• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.693-699
• /
• 2023

Ultrasound is widely used in the medical field for non-destructive and non-invasive disease diagnosis. In order to improve the disease diagnosis accuracy of diagnostic medical images, improving spatial resolution is a very important factor. In this study, we aim to model the super resolution convolutional neural network (SRCNN) algorithm in ultrasound images and analyze its applicability in the medical diagnostic field. The study was conducted as an experimental study using Field II simulation and open source clinical liver hemangioma ultrasound imaging. The proposed SRCNN algorithm was modeled so that end-to-end learning can be applied from low resolution (LR) to high resolution. As a result of the simulation, we confirmed that the full width at half maximum in the phantom image using a Field II program was improved by 41.01% compared to LR when SRCNN was used. In addition, the peak to signal to noise ratio (PSNR) and structural similarity index (SSIM) evaluation results showed that SRCNN had the excellent value in both simulated and real liver hemangioma ultrasound images. In conclusion, the applicability of SRCNN to ultrasound images has been proven, and we expected that proposed algorithm can be used in various diagnostic medical fields.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.3
• /
• pp.498-504
• /
• 2009

In the PACS system, the radiology image(X-ray) and its report are saved as separated parts. The exchange of the radiology image between clinics that installed this system are easily achieved by the DICOM standardization. But it is difficult to exchange the radiology report between clinics because a solution of PACS system is different according to manufacturers. The radiology report should be unified the vocabulary and the type of code for effective sharing and exchanging, and also the radiology image and its report should be integrated for the accurate analysis. In this paper, we propose the sharing system of medical information based on HL7-CDA, it defines the templates and converts the structured documents. For this purpose, we design the XML schema of the radiology report and turn the DICOM files into defined schema. The HL7-CDA documents based on XML is easily displayed on web browser and can help the diagnosis by inserting the radiology image.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1991.06a
• /
• pp.136-141
• /
• 1991

초음파 영상 진단기에서 영상의 질을 높이기 위해서는 넓은 범우에서 높은 측 방향 해상도가 요구된다. 측 방향 해상도는 변환기에 의해 발생되는 초음파 빔폭에 의해 좌우되는데 기존의 변환기는 초점 부근에서는 빔폭이 매우 좁으나 집속 범위가 제한되는 단점이 있다. 본 논문에서는 넓은 범위에서 균일한 빔폭을 얻을 수 있는 새로운 형태의 변환기를 제안하고 변환기에 의한 음장 분포를 전산기 모의 실험을 통해 구하였으며 그 결과 초점 부근에서는 빔 폭이 기존의 변환기에 비해 다소 넓어지나 집속 범위가 기존의 변화기에 비해 넓어지는 것을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.291-292
• /
• 2019

본 논문은 의료영상을 기반으로 근감소증의 정량적 평가를 위한 특화된 분석 소프트웨어에 대하여 기술한다. 특히, 제안한 분석 소프트웨어는 복부 CT영상에서 근감소증 영상분석에 중요한 인자인 근육, 피하지방 그리고 내장지방의 영역을 반자동 방식으로 세그멘테이션하여 정량화 할 수 있다. 또한 각각의 영역별 레이블링 영상을 다양한 포맷으로 생성할 수 있다. 분석 소프트웨어는 근감소증의 진단 및 정량적 평가를 정의하는 출발점이 될 것으로 기대하고 있으며, 다양한 질환에 대해 분석에 적용이 가능하다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.609-612
• /
• 2020

최근 코로나 19에 대한 세계적인 팬데믹 선언에 의해 의료서비스의 변화가 오고 있다. 특히, 국내 법제도적으로 묶여 있던 원격 서비스에 대한 재검토가 되고 있는 실정이다. 본 논문에서 제안하는 커넥티드 라디올로지 케어 시스템은 모바일 의료영상진단기기를 기반으로 의료사각지대에 있는 환자들의 영상촬영과 이에 대한 판독 서비스를 제공하기 위한 시스템이다. 제안한 시스템은 의료환경에 적용하기 위해 환자의 개인정보 보호를 위한 방법과 절차가 반드시 포함되어야 한다. 이를 위해 전체 시스템 구조와 익명화 처리과정을 보인다. 그리고 끝으로 구축된 시스템의 수행과정을 보인다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.279-282
• /
• 2022

