# Attenuation correction

Multi-pinhole SPECT gains sensitivity but stacks overlapping projections with attenuation, scatter, quantum noise and aperture effects, and attenuation correction usually needs an attenuation coefficient map from X-ray CT. A U-Net++ convolutional network takes Monte Carlo-simulated overlapping projections as input and ray-traced ideal projections as target, separating overlaps and correcting the degradations together before maximum-likelihood expectation-maximization reconstruction. On 60 public brain cases under quasi-stationary acquisition, it reached NMSE 0.18±0.02, PSNR 18.42±0.69 dB and SSIM 0.81±0.04, better than 11-pinhole reconstruction and fan-beam reconstruction with 20-fold longer acquisition.

Multi-pinhole SPECT gains sensitivity but stacks overlapping projections with attenuation, scatter, quantum noise and aperture effects, and attenuation correction usually needs an attenuation coefficient map from X-ray CT. A U-Net++ convolutional network takes Monte Carlo-simulated overlapping projections as input and ray-traced ideal projections as target, separating overlaps and correcting the degradations together before maximum-likelihood expectation-maximization reconstruction. On 60 public brain cases under quasi-stationary acquisition, it reached NMSE 0.18±0.02, PSNR 18.42±0.69 dB and SSIM 0.81±0.04, better than 11-pinhole reconstruction and fan-beam reconstruction with 20-fold longer acquisition.

This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.

This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.