Search

In the recent past, the Classifiers are based on genetic signatures in which many microarray studies are analyzed to predict medical results for cancer patients. However, the Signatures from different studies have been benefitted with low-intensity ratio during the classification of individual datasets has been considered as a significant point of research in the present scenario. Hence to overcome the above-discussed issue, this paper provides a Deep Learning Framework that combines an algorithm of necessary processing of Linear Discriminant Analysis (LDA) and Auto Encoder (AE) Neural Network to classify different features within the profile of gene expression. Hence, an advanced ensemble classification has been developed based on the Deep Learning (DL) algorithm to assess the clinical outcome of breast cancer. Furthermore, numerous independent breast cancer datasets and representations of the signature gene, including the primary method, have been evaluated for the optimization parameters. Finally, the experiment results show that the suggested deep learning frameworks achieve 98.27% accuracy than many other techniques such as genomic data and pathological images with multiple kernel learning (GPMKL), Multi-Layer Perception (MLP), Deep Learning Diagnosis (DLD), and Spatiotemporal Wavelet Kinetics (SWK).

Refractory epilepsy is a complex case of epileptic disease. The quantitative analysis of fluorodeoxyglucose positron emission tomography (FDG-PET) images complements visual assessment and helps localize the epileptogenic zone (EZ) for better curative treatment. Statistical parametric mapping (SPM) and its computational anatomy toolbox (SPM-CAT) are two commonly applied tools in neuroimaging analysis. This study compares SPM and SPM-CAT with different parameters to find the optimal approach for localizing EZ in refractory epilepsy. The current study enrolled 45 subjects, including 25 refractory epilepsy patients and 20 healthy controls. All of the 25 patients underwent surgical operations. Pathological results and the postoperative outcome evaluation by the Engel scale were likewise presented. SPM and SPM-CAT were used to assess FDG-PET images with three different uncorrected p-values and the corresponding cluster sizes (k), as in voxels in the cluster, namely p < 0.0002, k > 25; p < 0.001, k > 100; p < 0.005, and k > 200. When combining three settings, SPM and SPM-CAT yielded overall positive finding scores of 96.0% (24/25) and 100.0% (25/25) respectively. However, for the individual setting, SPM-CAT achieved the diverse positive finding scores of 96.0% (24/25), 96.0% (24/25), and 88.0% (22/24), which are higher than those of SPM [88.0% (22/25), 76.0% (19/25), and 72.0% (18/25)]. SPM and SPM-CAT localized EZ correctly with 28.0% (7/25) and 64.0% (16/25), respectively. SPM-CAT with parameter settings p < 0.0002 and k > 25 yielded a correct localization at 56.0% (14/25), which is slightly higher than that for the other two settings (48.0 and 20.0%). Moderate concordance was found between the confirmed and pre-surgical EZs, identified by SPM-CAT (kappa value = 0.5). Hence, SPM-CAT is more efficient than SPM in localizing EZ for refractory epilepsy by quantitative analysis of FDG-PET images. SPM-CAT with the setting of p < 0.0002 and k > 25 might perform as an objective complementary tool to the visual assessment for EZ localization.

