Direct decoding of nonlinear OFDM-QAM signals using convolutional neural network.

Nonlinear Fourier transform, as a technique that has a great potential to overcome the capacity limit in fibre optical communication system, faces speed and accuracy bottlenecks in practice. Machine learning using convolutional neural networks shows great potential in NFT-based applications. We have developed a convolutional neural network for decoding information in NFT-based communication and numerically demonstrated its performance in comparison to a fast NFT algorithm. The comparison indicates the potential of conventional neural network to replace NFT calculations for decoding of information.

Real-time monitoring radiofrequency ablation using tree-based ensemble learning models.

BACKGROUND: Radiofrequency ablation is a minimally-invasive treatment method that aims to destroy undesired tissue by exposing it to alternating current in the 100 kHz-800 kHz frequency range and heating it until it is destroyed via coagulative necrosis. Ablation treatment is gaining momentum especially in cancer research, where the undesired tissue is a malignant tumor. While ablating the tumor with an electrode or catheter is an easy task, real-time monitoring the ablation process is a must in order to maintain the reliability of the treatment. Common methods for this monitoring task have proven to be accurate, however, they are all time-consuming or require expensive equipment, which makes the clinical ablation process more cumbersome and expensive due to the time-dependent nature of the clinical procedure. METHODS: A machine learning (ML) approach is presented that aims to reduce the monitoring time while keeping the accuracy of the conventional methods. Two different hardware setups are used to perform the ablation and collect impedance data at the same time and different ML algorithms are tested to predict the ablation depth in 3 dimensions, based on the collected data. RESULTS: Both the random forest and adaptive boosting (adaboost) models had over 98% R2 on the data collected with the embedded system-based hardware instrumentation setup, outperforming Neural Network-based models. CONCLUSIONS: It is shown that an optimal pair of hardware setup and ML algorithm (Adaboost) is able to control the ablation by estimating the lesion depth within a test average of 0.3mm while keeping the estimation time within 10ms on a ×86-64 workstation.

Real-time estimation of lesion depth and control of radiofrequency ablation within ex vivo animal tissues using a neural network.

BACKGROUND: Radiofrequency ablation (RFA), a method of inducing thermal ablation (cell death), is often used to destroy tumours or potentially cancerous tissue. Current techniques for RFA estimation (electrical impedance tomography, Nakagami ultrasound, etc.) require long compute times (≥ 2 s) and measurement devices other than the RFA device. This study aims to determine if a neural network (NN) can estimate ablation lesion depth for control of bipolar RFA using complex electrical impedance - since tissue electrical conductivity varies as a function of tissue temperature - in real time using only the RFA therapy device's electrodes. METHODS: Three-dimensional, cubic models comprised of beef liver, pork loin or pork belly represented target tissue. Temperature and complex electrical impedance from 72 data generation ablations in pork loin and belly were used for training the NN (403 s on Xeon processor). NN inputs were inquiry depth, starting complex impedance and current complex impedance. Training-validation-test splits were 70%-0%-30% and 80%-10%-10% (overfit test). Once the NN-estimated lesion depth for a margin reached the target lesion depth, RFA was stopped for that margin of tissue. RESULTS: The NN trained to 93% accuracy and an NN-integrated control ablated tissue to within 1.0 mm of the target lesion depth on average. Full 15-mm depth maps were calculated in 0.2 s on a single-core ARMv7 processor. CONCLUSIONS: The results show that a NN could make lesion depth estimations in real-time using less in situ devices than current techniques. With the NN-based technique, physicians could deliver quicker and more precise ablation therapy.

Optimization of Polydiacetylene-Coated Superparamagnetic Magnetite Biosensor for Colorimetric Detection of Biomarkers.

Biosensors for point-of-care testing of critical illnesses are urgently needed, especially in many areas of poor healthcare infrastructure. Polydiacetylene-based sensors are ideal because of their unique colorimetric properties where blue to red color shifts can be observed with the naked eye. In this work, a colorimetric biosensor capable of simple, rapid magnetic separation is optimized, using horse IgG as a model antibody, to obtain higher sensitivity. Composed of a unique combination of polydiacetylene and superparamagnetic iron oxide, the biosensor is fabricated at varying ratios of polydiacetylene to demonstrate optimization of color responsiveness. At increasing polydiacetylene ratios, improved color responsiveness and aqueous dispersion are observed, but the magnetic separation efficiency starts to suffer. The optimal color response is obtained at 90 wt% polydiacetylene. In addition, a 50 times improved lower detection limit of 0.01 mg/mL horse IgG is achieved, a relevant biomarker concentration for diagnosing sepsis. This platform provides a promising colorimetric biosensor for point-of-care use.

