Boston Children's Hospital

At the Dresden University Cancer Center's MASTERsg precision oncology program, a gradient-boosting model re-reads the raw bin-level copy-number data from TSO500 panel sequencing to find focal PTEN deletions that the standard pipeline misses. TSO500 averages read counts across bins within a gene, so focal events fall short of its fold-change threshold; the model flagged deletions in 33 of 204 samples classified as PTEN wild-type, and 15 of the 20 stainable cases showed absent or reduced PTEN protein.

At the Dresden University Cancer Center's MASTERsg precision oncology program, a gradient-boosting model re-reads the raw bin-level copy-number data from TSO500 panel sequencing to find focal PTEN deletions that the standard pipeline misses. TSO500 averages read counts across bins within a gene, so focal events fall short of its fold-change threshold; the model flagged deletions in 33 of 204 samples classified as PTEN wild-type, and 15 of the 20 stainable cases showed absent or reduced PTEN protein.

The authors built dSC1, a large-scale, synapse-resolved electron microscopy dataset of the mouse spinal dorsal horn, and SPINE, a deep-learning pipeline that identifies major sensory neuron subtypes directly from EM images; applying SPINE to dSC1 revealed that low-threshold mechanoreceptors form substantially more synapses and receive far more GABAergic presynaptic inhibition than high-threshold mechanoreceptors, thermoreceptors and nociceptors, and identified five populations of spinal inhibitory neurons (IhNs) each preferentially driven by and presynaptically inhibiting a single sensory subtype, with most also feedforwardly inhibiting other sensory pathways, together suggesting a dual-mode logic of sensory-evoked inhibition.

The authors built dSC1, a large-scale, synapse-resolved electron microscopy dataset of the mouse spinal dorsal horn, and SPINE, a deep-learning pipeline that identifies major sensory neuron subtypes directly from EM images; applying SPINE to dSC1 revealed that low-threshold mechanoreceptors form substantially more synapses and receive far more GABAergic presynaptic inhibition than high-threshold mechanoreceptors, thermoreceptors and nociceptors, and identified five populations of spinal inhibitory neurons (IhNs) each preferentially driven by and presynaptically inhibiting a single sensory subtype, with most also feedforwardly inhibiting other sensory pathways, together suggesting a dual-mode logic of sensory-evoked inhibition.

The work proposes Gabor primitives for MRI reconstruction, modulating each Gaussian envelope with a complex exponential so its spectral support can be placed at an arbitrary k-space location, and designs a two-basis low-rank temporal model separating geometry and signal-intensity dynamics; on 99 Cartesian (R=12, R=16) and 102 radial (R≈23) cardiac cine acquisitions, Gabor primitives achieve the highest PSNR and SSIM in all settings, improving over Gaussian primitives by +1.11/+0.72/+0.86 dB and over PICS by +2.34 dB on radial data, with a parameter ratio ρ<0.5 and continuous-resolution evaluation enabling 4× super-resolution.

The work proposes Gabor primitives for MRI reconstruction, modulating each Gaussian envelope with a complex exponential so its spectral support can be placed at an arbitrary k-space location, and designs a two-basis low-rank temporal model separating geometry and signal-intensity dynamics; on 99 Cartesian (R=12, R=16) and 102 radial (R≈23) cardiac cine acquisitions, Gabor primitives achieve the highest PSNR and SSIM in all settings, improving over Gaussian primitives by +1.11/+0.72/+0.86 dB and over PICS by +2.34 dB on radial data, with a parameter ratio ρ<0.5 and continuous-resolution evaluation enabling 4× super-resolution.

This mixed-methods case study analyzed 14 months of utilization of "InternalGPT," a HIPAA-compliant LLM chatbot at an academic pediatric medical center, finding that 2,149 of approximately 15,788 employees (13.6%) requested access, 52.8% recorded at least one token use, the top 20% of users consumed 69.4% of tokens, and among 461 sustained users, 92 self-report survey respondents indicated a mean 30% productivity gain corresponding to an exploratory perceived productivity value of $6.3M to $18.9M under varying extrapolation assumptions.

This mixed-methods case study analyzed 14 months of utilization of "InternalGPT," a HIPAA-compliant LLM chatbot at an academic pediatric medical center, finding that 2,149 of approximately 15,788 employees (13.6%) requested access, 52.8% recorded at least one token use, the top 20% of users consumed 69.4% of tokens, and among 461 sustained users, 92 self-report survey respondents indicated a mean 30% productivity gain corresponding to an exploratory perceived productivity value of $6.3M to $18.9M under varying extrapolation assumptions.