Prediction of radiologic outcome-optimized dose plans and post-treatment magnetic resonance images: A proof-of-concept study in breast cancer brain metastases treated with stereotactic radiosurgery.

Background and purpose: Information in multiparametric Magnetic Resonance (mpMR) images is relatable to voxel-level tumor response to Radiation Treatment (RT). We have investigated a deep learning framework to predict (i) post-treatment mpMR images from pre-treatment mpMR images and the dose map ("forward models"), and, (ii) the RT dose map that will produce prescribed changes within the Gross Tumor Volume (GTV) on post-treatment mpMR images ("inverse model"), in Breast Cancer Metastases to the Brain (BCMB) treated with Stereotactic Radiosurgery (SRS). Materials and methods: Local outcomes, planning computed tomography (CT) images, dose maps, and pre-treatment and post-treatment Apparent Diffusion Coefficient of water (ADC) maps, T1-weighted unenhanced (T1w) and contrast-enhanced (T1wCE), T2-weighted (T2w) and Fluid-Attenuated Inversion Recovery (FLAIR) mpMR images were curated from 39 BCMB patients. mpMR images were co-registered to the planning CT and intensity-calibrated. A 2D pix2pix architecture was used to train 5 forward models (ADC, T2w, FLAIR, T1w, T1wCE) and 1 inverse model on 1940 slices from 18 BCMB patients, and tested on 437 slices from another 9 BCMB patients. Results: Root Mean Square Percent Error (RMSPE) within the GTV between predicted and ground-truth post-RT images for the 5 forward models, in 136 test slices containing GTV, were (mean ± SD) 0.12 ± 0.044 (ADC), 0.14 ± 0.066 (T2w), 0.08 ± 0.038 (T1w), 0.13 ± 0.058 (T1wCE), and 0.09 ± 0.056 (FLAIR). RMSPE within the GTV on the same 136 test slices, between the predicted and ground-truth dose maps, was 0.37 ± 0.20 for the inverse model. Conclusions: A deep learning-based approach for radiologic outcome-optimized dose planning in SRS of BCMB has been demonstrated.

Joint total variation-based reconstruction of multiparametric magnetic resonance images for mapping tissue types.

Multispectral analysis of coregistered multiparametric magnetic resonance (MR) images provides a powerful method for tissue phenotyping and segmentation. Acquisition of a sufficiently varied set of multicontrast MR images and parameter maps to objectively define multiple normal and pathologic tissue types can require long scan times. Accelerated MRI on clinical scanners with multichannel receivers exploits techniques such as parallel imaging, while accelerated preclinical MRI scanning must rely on alternate approaches. In this work, tumor-bearing mice were imaged at 7 T to acquire k-space data corresponding to a series of images with varying T1-, T2- and T2*-weighting. A joint reconstruction framework is proposed to reconstruct a series of T1-weighted images and corresponding T1 maps simultaneously from undersampled Cartesian k-space data. The ambiguity introduced by undersampling was resolved by using model-based constraints and structural information from a reference fully sampled image as the joint total variation prior. This process was repeated to reconstruct T2-weighted and T2*-weighted images and corresponding maps of T2 and T2* from undersampled Cartesian k-space data. Validation of the reconstructed images and parameter maps was carried out by computing tissue-type maps, as well as maps of the proton density fat fraction (PDFF), proton density water fraction (PDwF), fat relaxation rate ( R2f*) and water relaxation rate ( R2w*) from the reconstructed data, and comparing them with ground truth (GT) equivalents. Tissue-type maps computed using 18% k-space data were visually similar to GT tissue-type maps, with dice coefficients ranging from 0.43 to 0.73 for tumor, fluid adipose and muscle tissue types. The mean T1 and T2 values within each tissue type computed using only 18% k-space data were within 8%-10% of the GT values from fully sampled data. The PDFF and PDwF maps computed using 27% k-space data were within 3%-15% of GT values and showed good agreement with the expected values for the four tissue types.

Novel Catheter Multiscope: A Feasibility Study.

