Objective To develop an automatic diagnostic tool based on deep learning for lumbar spine stability and validate diagnostic accuracy. Methods Preoperative lumbar hyper-flexion and hyper-extension X-ray films were collected from 153 patients with lumbar disease. The following 5 key points were marked by 3 orthopedic surgeons: L4 posteroinferior, anterior inferior angles as well as L5 posterosuperior, anterior superior, and posterior inferior angles. The labeling results of each surgeon were preserved independently, and a total of three sets of labeling results were obtained. A total of 306 lumbar X-ray films were randomly divided into training (n=156), validation (n=50), and test (n=100) sets in a ratio of 3∶1∶2. A new neural network architecture, Swin-PGNet was proposed, which was trained using annotated radiograph images to automatically locate the lumbar vertebral key points and calculate L4, 5 intervertebral Cobb angle and L4 lumbar sliding distance through the predicted key points. The mean error and intra-class correlation coefficient (ICC) were used as an evaluation index, to compare the differences between surgeons’ annotations and Swin-PGNet on the three tasks (key point positioning, Cobb angle measurement, and lumbar sliding distance measurement). Meanwhile, the change of Cobb angle more than 11° was taken as the criterion of lumbar instability, and the lumbar sliding distance more than 3 mm was taken as the criterion of lumbar spondylolisthesis. The accuracy of surgeon annotation and Swin-PGNet in judging lumbar instability was compared. Results ① Key point: The mean error of key point location by Swin-PGNet was (1.407±0.939) mm, and by different surgeons was (3.034±2.612) mm. ② Cobb angle: The mean error of Swin-PGNet was (2.062±1.352)° and the mean error of surgeons was (3.580±2.338)°. There was no significant difference between Swin-PGNet and surgeons (P>0.05), but there was a significant difference between different surgeons (P<0.05). ③ Lumbar sliding distance: The mean error of Swin-PGNet was (1.656±0.878) mm and the mean error of surgeons was (1.884±1.612) mm. There was no significant difference between Swin-PGNet and surgeons and between different surgeons (P>0.05). The accuracy of lumbar instability diagnosed by surgeons and Swin-PGNet was 75.3% and 84.0%, respectively. The accuracy of lumbar spondylolisthesis diagnosed by surgeons and Swin-PGNet was 70.7% and 71.3%, respectively. There was no significant difference between Swin-PGNet and surgeons, as well as between different surgeons (P>0.05). ④ Consistency of lumbar stability diagnosis: The ICC of Cobb angle among different surgeons was 0.913 [95%CI (0.898, 0.934)] (P<0.05), and the ICC of lumbar sliding distance was 0.741 [95%CI (0.729, 0.796)] (P<0.05). The result showed that the annotating of the three surgeons were consistent. The ICC of Cobb angle between Swin-PGNet and surgeons was 0.922 [95%CI (0.891, 0.938)] (P<0.05), and the ICC of lumbar sliding distance was 0.748 [95%CI(0.726, 0.783)] (P<0.05). The result showed that the annotating of Swin-PGNet were consistent with those of surgeons. ConclusionThe automatic diagnostic tool for lumbar instability constructed based on deep learning can realize the automatic identification of lumbar instability and spondylolisthesis accurately and conveniently, which can effectively assist clinical diagnosis.
To solve the problems of noise interference and edge signal weakness for the existing medical image, we used two-dimensional wavelet transform to process medical images. Combined the directivity of the image edges and the correlation of the wavelet coefficients, we proposed a medical image processing algorithm based on wavelet characteristics and edge blur detection. This algorithm improved noise reduction capabilities and the edge effect due to wavelet transformation and edge blur detection. The experimental results showed that directional correlation improved edge based on wavelet transform fuzzy algorithm could effectively reduce the noise signal in the medical image and save the image edge signal. It has the advantage of the high-definition and de-noising ability.
We searched and retrieved literature on the topic of medical image processing published on SCI journals in the past 10 years. We then imported the retrieved literature into TDA for data cleanup before data analysis and processing by EXCLE and UCINET to generate tables and figures that could indicate disciplinary correlation and research hotspots from the perspective of bibliometrics. The results indicated that people in Europe and USA were leading researchers on medical image processing with close international cooperation. Many disciplines contributed to the fast development of medical image processing with intense interdisciplinary researches. The papers that we found show recent research hotspots of the algorithm, system, model, image and segmentation in the field of medical image processing. Cluster analysis on key words of high frequency demonstrated complicated clustering relationship.
