共查询到20条相似文献，搜索用时 31 毫秒
1.
Background
The purpose of this study is to explore the potential of phase contrast imaging to detect fibrotic progress in its early stage; to investigate the feasibility of texture features for quantified diagnosis of liver fibrosis; and to evaluate the performance of back propagation (BP) neural net classifier for characterization and classification of liver fibrosis.Methods
Fibrous mouse liver samples were imaged by X-ray phase contrast imaging, nine texture measures based on gray-level co-occurrence matrix were calculated and the feasibility of texture features in the characterization and discrimination of liver fibrosis at early stages was investigated. Furthermore, 36 or 18 features were applied to the input of BP classifier; the classification performance was evaluated using receiver operating characteristic curve.Results
The phase contrast images displayed a vary degree of texture pattern from normal to severe fibrosis stages. The BP classifier could distinguish liver fibrosis among normal, mild, moderate and severe stages; the average accuracy was 95.1% for 36 features, and 91.1% for 18 features.Conclusion
The study shows that early stages of liver fibrosis can be discriminated by the morphological features on the phase contrast images. BP network model based on combination of texture features is demonstrated effective for staging liver fibrosis.2.
Background
Convenient and precise measurement of the Cobb angle using a small size X-ray detector has been required for local clinics.Methods
Cobb angle measurement system using a conventional X-ray source and detector is proposed for accurate Cobb angle measurement. The system consists of a conventional X-ray source, a ruler-added X-ray table, a conventional X-ray detector, and an image processing program. The X-ray table has the lead ruler patterns. The patterns remain white ruler patterns on X-ray images. The proposed image processing program merges the three spinal X-ray images into one whole spinal X-ray image by detecting the ruler patterns on the three spinal X-ray images.Results
In order to evaluate our program, Cobb angle measured in the merged image is compared with Cobb angle measured in the X-ray image taken by a large X-ray detector. Average of difference between them is 2.251 degree and standard deviation is 1.339.Conclusion
The developed measurement system demonstrated its measurement performance accurately and practically. 相似文献3.
Background
Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status.Methods
Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA) and are evaluated using Backpropagation Neural Network (BPNN).Results
Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (τ = 1%), is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, τ = 1%) or color (90.52%, τ = 1%) features.Conclusion
In conclusion, novel methods for extracting new texture- and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.4.
Background
Neutrosophic based methods are becoming very popular in denoising of images due to the capability of handling indeterminacy. The main goal of denoising is to maintain balance between edge preservation and speckle reduction.Methods
To achieve this, neutrosophic based total variation method using Nakagami statistics have been explored to develop an efficient speckle reduction method. The proposed Neutrosophic based Nakagami Total Variation (NNTV) method initially transforms the image into the neutrosophic domain and then employs the neutrosophic filtering process for speckle reduction. The NNTV quantifies the indeterminacy of image by determining the entropy of indeterminate set.Results
The performance of the proposed method has been evaluated quantitatively by quality metrics on synthetic images, qualitatively using real thyroid ultrasound images through visual examination by medical experts and by Mean Opinion Score.Conclusion
From results, it has been observed that NNTV method performed better than other speckle reduction methods in terms of both speckle suppression and edge preservation. 相似文献5.
S. Mirzaei M. El Yacoubi S. Garcia-Salicetti J. Boudy C. Kahindo V. Cristancho-Lacroix H. Kerhervé A.-S. Rigaud 《IRBM》2018,39(6):430-435
Background
The goal of this work is to develop a non-invasive method in order to help detecting Alzheimer's disease in its early stages, by implementing voice analysis techniques based on machine learning algorithms.Methods
We extract temporal and acoustical voice features (e.g. Jitter and Harmonics-to-Noise Ratio) from read speech of patients in Early Stage of Alzheimer's Disease (ES-AD), with Mild Cognitive Impairment (MCI), and from a Healthy Control (HC) group. Three classification methods are used to evaluate the efficiency of these features, namely kNN, SVM and decision Tree. To assess the effectiveness of this set of features, we compare them with two sets of feature parameters that are widely used in speech and speaker recognition applications. A two-stage feature selection process is conducted to optimize classification performance. For these experiments, the data samples of HC, ES-AD and MCI groups were collected at AP-HP Broca Hospital, in Paris.Results
First, a wrapper feature selection method for each feature set is evaluated and the relevant features for each classifier are selected. By combining, for each classifier, the features selected from each initial set, we improve the classification accuracy by a relative gain of more than 30% for all classifiers. Then the same feature selection procedure is performed anew on the combination of selected feature sets, resulting in an additional significant improvement of classification accuracy.Conclusion
The proposed method improved the classification accuracy for ES-AD, MCI and HC groups and promises the effectiveness of speech analysis and machine learning techniques to help detect pathological diseases. 相似文献6.
