Evaluation framework to guide implementation of AI systems into healthcare settings.

Objectives: To date, many artificial intelligence (AI) systems have been developed in healthcare, but adoption has been limited. This may be due to inappropriate or incomplete evaluation and a lack of internationally recognised AI standards on evaluation. To have confidence in the generalisability of AI systems in healthcare and to enable their integration into workflows, there is a need for a practical yet comprehensive instrument to assess the translational aspects of the available AI systems.

Shearlet-based compressed sensing for fast 3D cardiac MR imaging using iterative reweighting.

High-resolution three-dimensional (3D) cardiovascular magnetic resonance (CMR) is a valuable medical imaging technique, but its widespread application in clinical practice is hampered by long acquisition times. Here we present a novel compressed sensing (CS) reconstruction approach using shearlets as a sparsifying transform allowing for fast 3D CMR (3DShearCS) using 3D radial phase encoding (RPE). An iterative reweighting scheme was applied during image reconstruction to ensure fast convergence and high image quality.

Analytical results on back propagation nonlinear compensator with coherent detection.

We derive analytic formulas for the improvement in effective optical signal-to-noise ratio brought by a digital nonlinear compensator for dispersion uncompensated links. By assuming Gaussian distributed nonlinear noise, we are able to take both nonlinear signal-to-signal and nonlinear signal-to-noise interactions into account. In the limit of weak nonlinear signal-to-noise interactions, we derive an upper boundary of the OSNR improvement.

Experimental Investigation of 126-Gb/s 6PolSK-QPSK signals.

We experimentally generate 28-GBd 6-ary polarization-shift keying quadrature phase-shift keying (6PolSK-QPSK) signals by utilizing a high-speed 4-channel digital-to-analog converter and an integrated dual-polarization I/Q modulator. In WDM transmission experiments over up to 4800 km standard single-mode fiber, we compare the performance of 126-Gb/s 6PolSK-QPSK and 112-Gb/s polarization-division multiplexing (PDM) QPSK signals. Furthermore, we discuss the implications of applying an inner Reed-Solomon RS(511,455) forward error correction code in order to correct burst errors due to the anti-Gray mapping of 6PolSK-QPSK.

Experimental investigation of 84-Gb/s and 112-Gb/s polarization-switched quadrature phase-shift keying signals.

We experimentally investigate 28-GBd (84-Gb/s) and 37.3-GBd (112-Gb/s) polarization-switched quadrature phase-shift keying (PS-QPSK) signals. In single-channel transmission experiments over up to 12500 km ultra large effective area fiber, we compare their performance to that of polarization-division multiplexing quadrature phase-shift keying (PDM-QPSK) signals at the same bit rates.

Comparison of 8 × 112 Gb/s PS-QPSK and PDM-QPSK signals over transoceanic distances.

We experimentally investigate polarization-switched quadrature phase-shift keying (PS-QPSK) with a symbol rate of 37.3 GBd corresponding to a bit rate of 112 Gb/s. In a wavelength-division multiplexing (WDM) experiment with 50 GHz channel spacing, the transmission performance of PS-QPSK is compared to that of polarization-division multiplexed QPSK (PDM-QPSK) over an EDFA amplified ultra-large-effective-area fiber link.