Skip to content
  • Home
  • Services
    • All Services
    • Custom DICOM Viewer
    • Case Studies
  • Products
    • All Products
    • PYCAD DICOM Viewer
    • PYCAD Dental Viewer
    • PYCAD SSR Engine
  • Case Studies
  • Blog
  • About us
  • Home
  • Services
    • All Services
    • Custom DICOM Viewer
    • Case Studies
  • Products
    • All Products
    • PYCAD DICOM Viewer
    • PYCAD Dental Viewer
    • PYCAD SSR Engine
  • Case Studies
  • Blog
  • About us
Get in Touch

Category: Computer Vision

KIR-NO: 3D MRI Reconstruction Trained Small, Deployed Large

Fig. 4 of arXiv:2611.14979 by Wang, Daftari and colleagues: half-resolution knee and brain MRI slices reconstructed by zero-filling, a 3D CNN and KIR-NO, each with an error map, the KIR-NO error maps showing the smallest residuals.

A neural operator trains full 3D MRI recon on downsampled k-space, then runs the same weights on finer grids. Repo not public yet.

N2N-iMF: Fast Self-Supervised CT Denoising Without Clean Scans

Fig. 4 of arXiv:2611.26370 by Yao, Ma and Chen: two real thin-slice photon-counting brain CT slices shown as noisy FBP, Noise2Noise output and N2N-iMF output, with the N2N-iMF images less grainy and cortical sulci still visible.

Trained on noisy CT pairs only, it averages fast generated samples per slice. Tested on real photon-counting brain CT. No code yet.

Geometry-Bridge Flow Matching: Fixing Head Motion in CBCT

Fig. 3, case 2 of arXiv:2611.23788 by Yun and Cho: axial and coronal head CBCT slices of a simulated motion-corrupted scan, uncorrected FDK with streaks and doubled bone edges, the geometry-bridge final reconstruction, and the ground truth CT.

A KAIST method recovers head pose for every CBCT projection from the raw data, then rebuilds the scan. Code is public; weights are not.

Plug-and-Play Prior vs Tuned TV: Sparse-View CT Beyond PSNR

Fig. 20 of arXiv:2611.18936 by Mohammed Abo Oraig: crops of three LoDoPaB-CT slices reconstructed from 60 views at full dose with Hann-filtered FBP, total variation, a Plug-and-Play DnCNN prior and PnP started from TV, red circles marking the strongest lesion-like blob not supported by the reference image.

A DnCNN prior roughly matches a well-tuned TV on real sparse-view CT, but PSNR and lesion detection rank the methods differently.

SIM: Zero-Shot MRI Reconstruction Learned From Simulated Data

Fig. 7a of arXiv:2611.15758 by Shang, Zhan, Jia and co-authors (SIAT Chinese Academy of Sciences, Peking University Shenzhen Hospital, Tencent): T1, T2 and FLAIR brain MRI from an Alzheimer's disease cohort, fully sampled reference above zero-shot SIM and E2EVarNet reconstructions at three accelerations, red arrows on residual aliasing.

A one-billion-parameter transformer trained on simulated k-space from photos reconstructs MRI from scanners it never saw, 0.3 T to 7 T.

X-Strata: Separating Aneurysm and Vessel Layers in 2D Angiography

Supplementary Fig. S3 of arXiv:2611.17743 by Wen, Chen, Li and co-authors (Tsinghua University, Hunan University, Chinese PLA General Hospital): six pairs of peak cine DSA frames of intracranial aneurysms next to layer overlays with the sac in blue, vessels in front in gold, vessels behind in gray and overlap in pink.

From two routine DSA cine runs, X-Strata recovers the full aneurysm sac, sorts crossing vessels in front or behind, and lifts both to 3D.

AgentCT: A CT Agent That Picks the Right Restoration Model

Fig. 2 of arXiv:2611.11503 by Chen, Gao, Niu, Liu, Zhang and Shan (Fudan University and co-authors): abdominal CT slices with simulated low-dose noise, sparse-view streaks and metal artifacts, comparing the degraded input, the all-in-one AMIR model, the AgentCT routed specialist and the clean reference, with zoomed regions and PSNR/SSIM.

A small vision-language model reads a CT slice, names the damage and sends it to a low-dose, sparse-view or metal specialist.

DuSS-PET: Low-Dose PET Reconstruction Without Full-Dose Pairs

Fig. 7 of arXiv:2611.11265 by Lin, He, Wang, Ma and Wang (Xi'an Jiaotong University): zero-shot brain FDG PET reconstructions on a Siemens scanner at dose reduction factors 20 and 100, comparing the low-dose input, the supervised RED model and the self-supervised DuSS-PET with the full-dose reference, plus error maps.

A self-supervised model learns to clean low-dose PET from low-dose scans alone and holds up on another vendor’s scanner.

GenStrain: DENSE-Quality Myocardial Strain From Routine Cine MRI

Fig. 6 of arXiv:2611.08544 by Paul, Ghadimi, Singulane, Patel, Epstein and Zhang (University of Virginia): end-systolic displacement fields, circumferential strain maps and segmental strain curves for one acute myocardial infarction patient, comparing the DENSE reference with DeepStrain, LaMoD and GenStrain.

A diffusion model trained on DENSE motion predicts myocardial displacement and strain maps from standard cine cardiac MRI.

OneStepBrainMRI: Forecasting Brain Atrophy From One Baseline MRI

Fig. 2 of arXiv:2611.10043 by Shiferaw, Farki, Koundal and Tohka (University of Eastern Finland): axial grey-matter density maps of one ADNI participant with MCI, showing the measured follow-up, the one-step diffusion prediction from a single baseline scan, and the absolute error at +2, +4, +6 and +9 years.

A one-step diffusion model predicts grey-matter maps 2 to 10 years ahead from one baseline MRI, age, diagnosis and APOE4.

Next →