Background
Label fusion is a core step of Multi-Atlas Segmentation (MAS), which has a decisive effect on segmentation results. Although existed strategies using image intensity or image shape to fuse labels have got acceptable results, there is still necessity for further performance improvement. Here, we propose a new label fusion strategy, which considers the joint information of intensity and registration quality.Methods
The correlation between any two atlases is taken into account and the probability that two atlases both give wrong label is used to compute the fusion weights. The probability is jointly determined by the registration error and intensity similarity of the two corresponding atlas-target image pairs. The proposed label fusion algorithm is named Registration Error and Intensity Similarity based Label Fusion (REIS-LF).Results
Using 3D Magnetic Resonance (MR) images, the proposed REIS-LF algorithm is validated in brain structure segmentation including the hippocampus, the thalamus and the nuclei of the basal ganglia. The REIS-LF algorithm has higher segmentation accuracy and robustness than the baseline AQUIRC-W algorithm.Conclusions
Taking the registration quality, the inter-atlas correlations and intensity differences into account in label fusion benefits to improve the object segmentation accuracy and robustness. 相似文献7.
A. Jabeen B. Reeder D. Svistunenko S. Hisaindee S. Ashraf S. Al-Zuhair S. Battah 《IRBM》2019,40(1):51-61
Background
In recent years, microalgae (MA) have attracted much interest considering their possible therapeutic application. They contain active natural compounds or derivatives (extracts, pure or chemically modified compounds) that have increasing applications in the pharmaceutical industry.Methods
The present study aims to examine microalgae for new photosensitizers, with a potential to be used in the light-associated treatment of tumors. Semi-purified extracts of several microalgae strains were evaluated as photosensitizers for photodynamic therapy (PDT) applications. Four tumor cell lines (A549, LNCap, MCF-7, and MDA-MB 435) were used to assess 34 samples extracted by three methods: cellulase enzyme, lysozyme enzyme and ultra-sonication. The fluorescence measurements and the recorded images alongside the spectral intensities between 650–800 nm wavelengths provided characteristic features to some of the contents of the examined extracts.Results
Several microalgae constituents activated by blue light (BL), red light (RL) or both (in sequence) exhibited significant effects on the viability of the tumor cell lines, decreasing it as much as 95% for certain MA constituents. Majority of the MA constituents showed a higher phototoxicity after exposure to both blue and red lights than the photo-induced toxicity when exposed to a single light source. The viability of the tumor cells exhibited the dose dependent response with the MA constituents.Conclusion
The results clearly showed that MA constituents are potential photosensitizers that have a significant photo-damage effects on the tested cancer cells. 相似文献8.
S.B. Akben 《IRBM》2018,39(5):353-358
Background
Chronic kidney disease (CKD) is a disorder associated with breakdown of kidney structure and function. CKD can be diagnosed in its early stage only by experienced nephrologists and urologists (medical experts) using the disease history, symptoms and laboratory tests. There are few studies related to the automatic diagnosis of CKD in the literature. However, these methods are not adequate to help the medical experts.Methods
In this study, a new method was proposed to automatically diagnose the chronic kidney disease in its early stage. The method aims to help the medical diagnosis utilizing the results of urine test, blood test and disease history. Classification algorithms were used as the data mining methods. In the method section of the study, analysis data were first subjected to pre-processing. In the first phase of the method section of the study, pre-processing was applied to CKD data. K-Means clustering method was used as the pre-processing method. Then, the classification methods (KNN, SVM, and Naïve Bayes) were applied to pre-processed data to diagnose the CKD.Results
Highest success rate obtained by classification methods is 97.8% (98.2% for ages 35 and older). This result showed that the data mining methods are useful for automatic diagnosis of CKD in its early stage.Conclusion
A new automatic early stage CKD diagnosis method was proposed to help the medical doctors. Attributes that would provide the highest diagnosis success rate were the use of specific gravity, albumin, sugar and red blood cells together. Also, the relation between the success rate of automatic diagnosis method and age was identified. 相似文献9.
