Journal of Medical Signals & Sensors最新文献

Background: The Gleason grading system has been the most effective prediction for prostate cancer patients. This grading system provides this possibility to assess prostate cancer's aggressiveness and then constitutes an important factor for stratification and therapeutic decisions. However, determining Gleason grade requires highly-trained pathologists and is time-consuming and tedious, and suffers from inter-pathologist variability. To remedy these limitations, this paper introduces an automatic methodology based on transfer learning with pretrained convolutional neural networks (CNNs) for automatic Gleason grading of prostate cancer tissue microarray (TMA).

Methods: Fifteen pretrained (CNNs): Efficient Nets (B0-B5), NasNetLarge, NasNetMobile, InceptionV3, ResNet-50, SeResnet 50, Xception, DenseNet121, ResNext50, and inception_resnet_v2 were fine-tuned on a dataset of prostate carcinoma TMA images. Six pathologists separately identified benign and cancerous areas for each prostate TMA image by allocating benign, 3, 4, or 5 Gleason grade for 244 patients. The dataset was labeled by these pathologists and majority vote was applied on pixel-wise annotations to obtain a unified label.

Results: Results showed the NasnetLarge architecture is the best model among them in the classification of prostate TMA images of 244 patients with accuracy of 0.93 and area under the curve of 0.98.

Conclusion: Our study can act as a highly trained pathologist to categorize the prostate cancer stages with more objective and reproducible results.

Background: Optical coherence tomography (OCT) imaging has emerged as a promising diagnostic tool, especially in ophthalmology. However, speckle noise and downsampling significantly degrade the quality of OCT images and hinder the development of OCT-assisted diagnostics. In this article, we address the super-resolution (SR) problem of retinal OCT images using a statistical modeling point of view.

Methods: In the first step, we utilized Weibull mixture model (WMM) as a comprehensive model to establish the specific features of the intensity distribution of retinal OCT data, such as asymmetry and heavy tailed. To fit the WMM to the low-resolution OCT images, expectation-maximization algorithm is used to estimate the parameters of the model. Then, to reduce the existing noise in the data, a combination of Gaussian transform and spatially constraint Gaussian mixture model is applied. Now, to super-resolve OCT images, the expected patch log-likelihood is used which is a patch-based algorithm with multivariate GMM prior assumption. It restores the high-resolution (HR) images with maximum a posteriori (MAP) estimator.

Results: The proposed method is compared with some well-known super-resolution algorithms visually and numerically. In terms of the mean-to-standard deviation ratio (MSR) and the equivalent number of looks, our method makes a great superiority compared to the other competitors.

Conclusion: The proposed method is simple and does not require any special preprocessing or measurements. The results illustrate that our method not only significantly suppresses the noise but also successfully reconstructs the image, leading to improved visual quality.

Background: Image enhancement, including image de-noising, super-resolution, registration, reconstruction, in-painting, and so on, is an important issue in different research areas. Different methods which have been exploited for image analysis were mostly based on matrix or low order analysis. However, recent researches show the superior power of tensor-based methods for image enhancement.

Method: In this article, a new method for image super-resolution using Tensor Ring decomposition has been proposed. The proposed image super-resolution technique has been derived for the super-resolution of low resolution and noisy images. The new approach is based on a modification and extension of previous tensor-based approaches used for super-resolution of datasets. In this method, a weighted combination of the original and the resulting image of the previous stage has been computed and used to provide a new input to the algorithm.

Result: This enables the method to do the super-resolution and de-noising simultaneously.

Conclusion: Simulation results show the effectiveness of the proposed approach, especially in highly noisy situations.

Background: Simulation of tomographic imaging systems with fan-beam geometry, estimation of scattered beam profile using Monte Carlo techniques, and scatter correction using estimated data have always been new challenges in the field of medical imaging. The most important aspect is to ensure the results of the simulation and the accuracy of the scatter correction. This study aims to simulate 128-slice computed tomography (CT) scan using the Geant4 Application for Tomographic Emission (GATE) program, to assess the validity of this simulation and estimate the scatter profile. Finally, a quantitative comparison of the results is made from scatter correction.

Methods: In this study, 128-slice CT scan devices with fan-beam geometry along with two phantoms were simulated by GATE program. Two validation methods were performed to validate the simulation results. The data obtained from scatter estimation of the simulation was used in a projection-based scatter correction technique, and the post-correction results were analyzed using four quantities, such as: pixel intensity, CT number inaccuracy, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR).

Results: Both validation methods have confirmed the appropriate accuracy of the simulation. In the quantitative analysis of the results before and after the scatter correction, it should be said that the pixel intensity patterns were close to each other, and the accuracy of the CT scan number reached <10%. Moreover, CNR and SNR have increased by more than 30%-65% respectively in all studied areas.

Conclusion: The comparison of the results before and after scatter correction shows an improvement in CNR and SNR while a reduction in cupping artifact according to pixel intensity pattern and enhanced CT number accuracy.

Background: Monitoring and evaluation of the techniques used in weightlifting are based on the subjective observation of the coach, which can ignore important aspects of short duration. This study aimed to implement an embedded system to register the angular variation of the hip, knee, and ankle joints, and plantar pressure during training.

Methods: Four professional and four amateur athletes performed five snatch lifts. To evaluate the angular measurement, the tests were simultaneously videotaped and the results were contrasted.

Results: The angular data presented a correlation coefficient of 0.92 and a delay of 495 ± 200 ms. The characterization of the sensors was implemented in a microcontroller with a mean absolute percentage error of 18.8% in the measurements. When comparing the average results between the elite and amateur groups, the amateur group performed a delayed descent in the first three phases of the lift and an accelerated descent in the fourth phase. A not uniform plantar pressure was registered in the same group, causing a reduction in the final speed of recovery with the barbell.

