• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1168-1177
• /
• 2019

In order to diagnose and prevent Alzheimer's Disease (AD), it is becoming increasingly important to develop a CAD(Computer-aided Diagnosis) system for AD diagnosis, which provides effective treatment for patients by analyzing 3D MRI images. It is essential to apply powerful deep learning algorithms in order to automatically classify stages of Alzheimer's Disease and to develop a Alzheimer's Disease support diagnosis system that has the function of detecting hippocampus and CSF(Cerebrospinal fluid) which are important biomarkers in diagnosis of Alzheimer's Disease. In this paper, for AD diagnosis, we classify a given MRI data into three categories of AD, mild cognitive impairment, and normal control according by applying 3D brain MRI image to the Faster R-CNN model and detect hippocampus and CSF in MRI image. To do this, we use the 2D MRI slice images extracted from the 3D MRI data of the Faster R-CNN, and perform the widely used majority voting algorithm on the resulting bounding box labels for classification. To verify the proposed method, we used the public ADNI data set, which is the standard brain MRI database. Experimental results show that the proposed method achieves impressive classification performance compared with other state-of-the-art methods.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.891-899
• /
• 2020

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.12
• /
• pp.339-344
• /
• 2016

Since transmissions of large amounts of data are frequent, users require more bandwidth, and the need for communications networks having greater bandwidth is increasing. One communications network satisfying this need is an optical communications network. Therefore, studies to increase the transmission capacity of optical communications systems have been carried out. However, in a general optical communications system, a signal transmitted through optical fiber (a transmission medium) is detected through direct detection in the receiving system. This method has a disadvantage in that the entire bandwidth of the optical signal cannot be utilized. Also, when transmitting an optical signal, there is a problem where the signal-to-noise ratio is affected by neighboring channels. To overcome this situation, various studies are being conducted to minimize the influence of external interference and noise. This paper overcomes the situation by transmitting spectrum-sliced signals using the digital transmission system, FSK. Analyzing the characteristics of the signals detected in the receiver of the optical communications system, Gaussian distribution is used for the PDF of the spectrum-sliced signal, and the signal at the receiving end of the optical communications system is assumed to have a k-square distribution. The results of the analysis confirmed it is better to transmit the spectrally divided signal rather than transmit the laser source.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.62-74
• /
• 2008

In this paper, we would like to propose the design of symmetric digital filter core in order to use in the radio astronomy. The function of FIR filter core would be designed by VHDL code required at the Data Acquisition System (DAS) of Korean VLBI Network (KVN) based on the FPGA chip of Vertex-4 SX55 model of Xilinx company. The designed digital filter has the symmetric structure to increase the effectiveness of system by sharing the digital filter coefficient. The SFFU(Symmetric FIR Filter Unit) use the parallel processing method to perform the data processing efficiently by using the constrained system clock. In this paper, therefore, for the effective design of SFFU, the Unified Synthesis software ISE Foundation and Core Generator which has excellent GUI environment were used to overall IP core synthesis and experiments. Through the synthesis results of digital filter core, we verified the resource usage is less than 40% such as Slice LUT and achieved the maximum operation frequency is more than 260MHz. We also confirmed the SFFU would be well operated without error according to the SFFU simulation result using the Modelsim 6.1a of Mentor Graphics Company. To verify the function of SFFU, we carried out the additional simulation experiments using the pseudo signal to the Matlab software. From the comparison experimental results of simulation and the designed digital FIR filter, we confirmed the FIR filter was well performed with filter's basic function. So we verified the effectiveness of the designed FIR digital filter with symmetric structure using FPGA and VHDL.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.