Objective To determine feasibility of texture analysis of non-enhanced CT scan for differential diagnosis of liver cancer and hepatic hemangioma. Methods Fifty-six patients with liver cancer or hepatic hemangioma confirmed by pathology were enrolled in this retrospective study. After exclusion of images of 4 patients with artifacts and lesion diameter less than 1.0 cm, images of 52 patients (57 lesions) were available to further analyze. Texture features derived from the gray-level histogram, co-occurrence and run-length matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher, probability of classification error and average correlation (POE+ACC), and mutual information coefficients (MI) were used to extract 10 optimized texture features. The texture characteristics were analyzed by using linear discriminant analysis (LDA) and nonlinear discriminant analysis (NDA) provided by B11 module in the Mazda software, the minimum error probability of differential diagnosis of liver cancer and hepatic hemangioma was calculated. Most discriminating features (MDF) of LDA was applied to K nearest neighbor classification (KNN); NDA to extract the data used in artificial neural network (ANN) for differential diagnosis. Results The NDA/ANN-POE+ACC was the best for identifying liver cancer and hepatic hemangioma, and the minimum error probability was the lowest as compared with the LDA/KNN-Fisher, LDA/KNN-POE+ACC, LDA/KNN-MI, NDA/ANN-Fisher, and NDA/ANN-MI respectively, the differences were statistically significant (χ2=4.56, 4.26, 3.14, 3.14, 3.33;P=0.020, 0.018, 0.026, 0.026, 0.022). Conclusions The minimum error probability is low for different texture feature selection methods and different analysis methods of Mazda texture analysis software in identifying liver cancer and hepatic hemangioma, and NDA/ANN-POE+ACC method is best. So it is feasible to use texture analysis of non-enhanced CT images to identify liver cancer and hepatic hemangioma.
Aiming at long signal acquisition time, low flux, bad signal-to-noise ratio and low intelligence in coloration biochip reader, a new kind of rapid device with high flux was developed. The device consisted of hardware system and software system. It used a charge-coupled device (CCD) as the photoelectric sensor elements and obtained the biochip microarray image. The device integrated the embedded operating system based on i.MX6 chip. The microarray image processing, data analysis and result output were achieved through the code information of the software chip. Experiments with the standard grayscale sheet and standard format chip were carried out. The results showed that the maximum measurement error was less than 0.1%, the value of R2 was 98.7%, and the value of CV was 1.096 1%. The comparison results of 200 samples showed that detection performance of the proposed device was better than that of the same kind of marketed equipment.
The quality inspection of magnetic resonance imaging (MRI) performance parameters is an important means to ensure the image quality and the reliability of diagnosis results. There are some problems in the manual calculation and eye recognition of the quality inspection parameters, such as strong subjectivity and low efficiency. In view of these facts, an automatic analysis system for MRI quality detection based on QT is proposed and implemented in C++ language. The image processing algorithm is introduced to automatically measure and calculate the quality inspection parameters. The software with comprehensive functions is designed to systematically manage the quality inspection information of MRI. The experimental results show that the automatically calculated parameters are consistent with the manually calculated ones. Accordingly, the accuracy and reliability of the algorithm is verified. The whole system is efficient, convenient and easy to operate, and it can meet the actual needs of MRI quality inspection.
Skin aging principles play important roles in skin disease diagnosis, the evaluation of skin cosmetic effect, forensic identification and age identification in sports competition, etc. This paper proposes a new method to evaluate the skin aging objectively and quantitatively by skin texture area. Firstly, the enlarged skin image was acquired. Then, the skin texture image was segmented by using the iterative threshold method, and the skin ridge image was extracted according to the watershed algorithm. Finally, the skin ridge areas of the skin texture were extracted. The experiment data showed that the average areas of skin ridges, of both men and women, had a good correlation with age (the correlation coefficient r of male was 0.938, and the correlation coefficient r of female was 0.922), and skin texture area and age regression curve showed that the skin texture area increased with age. Therefore, it is effective to evaluate skin aging objectively by the new method presented in this paper.
Skin aging is the most intuitive and obvious sign of the human aging processes. Qualitative and quantitative determination of skin aging is of particular importance for the evaluation of human aging and anti-aging treatment effects. To solve the problem of subjectivity of conventional skin aging grading methods, the self-organizing map (SOM) network was used to explore an automatic method for skin aging grading. First, the ventral forearm skin images were obtained by a portable digital microscope and two texture parameters, i.e., mean width of skin furrows and the number of intersections were extracted by image processing algorithm. Then, the values of texture parameters were taken as inputs of SOM network to train the network. The experimental results showed that the network achieved an overall accuracy of 80.8%, compared with the aging grading results by human graders. The designed method appeared to be rapid and objective, which can be used for quantitative analysis of skin images, and automatic assessment of skin aging grading.
Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.
Based on repeated experiments as well as continuous researching and improving, an efficient scheme to measure velocity and displacement of the coxa and knee movements based on video image processing technique is presented in this paper. The scheme performed precise and real-time quantitative measurements of 2D velocity or displacement of the coxa and knee using a video camera mounted on one side of the healing and training beds. The beds were based on simplified pinhole projection model. In addition, we used a special-designed auxiliary calibration target, composed by 24 circle points uniformly located on two concentric circles and two straight rods which can rotate freely along the concentric center within the vertical plane, to do the measurements. Experiments carried out in our laboratory showed that the proposed scheme could basically satisfy the requirements about precision and processing speed of such kind of system, and would be very suitable to be applied to smart evaluation/training and healing system for muscles/balance function disability as an advanced and intuitional helping method.