AI Paper Atlas

Research map / Image generation / Image restoration

A Deep Step Pattern Representation for Multimodal Retinal Image Registration

Jimmy Addison Lee, Peng Liu, Jun Cheng, Huazhu Fu

ICCV 2019 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 58 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on mixed multimodal data instead of best single-modality model (ablation)DeepSPa CNN · Patch classification, total (no thresholding)accuracy (%): 63.10 -> 86.04Improved
train on mixed multimodal data instead of best single-modality model (ablation)DeepSPa CNN · Patch classification, total (threshold 0.68)accuracy (%): 71.13 -> 90.11Improved
add confidence thresholding at 0.68 (ablation)DeepSPa multimodal CNN · Patch classification, totalaccuracy (%): 86.04 -> 90.11Improved
add confidence thresholding at 0.68 (ablation)FA-only CNN · Patch classification, totalaccuracy (%): 59.19 -> 65.61Improved
raise classification confidence threshold (ablation)DeepSPa CNN · Patch classificationaccuracy and remaining features: accuracy increases, remaining features dropMixed
use DeepSPa learned step patterns instead of LoSPA hand-designed patternsregistration pipeline · Color fundus-FA (mild-to-moderate)success rate (%): 93.33 -> 96.67Improved
use DeepSPa learned step patterns instead of LoSPA hand-designed patternsregistration pipeline · Color fundus-FA (severe)success rate (%): 79.17 -> 86.5Improved
use DeepSPa learned step patterns instead of LoSPA hand-designed patternsregistration pipeline · Color fundus-OCTsuccess rate (%): 63.75 -> 81.25Improved
use DeepSPa instead of LoSPAregistration pipeline · Color fundus-OCTaverage RMSE (pixels): 3.43 -> 2.62Improved
use affine instead of second-order polynomial transformation (ablation)DeepSPa · Retinal registrationregistration accuracyNo clear effect
rotate floating image from 0 to 180 degreesDeepSPa · 20 multimodal pairs, rotation testregistration success: all pairs registered at 0 to 180 degreesNo clear effect
rescale floating image up to factor 2.8DeepSPa · 20 multimodal pairs, scale testregistration success: robust at 1.8 and below, usually fails above 1.9Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy