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.
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.
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.
Kidney tumor is one of the diseases threatening human health. Ultrasound is widely applied in kidney tumor diagnosis due to its high popularization, low price and no radiation. Accurate segmentation of kidney tumor is the basis of precise treatment. Kidney tumors often grow in the middle of cortex, so that segmentation is easy disturbed by nearby organs. Besides, ultrasound images own low contrast and large speckle, leading to difficult segmentation. This paper proposed a novel kidney tumor segmentation method in ultrasound images using adaptive sub-regional evolution level set models (ASLSM). Regions of interest are firstly divided into subareas. Secondly, object function is designed by integrating inside and outside energy and gradient, in which the ratio of these two parts are adjusted adaptively. Thirdly, ASLSM adapts convolution radius and curvature according to centroid principle and similarity inside and outside zero level set. Hausdorff distance (HD) of (8.75 ± 4.21) mm, mean absolute distance (MAD) of (3.26 ± 1.69) mm, dice-coefficient (DICE) of 0.93 ± 0.03 were obtained in the experiment. Compared with traditional ultrasound segmentation method, ASLSM is more accurate in kidney tumor segmentation. ASLSM may offer convenience for doctor to locate and diagnose kidney tumor in the future.
Monitoring of bowel sounds is an important method to assess bowel motility during sleep, but it is seriously affected by snoring noise. In this paper, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method was applied to remove snoring noise from bowel sounds during sleep. Specifically, the noisy bowel sounds were first band-pass filtered, then decomposed by the CEEMDAN method, and finally the appropriate components were selected to reconstruct the pure bowel sounds. The results of semi-simulated and real data showed that the CEEMDAN method was better than empirical mode decomposition and wavelet denoising method. The CEEMDAN method is used to remove snoring noise from bowel sounds during sleep, which lays an important foundation for using bowel sounds to assess the intestinal motility during sleep.
Traditional speech detection methods regard the noise as a jamming signal to filter, but under the strong noise background, these methods lost part of the original speech signal while eliminating noise. Stochastic resonance can use noise energy to amplify the weak signal and suppress the noise. According to stochastic resonance theory, a new method based on adaptive stochastic resonance to extract weak speech signals is proposed. This method, combined with twice sampling, realizes the detection of weak speech signals from strong noise. The parameters of the system a, b are adjusted adaptively by evaluating the signal-to-noise ratio of the output signal, and then the weak speech signal is optimally detected. Experimental simulation analysis showed that under the background of strong noise, the output signal-to-noise ratio increased from the initial value-7 dB to about 0.86 dB, with the gain of signal-to-noise ratio is 7.86 dB. This method obviously raises the signal-to-noise ratio of the output speech signals, which gives a new idea to detect the weak speech signals in strong noise environment.
Heart sound signal is a kind of physiological signal with nonlinear and nonstationary features. In order to improve the accuracy and efficiency of the phonocardiogram (PCG) classification, a new method was proposed by means of support vector machine (SVM) in which the complete ensemble empirical modal decomposition with adaptive noise (CEEMDAN) permutation entropy was as the eigenvector of heart sound signal. Firstly, the PCG was decomposed by CEEMDAN into a number of intrinsic mode functions (IMFs) from high to low frequency. Secondly, the IMFs were sifted according to the correlation coefficient, energy factor and signal-to-noise ratio. Then the instantaneous frequency was extracted by Hilbert transform, and its permutation entropy was constituted into eigenvector. Finally, the accuracy of the method was verified by using a hundred PCG samples selected from the 2016 PhysioNet/CinC Challenge. The results showed that the accuracy rate of the proposed method could reach up to 87%. In comparison with the traditional EMD and EEMD permutation entropy methods, the accuracy rate was increased by 18%–24%, which demonstrates the efficiency of the proposed method.
Nowadays, for gait instability phenomenon, many researches have been carried out at home and abroad. However, the relationship between plantar pressure and gait parameters in the process of balance adjustment is still unclear. This study describes the human body adaptive balance reaction during slip events on slippery level walk by plantar pressure and gait analysis. Ten healthy male subjects walked on a level path wearing shoes with two contrastive contaminants (dry, oil). The study collected and analyzed the change rule of spatiotemporal parameters, plantar pressure parameters, vertical ground reaction force (VGRF), etc. The results showed that the human body adaptive balance reaction during slip events on slippery level walk mainly included lighter touch at the heel strikes, tighter grip at the toe offs, a lower velocity, a shorter stride length and longer support time. These changes are used to maintain or recover body balance. These results would be able to explore new ideas and provide reference value for slip injury prevention, walking rehabilitation training design, research and development of walking assistive equipments, etc.
Image-guided radiation therapy using magnetic resonance imaging (MRI) is a new technology that has been widely studied and developed in recent years. The technology combines the advantages of MRI imaging, and can offer online real-time tracking of tumor and adjacent organs at risk, as well as real-time optimization of radiotherapy plan. In order to provide a comprehensive understanding of this technology, and to grasp the international development and trends in this field, this paper reviews and summarizes related researches, so as to make the researchers and clinical personnel in this field to understand recent status of this technology, and carry out corresponding researches. This paper summarizes the advantages of MRI and the research progress of MRI linear accelerator (MR-Linac), online guidance, adaptive optimization, and dosimetry-related research. Possible development direction of these technologies in the future is also discussed. It is expected that this review can provide a certain reference value for clinician and related researchers to understand the research progress in the field.
Ensemble empirical mode decomposition (EEMD) is an effective method for non-stationary signal analysis, such as electrocardiogram (ECG) signals. However, the precision and correctness of EEMD are affected by the two parameters, ratio of the added noise and ensemble number. The values of two parameters are set relying on experience and lacking of adaptability for uncertain signals. In order to solve these problems, we proposed a method based on white noise decomposed by EEMD in the present study shown in this paper. Empirical mode decomposition (EMD) was applied to decompose the signal to different intrinsic mode functions (IMFs) in the de-noising process. The white noise IMFs were selected to constitute high frequency part based on the character that the product of the energy density of white noise and its average period tended to be a constant. Then the two parameters of EEMD were adaptively obtained according to the criterion which was used to avoid modal aliasing. Experimental results showed that the method was an effective one for ECG signal de-noising.