Open Challenges: Continuous monitoring of fundamental cardiovascular hemodynamic parameters is essential to accomplish critical care diagnostics. Today's standard of care measures these critical parameters using multiple monitoring technologies. These state-of-the-art technologies require expensive instrumentation and complex infrastructure. Therefore, it is challenging to use current technologies to accomplish monitoring in a low resource setting. OBJECTIVE: In order to address the challenges caused by having to use multiple monitoring systems, a point of care monitoring device was developed in this work to provide multiple critical parameters by uniquely measuring the hemodynamic process. METHODS: To demonstrate the usability of this novel catheter multiscope, a feasibility study was performed using an animal model. The developed measurement system first acquires the dynamics of blood flow through a minimally invasive catheter. Then, a signal processing framework was developed to characterize the blood flow dynamics and to obtain critical parameters such as heart rate, respiratory rate, and blood pressure. The framework used to extract the physiological data corresponding to the acoustic field of the blood flow consisted of a noise cancellation method and wavelet-based source separation. RESULTS: The preliminary results of the acoustic pressure field of the blood flow revealed the presence of acoustic heart and respiratory pulses. A unique framework was also developed to extract continuous blood pressure from the acoustic pressure field of the blood flow. Finally, the computed heart and respiratory rates, systolic and diastolic pressures were benchmarked with actual values measured using conventional devices to validate the hypothesis. CONCLUSION: The results confirm that catheter multiscope can provide multiple critical parameters with clinical reliability. SIGNIFICANCE: A novel critical care monitoring system has been developed to accurately measure heart rate, respiratory rate, systolic and diastolic pressures from the blood flow dynamics.

A novel acoustic catheter stethoscope based acquisition and signal processing framework to extract multiple bio signals.

In this study, a novel acoustic stethoscope based on an intravenous catheter was introduced to measure vascular pressures from a Yorkshire pig. Our hypothesis is that by means of this single device (measurement system) and by applying signal analysis and processing framework, multiple vital bio signals can be extracted. In contrast, current conventional state-of-the-art technologies use multiple devices to provide the same information. The framework used to extract these bio signals consisted of a noise cancellation technique and wavelet based source separation. The preliminary results obtained from the acquired pressure data revealed the presence of acoustic heart and respiratory pulses. Finally, the computed heart and respiratory rates were benchmarked with actual values measured using conventional devices to validate our hypothesis.

Modeling battery behavior on sensory operations for context-aware smartphone sensing.

Energy consumption is a major concern in context-aware smartphone sensing. This paper first studies mobile device-based battery modeling, which adopts the kinetic battery model (KiBaM), under the scope of battery non-linearities with respect to variant loads. Second, this paper models the energy consumption behavior of accelerometers analytically and then provides extensive simulation results and a smartphone application to examine the proposed sensor model. Third, a Markov reward process is integrated to create energy consumption profiles, linking with sensory operations and their effects on battery non-linearity. Energy consumption profiles consist of different pairs of duty cycles and sampling frequencies during sensory operations. Furthermore, the total energy cost by each profile is represented by an accumulated reward in this process. Finally, three different methods are proposed on the evolution of the reward process, to present the linkage between different usage patterns on the accelerometer sensor through a smartphone application and the battery behavior. By doing this, this paper aims at achieving a fine efficiency in power consumption caused by sensory operations, while maintaining the accuracy of smartphone applications based on sensor usages. More importantly, this study intends that modeling the battery non-linearities together with investigating the effects of different usage patterns in sensory operations in terms of the power consumption and the battery discharge may lead to discovering optimal energy reduction strategies to extend the battery lifetime and help a continual improvement in context-aware mobile services.

Integrated approach for smart implantable cardioverter defibrillator (ICD) device with real time ECG monitoring: use of flexible sensors for localized arrhythmia sensing and stimulation.

Arrhythmias are the most common cause of death associated with sudden death and are common in US and worldwide. Cardiac resynchronization therapy (CRT), evolving from pacemakers and development of implantable cardioverter defibrillator (ICD), has been adopted for therapeutic use and demonstrated benefits in patients over the years due to its design and intricate functionality. Recent research has been focused on significant design improvement and efforts are dedicated toward device size reduction, weight and functionality in commercially available ICD's since its invention in the 1960's. Commercially available CRT-D has shown advancement on both clinical and technical side. However, improved focus is required on the device miniaturization, technologically supported and integrated wireless based system for real time heart monitoring electrocardiogram (ECG). In the present report a concise overview for the state-of-the art technology in ICDs and avenues for future development are presented. A unique perspective is also included for ICD device miniaturization and integration of flexible sensing array. Sensor array integration along with its capabilities for identifying localized arrhythmia detection and targeted stimulation for enhancing ICD device capabilities is reviewed.

