The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Portrait of Predrag Bakic. Photo

Predrag Bakic

Associate Professor

Portrait of Predrag Bakic. Photo

Using simulated breast lesions based on Perlin noise for evaluation of lesion segmentation

Author

  • Hanna Tomic
  • Zhikai Yang
  • Anders Tingberg
  • Sophia Zackrisson
  • Rodrigo Moreno
  • Örjan Smedby
  • Magnus Dustler
  • Predrag Bakic

Editor

  • Rebecca Fahrig
  • John M. Sabol
  • Ke Li

Summary, in English

Segmentation of diagnostic radiography images using deep learning is progressively expanding, which sets demands on the accessibility, availability, and accuracy of the software tools used. This study aimed at evaluating the performance of a segmentation model for digital breast tomosynthesis (DBT), with the use of computer-simulated breast anatomy. We have simulated breast anatomy and soft tissue breast lesions, by utilizing a model approach based on the Perlin noise algorithm. The obtained breast phantoms were projected and reconstructed into DBT slices using a publicly available open-source reconstruction method. Each lesion was then segmented using two approaches: 1. the Segment Anything Model (SAM), a publicly available AI-based method for image segmentation and 2. manually by three human observers. The lesion area in each slice was compared to the ground truth area, derived from the binary mask of the lesion model. We found similar performance between SAM and manual segmentation. Both SAM and the observers performed comparably in the central slice (mean absolute relative error compared to the ground truth and standard deviation SAM: 4 ± 3 %, observers: 3 ± 3 %). Similarly, both SAM and the observers overestimated the lesion area in the peripheral reconstructed slices (mean absolute relative error and standard deviation SAM: 277 ± 190 %, observers: 295 ± 182 %). We showed that 3D voxel phantoms can be used for evaluating different segmentation methods. In preliminary comparison, tumor segmentation in simulated DBT images using SAM open-source method showed a similar performance as manual tumor segmentation.

Department/s

  • Radiology Diagnostics, Malmö
  • LUCC: Lund University Cancer Centre
  • Medical Radiation Physics, Malmö
  • LU Profile Area: Light and Materials
  • LTH Profile Area: Photon Science and Technology
  • EpiHealth: Epidemiology for Health

Publishing year

2024

Language

English

Publication/Series

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Volume

12925

Document type

Conference paper

Publisher

SPIE

Topic

  • Medical Image Processing

Keywords

  • AI
  • Breast phantom
  • computer simulations and VCT
  • segmentation

Conference name

Medical Imaging 2024: Physics of Medical Imaging

Conference date

2024-02-19 - 2024-02-22

Conference place

San Diego, United States

Status

Published

Research group

  • Radiology Diagnostics, Malmö
  • Medical Radiation Physics, Malmö

ISBN/ISSN/Other

  • ISSN: 1605-7422
  • ISBN: 9781510671546