Background
Stem cell therapy has a huge potential to enhance the recovery of damaged tissues and organs. However, it has been reported that majority of implanted stem cells cannot survive after implantation. Therefore, noninvasive monitoring of stem cell viability is essential to estimate the efficacy of stem cell therapy. However, current imaging methods have disadvantages for monitoring of stem cell viability such as cost, penetration depth, and safety. To overcome the limitations, photoacoustic imaging well known for sufficient penetration depth, relatively low cost, and non-ionizing radiation can be a novel alternative assessment method of stem cell viability.Methods
In this study, indocyanine green was used as exogenous photoacoustic contrast agents to label mesenchymal stem cells. The photoacoustic signals were acquired before and after the cell death and quantified to monitor photoacoustic signal changes related to the cell viability.Results
The fluorescence intensity changes of ICG labeled MSCs corresponded to decrease of PA intensity after cell death. Furthermore, the PA imaging of MSCs showed similarity between the PA intensity and the cell viability.Conclusion
The experimental results imply the feasibility of noninvasive detection of stem cell viability during therapeutic procedures. 相似文献10.
Background
Ultrasound-targeted microbubble destruction (UTMD) is a type of ultrasound therapy, in which low frequency moderate power ultrasound is combined with microbubbles to trigger cavitation. Cavitation is the process of oscillation of gas bubbles causing biophysical effects such as pushing and pulling or shock waves that permeabilize biological barriers. In vivo, cavitation results in tissue permeabilization and is used to enable local delivery of nanomedicine. While cavitation can occur in biological liquids when high pressure ultrasound is applied, the use of microbubbles as cavitation nuclei in UTMD largely facilitates the induction of cavitation. UTMD is intensively studied for drug delivery into tumor tissue, but also for the activation of anti-tumor immune responses. The first clinical studies of UTMD-mediated chemotherapy delivery confirmed safety and efficacy of this approach.Aim
The present review summarizes ultrasound settings, cavitation approaches, biophysical mechanisms of drug delivery, drug carriers, and pre-clinical and clinical applications of UTMD for drug delivery into tumors. 相似文献11.
Background
Epileptic seizures are unpredictable in nature and its quick detection is important for immediate treatment of patients. In last few decades researchers have proposed different algorithms for onset and offset detection of seizure using Electroencephalogram (EEG) signals.Methods
In this paper, a combined approach for onset and offset detection is proposed using Triadic wavelet decomposition based features. Standard deviation, variance and higher order moments, extracted as significant features to represent different EEG activities.Classification between seizure and non-seizure EEG was carried out using linear discriminant analysis (LDA) and k-nearest neighbour (KNN) classifiers. The method was tested using two benchmark EEG datasets in the field of seizure detection.CHBMIT EEG dataset was used for evaluating the performance of proposed seizure onset and offset detection method.Further for testing the robustness of the algorithm, the effect of the signal-to-noise ratio on the detection accuracy has been also investigated using Bonn University EEG dataset.Results
The seizure onset and offset detection method yielded classification accuracy, specificity and sensitivity of 99.45%, 99.62% and 98.36% respectively with 6.3 s onset and ?1.17 s offset latency using KNN classifier.The seizure detection method using Bonn University EEG dataset got classification accuracy of 92% when SNR = 5 dB, 94% when SNR = 10 dB, and 96% when SNR = 20 dB, while it also yielded 96% accuracy for noiseless EEG.Conclusion
The present study focuses on detection of seizure onset and offset rather than only seizure detection. The major contribution of this work is that the novel triadic wavelet transform based method is developed for the analysis of EEG signals. The results show improvement over other existing dyadic wavelet based Triadic techniques. 相似文献12.
