|
Automatic Segmentation of Finger Bone Regions from CR Images Using Improved DeepLabv3+ |
|
Hikaru Ono, Tohru Kamiya(Kyushu Institute of Technology, Japan) |
| The major causes of bedridden patients are bone and joint disorders caused by rheumatoid arthritis and osteoporosis. Early detection and treatment of these diseases are important because they significantly interfere with the quality of life as the symptoms progress. We propose a method for automatic extraction of phalange regions for a computer aided diagnosis system to diagnose these diseases. The proposed method can extract the phalanges with high accuracy by using the improved DeepLabv3+. In this paper, we apply the proposed method to 101 cases of CR images and mIoU of 0.949 was obtained. |
|
|
Extraction of Cervical Lymph Nodes Based on Three-Dimensional Image Registration |
|
Nozomi Shime, Tohru Kamiya(Kyushu Institute of Technology, Japan) |
| We proposed an image alignment method for generating temporal subtraction images from images taken before and after contrast agent was administered to the cervical lymph nodes of the same subject. In addition, we propose an image analysis method that suppresses overextraction of lymph node candidate regions on the temporal subtraction image based on the features of lymph nodes. We compared the temporal subtraction images with the final lymph node extraction images, and confirmed that the proposed method can suppress the overextraction of lymph node regions. |
|
|
A Method for Evaluating of Asymmetry on Cleft Lip Using Symmetry Plane |
|
Satoru Sawada, Tohru Kamiya(Kyushu Institute of Technology, Japan) |
| Treatment of cleft lip have a problem that the degree of symmetry is difficult to evaluate quantitatively. In previous studies, there remained a problem with the accuracy of separation of asymmetry between patients and healthy subjects. In this paper, we propose an asymmetry evaluation method with high separation accuracy using the plane of symmetry of the face. By comparing the proposed method with the conventional method, more useful results were obtained as an evaluation index. |
|
|
Detection of the Root Resorption from Panoramic X-ray Images using Deep Metric Learning |
|
Kosei Tamura, Kamiya Tohru(Kyushu Institute of Technology, Japan) |
| Root resorption is a pathological process characterized by the loss of tooth roots. However, it is difficult to detect the root resorption using a panoramic radiograph. We propose an image analysis method for detecting the root resorption on panoramic radiograph. We incorporate the EfficientNet for feature extraction in deep learning to the center loss and triplet loss as the loss function for metric learning. Our proposed method performed to 337 images which is obtained by panoramic radiograph. Accuracy of 71％, true positive rate of 77％, false positive rate of 30％ were obtained. |
|
|
Classification of Respiratory Sounds by Generated Image and Improved CRNN |
|
Naoki Asatani, Tohru Kamiya(Kyushu Institute of Technology, Japan) |
| In this study, we proposed a new respiratory sound classification method that generates multiple respiratory sound transform images (time-frequency domain) for the respiratory sound data contained in the ICBHI 2017 Challenge Respiratory Sound Database and automatically classifies them into normal and abnormal (three classes) by using an improved Convolutional Recurrent Neural Network. As a result, Sensitivity: 0.64, Specificity: 0.83, Average Score: 0.74, Harmonic Score: 0.72 were obtained, and excellent results were achieved compared with other methods. |
| |