• 인터넷정보학회논문지
• /
• 제21권4호
• /
• pp.17-23
• /
• 2020

인간의 특성과 관련된 측정 항목을 나타내는 생체정보는 도난이나 분실의 염려가 없으므로 높은 신뢰성을 가진 보안 기술로서 큰 주목을 받고 있다. 이러한 생체정보 중 지문은 본인 인증, 신원 파악 등의 분야에 주로 사용된다. 신원을 파악할 때 지문 이미지에 인증을 수행하기 어려운 상처, 주름, 습기 등의 문제가 있을 경우, 지문 전문가가 전처리단계를 통해 직접 지문에 어떠한 문제가 있는지 파악하고 문제에 맞는 영상처리 알고리즘을 적용해 문제를 해결한다. 이때 지문에 상처와 주름이 있는 지문 영상을 판별해주는 인공지능 소프트웨어를 구현하면 손쉽게 상처나 주름의 여부를 확인할 수 있고, 알맞은 알고리즘을 선정해 쉽게 지문 이미지를 개선할 수 있다. 본 연구에서는 이러한 인공지능 소프트웨어의 개발을 위해 캄보디아 왕립대학교의 학생 1,010명, Sokoto 오픈 데이터셋 600명, 국내 학생 98명의 모든 손가락 지문을 취득해 총 17,080개의 지문 데이터베이스를 구축했다. 구축한 데이터베이스에서 상처나 주름이 있는 경우를 판별하기 위해 기준을 확립하고 전문가의 검증을 거쳐 데이터 어노테이션을 진행했다. 트레이닝 데이터셋과 테스트 데이터셋은 캄보디아의 데이터, Sokoto 데이터로 구성하였으며 비율을 8:2로 설정했다. 그리고 국내 학생 98명의 데이터를 검증 데이터 셋으로 설정했다, 구성된 데이터셋을 사용해 Classic CNN, AlexNet, VGG-16, Resnet50, Yolo v3 등의 다섯 가지 CNN 기반 아키텍처를 구현해 학습을 진행했으며 지문의 상처와 주름 판독에서 가장 좋은 성능을 보이는 모델을 찾는 연구를 수행했다. 다섯가지 아키텍처 중 지문 영상에서 상처와 주름 여부를 가장 잘 판별할 수 있는 아키텍처는 ResNet50으로 검증 결과 81.51%로 가장 좋은 성능을 보였다.

• 융합신호처리학회논문지
• /
• 제21권4호
• /
• pp.183-194
• /
• 2020

최근 영유아 성장기에 발생하는 고관절 이형성증(Developmental Dysplasia of Hip, DDH)의 숫자가 늘어나고 있다. DDH는 영유아 성장을 방해하고 다른 부작용도 많이 발생시키기 때문에 최대한 조기에 발견하여 치료해야 한다. 최근 들어 Convolutional Neural Networks (CNN) 및 개선된 Resnet50을 활용한 머신러닝 기법이 초음파 영상 분석에 많이 활용되고 있다. 연구 결과를 보면 컴퓨터 보조 이미지 분석이 의료현장에서 객관성과 생산성을 크게 향상시키고 있다. 본 연구의 결과는 정형외과에서의 난제인 초음파 영상을 통한 DDH 컴퓨터 보조 진단 알고리즘에도 충분히 활용될 수 있다는 것을 보여주고 있다. 본 논문에서는 CNN을 활용하여 DDH를 자동으로 측정하고 진단할 수 있는 컴퓨터 보조 진단 알고리즘을 제안하였다. DDH 측정을 위해 유아 고관절의 정상/비정상 판독을 위해 Acetabulum-Femoral head의 angle을 자동으로 계산하였으며 기존 영상을 딥 러닝하여 진단을 자동으로 하는 알고리즘을 설계하였다. 실험 결과 의사와 비교하여 진단의 속도와 정확도가 향상된다는 것을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.182-189
• /
• 2023

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative evaluation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial resolution and contrast resolution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1841-1857
• /
• 2023

CenterNet, a novel object detection algorithm without anchor based on key points, regards the object as a single center point for prediction and directly regresses the object's height and width. However, because the objects have different sizes, directly regressing their height and width will make the model difficult to converge and lose the intrinsic relationship between object's width and height, thereby reducing the stability of the model and the consistency of prediction accuracy. For this problem, we proposed an algorithm based on the regression of the diagonal half-length and the center angle, which significantly compresses the solution space of the regression components and enhances the intrinsic relationship between the decoded components. First, encode the object's width and height into the diagonal half-length and the center angle, where the center angle is the angle between the diagonal and the vertical centreline. Secondly, the predicted diagonal half-length and center angle are decoded into two length components. Finally, the position of the object bounding box can be accurately obtained by combining the corresponding center point coordinates. Experiments show that, when using CenterNet as the improved baseline and resnet50 as the Backbone, the improved model achieved 81.6% and 79.7% mAP on the VOC 2007 and 2012 test sets, respectively. When using Hourglass-104 as the Backbone, the improved model achieved 43.3% mAP on the COCO 2017 test sets. Compared with CenterNet, the improved model has a faster convergence rate and significantly improved the stability and prediction accuracy.

• 대한의용생체공학회:의공학회지
• /
• 제39권5호
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.