Breast cancer diagnosis using feature extraction and boosted C5.0 decision tree algorithm with penalty factor.

To overcome the two class imbalance problem among breast cancer diagnosis, a hybrid method by combining principal component analysis (PCA) and boosted C5.0 decision tree algorithm with penalty factor is proposed to address this issue. PCA is used to reduce the dimension of feature subset. The boosted C5.0 decision tree algorithm is utilized as an ensemble classifier for classification. Penalty factor is used to optimize the classification result. To demonstrate the efficiency of the proposed method, it is implemented on biased-representative breast cancer datasets from the University of California Irvine(UCI) machine learning repository. Given the experimental results and further analysis, our proposal is a promising method for breast cancer and can be used as an alternative method in class imbalance learning. Indeed, we observe that the feature extraction process has helped us improve diagnostic accuracy. We also demonstrate that the extracted features considering breast cancer issues are essential to high diagnostic accuracy.

Feasibility of MRI based oxygenation imaging for the assessment of acute limb ischemia.

BACKGROUND: Acute limb ischemia (ALI) can lead to death and amputation. Evaluating the severity of ischemia is important but difficult, through current methods of examination. The purpose of this research was to demonstrate the feasibility of magnetic resonance imaging (MRI) susceptibility-based imaging techniques for use in assessing muscle oxygenation alterations in ALI. METHODS: ALI animal models were established in 11 rabbits. Their left iliac arteries were embolized by microspheres. MRI scans were conducted 24 hours before (Pre) and 1 hour (Post 1) and 3 hours (Post 2) after the procedure. A susceptibility model was used to calculate skeletal muscle oxygenation extraction fraction (SMOEF) and relaxation rate (R2'). T2 weighted (T2w) imaging and diffusion-weighted (DW) imaging were performed. RESULTS: The average calf muscle SMOEF in the embolized hindlimbs increased from 0.43±0.02 (Pre) to 0.48±0.02 (Post 1) and 0.50±0.02 (Post 2), both P<0.05. The R2' value increased from 13.01±2.31 s-1 (Pre) to 16.78±2.28 s-1 (Post 1) and 17.90±3.29 s-1 (Post 2), both P<0.05. No significant changes of SMOEF and R2' were found after embolization in the contralateral hindlimbs. Apparent diffusion coefficient (ADC) values derived from DW imaging remained unchanged at different stages compared to before the procedures (all P>0.05). No abnormal signals were observed in the anatomical T2w images at Post 1 and Post 2. CONCLUSIONS: This study demonstrates the feasibility of using SMOEF for the assessment of oxygenation alterations in ALI models. SMOEF is more sensitive than T2w and DW imaging in detecting acute muscle ischemia at an early stage.

Quantitative renal function assessment of atheroembolic renal disease using view-shared compressed sensing based dynamic-contrast enhanced MR imaging: An in vivo study.

Atheroembolic renal disease (AERD) is the major cause of renal insufficiency in the elderly, and particularly, the diagnose of AERD is often delayed and even missed due to its nonspecific presentation and the sudden occurrence of an embolic event. To investigate the feasibility of the view-shared compressed sensing (VCS) based dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) in the assessment of AERD in animal models. The reproducibility of VCS DCE-MRI based glomerular filtration rate (GFR) estimation was first evaluated using the three healthy rabbits. Animal models of unilateral AERD were then conducted. All the rabbits underwent VCS DCE-MRI and the GFR maps were estimated by a commonly used cortical-compartment model. The whole kidney and suspicious lesion region GFR values of embolized kidneys were then compared with the corresponding values of normal kidneys. Finally, the suspicious lesion regions were confirmed by the corresponding renal specimens and histological findings. The reproducibility of GFR measurements was analyzed using the coefficient of variation and Bland-Altman analysis. The GFR values of normal and embolized kidneys were compared using the Student t-test. Contrast-enhanced images with sufficient diagnostic quality and reduced motion artifacts are obtained at a temporal resolution of 2.5 s. The Bland-Altman plot indicated close agreement between the GFR values estimated from between-day scans in healthy rabbits. Besides, there existed significant differences between the pixel-wise GFR values of normal and AERD kidneys in region-based comparison(P < 0.0001). The suspicious lesions are consistent well with the renal specimen and histological findings. The preliminary animal study verified the feasibility of VCS DCE-MRI for renal function evaluation, and the strategy could potentially provide a valuable tool to identify AERD.

