Toward Artifact-Free Dermoscopy: Characterization of ISIC 2019 Image Defects for Deep Learning Applications
Victoria Wegley, Joshua Hoog, Tristan Crawford, Keith Miller, William Fons, Kacy Pugh, Jackson Taylor, Sami Swinfard, Avigail Fernandes, Gehana Patel, Jason Hagerty, William V. Stoecker, R. Joe Stanley
Abstract
The International Skin Imaging Collaboration (ISIC) archive offers the largest publicly available collection of dermoscopic images for skin lesion analysis. However, the ISIC 2019 dataset suffers from several acquisition artifacts such as hair occlusions, vignetting, surgical ink markings, and ruler scales, all of which compromise its utility in deep learning workflows by introducing non-biological visual structures. To address these limitations, we present a rigorously annotated version of ISIC 2019 that includes binary masks for key artifact types. Ink marks and vignetting were annotated through systematic manual review and iterative refinement using professional image editing software. For hair and ruler artifacts, we implemented a semi-automatic pipeline based on our previously developed deep learning architecture, ChimeraNet. Automated predictions were then manually corrected as needed for precision. The resulting dataset supports both the development of our own melanoma detection model and broader community research requiring artifact-mitigated dermoscopic images.
Create a lesson
Related papers
ELiCv2: Learned LiDAR Geometry Compression under Real-Time Embedded Constraints
Soowoong Kim, Junsik Kim, Gun Bang et al.
Simulation-Driven Approach for Occlusion-Based Non-Line-Of-Sight Detection Using a Low-Cost Flash LiDAR
Peizhao Qiu, Emmanuel A Olowe, Zhenya Zang et al.
DUNEDepth: Bronchoscopic Depth and Pose Estimation via Hybrid Adaptation of a 3D-Vision Foundation Model
Qi Chang, Austin Kao, Ange Lou et al.
Evaluating the Impact of Nonlinear Registration on Longitudinal PET Analysis in a Rodent Stroke Model
Haytham Ziani, El Mostafa Kalmoun, Zohaib Atif et al.
Measure Before You Repair: An Explainable Agent for Blind Restoration of Multi-Artifact 3-D MRI
Necati Sefercioglu, Mehmet Ozan Unal, Metin Ertas et al.
A Novel Conditional Adversarial Diffusion Model for High-Fidelity OCT-to-OCT Image Translation and Precise Anti-VEGF Therapy Response Prediction in Diabetic Macular Edema
Reza Rasti, Armin Biglari, Sobhan Mohammadi Hafshejani et al.