A new enhancement method is proposed based on the characteristics of fundus images in this paper. Firstly, top-hat transform is utilized to weaken the background. Secondly, contrast limited adaptive histogram equalization (CLAHE) is performed to improve the uneven illumination. Finally, two-dimensional matched filters are designed to further enhance the contrast between blood vessels and background. The algorithm was tested in DIARETDB0 databases and showed good applicability for both normal and pathological fundus images. A new no-reference image quality assessment method was used to evaluate the enhancement methods objectively. The results demonstrated that the proposed method could effectively weaken the background, increase contrast, enhance details in the fundus images and improve the image quality greatly.
Objective To investigate the predictive value of mechanical power (MP) in the weaning outcome of adaptive mechanical ventilation plus intelligent trigger (AMV+IntelliCycle, simply called AMV) mode for acute respiratory distress syndrome (ARDS) patients. Methods From November 2019 to March 2021, patients with mild to moderate ARDS who were treated with invasive mechanical ventilation in the intensive care unit of the First Affiliated Hospital of Jinzhou Medical University were divided into successful weaning group and failed weaning group according to the outcome of weaning. All patients were treated with AMV mode during the trial. The MP, oral closure pressure (P0.1), respiratory rate (RR) and tidal volume (VT) of the two groups were compared 30 min and 2 h after spontaneous breathing trial (SBT). The correlation between 30 min and 2 h MP and shallow rapid respiratory index (RSBI) was analyzed by Pearson correlation. Receiver operating characteristic (ROC) curve was used to analyze the predictive value of 30 min MP in ARDS patients with AMV mode weaning failure. Results Sixty-eight patients were included in the study, 49 of them were successfully removed and 19 of them failed. There was no statistical significance in age, gender, body mass index, oxygenation index, acute physiology and chronic health evaluation Ⅱ score, reasons for mechanical ventilation (respiratory failure, sepsis, intracranial lesions, and others) between the two groups (all P>0.05). The MP, P0.1 and RR at SBT 30 min and 2 h of the successful weaning group was lower than those of the failed weaning group (all P<0.05), but the VT of the successful weaning group was higher than the failed weaning group (all P<0.05). There was a significant relation between the MP at SBT 30 min and 2 h and RSBI (r value was 0.640 and 0.702 respectively, both P<0.05). The area under ROC curve of MP was 0.674, 95% confidence interval was 0.531 - 0.817, P value was 0.027, sensitivity was 71.73%, specificity was 91.49%, positive predictive value was 0.789, negative predictive value was 0.878, optimal cutoff value was 16.500. The results showed that 30 min MP had a good predictive value for the failure of weaning in AMV mode in ARDS patients. Conclusion MP can be used as an accurate index to predict the outcome of weaning in ARDS patients with AMV mode.
Recently, deep learning has achieved impressive results in medical image tasks. However, this method usually requires large-scale annotated data, and medical images are expensive to annotate, so it is a challenge to learn efficiently from the limited annotated data. Currently, the two commonly used methods are transfer learning and self-supervised learning. However, these two methods have been little studied in multimodal medical images, so this study proposes a contrastive learning method for multimodal medical images. The method takes images of different modalities of the same patient as positive samples, which effectively increases the number of positive samples in the training process and helps the model to fully learn the similarities and differences of lesions on images of different modalities, thus improving the model's understanding of medical images and diagnostic accuracy. The commonly used data augmentation methods are not suitable for multimodal images, so this paper proposes a domain adaptive denormalization method to transform the source domain images with the help of statistical information of the target domain. In this study, the method is validated with two different multimodal medical image classification tasks: in the microvascular infiltration recognition task, the method achieves an accuracy of (74.79 ± 0.74)% and an F1 score of (78.37 ± 1.94)%, which are improved as compared with other conventional learning methods; for the brain tumor pathology grading task, the method also achieves significant improvements. The results show that the method achieves good results on multimodal medical images and can provide a reference solution for pre-training multimodal medical images.