A feasibility study of using noninvasive renal oxygenation imaging for the early assessment of ischemic acute kidney injury in an embolization model.

PURPOSE: To investigate the feasibility of using MRI based oxygenation imaging for early assessment of ischemic acute kidney injury (AKI) in an embolization model. METHODS: Ischemic AKI model was induced in 40 rabbits by injection of microspheres into the right renal arteries. Animals were grouped according to the dose of microspheres: Severe AKI group, 2.0 mg (N = 10); Moderate AKI group, 1.0 mg (N = 10); Mild AKI group, 0.5 mg (N = 10); Control group, saline without microspheres (N = 10). A serial MRI examination was performed at intervals of 1 h, 1 day, 1 week and 4 weeks to evaluate the deterioration of renal function. A multi-echo ASE sequence was implemented for renal oxygenation measurement 1 h after surgery. Pathological examinations were performed 4 weeks after the surgery. RESULTS: In renal cortex, renal oxygen extraction fraction (OEF) raised significantly after embolization procedures in all experimental groups (severe AKI: 0.39 ±â€¯0.05, P < 0.05; moderate AKI: 0.36 ±â€¯0.03, P < 0.05; mild AKI: 0.34 ±â€¯0.02, P < 0.05) compared to the control group (0.29 ±â€¯0.02). In outer medulla, significant difference was observed between control group (0.29 ±â€¯0.03) and severe AKI group (0.35 ±â€¯0.03, P < 0.05), and between control group and moderate AKI group (0.34 ±â€¯0.04, P < 0.05). Corresponding lesions were found in pathological examinations 4 weeks after the procedure. CONCLUSION: This study demonstrates the feasibility of using oxygenation imaging to assess the embolization induced ischemic AKI at an early stage.

Early assessment of acute kidney injury using targeted field of view diffusion-weighted imaging: An in vivo study.

Acute kidney injury (AKI) is a common complication in various clinical settings. In recent years, AKI diagnostics have been investigated intensively showing the emerging need for early characterization of this disease. To verify whether targeted field-of-view diffusion-weighted imaging (tFOV-DWI) is feasible to significantly improve the performance of traditional full field-of-view diffusion-weighted imaging (fFOV-DWI) in the early assessment of AKI. 14 rabbits with unilateral AKI were induced by injection of microspheres under the guidance of digital subtraction angiography (DSA). All rabbits underwent tFOV-DWI and fFOV-DWI immediately after the surgery. Artifacts, distortion and lesion identification were graded by two experienced radiologists, and the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured. Apparent diffusion coefficient (ADC) maps were then derived. Blood samples were collected pre- and post-surgery and serum creatinine weres measured. Renal specimen and biopsy were performed as the reference standard. Student t-test was used to ascertain statistical significance between the above parameters for tFOV-DWI and fFOV-DWI. The interobserver agreement and ADC measurements agreement were assessed. A higher percentage of renal lesions (17 out of 19) were detected in tFOV-DWI compared with fFOV-DWI (14 out of 19). Significant differences were observed in ADC value for both techniques between the lesion regions and normal tissues (p < 0.001). Histological findings were inversely correlated with ADC values of tFOV-DWI (r = -0.97, P < 0.001 for cortex; r = -0.98, P < 0.001 for medulla) and fFOV-DWI sequences (r = -0.95, P < 0.001 for cortex; r = -0.98, P < 0.001 for medulla). Those tFOV-DW images rated by the radiologists exhibit superior performance in terms of all assessed measures (P < 0.05), and interobserver agreement was excellent (ICC, 0.78 to 0.92). Besides, the ADC values derived from tFOV-DWI had a satisfactory agreement with those estimated by fFOV-DWI. The animal study demonstrates that the tFOV-DWI strategy provided visually better image quality and lesion depiction than conventional fFOV-DWI for early assessment of AKI.

An improved automated type-based method for area assessment of wound surface.

