In order to get the adaptive bandwidth of mean shift to make the tumor segmentation of brain magnetic resonance imaging (MRI) to be more accurate, we in this paper present an advanced mean shift method. Firstly, we made use of the space characteristics of brain image to eliminate the impact on segmentation of skull; and then, based on the characteristics of spatial agglomeration of different tissues of brain (includes tumor), we applied edge points to get the optimal initial mean value and the respectively adaptive bandwidth, in order to improve the accuracy of tumor segmentation. The results of experiment showed that, contrast to the fixed bandwidth mean shift method, the method in this paper could segment the tumor more accurately.
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.
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.
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.
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.
In order to improve the speech quality and auditory perceptiveness of electronic cochlear implant under strong noise background, a speech enhancement system used for electronic cochlear implant front-end was constructed. Taking digital signal processing (DSP) as the core, the system combines its multi-channel buffered serial port (McBSP) data transmission channel with extended audio interface chip TLV320AIC10, so speech signal acquisition and output with high speed are realized. Meanwhile, due to the traditional speech enhancement method which has the problems as bad adaptability, slow convergence speed and big steady-state error, versiera function and de-correlation principle were used to improve the existing adaptive filtering algorithm, which effectively enhanced the quality of voice communications. Test results verified the stability of the system and the de-noising performance of the algorithm, and it also proved that they could provide clearer speech signals for the deaf or tinnitus patients.
Surface electromyogram (sEMG) may have low signal to noise ratios. An adaptive wavelet thresholding technique was developed in this study to remove noise contamination from sEMG signals. Compared with conventional wavelet thresholding methods, the adaptive approach can adjust thresholds based on different signal to noise ratios of the processed signal, thus effectively removing noise contamination and reducing distortion of the EMG signal. The advantage of the developed adaptive thresholding method was demonstrated using simulated and experimental sEMG recordings.
This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4th International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), k nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30% of the target domain instance data is migrated, with an average classification accuracy of 86.17%, a Kappa value of 0.723 3, and an AUC value of 0.849 8. These results suggest that the algorithm can be used to recognize MI signals across individuals, providing a new way to improve the generalization capability of BCI recognition models.
Ballistocardiogram (BCG) signal is a physiological signal, reflecting heart mechanical status. It can be measured without any electrodes touching subject's body surface and can realize physiological monitoring ubiquitously. However, BCG signal is so weak that it would often be interferred by superimposed noises. For measuring BCG signal effectively, we proposed an approach using joint time-frequency distribution and empirical mode decomposition (EMD) for BCG signal de-noising. We set up an adaptive optimal kernel for BCG signal and extracted BCG signals components using it. Then we de-noised the BCG signal by combing empirical mode decomposition with it. Simulation results showed that the proposed method overcome the shortcomings of empirical mode decomposition for the signals with identical frequency content at different times, realized the filtering for BCG signal and also reconstructed the characteristics of BCG.
Photoplethysmography (PPG) is a non-invasive technique to measure heart rate at a lower cost, and it has been recently widely used in smart wearable devices. However, as PPG is easily affected by noises under high-intensity movement, the measured heart rate in sports has low precision. To tackle the problem, this paper proposed a heart rate extraction algorithm based on self-adaptive heart rate separation model. The algorithm firstly preprocessed acceleration and PPG signals, from which cadence and heart rate history were extracted respectively. A self-adaptive model was made based on the connection between the extracted information and current heart rate, and to output possible domain of the heart rate accordingly. The algorithm proposed in this article removed the interference from strong noises by narrowing the domain of real heart rate. From experimental results on the PPG dataset used in 2015 IEEE Signal Processing Cup, the average absolute error on 12 training sets was 1.12 beat per minute (bpm) (Pearson correlation coefficient: 0.996; consistency error: −0.184 bpm). The average absolute error on 10 testing sets was 3.19 bpm (Pearson correlation coefficient: 0.990; consistency error: 1.327 bpm). From experimental results, the algorithm proposed in this paper can effectively extract heart rate information under noises and has the potential to be put in usage in smart wearable devices.