventional TRISS in a trauma population of blunt head and neck trauma.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.22-29
• /
• 2016

Many studies in detection and classification of the targets in the underwater environments have been conducted for military purposes, as well as for non-military purpose. Due to the complicated characteristics of underwater acoustic signal reflecting multipath environments and spatio-temporal varying characteristics, active sonar target detection technique has been considered as a difficult technique. In this paper, we describe the basic concept of Fractional Fourier transform and optimal transform order. Then we analyze the relationship between time-frequency characteristics of an LFM signal and its spectrum using Fractional Fourier transform. Based on the analysis results, we present active sonar target detection method. To verify the performance of proposed methods, we compared the results with conventional FFT-based matched filter. The experimental results demonstrate the superiority of the proposed method compared to the conventional method in the aspect of AUC(Area Under the ROC Curve).

• Parasites, Hosts and Diseases
• /
• v.54 no.6
• /
• pp.769-775
• /
• 2016

This retrospective case-control study explored the factors associated with anaphylactic shock during surgery for cystic echinococcosis (CE) at the First Affiliated Hospital of Xinjiang Medical University between October 2008 and September 2013. Patients who suffered from anaphylactic shock (n=16) were age-matched 3:1 to patients who did not (n=43). Multivariate analysis suggested that IL-4 levels (odds ratio=1.096; 95% confidence interval=1.015-1.185; P=0.02) and cyst size (odds ratio=3.028, 95% confidence interval=1.259-7.283, P=0.013) were independently associated with CE-induced perioperative anaphylactic shock. Using the receiver operating characteristic (ROC) curves and a cut-off value of 415.7 ng/ml, IL-4 showed an area under the ROC (AUC) of 0.926, sensitivity of 75.0%, and specificity of 97.7%. Using a cut-off value of 7.8 cm, cyst size showed an AUC of 0.828, sensitivity of 81.3%, and specificity of 76.7%. In conclusion, results suggest that levels of IL-4 and cyst size were independently associated with echinococcosis-induced perioperative anaphylactic shock. These results could help identifying patients with echinococcosis at risk of anaphylactic shock in whom appropriate prophylaxis could be undertaken.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.81-88
• /
• 2018

Spectrum sensing, the key technology of the cognitive radio networks, is used by a secondary user to determine the frequency state of a primary user. The energy detection in the spectrum sensing determines the presence or absence of a primary user according to the intensity of the allocated channel signal. Since this technique simply uses the strength of the signal for spectrum sensing, it is difficult to detect the signal of a primary user in the low SNR band. In this paper, we propose a way to combine spectrum sensing and support vector machine using wavelet packet decomposition to overcome performance degradation in low SNR band. In our proposed scheme, the sensing signals were extracted by wavelet packet decomposition and then used as training data and test data for support vector machine. The simulation results of the proposed scheme are compared with the energy detection using the AUC of the ROC curve and the accuracy according to the SNR band. With simulation results, we demonstrate that the proposed scheme show better determining performance than one of energy detection in the low SNR band.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.6
• /
• pp.72-79
• /
• 2017

In this paper, we present a new saliency detection algorithm using the mutual information of wavelet subbands. Our method constructs an intermediate saliency map using the power operation and Gaussian blurring for high-frequency wavelet coefficients. After combining three intermediate saliency maps according to the direction of wavelet subband, we find the main directional components using entropy measure. The amount of mutual information of each subband is obtained centering on the subband having the minimum entropy The final saliency map is detected using Minkowski sum based on weights calculated by the mutual information. As a result of the experiment on CAT2000 and ECSSD databases, our method showed good detection results in terms of ROC and AUC with few computation times compared with the conventional methods.

• Journal of Yeungnam Medical Science
• /
• v.37 no.2
• /
• pp.106-111
• /
• 2020

Background: Fever is a common cause of pediatric consultation in the emergency department. However, identifying the source of infection in many febrile infants is challenging because of insufficient presentation of signs and symptoms. Meningitis is a critical cause of fever in infants, and its diagnosis is confirmed invasively by lumbar puncture. This study aimed to evaluate potential laboratory markers for meningitis in febrile infants. Methods: We retrospectively analyzed infants aged <3 months who visited the emergency department of our hospital between May 2012 and May 2017 because of fever of unknown etiology. Clinical information and laboratory data were evaluated. Receiver operating characteristic (ROC) curves were constructed. Results: In total, 145 febrile infants aged <3 months who underwent lumbar punctures were evaluated retrospectively. The mean C-reactive protein (CRP) level was significantly higher in the meningitis group than in the non-meningitis group, whereas the mean white blood cell count or absolute neutrophil count (ANC) did not significantly differ between groups. The area under the ROC curve (AUC) for CRP was 0.779 (95% confidence interval [CI], 0.701-0.858). The AUC for the leukocyte count was 0.455 (95% CI, 0.360-0.550) and that for ANC was 0.453 (95% CI, 0.359-0.547). The CRP cut-off value of 10 mg/L was optimal for identifying possible meningitis. Conclusion: CRP has an intrinsic predictive value for meningitis in febrile infants aged <3 months. Despite its invasiveness, a lumbar puncture may be recommended to diagnose meningitis in young, febrile infants with a CRP level >10 mg/L.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2019

As the fourth industrial revolution is emerging, many companies are increasingly interested in smart factories and the importance of sensors is being emphasized. In the case that sensors for collecting sensing data fail, the plant could not be optimized and further it could not be operated properly, which may incur a financial loss. For this purpose, it is necessary to diagnose the status of sensors to prevent sensor' fault. In the paper, we propose a scheme to diagnose digital-sensor' fault by analyzing the rising time and falling time of digital sensors through the LSTM(Long Short Term Memory) of Deep Learning RNN algorithm. Experimental results of the proposed scheme are compared with those of rule-based fault diagnosis algorithm in terms of AUC(Area Under the Curve) of accuracy and ROC(Receiver Operating Characteristic) curve. Experimental results show that the proposed system has better and more stable performance than the rule-based fault diagnosis algorithm.