Understanding handpump sustainability: Determinants of rural water source functionality in the Greater Afram Plains region of Ghana.

Safe drinking water is critical to human health and development. In rural sub-Saharan Africa, most improved water sources are boreholes with handpumps; studies suggest that up to one third of these handpumps are nonfunctional at any given time. This work presents findings from a secondary analysis of cross-sectional data from 1509 water sources in 570 communities in the rural Greater Afram Plains (GAP) region of Ghana; one of the largest studies of its kind. 79.4% of enumerated water sources were functional when visited; in multivariable regressions, functionality depended on source age, management, tariff collection, the number of other sources in the community, and the district. A Bayesian network (BN) model developed using the same data set found strong dependencies of functionality on implementer, pump type, management, and the availability of tools, with synergistic effects from management determinants on functionality, increasing the likelihood of a source being functional from a baseline of 72% to more than 97% with optimal management and available tools. We suggest that functionality may be a dynamic equilibrium between regular breakdowns and repairs, with management a key determinant of repair rate. Management variables may interact synergistically in ways better captured by BN analysis than by logistic regressions. These qualitative findings may prove generalizable beyond the study area, and may offer new approaches to understanding and increasing handpump functionality and safe water access.

Serial and parallel convolutional neural network schemes for NFDM signals.

Two conceptual convolutional neural network (CNN) schemes are proposed, developed and analysed for directly decoding nonlinear frequency division multiplexing (NFDM) signals with hardware implementation taken into consideration. A serial network scheme with a small network size is designed for small user applications, and a parallel network scheme with high speed is designed for places such as data centres. The work aimed at showing the potential of using CNN for practical NFDM-based fibre optic communication. In the numerical demonstrations, the serial network only occupies 0.5 MB of memory space while the parallel network occupies 128 MB of memory but allows parallel computing. Both network schemes were trained with simulated data and reached more than 99.9% accuracy.

A correlation propagation model for nonlinear fourier transform of second order solitons.

Inverse scattering transform or nonlinear Fourier transform (NFT) has been proposed for optic communication to increase channel capacity beyond the well known Shannon limit. Within NFT, solitons, as discrete outputs of the transform, can be a type of resource to carry information. Second-order solitons as the most basic higher order solitons show correlations among their parameters in the nonlinear Fourier domain as they propagate along a fibre. In this work, we report, for the first time, a correlation propagation model for second-order soliton pulses in the nonlinear Fourier domain. The model can predict covariance matrices of soliton pulses at any propagation distance using only the covariance matrices calculated at the input of the fibre with different phases in the nonlinear Fourier domain without the need of propagating the pulses.

Correlated Eigenvalues of Multi-Soliton Optical Communications.

There is a fundamental limit on the capacity of fibre optical communication system (Shannon Limit). This limit can be potentially overcome via using Nonlinear Frequency Division Multiplexing. Dealing with noises in these systems is one of the most critical parts in implementing a practical system. In this paper, we discover and characterize the correlations among the NFT channels. It is demonstrated that the correlation is universal (i.e., independent of types of system noises) and can be exploited to maximize transmission throughput. We propose and experimentally confirm a noise model showing that end-to-end noise can be modelled as the accumulation of noise associated with each segment of optical communication which can be dealt with independently. Also, each point noise can be further decomposed into different components, some of which are more significant (and even dominating) than others. Hence, one can further approximate and simplify the noise model by focusing on the significant component.

Quasi-Spatially Periodic Signals for Optical Fibre Communications.

We study quasi-spatially periodic signals (QSPSs) as a class of input signals of interest, which maintain their shapes quasi-periodically (with a phase change and a time shift) during propagation in an optical fibre. Instead of the computationally expensive nonlinear Fourier transform (NFT), the property of quasi-periodic shape invariant could be used as an alternative for decoding at the receiver. In this paper, properties of QSPSs and the signal design problem are studied, including the trade-off between various system parameters.

Acute augmentation for interstitial insufficiency of the posterior cruciate ligament. A two to five year clinical and radiographic study.

BACKGROUND: there is need to ascertain clinical and imaging outcomes after posterior cruciate ligament (PCL) augmentation. METHODS: we performed a retrospective analysis of clinical, imaging and functional data on 21 physically active males who underwent arthroscopic trans-tibial augmentation of the PCL for symptomatic grade III PCL insufficiency. The average follow-up time was 50 months (24-60 months). The Lysholm knee score was administered to all the patients, ligament laxity was evaluated with the posterior drawer test, the KT-1000 arthrometer, and the anteromedial tibial step-off. Standing antero-posterior, lateral and Merchant's view radiographs were taken preoperatively and at annual follow-up. RESULTS: post-operatively, ligament laxity and Lysholm knee scores were significantly improved than at baseline. Sixteen patients (73%) returned to pre-injury sport activity level, 3 patients (14%) returned to a lower level, 2 had to stop. We found radiographic degenerative changes in 5 of 22 affected knees (23%), with evidence of a statistically significant association between the occurrence of degenerative changes and the interval time from injury to surgery and duration of the follow up. CONCLUSIONS: arthroscopic transtibial single bundle autograft hamstring augmentation significantly improves the function of the knee, with an overall satisfactory outcome of 82% at 2-5 years from surgery.