Electrocardiogram (ECG) signals are easily disturbed by internal and external noise, and its morphological characteristics show significant variations for different patients. Even for the same patient, its characteristics are variable under different temporal and physical conditions. Therefore, ECG signal detection and recognition for the heart disease real-time monitoring and diagnosis are still difficult. Based on this, a wavelet self-adaptive threshold denoising combined with deep residual convolutional neural network algorithm was proposed for multiclass arrhythmias recognition. ECG signal filtering was implemented using wavelet adaptive threshold technology. A 20-layer convolutional neural network (CNN) containing multiple residual blocks, namely deep residual convolutional neural network (DR-CNN), was designed for recognition of five types of arrhythmia signals. The DR-CNN constructed by residual block local neural network units alleviated the difficulty of deep network convergence, the difficulty in tuning and so on. It also overcame the degradation problem of the traditional CNN when the network depth was increasing. Furthermore, the batch normalization of each convolution layer improved its convergence. Following the recommendations of the Association for the Advancements of Medical Instrumentation (AAMI), experimental results based on 94 091 2-lead heart beats from the MIT-BIH arrhythmia benchmark database demonstrated that our proposed method achieved the average detection accuracy of 99.034 9%, 99.498 0% and 99.334 7% for multiclass classification, ventricular ectopic beat (Veb) and supra-Veb (Sveb) recognition, respectively. Using the same platform and database, experimental results showed that under the comparable network complexity, our proposed method significantly improved the recognition accuracy, sensitivity and specificity compared to the traditional deep learning networks, such as deep Multilayer Perceptron (MLP), CNN, etc. The DR-CNN algorithm improves the accuracy of the arrhythmia intelligent diagnosis. If it is combined with wearable equipment, internet of things and wireless communication technology, the prevention, monitoring and diagnosis of heart disease can be extended to out-of-hospital scenarios, such as families and nursing homes. Therefore, it will improve the cure rate, and effectively save the medical resources.
In order to eliminate the influence of motion artifacts, high-frequency noise and baseline drift on photoplethysmographic (PPG), and to obtain the accurate value of heart rate in motion state, this paper proposed a de-noising method of PPG signal based on normalized least mean square (NLMS) adaptive filtering combining ensemble empirical mode decomposition(EEMD). Firstly, the PPG signal containing noise is passed through an adaptive filter with a 3-axis acceleration sensor as a reference signal to filter out motion artifacts. Secondly, the PPG signal is decomposed by EEMD to obtain a series of intrinsic modal function (IMF) according to the frequency from high to low. The threshold range of the signal is judged by the permutation entropy (PE) criterion, thereby filtering out the high frequency noise and the baseline drift. The experimental results show that the Pearson correlation coefficient between the calculated heart rate of PPG signal and the standard heart rate based on electrocardiogram (ECG) signal is 0.731 and the average absolute error percentage is 6.10% under different motion states, which indicates that the method can accurately calculate the heart rate in moving state and is beneficial to the physiological monitoring under the state of human motion.
The mechanical behavior modeling of human soft biological tissues is a key issue for a large number of medical applications, such as surgery simulation, surgery planning, diagnosis, etc. To develop a biomechanical model of human soft tissues under large deformation for surgery simulation, the adaptive quasi-linear viscoelastic (AQLV) model was proposed and applied in human forearm soft tissues by indentation tests. An incremental ramp-and-hold test was carried out to calibrate the model parameters. To verify the predictive ability of the AQLV model, the incremental ramp-and-hold test, a single large amplitude ramp-and-hold test and a sinusoidal cyclic test at large strain amplitude were adopted in this study. Results showed that the AQLV model could predict the test results under the three kinds of load conditions. It is concluded that the AQLV model is feasible to describe the nonlinear viscoelastic properties of in vivo soft tissues under large deformation. It is promising that this model can be selected as one of the soft tissues models in the software design for surgery simulation or diagnosis.