C.R. Bawiec W.A. N&#x;Djin G. Bouchoux N. Sénégond N. Guillen J.-Y. Chapelon 《IRBM》2018,39(5):295-306
Background
Treatment of prostate cancer using endocavitary High Intensity Focused Ultrasound (HIFU) has become more commonplace since the first treatments in the 1990s. The gold standard HIFU strategy to treat prostate cancer is the complete thermal ablation of the entire prostate gland under real-time ultrasound (US) image guidance. A more desirable treatment and the current trend, however, is towards a focal treatment but more accurate and finely tunable thermal lesions are needed along with improved US imaging guidance. In this study, Capacitive Micromachined Ultrasound Transducer (CMUT) technology is being investigated, as they have shown recent promise for US imaging and potential to be used for HIFU therapy. They offer potential advantages over current piezoelectric designs in the context of ultrasound-guided HIFU (USgHIFU) focal therapies.Objective
The presented study evaluates the ability of a planar annular array CMUT design to achieve HIFU dynamic focusing and feasibility of generating thermal lesions in biological tissues.Method
The proposed CMUT design consists of a 64-element annular array for HIFU delivery with a space in the center that accommodates a high-resolution 256-element linear imaging array. The pressure field simulations of the HIFU portion of the array were performed using the Rayleigh integral method. The bioheat transfer equation was then used to predict lesion formation. The HIFU performances of the proposed CMUT phased-array design were compared to those of the device currently used in the clinic. Partial CMUT prototypes, including the therapeutic part only, were fabricated and experimentally characterized (electromechanical CMUT behavior, ultrasound pressure field distribution and acoustic intensity).Results
The planar 64-element annular CMUT design is capable of dynamically focusing a 3 MHz ultrasound beam at distances ranging from 32 to 72 mm, comparable in size and shape to the ones obtained with the clinical device. The simulated ultrasound fields correlated well to experimental measurements. Visual observation and impedance measurements of the CMUT cells allowed direct estimation of the collapse and snapback voltages of the ring-elements. The surface acoustic intensity of the CMUT ring-elements with both AC driving and DC bias voltages can achieve over 6 W/cm2, shown in simulation to be compatible with the generation of thermal lesions. The electro-acoustic efficiency of the CMUT elements increased with increasing DC bias voltages to reach 31%, and remained stable with increasing AC driving voltages. The ultrasound energy could be dynamically focused from this planar CMUT array during several dozen of minutes.Conclusion
This work demonstrates the feasibility of utilizing a planar CMUT probe for generating dynamic HIFU focusing and lesioning compatible with the ablation of prostate tissues under endocavitary treatment approach. Future investigations will consist of validating the lesioning capability experimentally both in vitro and in vivo. 相似文献13.
K. Langlois H. Pillet F. Lavaste G. Rochcongar P. Rouch P. Thoreux W. Skalli 《IRBM》2018,39(4):251-260
Background
Several methods can be used to assess joint kinematics going from optoelectronic motion analysis to biplanar fluoroscopy. The aim of the present work was to evaluate the reliability of the use of biplane radiography to quantify the sequential 3D kinematics of the femoro-tibial joint.Methods
Bi-planar X-rays (EOS imaging) of 12 lower limbs (6 specimens in vitro and 6 subjects in vivo) were taken for various knee flexion angles. 3D personalized models of the femur and the tibia were registered on each pair of views. To quantify the bias, the kinematic parameters calculated from the registered models were compared to those obtained from the tripods embedded in the specimens. Intra and inter-operator repeatability of each parameter were assessed from the registrations made by 3 operators in vivo.Results
In vitro, the bias of the tibia pose estimation obtained from the registration method was inferior to 1.6 mm and 0.4°. In vivo, the repeatability of the sequential kinematic parameters was inferior to 0.3°, 2.1° and 1.8°, for respectively flexion, varus-valgus and medial-lateral rotation and inferior to 1.8 mm for translations.Conclusion
Compared to simple fluoroscopy, the accuracy of our method based on sequential images was of the same order of magnitude, with better results for the translation in the frontal plane. The low dose of radiation of the EOS system offers promising prospects for a clinical use of this method to assess the femoro-tibial sequential kinematics. 相似文献14.
Background
In developed countries, 10% of labors occur prematurely and are mainly due to contractions appearing too soon during the pregnancy. To detect such contractions, we developed a wearable device able to record both the electrical activity of the uterus, electrohysterograms (EHG), thanks to 18 electrodes, but also the mother movements, thanks to an embedded accelerometer.Methods
In this study, we investigated the detectability of a begin/end of contraction by analyzing EHG signals with the Bayes Information Criterion, and we analyzed the three axis accelerometer signals to characterize the mother activity when she is carrying the device (such movements being possible sources of artifacts in the EHG signals).Results
For the contraction detections, we obtained 68.38% (599/876) of good detection but a too high number of false alarms (1073). To reduce this false alarm number, we analyzed the three accelerometer signals and detected 98.7% of static phases of the mother and 95% of dynamic ones.Discussion
The detection of precise movements inside the dynamic cluster still has to be investigated to improve the first obtained results, as well as the combination of these two research ways (EHG and accelerometer) applied at the same time during recording. 相似文献15.