The Impact of the Oncotype DX Breast Cancer Assay on Treatment Decisions for Women With Estrogen Receptor-Positive, Node-Negative Breast Carcinoma in Hong Kong.

BACKGROUND: The Oncotype DX Breast Cancer Assay is validated to assess risk of distant recurrence and likelihood of chemotherapy (CT) benefit in estrogen receptor-positive ESBC in various populations. In Hong Kong, > 80% of breast cancers are early stage breast cancer (ESBC) and > 60% of these women receive CT. This prospective study measured changes in CT type and recommendations, as well as physician impression of assay impact in a homogenous Chinese population. METHODS: Consecutive patients with estrogen receptor-positive, T1-3 N0-1mi M0 ESBC were offered enrollment. After surgery, physicians discussed treatment options with patients, then ordered the assay, then reassessed treatment recommendation considering assay results. Changes in treatment recommendation, CT utilization, physician confidence, and physician rating of influence on their treatment recommendations were measured. RESULTS: A total of 146 evaluable patients received pre- and post-testing treatment recommendations. CT recommendations (including changes in intensity of CT) were changed for 34 of 146 patients (23.3%; 95% confidence interval, 16.7%-31.0%); change in intensity occurred in 7 of 146 (4.8%). There were 27 changes in treatment recommendations of adding or removing CT altogether (18.5% change; 95% confidence interval, 12.6%-25.8%). CT recommendations decreased from 52.1% to 37.7%, a net absolute reduction of 14.4% (P < .001; 27.6% net relative reduction). Pre-assay, 96% of physicians agreed/strongly agreed that they were confident in their treatment recommendation; post-assay, 90% of physicians agreed/strongly agreed with the same statement. Thirty percent of physicians agreed/strongly agreed that the test had influenced their recommendation, similar to the proportion of changed recommendations. CONCLUSIONS: The Oncotype DX Assay appears to influence physician ESBC adjuvant treatment recommendations in Hong Kong.

APLAC interpretation and guidance on the estimation of uncertainty of measurement in testing.

The Asia Pacific Laboratory Accreditation Cooperation (APLAC) is the organization representing the community of bodies that accredit testing and calibration laboratories throughout the Asia Pacific region, including China and North America. APLAC members assess the competence of laboratories and grant them accreditation. They also provide mutual recognition of the equivalence of their accreditations, which facilitates international trade and acceptance by regulators. Harmonization of accreditation requirements is therefore vital to maintaining Mutual Recognition Arrangements. APLAC establishes management and technical criteria for accreditation and publishes guidance documents for accreditation bodies and laboratories.

Development of acolorimetric, superparamagnetic biosensor for the capture and detection of biomolecules.

Polydiacetylenes are ideal sensing materials due to their ability to change color in response to external stimuli. Here we report a new colorimetric, magnetically separable biosensor using a diacetylene monomer modified with a hydrophilic lysine derivative and superparamagnetic iron oxide nanoparticles. The particles demonstrated a distinct blue to red color transition when added to ethanol and could be quickly separated from solution with a common magnet. Surface functionalization of the particles with bovine serum albumin (BSA) showed the ability to capture and detect anti-BSA antibody from antiserum with a colorimetric response, demonstrating our biosensors can serve as a platform for diagnostic applications including point-of-care testing.

Early diagnosis of sepsis using serum biomarkers.

Sepsis, an innate immunological response of systemic inflammation to infection, is a growing problem worldwide with a relatively high mortality rate. Immediate treatment is required, necessitating quick, early and accurate diagnosis. Rapid molecular-based tests have been developed to address this need, but still suffer some disadvantages. The most commonly studied biomarkers of sepsis are reviewed for their current uses and diagnostic accuracies, including C-reactive protein, procalcitonin, serum amyloid A, mannan and IFN-γ-inducible protein 10, as well as other potentially useful biomarkers. A singular ideal biomarker has not yet been identified; an alternative approach is to shift research focus to determine the diagnostic relevancy of multiple biomarkers when used in concert. Challenges facing biomarker research, including lack of methodology standardization and assays with better detection limits, are discussed. The ongoing efforts in the development of a multiplex point-of-care testing kit, enabling quick and reliable detection of serum biomarkers, may have great potential for early diagnosis of sepsis.