Computational fluid dynamic analysis of flow velocity waveform notching in umbilical arteries.

Umbilical artery Doppler velocimetry waveform notching has long been associated with umbilical cord abnormalities, such as distortion, torsion, and/or compression (i.e., constriction). The physical mechanism by which the notching occurs has not been elucidated. Flow velocity waveforms (FVWs) from two-dimensional pulsatile flows in a constricted channel approximating a compressed umbilical cord are analyzed, leading to a clear relationship between the notching and the constriction. Two flows with an asymmetric, semi-elliptical constriction are computed using a stabilized finite-element method. In one case, the constriction blocks 75% of the flow passage, and in the other the constriction blocks 85%. Channel width and prescribed flow rates at the channel inflow are consistent with typical cord diameters and flow rates reported in the literature. Computational results indicate that waveform notching is caused by flow separation induced by the constriction, giving rise to a vortex (core) wave and associated eddies. Notching in FVWs based on centerline velocity (centerline FVW) is directly related to the passage of an eddy over the point of measurement on the centerline. Notching in FVWs based on maximum cross-sectional velocity (envelope FVW) is directly related to acceleration and deceleration of the fluid along the vortex wave. Results show that notching in envelope FVW is not present in flows with less than a 75% constriction. Furthermore, notching disappears as the vortex wave is attenuated at distances downstream of the constriction. In the flows with 75 and 85% constriction, notching of the envelope FVW disappears at ∼3.8 and ∼4.3 cm (respectively) downstream of the constriction. These results are of significant medical importance, given that envelope FVW is typically measured by commercial Doppler systems.

A novel approach to nodule feature optimization on thin section thoracic CT.

RATIONALE AND OBJECTIVES: An analysis for the optimum selection of image features in feature domain to represent lung nodules was performed, with implementation into a classification module of a computer-aided diagnosis system. MATERIALS AND METHODS: Forty-two regions of interest obtained from 38 cases with effective diameters of 3 to 8.5 mm were used. On the basis of image characteristics and dimensionality, 11 features were computed. Nonparametric correlation coefficients, multiple regression analysis, and principal-component analysis were used to map the relation between the represented features from four radiologists and the computed features. An artificial neural network was used for the classification of benign and malignant nodules to test the hypothesis obtained from the mapping analysis. RESULTS: Correlation coefficients ranging from 0.2693 to 0.5178 were obtained between the radiologists' annotations and the computed features. Of the 11 features used, three were found to be redundant when both nodule and non-nodule cases were used, and five were found redundant when nodule or non-nodule cases were used. Combination of analysis from correlation coefficients, regression analysis, principal-component analysis, and the artificial neural network resulted in the selection of optimum features to achieve F-test values of 0.821 and 0.643 for malignant and benign nodules, respectively. CONCLUSION: This study demonstrates that for the optimum selection of features, each feature should be analyzed individually and collectively to evaluate the impact on the computer-aided diagnosis system on the basis of its class representation. This methodology will ultimately aid in improving the generalization capability of a classification module for early lung cancer diagnosis.

Size-Exclusion "capture and release" separations using surface-patterned poly(N-isopropylacrylamide) hydrogels.

Micrometer-scale poly(N-isopropylacrylamide) (poly-NIPAAm) hydrogel monolith patterns were fabricated on solid surfaces using soft lithography. At sufficiently high aspect ratios, the hydrogel monoliths swell and contract laterally with temperature. The spaces between the monoliths form a series of trenches that catch, hold, and release appropriately sized targets. A series of poly-NIPAAm monoliths were fabricated with dry dimensions of 40 microm height, 12 microm diameter, and a spacing of 12 microm between monoliths. Above the lower critical solution temperature (LCST), the monoliths collapse to their dry dimensions and the spacing between monoliths is 12 microm. Below the LCST, the monoliths swell by 70% in the lateral direction, reducing the gap size between monoliths to 3 microm. The potential use of the hydrogel monoliths as size-selective "catch and release" structures was demonstrated with a mixture of 6 and 20 microm polystyrene microspheres, where the 6 microm diameter particles were selectively concentrated and separated from the larger particles.