Background
The electrocardiogram (ECG) signals provide important information about the heart electrical activities in medical and diagnostic applications. This signal may be contaminated by different types of noises. One of the noise types which has a considerable overlap with the ECG signals in frequency domain is electromyogram (EMG). Among the exciting approaches for de-noising the ECG signals, those based on singular spectrum analysis (SSA) are popular.Methods
In this paper, we propose a method based on SSA to separate the ECG signals from EMG noises. In general, SSA contains four steps as: embedding, singular value decomposition, grouping, and diagonal averaging. Among these steps, grouping step contains parameter (indices) which can be adjusted to achieve the desirable results. Indeed, grouping is one of the important steps of SSA as the ECG and EMG signals are separated in this step. Hence, in the proposed method, a new criterion is presented to select the indices in grouping step to separate the ECG from EMG signal with higher accuracy.Results
Performance of the proposed method is investigated using several experiments. Two sub-sets from Physionet MIT-BIH arrhythmia database are used for this purpose.Conclusion
The experimental results demonstrate effectiveness of the proposed method in comparison with other SSA-based techniques. 相似文献16.
Background
Routine ergonomic assessment of postures and gestures in the workplace are mostly conducted by visual observations, either direct or based on video recordings. Nowadays, low-cost three-dimensional cameras like Microsoft Kinect offers the possibility of recording the full kinematics of workers in a non-intrusive way, providing a more precise, and reliable assessment of their motor strategies.Methods
We have developed a tracking application using the Kinect SDK for Windows in C?, allowing the simultaneous recording of the three-dimensional coordinates of all the body points tracked by the Microsoft Kinect at a sampling frequency of 30 Hz and an expected accuracy of 3 cm. Measurements are performed on violinists, whose playing is representative of a work situation involving repeated gestures and postures that can be described as non-ergonomic.Results
Microsoft Kinect can be efficiently used to quantify the motion performed by the violinists. Playing strategies can even be noticed despite the low-cost nature of the sensor used.Conclusion
Low-cost three-dimensional cameras can be a useful aid in ergonomic risk assessment of developing musculoskeletal disorders and give the example of the repetition of movements and postural items included in the OCRA checklist, whose scoring can be facilitated by such a device. 相似文献17.
18.
Background
The contrast enhancement of Magnetic Resonance Imaging (MRI) data is quite challenging as the noise present in this data also get amplified in this process. Dynamic Stochastic Resonance (DSR) is the technique that utilizes the noise to enhance the contrast of MRI data.Method
The present study proposes the cascaded stochastic resonance, which exploits the properties of modified potential neuron model and quartic bistable model of DSR. The Multi-objective Particle Swarm Optimization (MOPSO) tunes the DSR parameters associated with the cascading of both the models. The MOPSO produces a set of the solution called Pareto front for the maximization of two image quality measures, i.e., contrast enhancement factor and universal image quality index. Further, the maximization of another image quality measure, i.e., anisotropy helps to obtain the optimum enhanced image from the Pareto fronts solution.Results
The present study included the simulated and real MRI data. The results show that the proposed method obtained mean contrast enhancement factor, universal image quality index and anisotropy equal to 1.79, 0.78 and 0.021 respectively. These values are better than those obtained for classical bistable DSR and other conventional contrast enhancement techniques. The proposed algorithm has been tested on real MRI data as well and found valuable in the diagnosis of lacunar infarct and mesial temporal sclerosis.Conclusion
The cascaded DSR based on MOPSO has shown promising results and may be highly beneficial to the diagnosis of different brain pathology. 相似文献19.
H. Tannous D. Istrate A. Benlarbi-Delai J. Sarrazin M.-C. Ho Ba Tho T.T. Dao 《IRBM》2018,39(6):440-444
Background
Serious games have recently immerged as a good tool for physical rehabilitation. This new technology can be used at home, to complement a traditional, clinic based, rehabilitation program. To implement a serious game at home, we need to use multiple sensors to record patients' data. Many serious games use visual motion capture techniques, like the Kinect camera, due to their low price and high portability. On the other hand, some other systems use inertial sensors to collect data at a higher degree of accuracy. In previous works, we showed that a serious gaming system could benefit from combining data from different sensors. However, the use of inertial sensors, in a home-based setting, remains a challenge since they need to be supplied by an independent battery source, which could influence the acceptability of such systems.Methods
In this paper, we present an energy consumption study, performed on the inertial sensors used in our serious game system.Results
The results show that the sensors are rarely affected by environmental factors. They also show that the sensors can function continuously for about 14 hours without battery recharge.Conclusion
Finally, these results allowed us to establish an optimal set up configuration for home based rehabilitation using serious games. 相似文献20.