1 / 2

Modeling the Dermoscopic Structure Pigment Network Using a Clinically Inspired Feature Set

Modeling the Dermoscopic Structure Pigment Network Using a Clinically Inspired Feature Set. # 19. Introduction TPN: “a light-to-dark-brown network with small, uniformly spaced network holes and thin network lines distributed more or less regularly throughout the lesion”

boris-dean
Télécharger la présentation

Modeling the Dermoscopic Structure Pigment Network Using a Clinically Inspired Feature Set

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Modeling the Dermoscopic Structure Pigment Network Using a Clinically Inspired Feature Set # 19 • Introduction • TPN: “a light-to-dark-brown network with small, uniformly spaced network holes and thin network lines distributed more or less regularly throughout the lesion” • APN: “a black, brown or gray network with irregular holes and thick lines” Absent Typical Atypical • Objective:A pigment network (PN) can be classified as either Typical or Atypical and the goal is to automatically classify a given image to one of three classes: Absent, Typical (TPN), or Atypical (APN). MaryamSadeghi 1a,b, MajidRazmara 2a, Paul Wighton 3a,b, Tim K. Lee 4b,c, M. Stella Atkins 5a aSchool of Computing Science, Simon Fraser University bCancer Control Research, BC Cancer Agency cDepartment of Dermatology and Skin Science, UBC

  2. Method Overview Results Our method is validated over a large, inclusive, real-world dataset consisting of 436 images. We achieved an accuracy of 82.3% discriminating between three classes (Absent, Typical or Atypical ) and an accuracy of 93.3% discriminating between two classes (Absent or Present).

More Related