Acute lymphoblastic leukemia is an acute leukemia caused by suppression of bone marrow function due to overgrowth of immature lymphocytes in the bone marrow. It accounts for 30% of acute leukemia in adults, and children show a cure rate of over 80% with chemotherapy, while adults show a low survival rate of 20% to 50%. However, research on a machine learning algorithm based on medical image data for the diagnosis of acute lymphoblastic leukemia is in the initial stage. In this paper, we compare and analyze CNN algorithm models for quick and accurate diagnosis. Using four models, an experimental environment for comparative analysis of acute lymphoblastic leukemia diagnostic models was established, and the algorithm with the best accuracy was selected for the given medical image data. According to the experimental results, among the four CNN models, the InceptionV3 model showed the best performance with an accuracy of 98.9%.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.429-440
• /
• 2023

This study explores recent research trends and potential applications of ultrasound optical imaging-based multimodal technology. Ultrasound imaging has been widely utilized in medical diagnostics due to its real-time capability and relative safety. However, the drawback of low resolution in ultrasound imaging has prompted active research on multimodal imaging techniques that combine ultrasound with other imaging modalities to enhance diagnostic accuracy. In particular, ultrasound optical imaging-based multimodal technology enables the utilization of each modality's advantages while compensating for their limitations, offering a means to improve the accuracy of the diagnosis. Various forms of multimodal imaging techniques have been proposed, including the fusion of optical coherence tomography, photoacoustic, fluorescence, fluorescence lifetime, and spectral technology with ultrasound. This study investigates recent research trends in ultrasound optical imaging-based multimodal technology, and its potential applications are demonstrated in the biomedical field. The ultrasound optical imaging-based multimodal technology provides insights into the progress of integrating ultrasound and optical technologies, laying the foundation for novel approaches to enhance diagnostic accuracy in the biomedical domain.

• Journal of Biomedical Engineering Research
• /
• v.24 no.3
• /
• pp.141-149
• /
• 2003

This paper proposes a method of measuring and imaging the stiffness of human soft tissue to diagnose cancers or tumors which have been difficult to detect in ultrasound B-mode imaging systems. To measure the soft tissue stiffness, sinusoidal vibrations are applied to it, and the magnitude of its mechanical vibration is determined by estimating the temporal variation of speckle pattern brightness in ultrasound B-mode images. It is verified by simulation and experiment that the proposed method can estimate the relative tissue stiffness from B-mode images with a relatively small amount of computation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.520-522
• /
• 2022

의료 인공지능은 특정 진단에서 높은 정확도를 보이지만 모델의 신뢰성 문제로 인해 활발하게 쓰이지 못하고 있다. 이에 따라 인공지능 모델의 진단에 대한 원인 설명의 필요성이 대두되었고 설명가능한 의료 인공지능에 관한 연구가 활발히 진행되고 있다. 하지만 MRI 등 의료 영상 인공지능 분야에서 주로 진행되고 있으며, 이미지 형태가 아닌 전자의무기록 데이터 (Electronic Health Record, EHR) 를 기반으로 한 모델의 설명가능성 연구는 EHR 데이터 자체의 복잡성 때문에 활발하게 진행 되지 않고 있다. 본 논문에서는 전자의무기록 데이터인 MIMIC-III (Medical Information Mart for Intensive Care) 를 전처리 및 그래프로 표현하고, GCT (Graph Convolutional Transformer) 모델을 학습시켰다. 학습 후, 어텐션 흐름 그래프를 시각화해서 모델의 예측에 대한 직관적인 설명을 제공한다.