An adaptive inertia weight particle swarm algorithm is proposed in this study to solve the local optimal problem with the method of traditional particle swarm optimization in the process of estimating magnetic resonance (MR) image bias field. An indicator measuring the degree of premature convergence was designed for the defect of traditional particle swarm optimization algorithm. The inertia weight was adjusted adaptively based on this indicator to ensure particle swarm to be optimized globally and to avoid it from falling into local optimum. The Legendre polynomial was used to fit bias field, the polynomial parameters were optimized globally, and finally the bias field was estimated and corrected. Compared to those with the improved entropy minimum algorithm, the entropy of corrected image was smaller and the estimated bias field was more accurate in this study. Then the corrected image was segmented and the segmentation accuracy obtained in this research was 10% higher than that with improved entropy minimum algorithm. This algorithm can be applied to the correction of MR image bias field.
We conducted this study to explore the influence of the ocular residual aberrations changes on contrast sensitivity (CS) function in eyes undergoing orthokeratology using adaptive optics technique. Nineteen subjects' nineteen eyes were included in this study. The subjects were between 12 and 20 years (14.27±2.23 years) of age. An adaptive optics (AO) system was adopted to measure and compensate the residual aberrations through a 4-mm artificial pupil, and at the same time the contrast sensitivities were measured at five spatial frequencies (2,4,8,16, and 32 cycles per degree).The CS measurements with and without AO correction were completed. The sequence of the measurements with and without AO correction was randomly arranged without informing the observers. A two-interval forced-choice procedure was used for the CS measurements. The paired t-test was used to compare the contrast sensitivity with and without AO correction at each spatial frequency. The results revealed that the AO system decreased the mean total root mean square (RMS) from 0.356 μm to 0.160 μm(t=10.517, P＜0.001), and the mean total higher-order RMS from 0.246 μm to 0.095 μm(t=10.113, P＜0.001). The difference in log contrast sensitivity with and without AO correction was significant only at 8 cpd (t=-2.51, P=0.02). Thereby we concluded that correcting the ocular residual aberrations using adaptive optics technique could improve the contrast sensitivity function at intermediate spatial frequency in patients undergoing orthokeratology.
It is difficult to distinguish the inferior alveolar nerve (IAN) from other tissues inside the IAN canal due to their similar CT values in the X image which are smaller than that of the bones. The direct reconstruction, therefore, is difficult to achieve the effects. The traditional clinical treatments mainly rely on doctors' manually drawing the X images so that some subjective results could not be avoided. This paper proposes the partition reconstruction of IAN canal based on shape features. According to the anatomical features of the IAN canal, we divided the image into three parts and treated the three parts differently. For the first, the directly part of the mandibular, we used Shape-driven Level-set Algorithm Restrained by Local Information (BSLARLI) segment IAN canal. For the second part, the mandibular body, we used Space B-spline curve fitting IAN canal's center, then along the center curve established the cross section. And for the third part, the mental foramen, we used an adaptive threshold Canny algorithm to extract IAN canal's edge to find center curve, and then along it established the cross section similarly. Finally we used the Visualization Toolkit (VTK) to reconstruct the CT data as mentioned above. The VTK reconstruction result by setting a different opacity and color values of tissues CT data can perspectively display the INA canal clearly. The reconstruction result by using this method is smoother than that using the segmentation results and the anatomical structure of mental foramen position is similar to the real tissues, so it provides an effective method for locating the spatial position of the IAN canal for implant surgeries.
The use of echocardiography ventricle segmentation can obtain ventricular volume parameters, and it is helpful to evaluate cardiac function. However, the ultrasound images have the characteristics of high noise and difficulty in segmentation, bringing huge workload to segment the object region manually. Meanwhile, the automatic segmentation technology cannot guarantee the segmentation accuracy. In order to solve this problem, a novel algorithm framework is proposed to segment the ventricle. Firstly, faster region-based convolutional neural network is used to locate the object to get the region of interest. Secondly, K-means is used to pre-segment the image; then a mean shift with adaptive bandwidth of kernel function is proposed to segment the region of interest. Finally, the region growing algorithm is used to get the object region. By this framework, ventricle is obtained automatically without manual localization. Experiments prove that this framework can segment the object accurately, and the algorithm of adaptive mean shift is more stable and accurate than the mean shift with fixed bandwidth on quantitative evaluation. These results show that the method in this paper is helpful for automatic segmentation of left ventricle in echocardiography.