This study investigates whether administration of low doses of gadolinium-based contrast agent (GBCA) for dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) can be as effective as a standard dose in distinguishing prostate cancer (PCa) from benign tissue. In addition, we evaluated the combination of kinetic parameters from the low- and high-dose injection as a new diagnostic marker.Patients (n = 17) with histologically confirmed PCa underwent preoperative 3 T MRI. Dynamic contrast-enhanced MRI images were acquired at 8.3-second temporal resolution with a low dose (0.015 mmol/kg) and close to the standard dose (0.085 mmol/kg) of gadobentate dimeglumine bolus injections. Low-dose images were acquired for 3.5 minutes, followed by a 5-minute gap before acquiring standard dose images for 8.3 minutes. The data were analyzed qualitatively to investigate whether lesions could be detected based on early focal enhancement and quantitatively by fitting signal intensity as a function of time with an empirical mathematical model to obtain a maximum enhancement projection (MEP) and signal enhancement rate (α).Both low- and standard-dose DCE-MRI showed similar sensitivity (13/26 = 50%) and lesion conspicuity score (4.0 ± 1.0 vs 4.2 ± 0.9; P = 0.317) for PCa diagnosis on qualitative analysis. Prostate cancer showed significantly increased α compared with benign tissue for low (9.98 ± 5.84 vs 5.12 ± 2.95 s) but not for standard (4.27 ± 2.20 vs 3.35 ± 1.48 s) dose. The ratio of low-dose α to standard-dose α was significantly greater (P = 0.02) for PCa (2.8 ± 2.3) than for normal prostate (1.6 ± 0.9), suggesting changes in water exchange and T2* effects associated with cancer. In addition, decreases in the percentage change in T1 relaxation rate as a function of increasing contrast media concentration (ie, the "saturation effect") can also contribute to the observed differences in high-dose and low-dose α. Area under the receiver operating characteristic curve for differentiating PCa from benign tissue using α was higher for low dose (0.769) compared with standard dose (0.625). There were no significant differences between MEP calculated for PCa and normal tissue at the low and standard doses. Moderate significant Pearson correlation for DCE parameters, MEP (r = 0.53) and α (r = 0.58), was found between low and standard doses of GBCA.These preliminary results suggest that DCE-MRI with a low GBCA dose distinguishes PCa from benign prostate tissue more effectively than does the standard GBCA dose, based on signal enhancement rate. Diagnostic accuracy is similar on qualitative assessment. Prostate cancer diagnosis may be feasible with DCE-MRI with low-dose GBCA. In addition, comparison of enhancement kinetics after low and high doses of contrast media may provide diagnostically useful information.

Due to large inter- and intra-patient variabilities of arterial input functions (AIFs), accurately modeling and using patient-specific AIF are very important for quantitative analysis of dynamic contrast enhanced MRI. Computer simulations were performed to evaluate and compare nine population AIF models with the Parker AIF used as ‘gold standard’. The Parker AIF was calculated with a temporal resolution of 1.5 s, and then the other nine AIF models were used to fit the Parker AIF. A total of 100 randomly generated volume transfer constants (Ktrans) and distribution volumes (ve) were used to calculate the contrast agent concentration curves based on the Parker AIF and the extended Tofts model with blood plasma volume (vp) = 0.0, 0.01, 0.05 and 0.10. Subsequently, nine AIF models were used to fit these curves to extract physiological parameters (Ktrans, ve and vp). The agreements between generated and extracted Ktrans and ve values were evaluated using Bland–Altman analysis. The effects of the second pass of the Parker AIF model with and without adding Rician noise on extracted physiological parameters were evaluated by 1000 simulations using one of the nine mathematical AIF models closest to the Parker model with the smallest number of parameters. The results demonstrated that a six-parameter linear function plus bi-exponential function AIF model was almost equivalent to the Parker AIF and that the corresponding generated and extracted Ktrans and ve were in excellent agreements. The effects of the second pass of contrast agent circulation were small on extracted physiological parameters using the extended Tofts model, unless noise was added with signal to noise ratio less than 10 dB.

