Accurate Recognition of Pneumonia and COVID-19 by Geometric Shape Normalization of Lung Region using Automatic Landmark Detection and Piecewise Affine Warping
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a system to automatically detect lung diseases like COVID-19 from chest X-ray images by first identifying key points on the lungs to align them into a standard shape. They used a combination of deep learning models to find lung landmarks, adjust the lung images geometrically, and then classify the diseases. Their approach improved detection accuracy by reducing interference from image artifacts compared to using raw images. Tests showed that aligning lungs anatomically helps in making disease recognition more consistent and reliable across different datasets.
ResNet-18landmark detectioncoordinate attentionGeneralized Procrustes AnalysisDelaunay triangulationpiecewise affine warpingtransfer learningcontrast enhancementF1-ScoreGrad-CAM
Authors
Salvador E. Ayala-Raggi, Rafael Alejandro Cruz-Ovando, Lauro Reyes-Cocoletzi, Aldrin Barreto-Flores
Abstract
This paper presents an automatic system for recognizing pulmonary diseases in chest X-rays using geometric normalization of the lung region. The method combines three modules: (1) a ResNet-18 landmark detector with coordinate attention that predicts 15 lung-contour landmarks, achieving a mean localization error of 3.61 pixels through an ensemble of four models with test-time augmentation; (2) a geometric normalizer based on Generalized Procrustes Analysis, Delaunay triangulation, and piecewise affine warping to map each lung region to a standardized shape; and (3) a ResNet-18 classifier with transfer learning and SAHS contrast enhancement to classify images as COVID-19, Viral Pneumonia, or Normal. On the COVID-19 Radiography Database, the normalized-image classifier achieved 98.60+/-0.26% accuracy and 98.00% F1-Macro using five-fold cross-validation. Although original images produced slightly higher raw accuracy, Grad-CAM and cropping experiments suggest that this advantage is partly influenced by acquisition artifacts. In contrast, geometrically normalized images outperformed artifact-masked/cropped unaligned images on both the COVID-19 Radiography Database (98.60% vs. 96.24%) and a balanced adult-pediatric mixed dataset including pediatric cases from the Kermany dataset (94.67% vs. 94.17%). These results suggest that anatomical alignment can provide a more controlled and artifact-resistant representation for pulmonary disease recognition.