Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Geometric-Based Nail Segmentation for Clinical Measurements

Bernat Galmés, Gabriel Moyà-Alcover, Pedro Bibiloni, Javier Varona, Antoni Jaume-i-Capó

TL;DR

Problem: robust toenail segmentation in clinical imaging for objective nail-area measurements under varied cameras and lighting. Approach: a geometry-driven pipeline combining Hough-based toe-tip and nail-circle estimation, Quickshift super-pixels, gradient-boosted classification with multi-channel color features, and watershed refinement. Findings: on a 348-image dataset with $N=348$, training/test split of $N_{train}=257$, $N_{test}=91$, the method achieves accuracy $0.993$ and F1 $0.925$, indicating strong robustness to nail shape, skin pigmentation, and illumination. Significance: enables standardized, explainable nail measurements in clinical studies and serves as a first step in objective quantification of nail-pathology incidence.

Abstract

A robust segmentation method that can be used to perform measurements on toenails is presented. The proposed method is used as the first step in a clinical trial to objectively quantify the incidence of a particular pathology. For such an assessment, it is necessary to distinguish a nail, which locally appears to be similar to the skin. Many algorithms have been used, each of which leverages different aspects of toenail appearance. We used the Hough transform to locate the tip of the toe and estimate the nail location and size. Subsequently, we classified the super-pixels of the image based on their geometric and photometric information. Thereafter, the watershed transform delineated the border of the nail. The method was validated using a 348-image medical dataset, achieving an accuracy of 0.993 and an F-measure of 0.925. The proposed method is considerably robust across samples, with respect to factors such as nail shape, skin pigmentation, illumination conditions, and appearance of large regions affected by a medical condition

Geometric-Based Nail Segmentation for Clinical Measurements

TL;DR

Problem: robust toenail segmentation in clinical imaging for objective nail-area measurements under varied cameras and lighting. Approach: a geometry-driven pipeline combining Hough-based toe-tip and nail-circle estimation, Quickshift super-pixels, gradient-boosted classification with multi-channel color features, and watershed refinement. Findings: on a 348-image dataset with , training/test split of , , the method achieves accuracy and F1 , indicating strong robustness to nail shape, skin pigmentation, and illumination. Significance: enables standardized, explainable nail measurements in clinical studies and serves as a first step in objective quantification of nail-pathology incidence.

Abstract

A robust segmentation method that can be used to perform measurements on toenails is presented. The proposed method is used as the first step in a clinical trial to objectively quantify the incidence of a particular pathology. For such an assessment, it is necessary to distinguish a nail, which locally appears to be similar to the skin. Many algorithms have been used, each of which leverages different aspects of toenail appearance. We used the Hough transform to locate the tip of the toe and estimate the nail location and size. Subsequently, we classified the super-pixels of the image based on their geometric and photometric information. Thereafter, the watershed transform delineated the border of the nail. The method was validated using a 348-image medical dataset, achieving an accuracy of 0.993 and an F-measure of 0.925. The proposed method is considerably robust across samples, with respect to factors such as nail shape, skin pigmentation, illumination conditions, and appearance of large regions affected by a medical condition
Paper Structure (16 sections, 1 equation, 15 figures, 3 tables)

This paper contains 16 sections, 1 equation, 15 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Structure of the paper
  3. Toenail Segmentation Method
  4. High-level Description of Toenails
  5. Tip of the toe and nail circle estimation
  6. Super-Pixel Classification
  7. Classifier Features
  8. Classification
  9. Comparison of the classifiers
  10. Toenail segmentation
  11. Experimentation and Results
  12. Experimental framework
  13. Method's performance
  14. Conclusions
  15. Qualitative analysis
  16. ...and 1 more sections

Figures (15)

  • Figure 1: Distribution of nail and toe pixel values accross the three channels of the CIELAB color space.
  • Figure 2: Designed template for both feet, to be printed in a high-quality matte paper of size A4.
  • Figure 3: Original photograph of a left foot on the template (left) and its normalization (right).
  • Figure 4: Flow Diagram of the robust toenail segmentation procedure.
  • Figure 5: Edges and figures computed in tip of the toe detection process.
  • ...and 10 more figures