RATIONALE AND OBJECTIVES: This study aimed to test high temporal resolution dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) for different zones of the prostate and evaluate its performance in the diagnosis of prostate cancer (PCa). Determine whether the addition of ultrafast DCE-MRI improves the performance of multiparametric MRI. MATERIALS AND METHODS: Patients (n = 20) with pathologically confirmed PCa underwent preoperative 3T MRI with T2-weighted, diffusion-weighted, and high temporal resolution (~2.2 seconds) DCE-MRI using gadoterate meglumine (Guerbet, Bloomington, IN) without an endorectal coil. DCE-MRI data were analyzed by fitting signal intensity with an empirical mathematical model to obtain parameters: percent signal enhancement, enhancement rate (α), washout rate (β), initial enhancement slope, and enhancement start time along with apparent diffusion coefficient (ADC) and T2 values. Regions of interests were placed on sites of prostatectomy verified malignancy (n = 46) and normal tissue (n = 71) from different zones. RESULTS: Cancer (α = 6.45 ± 4.71 s(−1), β = 0.067 ± 0.042 s(−1), slope = 3.78 ± 1.90 s(−1)) showed significantly (P < .05) faster signal enhancement and washout rates than normal tissue (α = 3.0 ± 2.1 s(−1), β = 0.034 ± 0.050 s(−1), slope = 1.9 ± 1.4 s(−1)), but showed similar percentage signal enhancement and enhancement start time. Receiver operating characteristic analysis showed area under the curve for DCE parameters was comparable to ADC and T2 in the peripheral (DCE 0.67–0.82, ADC 0.80, T2 0.89) and transition zones (DCE 0.61–0.72, ADC 0.69, T2 0.75), but higher in the central zone (DCE 0.79–0.88, ADC 0.45, T2 0.45) and anterior fibromuscular stroma (DCE 0.86–0.89, ADC 0.35, T2 0.12). Importantly, combining DCE with ADC and T2 increased area under the curve by ~30%, further improving the diagnostic accuracy of PCa detection. CONCLUSION: Quantitative parameters from empirical mathematical model fits to ultrafast DCE-MRI improve diagnosis of PCa. DCE-MRI with higher temporal resolution may capture clinically useful information for PCa diagnosis that would be missed by low temporal resolution DCE-MRI. This new information could improve the performance of multiparametric MRI in PCa detection.

Differences between region-of-interest (ROI) and pixel-by-pixel analysis of dynamic contrast enhanced (DCE) MRI data were investigated in this study with computer simulations and pre-clinical experiments. ROIs were simulated with 10, 50, 100, 200, 400, and 800 different pixels. For each pixel, a contrast agent concentration as a function of time, C(t), was calculated using the Tofts DCE-MRI model with randomly generated physiological parameters (K trans and v e) and the Parker population arterial input function. The average C(t) for each ROI was calculated and then K trans and v e for the ROI was extracted. The simulations were run 100 times for each ROI with new K trans and v e generated. In addition, white Gaussian noise was added to C(t) with 3, 6, and 12 dB signal-to-noise ratios to each C(t). For pre-clinical experiments, Copenhagen rats (n = 6) with implanted prostate tumors in the hind limb were used in this study. The DCE-MRI data were acquired with a temporal resolution of ~5 s in a 4.7 T animal scanner, before, during, and after a bolus injection (

This study investigates the multiparametric MRI (mpMRI) appearance of different types of benign prostatic hyperplasia (BPH) and whether quantitative mpMRI is effective in differentiating between prostate cancer (PCa) and BPH. Patients (n = 60) with confirmed PCa underwent preoperative 3T MRI. T2-weighted, multi-echo T2-weighted, diffusion weighted and dynamic contrast enhanced images (DCE) were obtained prior to undergoing prostatectomy. PCa and BPH (cystic, glandular or stromal) were identified in the transition zone and matched with MRI. Quantitative mpMRI metrics: T2, ADC and DCE-MRI parameters using an empirical mathematical model were measured. ADC values were significantly lower (p

