Fuzzy multi-class statistical modeling for efficient total lesion metabolic activity estimation from realistic PET images

  • Authors:

  • Jose George;Kathleen Vunckx;Elke Van de Casteele;Sabine Tejpar;Christophe M. Deroose;Johan Nuyts;Dirk Loeckx;Paul Suetens

  • Affiliations:

  • Medical Imaging Research Center, UZ Leuven, Belgium, Future Health Department, IBBT-KU Leuven, Belgium, Medical Image Computing (ESAT/PSI/MIC), KU Leuven, Belgium;Medical Imaging Research Center, UZ Leuven, Belgium, Nuclear Medicine, KU Leuven, Belgium;Medical Imaging Research Center, UZ Leuven, Belgium, Future Health Department, IBBT-KU Leuven, Belgium, Medical Image Computing (ESAT/PSI/MIC), KU Leuven, Belgium;Gastroenterology, KU Leuven, Belgium;Nuclear Medicine, KU Leuven, Belgium;Medical Imaging Research Center, UZ Leuven, Belgium, Nuclear Medicine, KU Leuven, Belgium;Medical Imaging Research Center, UZ Leuven, Belgium, Medical Image Computing (ESAT/PSI/MIC), KU Leuven, Belgium, icoMetrix NV, Leuven, Belgium;Medical Imaging Research Center, UZ Leuven, Belgium, Future Health Department, IBBT-KU Leuven, Belgium, Medical Image Computing (ESAT/PSI/MIC), KU Leuven, Belgium

  • Venue:
  • MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) has become the de facto standard for current clinical therapy follow up evaluations. In pursuit of robust biomarkers for predicting early therapy response, an efficient marker quantification procedure is certainly a necessity. Among various PET derived markers, the clinical investigations indicated that the total lesion metabolic activity (TLA) of a tumor lesion has a good prognostic value in several longitudinal studies. We utilize a fuzzy multi-class modeling using a stochastic expectation maximization (SEM) algorithm to fit a finite mixture model (FMM) to the PET image. We then propose a direct estimation formula for TLA and SUVmean from this multi-class statistical model. In order to evaluate our proposition, a realistic liver lesion is simulated and reconstructed. All results were evaluated with reference to the ground truth knowledge. Our experimental study conveys that the proposed method is robust enough to handle background heterogeneities in realistic scenarios.