Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes

We present a deep-learning and optimization-based approach to detect and track lesions on 3D total-body scans. The 3D textured meshes are unwrapped to leverage 2D region detection approaches, and the detected lesions are mapped to 3D coordinates and tracked across 3D meshes. This automated approach to detect skin lesions performs similar to human annotators. We publicly release over 25,000 manual bounding-box annotations of lesions on 3D body scans.

Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes

Abstract

We present an automated approach to detect and longitudinally track skin lesions on 3D total-body skin surface scans. The acquired 3D mesh of the subject is unwrapped to a 2D texture image, where a trained objected detection model, Faster R-CNN, localizes the lesions within the 2D domain. These detected skin lesions are mapped back to the 3D surface of the subject and, for subjects imaged multiple times, we construct a graph-based matching procedure to longitudinally track lesions that considers the anatomical correspondences among pairs of meshes and the geodesic proximity of corresponding lesions and the inter-lesion geodesic distances.

We evaluated the proposed approach using 3DBodyTex, a publicly available dataset composed of 3D scans imaging the coloured skin (textured meshes) of 200 human subjects. We manually annotated locations that appeared to the human eye to contain a pigmented skin lesion as well as tracked a subset of lesions occurring on the same subject imaged in different poses. Our results, when compared to three human annotators, suggest that the trained Faster R-CNN detects lesions at a similar performance level as the human annotators. Our lesion tracking algorithm achieves an average matching accuracy of 88% on a set of detected corresponding pairs of prominent lesions of subjects imaged in different poses, and an average longitudinal accuracy of 71% when encompassing additional errors due to lesion detection. As there currently is no other large-scale publicly available dataset of 3D total-body skin lesions, we publicly release over 25,000 3DBodyTex manual annotations, which we hope will further research on total-body skin lesion analysis.

BibTeX

@article{zhao2021skin3d,

doi = {10.1016/j.media.2021.102329},

url = {https://doi.org/10.1016/j.media.2021.102329},

year = {2021},

month = Dec,

publisher = {Elsevier {BV}},

pages = {102329},

author = {Mengliu Zhao and Jeremy Kawahara and Kumar Abhishek and Sajjad Shamanian and Ghassan Hamarneh},

title = {Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes},

journal = {Medical Image Analysis}

}

Acknowledgments