Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

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

Tomic, Hanna LU ; Yang, Zhikai ; Tingberg, Anders LU orcid ; Zackrisson, Sophia LU ; Moreno, Rodrigo ; Smedby, Örjan ; Dustler, Magnus LU and Bakic, Predrag LU (2024) Medical Imaging 2024: Physics of Medical Imaging In Progress in Biomedical Optics and Imaging - Proceedings of SPIE 12925.
Abstract

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... (More)

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.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
AI, Breast phantom, computer simulations and VCT, segmentation
host publication
Medical Imaging 2024 : Physics of Medical Imaging - Physics of Medical Imaging
series title
Progress in Biomedical Optics and Imaging - Proceedings of SPIE
editor
Fahrig, Rebecca ; Sabol, John M. and Li, Ke
volume
12925
article number
129251P
publisher
SPIE
conference name
Medical Imaging 2024: Physics of Medical Imaging
conference location
San Diego, United States
conference dates
2024-02-19 - 2024-02-22
external identifiers
  • scopus:85193540163
ISSN
1605-7422
ISBN
9781510671546
DOI
10.1117/12.3008840
language
English
LU publication?
yes
id
ccd15401-d633-49a7-b613-61735c5c6fab
date added to LUP
2024-06-13 15:03:18
date last changed
2024-06-13 15:03:54
@inproceedings{ccd15401-d633-49a7-b613-61735c5c6fab,
  abstract     = {{<p>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.</p>}},
  author       = {{Tomic, Hanna and Yang, Zhikai and Tingberg, Anders and Zackrisson, Sophia and Moreno, Rodrigo and Smedby, Örjan and Dustler, Magnus and Bakic, Predrag}},
  booktitle    = {{Medical Imaging 2024 : Physics of Medical Imaging}},
  editor       = {{Fahrig, Rebecca and Sabol, John M. and Li, Ke}},
  isbn         = {{9781510671546}},
  issn         = {{1605-7422}},
  keywords     = {{AI; Breast phantom; computer simulations and VCT; segmentation}},
  language     = {{eng}},
  publisher    = {{SPIE}},
  series       = {{Progress in Biomedical Optics and Imaging - Proceedings of SPIE}},
  title        = {{Using simulated breast lesions based on Perlin noise for evaluation of lesion segmentation}},
  url          = {{http://dx.doi.org/10.1117/12.3008840}},
  doi          = {{10.1117/12.3008840}},
  volume       = {{12925}},
  year         = {{2024}},
}