PMID- 28152264
OWN - NLM
STAT- MEDLINE
DCOM- 20180507
LR  - 20220330
IS  - 1522-2586 (Electronic)
IS  - 1053-1807 (Linking)
VI  - 46
IP  - 2
DP  - 2017 Aug
TI  - Prediction of malignancy by a radiomic signature from contrast agent-free 
      diffusion MRI in suspicious breast lesions found on screening mammography.
PG  - 604-616
LID - 10.1002/jmri.25606 [doi]
AB  - PURPOSE: To assess radiomics as a tool to determine how well lesions found 
      suspicious on breast cancer screening X-ray mammography can be categorized into 
      malignant and benign with unenhanced magnetic resonance (MR) mammography with 
      diffusion-weighted imaging and T(2) -weighted sequences. MATERIALS AND METHODS: 
      From an asymptomatic screening cohort, 50 women with mammographically suspicious 
      findings were examined with contrast-enhanced breast MRI (ceMRI) at 1.5T. Out of 
      this protocol an unenhanced, abbreviated diffusion-weighted imaging protocol 
      (ueMRI) including T(2) -weighted, (T(2) w), diffusion-weighted imaging (DWI), and 
      DWI with background suppression (DWIBS) sequences and corresponding apparent 
      diffusion coefficient (ADC) maps were extracted. From ueMRI-derived radiomic 
      features, three Lasso-supervised machine-learning classifiers were constructed 
      and compared with the clinical performance of a highly experienced radiologist: 
      1) univariate mean ADC model, 2) unconstrained radiomic model, 3) constrained 
      radiomic model with mandatory inclusion of mean ADC. RESULTS: The unconstrained 
      and constrained radiomic classifiers consisted of 11 parameters each and achieved 
      differentiation of malignant from benign lesions with a .632 + bootstrap receiver 
      operating characteristics (ROC) area under the curve (AUC) of 84.2%/85.1%, 
      compared to 77.4% for mean ADC and 95.9%/95.9% for the experienced radiologist 
      using ceMRI/ueMRI. CONCLUSION: In this pilot study we identified two ueMRI 
      radiomics classifiers that performed well in the differentiation of malignant 
      from benign lesions and achieved higher performance than the mean ADC parameter 
      alone. Classification was lower than the almost perfect performance of a highly 
      experienced breast radiologist. The potential of radiomics to provide a 
      training-independent diagnostic decision tool is indicated. A performance 
      reaching the human expert would be highly desirable and based on our results is 
      considered possible when the concept is extended in larger cohorts with further 
      development and validation of the technique. LEVEL OF EVIDENCE: 1 Technical 
      Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;46:604-616.
CI  - (c) 2017 International Society for Magnetic Resonance in Medicine.
FAU - Bickelhaupt, Sebastian
AU  - Bickelhaupt S
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Paech, Daniel
AU  - Paech D
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Kickingereder, Philipp
AU  - Kickingereder P
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
AD  - Department of Neuroradiology, University of Heidelberg Medical Center, 
      Heidelberg, Germany.
FAU - Steudle, Franziska
AU  - Steudle F
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Lederer, Wolfgang
AU  - Lederer W
AD  - Radiological Clinic at the ATOS Clinic Heidelberg, Heidelberg, Germany.
FAU - Daniel, Heidi
AU  - Daniel H
AD  - Radiology Center Mannheim (RZM), Mannheim, Germany.
FAU - Gotz, Michael
AU  - Gotz M
AD  - Junior Group Medical Image Computing, German Cancer Research Center (DKFZ), 
      Heidelberg, Germany.
FAU - Gahlert, Nils
AU  - Gahlert N
AD  - Junior Group Medical Image Computing, German Cancer Research Center (DKFZ), 
      Heidelberg, Germany.
FAU - Tichy, Diana
AU  - Tichy D
AD  - Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Wiesenfarth, Manuel
AU  - Wiesenfarth M
AD  - Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Laun, Frederik B
AU  - Laun FB
AD  - Department of Medical Physics in Radiology, German Cancer Research Center (DKFZ), 
      Heidelberg, Germany.
FAU - Maier-Hein, Klaus H
AU  - Maier-Hein KH
AD  - Junior Group Medical Image Computing, German Cancer Research Center (DKFZ), 
      Heidelberg, Germany.
FAU - Schlemmer, Heinz-Peter
AU  - Schlemmer HP
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
FAU - Bonekamp, David
AU  - Bonekamp D
AD  - Department of Radiology, German Cancer Research Center (DKFZ), Heidelberg, 
      Germany.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20170202
PL  - United States
TA  - J Magn Reson Imaging
JT  - Journal of magnetic resonance imaging : JMRI
JID - 9105850
RN  - 0 (Contrast Media)
SB  - IM
MH  - Aged
MH  - Biopsy
MH  - Breast/diagnostic imaging
MH  - Breast Neoplasms/*diagnostic imaging
MH  - Contrast Media/*chemistry
MH  - *Diffusion Magnetic Resonance Imaging
MH  - Early Detection of Cancer
MH  - Female
MH  - Humans
MH  - Image Interpretation, Computer-Assisted
MH  - Image Processing, Computer-Assisted
MH  - *Mammography
MH  - Middle Aged
MH  - Pilot Projects
MH  - Prospective Studies
MH  - Radiology
MH  - Retrospective Studies
MH  - X-Rays
OTO - NOTNLM
OT  - DWIBS
OT  - apparent diffusion coefficient
OT  - diffusion-weighted imaging with background suppression
OT  - magnetic resonance
OT  - mammography
OT  - radiomics
EDAT- 2017/02/06 06:00
MHDA- 2018/05/08 06:00
CRDT- 2017/02/03 06:00
PHST- 2016/10/12 00:00 [received]
PHST- 2016/12/07 00:00 [accepted]
PHST- 2017/02/06 06:00 [pubmed]
PHST- 2018/05/08 06:00 [medline]
PHST- 2017/02/03 06:00 [entrez]
AID - 10.1002/jmri.25606 [doi]
PST - ppublish
SO  - J Magn Reson Imaging. 2017 Aug;46(2):604-616. doi: 10.1002/jmri.25606. Epub 2017 
      Feb 2.