Performance of a fully automatic lesion detection system for breast DCE-MRI

Anna Vignati, Valentina Giannini, Massimo De Luca, Lia Morra, Diego Persano, Luca A. Carbonaro, Ilaria Bertotto, Laura Martincich, Daniele Regge, Alberto Bert, Francesco Sardanelli

Research output: Contribution to journalArticle

Abstract

Purpose: To describe and test a new fully automatic lesion detection system for breast DCE-MRI. Materials and Methods: Studies were collected from two institutions adopting different DCE-MRI sequences, one with and the other one without fat-saturation. The detection pipeline consists of (i) breast segmentation, to identify breast size and location; (ii) registration, to correct for patient movements; (iii) lesion detection, to extract contrast-enhanced regions using a new normalization technique based on the contrast-uptake of mammary vessels; (iv) false positive (FP) reduction, to exclude contrast-enhanced regions other than lesions. Detection rate (number of system-detected malignant and benign lesions over the total number of lesions) and sensitivity (system-detected malignant lesions over the total number of malignant lesions) were assessed. The number of FPs was also assessed. Results: Forty-eight studies with 12 benign and 53 malignant lesions were evaluated. Median lesion diameter was 6 mm (range, 5-15 mm) for benign and 26 mm (range, 5-75 mm) for malignant lesions. Detection rate was 58/65 (89%; 95% confidence interval [CI] 79%-95%) and sensitivity was 52/53 (98%; 95% CI 90%-99%). Mammary median FPs per breast was 4 (1st-3rd quartiles 3-7.25). Conclusion: The system showed promising results on MR datasets obtained from different scanners producing fat-sat or non-fat-sat images with variable temporal and spatial resolution and could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve lesion detection. Further evaluation is needed before it may be used in clinical practice.

Original languageEnglish
Pages (from-to)1341-1351
Number of pages11
JournalJournal of Magnetic Resonance Imaging
Volume34
Issue number6
DOIs
Publication statusPublished - Dec 2011

Fingerprint

Breast
Fats
Confidence Intervals
Reading
Early Diagnosis
Breast Neoplasms

Keywords

  • automatic detection
  • breast cancer
  • computer aided detection (CAD)
  • DCE-MRI
  • fat-saturation

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Performance of a fully automatic lesion detection system for breast DCE-MRI. / Vignati, Anna; Giannini, Valentina; De Luca, Massimo; Morra, Lia; Persano, Diego; Carbonaro, Luca A.; Bertotto, Ilaria; Martincich, Laura; Regge, Daniele; Bert, Alberto; Sardanelli, Francesco.

In: Journal of Magnetic Resonance Imaging, Vol. 34, No. 6, 12.2011, p. 1341-1351.

Research output: Contribution to journalArticle

@article{9a5ff183dca645dabcba44bdc92ad931,
title = "Performance of a fully automatic lesion detection system for breast DCE-MRI",
abstract = "Purpose: To describe and test a new fully automatic lesion detection system for breast DCE-MRI. Materials and Methods: Studies were collected from two institutions adopting different DCE-MRI sequences, one with and the other one without fat-saturation. The detection pipeline consists of (i) breast segmentation, to identify breast size and location; (ii) registration, to correct for patient movements; (iii) lesion detection, to extract contrast-enhanced regions using a new normalization technique based on the contrast-uptake of mammary vessels; (iv) false positive (FP) reduction, to exclude contrast-enhanced regions other than lesions. Detection rate (number of system-detected malignant and benign lesions over the total number of lesions) and sensitivity (system-detected malignant lesions over the total number of malignant lesions) were assessed. The number of FPs was also assessed. Results: Forty-eight studies with 12 benign and 53 malignant lesions were evaluated. Median lesion diameter was 6 mm (range, 5-15 mm) for benign and 26 mm (range, 5-75 mm) for malignant lesions. Detection rate was 58/65 (89{\%}; 95{\%} confidence interval [CI] 79{\%}-95{\%}) and sensitivity was 52/53 (98{\%}; 95{\%} CI 90{\%}-99{\%}). Mammary median FPs per breast was 4 (1st-3rd quartiles 3-7.25). Conclusion: The system showed promising results on MR datasets obtained from different scanners producing fat-sat or non-fat-sat images with variable temporal and spatial resolution and could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve lesion detection. Further evaluation is needed before it may be used in clinical practice.",
keywords = "automatic detection, breast cancer, computer aided detection (CAD), DCE-MRI, fat-saturation",
author = "Anna Vignati and Valentina Giannini and {De Luca}, Massimo and Lia Morra and Diego Persano and Carbonaro, {Luca A.} and Ilaria Bertotto and Laura Martincich and Daniele Regge and Alberto Bert and Francesco Sardanelli",
year = "2011",
month = "12",
doi = "10.1002/jmri.22680",
language = "English",
volume = "34",
pages = "1341--1351",
journal = "Journal of Magnetic Resonance Imaging",
issn = "1053-1807",
publisher = "John Wiley and Sons Inc.",
number = "6",

