The aim of this paper is to present the operational performance of a new MDASS (Melanoma Diagnosis Active Support System) prototype able to distil optimal knowledge from acquired data to automatically capture and reliably discriminate and quantify the stage of disease evolution. Automated classification dermatoscopical parameters can be divided into two main classes: Size Descriptor (point size, local, and global) and Intrinsic Descriptor (morphological, geometrical, chromatic, others). Usually elementary geometric shape robust and effective characterization, invariant to environment and optical geometry transformations, on a rigorous mathematical level is a key and computational intensive problem. MDASS uses GEOGINE (GEOmetrical enGINE), a state-of-the-art OMG (Ontological Model Generator) based on n-D Tensor Moment Invariants for shape/texture effective description. MDASS main results show robust disease classification procedure with distillation of minimal reference grids for pathological cases and they ultimately achieve effective early diagnosis of melanocytic lesion. System results are validated by carefully designed experiments with certified clinical reference database. Overall system operational performance is presented. Finally, MDASS error analysis and computational complexity are addressed and discussed.

A New Melanoma Diagnosis Active Support System

DACQUINO, GIANFRANCO;FIORINI, RODOLFO
2005-01-01

Abstract

The aim of this paper is to present the operational performance of a new MDASS (Melanoma Diagnosis Active Support System) prototype able to distil optimal knowledge from acquired data to automatically capture and reliably discriminate and quantify the stage of disease evolution. Automated classification dermatoscopical parameters can be divided into two main classes: Size Descriptor (point size, local, and global) and Intrinsic Descriptor (morphological, geometrical, chromatic, others). Usually elementary geometric shape robust and effective characterization, invariant to environment and optical geometry transformations, on a rigorous mathematical level is a key and computational intensive problem. MDASS uses GEOGINE (GEOmetrical enGINE), a state-of-the-art OMG (Ontological Model Generator) based on n-D Tensor Moment Invariants for shape/texture effective description. MDASS main results show robust disease classification procedure with distillation of minimal reference grids for pathological cases and they ultimately achieve effective early diagnosis of melanocytic lesion. System results are validated by carefully designed experiments with certified clinical reference database. Overall system operational performance is presented. Finally, MDASS error analysis and computational complexity are addressed and discussed.
2005
-
Healthcare Information Technology; Biomedical Imaging; Image Processing; Dermatological Applications; DELM; MDASS; Melanoma; Ontological Model Generator; Machine Learning
File in questo prodotto:
File Dimensione Formato  
092raf2005.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 308.06 kB
Formato Adobe PDF
308.06 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/271125
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 3
social impact