Conclusions: The proposed system has been developed for biaxial angular registration of hip, knee, ankle, and plantar pressure during weightlifting snatch. The option to contrast between signals presented by the system met the requirements requested by the coaching staff and is seen as a promising quantitative analysis tool to support the coach and the athlete.

Background: Metal screws are commonly used for fracture fixations. However, the high modulus of elasticity relative to bones and releasing metallic ions by the metal screw needed a second surgery to remove the implant after the healing period. Furthermore, the removal of metal screws following the healing of the bone is a serious problem that can lead to refracture due to the presence of holes in the screw. Bioresorbable screws can overcome most of the problems associated with metallic screws which motivated research on manufacturing nonmetallic screws.

Methods: In this study, three-layer poly L-lactic acid/bioactive glass composite screws were manufactured according to functionally graded material theory, by the forging process. All of the physical and chemical parameters in the manufacturing stages from making composite layers to the forging process were optimized to obtain suitable mechanical properties and durability off the screw in load-bearing positions.

Results: The tri-layer composite screw with unidirectional, ±20° angled, and random fibers orientation from core to shell shows a flexural load of 661.5 ± 20.3 (N) with a decrease about 31% after 4-week degradation. Furthermore, its pull-out force was 1.8 ± 0.1 (N) which is considerably more than the degradable polymeric screws. Moreover, the integrity of the composite screws was maintained during the degradation process.

Conclusions: By optimizing the manufacturing process and composition of the composite and crystallinity, mechanical properties (flexural, torsion, and pull-out) were improved and making it a perfect candidate for load-bearing applications in orthopedic implants. Improving the fiber/matrix interface through the use of a coupling agent was also considered to preserve the initial mechanical properties. The manufactured screw is sufficiently robust enough to replace metals for orthopedic load-bearing applications.

Background: Diagnosing emotional states would improve human-computer interaction (HCI) systems to be more effective in practice. Correlations between Electroencephalography (EEG) signals and emotions have been shown in various research; therefore, EEG signal-based methods are the most accurate and informative.

Methods: In this study, three Convolutional Neural Network (CNN) models, EEGNet, ShallowConvNet and DeepConvNet, which are appropriate for processing EEG signals, are applied to diagnose emotions. We use baseline removal preprocessing to improve classification accuracy. Each network is assessed in two setting ways: subject-dependent and subject-independent. We improve the selected CNN model to be lightweight and implementable on a Raspberry Pi processor. The emotional states are recognized for every three-second epoch of received signals on the embedded system, which can be applied in real-time usage in practice.

Results: Average classification accuracies of 99.10% in the valence and 99.20% in the arousal for subject-dependent and 90.76% in the valence and 90.94% in the arousal for subject independent were achieved on the well-known DEAP dataset.

Conclusion: Comparison of the results with the related works shows that a highly accurate and implementable model has been achieved for practice.

Background: Medical images of cancer patients are usually evaluated qualitatively by clinical specialists which makes the accuracy of the diagnosis subjective and related to the skills of clinicians. Quantitative methods based on the textural feature analysis may be useful to facilitate such evaluations. This study aimed to analyze the gray level co-occurrence matrix (GLCM)-based texture features extracted from T1-axial magnetic resonance (MR) images of glioblastoma multiform (GBM) patients to determine the distinctive features specific to treatment response or disease progression.

Methods: 20 GLCM-based texture features, in addition to mean, standard deviation, entropy, RMS, kurtosis, and skewness were extracted from step I MR images (obtained 72 h after surgery) and step II MR images (obtained three months later). Responded and not responded patients to treatment were classified manually based on the radiological evaluation of step II images. Extracted texture features from Step I and Step II images were analyzed to determine the distinctive features for each group of responsive or progressive diseases. MATLAB 2020 was applied to feature extraction. SPSS version 26 was used for the statistical analysis. P value < 0.05 was considered statistically significant.

Results: Despite no statistically significant differences between Step I texture features for two considered groups, almost all step II extracted GLCM-based texture features in addition to entropy M and skewness were significantly different between responsive and progressive disease groups.

Conclusions: GLCM-based texture features extracted from MR images of GBM patients can be used with automatic algorithms for the expeditious prediction or interpretation of response to the treatment quantitatively besides qualitative evaluations.

Background: Optical coherence tomography (OCT) imaging significantly contributes to ophthalmology in the diagnosis of retinal disorders such as age-related macular degeneration and diabetic macular edema. Both diseases involve the abnormal accumulation of fluids, location, and volume, which is vitally informative in detecting the severity of the diseases. Automated and accurate fluid segmentation in OCT images could potentially improve the current clinical diagnosis. This becomes more important by considering the limitations of manual fluid segmentation as a time-consuming and subjective to error method.

Methods: Deep learning techniques have been applied to various image processing tasks, and their performance has already been explored in the segmentation of fluids in OCTs. This article suggests a novel automated deep learning method utilizing the U-Net structure as the basis. The modifications consist of the application of transformers in the encoder path of the U-Net with the purpose of more concentrated feature extraction. Furthermore, a custom loss function is empirically tailored to efficiently incorporate proper loss functions to deal with the imbalance and noisy images. A weighted combination of Dice loss, focal Tversky loss, and weighted binary cross-entropy is employed.

Results: Different metrics are calculated. The results show high accuracy (Dice coefficient of 95.52) and robustness of the proposed method in comparison to different methods after adding extra noise to the images (Dice coefficient of 92.79).

Conclusions: The segmentation of fluid regions in retinal OCT images is critical because it assists clinicians in diagnosing macular edema and executing therapeutic operations more quickly. This study suggests a deep learning framework and novel loss function for automated fluid segmentation of retinal OCT images with excellent accuracy and rapid convergence result.