}

TY - JOUR

T1 - Performance of a fully automatic lesion detection system for breast DCE-MRI

AU - Vignati, Anna

AU - Giannini, Valentina

AU - De Luca, Massimo

AU - Morra, Lia

AU - Persano, Diego

AU - Carbonaro, Luca A.

AU - Bertotto, Ilaria

AU - Martincich, Laura

AU - Regge, Daniele

AU - Bert, Alberto

AU - Sardanelli, Francesco

PY - 2011/12

Y1 - 2011/12

N2 - Purpose: To describe and test a new fully automatic lesion detection system for breast DCE-MRI. Materials and Methods: Studies were collected from two institutions adopting different DCE-MRI sequences, one with and the other one without fat-saturation. The detection pipeline consists of (i) breast segmentation, to identify breast size and location; (ii) registration, to correct for patient movements; (iii) lesion detection, to extract contrast-enhanced regions using a new normalization technique based on the contrast-uptake of mammary vessels; (iv) false positive (FP) reduction, to exclude contrast-enhanced regions other than lesions. Detection rate (number of system-detected malignant and benign lesions over the total number of lesions) and sensitivity (system-detected malignant lesions over the total number of malignant lesions) were assessed. The number of FPs was also assessed. Results: Forty-eight studies with 12 benign and 53 malignant lesions were evaluated. Median lesion diameter was 6 mm (range, 5-15 mm) for benign and 26 mm (range, 5-75 mm) for malignant lesions. Detection rate was 58/65 (89%; 95% confidence interval [CI] 79%-95%) and sensitivity was 52/53 (98%; 95% CI 90%-99%). Mammary median FPs per breast was 4 (1st-3rd quartiles 3-7.25). Conclusion: The system showed promising results on MR datasets obtained from different scanners producing fat-sat or non-fat-sat images with variable temporal and spatial resolution and could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve lesion detection. Further evaluation is needed before it may be used in clinical practice.

AB - Purpose: To describe and test a new fully automatic lesion detection system for breast DCE-MRI. Materials and Methods: Studies were collected from two institutions adopting different DCE-MRI sequences, one with and the other one without fat-saturation. The detection pipeline consists of (i) breast segmentation, to identify breast size and location; (ii) registration, to correct for patient movements; (iii) lesion detection, to extract contrast-enhanced regions using a new normalization technique based on the contrast-uptake of mammary vessels; (iv) false positive (FP) reduction, to exclude contrast-enhanced regions other than lesions. Detection rate (number of system-detected malignant and benign lesions over the total number of lesions) and sensitivity (system-detected malignant lesions over the total number of malignant lesions) were assessed. The number of FPs was also assessed. Results: Forty-eight studies with 12 benign and 53 malignant lesions were evaluated. Median lesion diameter was 6 mm (range, 5-15 mm) for benign and 26 mm (range, 5-75 mm) for malignant lesions. Detection rate was 58/65 (89%; 95% confidence interval [CI] 79%-95%) and sensitivity was 52/53 (98%; 95% CI 90%-99%). Mammary median FPs per breast was 4 (1st-3rd quartiles 3-7.25). Conclusion: The system showed promising results on MR datasets obtained from different scanners producing fat-sat or non-fat-sat images with variable temporal and spatial resolution and could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve lesion detection. Further evaluation is needed before it may be used in clinical practice.

KW - automatic detection

KW - breast cancer

KW - computer aided detection (CAD)

KW - DCE-MRI

KW - fat-saturation

UR - http://www.scopus.com/inward/record.url?scp=81755183120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81755183120&partnerID=8YFLogxK

U2 - 10.1002/jmri.22680

DO - 10.1002/jmri.22680

M3 - Article

C2 - 21965159

AN - SCOPUS:81755183120

VL - 34

SP - 1341

EP - 1351

JO - Journal of Magnetic Resonance Imaging

JF - Journal of Magnetic Resonance Imaging

SN - 1053-1807

IS - 6

ER -