Subclinical depression (SD) has been considered as the precursor to major depressive disorder. Accurate prediction of SD and identification of its etiological origin are urgent. Bursts within the lateral habenula (LHb) drive depression in rats, but whether dysfunctional LHb is associated with SD in human is unknown. Here we develop connectome-based biomarkers which predict SD and identify dysfunctional brain regions and connections. T1 weighted images and resting-state functional MRI (fMRI) data were collected from 34 subjects with SD and 40 healthy controls (HCs). After the brain is parcellated into 48 brain regions (246 subregions) using the human Brainnetome Atlas, the functional network of each participant is constructed by calculating the correlation coefficient for the time series of fMRI signals of each pair of subregions. Initial candidates of abnormal connections are identified by the two-sample t-test and input into Support Vector Machine models as features. A total of 24 anatomical-region-based models, 231 sliding-window-based models, and 100 random-selection-based models are built. The performance of these models is estimated through leave-one-out cross-validation and evaluated by measures of accuracy, sensitivity, confusion matrix, receiver operating characteristic curve, and the area under the curve (AUC). After confirming the region with the highest accuracy, subregions within the thalamus and connections associated with subregions of LHb are compared. It is found that five prediction models using connections of the thalamus, posterior superior temporal sulcus, cingulate gyrus, superior parietal lobule, and superior frontal gyrus achieve an accuracy >0.9 and an AUC >0.93. Among 90 abnormal connections associated with the thalamus, the subregion of the right posterior parietal thalamus where LHb is located has the most connections (n = 18), the left subregion only has 3 connections. In SD group, 10 subregions in the thalamus have significantly different node degrees with those in the HC group, while 8 subregions have lower degrees ( p < 0.01), including the one with LHb. These results implicate abnormal brain connections associated with the thalamus and LHb to be associated with SD. Integration of these connections by machine learning can provide connectome-based biomarkers to accurately diagnose SD.

Aortic pulse wave reflects cardiovascular status, but, unlike the peripheral pulse wave, is difficult to be measured reliably using noninvasive techniques. Thus, the estimation of aortic pulse wave from peripheral ones is of great significance. This study proposed an adaptive transfer function (ATF) method to estimate the aortic pulse wave from the brachial pulse wave. Aortic and brachial pulse waves were derived from 26 patients who underwent cardiac catheterization. Generalized transfer functions (GTF) were derived based on the autoregressive exogenous model. Then, the GTF was adapted by its peak resonance frequency. And the optional peak resonance frequency for an individual was determined by regression formulas using brachial systolic blood pressure. The method was validated using the leave-one-out cross validation method. Compared with previous studies, the ATF method showed better performance in estimating the aortic pulse wave and predicting the feature parameters. The prediction error of the aortic systolic blood pressure and pulse pressure were 0.2 ± 3.1 and -0.9 ± 3.1 mmHg, respectively. The percentage errors of augmentation index, percentage notch amplitude, and ejection duration were -2.1 ± 32.7%, 12.4 ± 9.2%, and -2.4 ± 3.3%, respectively.

The Tofts pharmacokinetic model requires multiple calculations for analysis of dynamic contrast enhanced (DCE) MRI. In addition, the Tofts model may not be appropriate for the prostate. This can result in error propagation that reduces the accuracy of pharmacokinetic measurements. In this study, we present a compact solution allowing estimation of physiological parameters K(trans) and v(e) from ultrafast DCE acquisitions, without fitting DCE-MRI data to the standard Tofts pharmacokinetic model. Since the standard Tofts model can be simplified to the Patlak model at early times when contrast efflux from the extravascular extracellular space back to plasma is negligible, K(trans) can be solved explicitly for a specific time. Further, v(e) can be estimated directly from the late steady-state signal using the derivative form of Tofts model. Ultrafast DCE-MRI data were acquired from 18 prostate cancer patients on a Philips Achieva 3T-TX scanner. Regions-of-interest (ROIs) for prostate cancer, normal tissue, gluteal muscle, and iliac artery were manually traced. The contrast media concentration as function of time was calculated over each ROI using gradient echo signal equation with pre-contrast tissue T1 values, and using the ‘reference tissue’ model with a linear approximation. There was strong correlation (r = 0.88–0.91, p < 0.0001) between K(trans) extracted from the Tofts model and K(trans) estimated from the compact solution for prostate cancer and normal tissue. Additionally, there was moderate correlation (r = 0.65–0.73, p < 0.0001) between extracted versus estimated v(e). Bland-Altman analysis showed moderate to good agreement between physiological parameters extracted from the Tofts model and those estimated from the compact solution with absolute bias less than 0.20 min(−1) and 0.10 for K(trans) and v(e), respectively. The compact solution may decrease systematic errors and error propagation, and could increase the efficiency of clinical workflow. The compact solution requires high temporal resolution DCE-MRI due to the need to adequately sample the early phase of contrast media uptake.

