The gray-scale ultrasound(US) imaging method is usually used to assess synovitis in rheumatoid arthritis(RA) in clinical practice. This four-grade scoring system depends highly on the sonographer's experience and ...The gray-scale ultrasound(US) imaging method is usually used to assess synovitis in rheumatoid arthritis(RA) in clinical practice. This four-grade scoring system depends highly on the sonographer's experience and has relatively lower validity compared with quantitative indexes. However, the training of a qualified sonographer is expensive and timeconsuming while few studies focused on automatic RA grading methods. The purpose of this study is to propose an automatic RA grading method using deep convolutional neural networks(DCNN) to assist clinical assessment. Gray-scale ultrasound images of finger joints are taken as inputs while the output is the corresponding RA grading results. Firstly,we performed the auto-localization of synovium in the RA image and obtained a high precision in localization. In order to make up for the lack of a large annotated training dataset, we performed data augmentation to increase the number of training samples. Motivated by the approach of transfer learning, we pre-trained the GoogLeNet on ImageNet as a feature extractor and then fine-tuned it on our own dataset. The detection results showed an average precision exceeding 90%. In the experiment of grading RA severity, the four-grade classification accuracy exceeded 90% while the binary classification accuracies exceeded 95%. The results demonstrate that our proposed method achieves performances comparable to RA experts in multi-class classification. The promising results of our proposed DCNN-based RA grading method can have the ability to provide an objective and accurate reference to assist RA diagnosis and the training of sonographers.展开更多
The distribution of speed of sound （SOS） in biomedical tissue and delay compensation （DC） have significant impact on the image quality of photoacoustic tomography （PAT）. When imaging human peripheral joints, usi...The distribution of speed of sound （SOS） in biomedical tissue and delay compensation （DC） have significant impact on the image quality of photoacoustic tomography （PAT）. When imaging human peripheral joints, using fixed SOS and DC can only ensure that the reconstructed images are focused in a limited depth range, whereas they are defoeused at other depths, which cause severe artifacts and blurring. In this work, a linear-DC based reconstruction approach is proposed to focus the whole PAT image region. It is proved by two in vivo experiments that, compared with traditional delay-and-sum back projection algorithms, the proposed method can effectively optimize the image quality of articular tissues in PAT.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.2017YFC0111402)the Natural Science Funds of Jiangsu Province of China(Grant No.BK20181256)
文摘The gray-scale ultrasound(US) imaging method is usually used to assess synovitis in rheumatoid arthritis(RA) in clinical practice. This four-grade scoring system depends highly on the sonographer's experience and has relatively lower validity compared with quantitative indexes. However, the training of a qualified sonographer is expensive and timeconsuming while few studies focused on automatic RA grading methods. The purpose of this study is to propose an automatic RA grading method using deep convolutional neural networks(DCNN) to assist clinical assessment. Gray-scale ultrasound images of finger joints are taken as inputs while the output is the corresponding RA grading results. Firstly,we performed the auto-localization of synovium in the RA image and obtained a high precision in localization. In order to make up for the lack of a large annotated training dataset, we performed data augmentation to increase the number of training samples. Motivated by the approach of transfer learning, we pre-trained the GoogLeNet on ImageNet as a feature extractor and then fine-tuned it on our own dataset. The detection results showed an average precision exceeding 90%. In the experiment of grading RA severity, the four-grade classification accuracy exceeded 90% while the binary classification accuracies exceeded 95%. The results demonstrate that our proposed method achieves performances comparable to RA experts in multi-class classification. The promising results of our proposed DCNN-based RA grading method can have the ability to provide an objective and accurate reference to assist RA diagnosis and the training of sonographers.
基金Supported by the National Natural Science Foundation of China under Grant Nos 61201425, 61100111 and 61300157, the Natural Science Foundation of Jinagsu Province under Grant No BK20131280, and the National Institutes of Health of the United States under Grant No R01AR060350.
文摘The distribution of speed of sound （SOS） in biomedical tissue and delay compensation （DC） have significant impact on the image quality of photoacoustic tomography （PAT）. When imaging human peripheral joints, using fixed SOS and DC can only ensure that the reconstructed images are focused in a limited depth range, whereas they are defoeused at other depths, which cause severe artifacts and blurring. In this work, a linear-DC based reconstruction approach is proposed to focus the whole PAT image region. It is proved by two in vivo experiments that, compared with traditional delay-and-sum back projection algorithms, the proposed method can effectively optimize the image quality of articular tissues in PAT.