Accurate and precise wound measurements are a critical component of wound detection and assessment. Digital cameras are convenient and objective tools that are being increasingly used worldwide to assist with wound measurements and assessments. However, heterogeneous wounds and poor lighting conditions continue to be obstacles to wound area recognition. This study, therefore, provides an improved automated type-based wound area assessment method that is robust to lighting conditions and can distinguish between different wound tissues based on wound colors. The results of both laboratory and clinical applications of the proposed method show excellent consistency of manual area measurements. This proposed technology is expected to provide wound care specialists with more clinical information about heterogeneous wounds, thereby enabling prospective cost savings for therapy and treatment.

Reduction of Dual-task Costs by Noninvasive Modulation of Prefrontal Activity in Healthy Elders.

Dual tasking (e.g., walking or standing while performing a cognitive task) disrupts performance in one or both tasks, and such dual-task costs increase with aging into senescence. Dual tasking activates a network of brain regions including pFC. We therefore hypothesized that facilitation of prefrontal cortical activity via transcranial direct current stimulation (tDCS) would reduce dual-task costs in older adults. Thirty-seven healthy older adults completed two visits during which dual tasking was assessed before and after 20 min of real or sham tDCS targeting the left pFC. Trials of single-task standing, walking, and verbalized serial subtractions were completed, along with dual-task trials of standing or walking while performing serial subtractions. Dual-task costs were calculated as the percent change in markers of gait and postural control and serial subtraction performance, from single to dual tasking. Significant dual-task costs to standing, walking, and serial subtraction performance were observed before tDCS (p < .01). These dual-task costs were less after real tDCS as compared with sham tDCS as well as compared with either pre-tDCS condition (p < .03). Further analyses indicated that tDCS did not alter single task performance but instead improved performance solely within dual-task conditions (p < .02). These results demonstrate that dual tasking can be improved by modulating prefrontal activity, thus indicating that dual-task decrements are modifiable and may not necessarily reflect an obligatory consequence of aging. Moreover, tDCS may ultimately serve as a novel approach to preserving dual-task capacity into senescence.

Transcranial direct current stimulation reduces the cost of performing a cognitive task on gait and postural control.

This proof-of-concept, double-blind study was designed to determine the effects of transcranial direct current stimulation (tDCS) on the 'cost' of performing a secondary cognitive task on gait and postural control in healthy young adults. Twenty adults aged 22 ± 2 years completed two separate double-blind visits in which gait and postural control were assessed immediately before and after a 20 min session of either real or sham tDCS (1.5 mA) targeting the left dorsolateral prefrontal cortex. Gait speed and stride duration variability, along with standing postural sway speed and area, were recorded under normal conditions and while simultaneously performing a serial-subtraction cognitive task. The dual task cost was calculated as the percent change in each outcome from normal to dual task conditions. tDCS was well tolerated by all subjects. Stimulation did not alter gait or postural control under normal conditions. As compared with sham stimulation, real tDCS led to increased gait speed (P = 0.006), as well as decreased standing postural sway speed (P = 0.01) and area (P = 0.01), when performing the serial-subtraction task. Real tDCS also diminished (P < 0.01) the dual task cost on each of these outcomes. No effects of tDCS were observed for stride duration variability. A single session of tDCS targeting the left dorsolateral prefrontal cortex improved the ability to adapt gait and postural control to a concurrent cognitive task and reduced the cost normally associated with such dual tasking. These results highlight the involvement of cortical brain networks in gait and postural control, and implicate the modulation of prefrontal cortical excitability as a potential therapeutic intervention.

Quantitative assessment of acute kidney injury by noninvasive arterial spin labeling perfusion MRI: a pilot study.

The kidneys are essential for maintaining homeostasis, are responsible for the reabsorption of water, glucose and amino acids, and filter the blood by removing waste. Acute kidney injury (AKI) is a syndrome characterized by the rapid loss of renal excretory function and the accumulation of end metabolic products of urea and creatinine. AKI is associated with the later development of chronic kidney disease and end-stage kidney disease, and may eventually be fatal. Early diagnosis of AKI and assessments of the effects of treatment, however, are challenging. The pathophysiological mechanism of AKI is thought to be the imbalance between oxygen supply and demand in the kidneys. We have assessed the ability of arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI), without the administration of contrast media, to quantify renal blood flow (RBF) non-invasively. We found that RBF was significantly lower in AKI patients than in healthy volunteers. These results suggest that ASL perfusion MRI, a noninvasive measurement of RBF, may be useful in the early diagnosis of AKI.