Pulse waves contain rich physiological and pathological information of the human vascular system. The pulse wave diagnosis systems are very helpful for the clinical diagnosis and treatment of cardiovascular diseases. Accurate pulse waveform is necessary to evaluate the performances of the pulse wave equipment. However, it is difficult to obtain accurate pulse waveform due to several kinds of physiological and pathological conditions for testing and maintaining the pulse wave acquisition devices. A pulse wave generator was designed and implemented in the present study for this application. The blood flow in the vessel was simulated by modeling the cardiovascular system with windkessel model. Pulse waves can be generated based on the vascular systems with four kinds of resistance. Some functional models such as setting up noise types and signal noise ratio (SNR) values were also added in the designed generator. With the need of portability, high speed dynamic response, scalability and low power consumption for the system, field programmable gate array (FPGA) was chosen as hardware platform, and almost all the works, such as developing an algorithm for pulse waveform and interfacing with memory and liquid crystal display (LCD), were implemented under the flow of system on a programmable chip (SOPC) development. When users input in the key parameters through LCD and touch screen, the corresponding pulse wave will be displayed on the LCD and the desired pulse waveform can be accessed from the analog output channel as well. The structure of the designed pulse wave generator is simple and it can provide accurate solutions for studying and teaching pulse waves and the detection of the equipments for acquisition and diagnosis of pulse wave.

In this paper, the radial pulse waveforms of the same subjects under various contact pressures were measured. Then, the feature points of the pulse wave contours were extracted and the physical parameters were calculated corresponding to different contact pressures. The various trends of parameters, including peripheral augmentation index, peripheral subendocardial viability ratio, and peripheral resistance, influenced by contact pressures were analyzed. By comparing the variation trend between different subject groups, it is notable that there exists a significant difference between the parameters of young healthy people and elder patients (P

The fall detection algorithm, which can recognize the fall of human body by collecting the acceleration signals in different directions of the body, is an important part of fall detection system for the elderly. The system, however, may have errors during analyzing the acceleration signal, due to that the coordinate system of the transducer does not coincide with the one of human motion. Furthermore, voltage variation of the battery also influences the accuracy of the acceleration signal. Therefore, in this paper, a fall detection system based on the 3D-acceleration transducer MMA7260 is designed, which can calibrate the acceleration data through compensation of voltage and transformation of coordinates. Experiments illustrated that the proposed method can accurately transform the collected data from the coordinate system of the transducer to that of the human motion, and can recognize various postural changes in the course of the motion of human body. Language: en

Objective: To judge whether the pulse rate variability can be used as a surrogate of heart rate variability, as well as investigate the quantitative relationship between them. Methods: Being simultaneously acquired, the pulse wave and ECG data were denoised, removed baseline drift. Then the pulse rate intervals and heart rate intervals were extracted. Finally, the relationship between the heart rate variability and pulse rate variability were studied in the time domain, frequency domain, and nonlinear analysis. Conclusion: By studying the pulse rate variabilities and heart rate variabilities of 30 healthy adolescents, we find that heart rate variability and pulse rate variability is correlated, but the difference is relatively small, in a resting condition, the difference of time domain is less than 3%, the Frequency domain is less than 9%, the nonlinear is less than 9%, which in a certain extent can replace each other. Furthermore, the influence from the neural regulation and respiration caused the delay of PRV in comparison with HRV, ranging from 6% to 20% of a heartbeat period. The breathing more greatly influences the PRV than HRV.