The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper introduces the Exponential Pixelating Integral (EPI) transform, which enhances pixel intensities in chest X‑rays to mitigate low‑contrast and noise issues. The enhanced images are polar‑transformed and represented using locally invariant Mandelbrot and Julia fractal geometries, producing dual fractal features. These features are classified with non‑parametric multivariate adaptive regression splines, achieving high accuracy (98.46–99.45%) and F1 scores (96.53–98.10%) on large benchmark datasets.
arXiv:2607. 05628v1 Announce Type: cross Abstract: Accurate and efficient classification of thoracic diseases in chest X-ray (CXR) images is crucial for timely diagnosis and treatment.
arXiv:2608.21571v1 Announce Type: new Abstract: Lung cancer remains a leading cause of cancer-related mortality worldwide, and early diagnosis is critical for improving survival. However, early-stage...
arXiv:2607. 04478v1 Announce Type: cross Abstract: Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures.
arXiv:2607. 26333v1 Announce Type: cross Abstract: Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment.
The article presents a comparative study of convolutional neural network (CNN) architectures for classifying COVID-19 from healthy lung images using CT and X‑ray scans. Multiple pre‑trained models—including VGG, DenseNet, ResNet, MobileNet, Xception, Inception, EfficientNet, and NasNet—were evaluated on two X‑ray and two CT datasets. ResNet and VGG achieved the highest accuracies, ranging from 95% to 98%, outperforming previous reports in the literature.