Deep learning analysis of contrast-enhanced spectral mammography to determine histoprognostic factors of malignant breast tumours.


Journal

European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774

Informations de publication

Date de publication:
Jul 2022
Historique:
received: 17 08 2021
accepted: 21 12 2021
revised: 20 12 2021
pubmed: 31 1 2022
medline: 24 6 2022
entrez: 30 1 2022
Statut: ppublish

Résumé

To evaluate if a deep learning model can be used to characterise breast cancers on contrast-enhanced spectral mammography (CESM). This retrospective mono-centric study included biopsy-proven invasive cancers with an enhancement on CESM. CESM images include low-energy images (LE) comparable to digital mammography and dual-energy subtracted images (DES) showing tumour angiogenesis. For each lesion, histologic type, tumour grade, estrogen receptor (ER) status, progesterone receptor (PR) status, HER-2 status, Ki-67 proliferation index, and the size of the invasive tumour were retrieved. The deep learning model used was a CheXNet-based model fine-tuned on CESM dataset. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated for the different models: images by images and then by majority voting combining all the incidences for one tumour. In total, 447 invasive breast cancers detected on CESM with pathological evidence, in 389 patients, which represented 2460 images analysed, were included. Concerning the ER, the deep learning model on the DES images had an AUC of 0.83 with the image-by-image analysis and of 0.85 for the majority voting. For the triple-negative analysis, a high AUC was observable for all models, in particularity for the model on LE images with an AUC of 0.90 for the image-by-image analysis and 0.91 for the majority voting. The AUC for the other histoprognostic factors was lower. Deep learning analysis on CESM has the potential to determine histoprognostic tumours makers, notably estrogen receptor status, and triple-negative receptor status. • A deep learning model developed for chest radiography was adapted by fine-tuning to be used on contrast-enhanced spectral mammography. • The adapted models allowed to determine for invasive breast cancers the status of estrogen receptors and triple-negative receptors. • Such models applied to contrast-enhanced spectral mammography could provide rapid prognostic and predictive information.

Identifiants

pubmed: 35094119
doi: 10.1007/s00330-022-08538-4
pii: 10.1007/s00330-022-08538-4
pmc: PMC8800426
doi:

Substances chimiques

Contrast Media 0
Receptors, Estrogen 0

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

4834-4844

Informations de copyright

© 2022. The Author(s), under exclusive licence to European Society of Radiology.

Références

Jochelson M (2014) Contrast-enhanced digital mammography. Radiol Clin North Am 52:609–616. https://doi.org/10.1016/j.rcl.2013.12.004
doi: 10.1016/j.rcl.2013.12.004 pubmed: 24792660
Lalji UC, Jeukens CRLPN, Houben I et al (2015) Evaluation of low-energy contrast-enhanced spectral mammography images by comparing them to full-field digital mammography using EUREF image quality criteria. Eur Radiol 25:2813–2820. https://doi.org/10.1007/s00330-015-3695-2
doi: 10.1007/s00330-015-3695-2 pubmed: 25813015 pmcid: 4562003
Dromain C, Balleyguier C, Adler G et al (2009) Contrast-enhanced digital mammography. Eur J Radiol 69:34–42. https://doi.org/10.1016/j.ejrad.2008.07.035
doi: 10.1016/j.ejrad.2008.07.035 pubmed: 18790584
Cheung Y-C, Lin Y-C, Wan Y-L et al (2014) Diagnostic performance of dual-energy contrast-enhanced subtracted mammography in dense breasts compared to mammography alone: interobserver blind-reading analysis. Eur Radiol 24:2394–2403. https://doi.org/10.1007/s00330-014-3271-1
doi: 10.1007/s00330-014-3271-1 pubmed: 24928280
Jochelson MS, Dershaw DD, Sung JS et al (2013) Bilateral contrast-enhanced dual-energy digital mammography: feasibility and comparison with conventional digital mammography and MR imaging in women with known breast carcinoma. Radiology 266:743–751. https://doi.org/10.1148/radiol.12121084
doi: 10.1148/radiol.12121084 pubmed: 23220903
Fallenberg EM, Schmitzberger FF, Amer H et al (2017) Contrast-enhanced spectral mammography vs. mammography and MRI – clinical performance in a multi-reader evaluation. Eur Radiol 27:2752–2764. https://doi.org/10.1007/s00330-016-4650-6
doi: 10.1007/s00330-016-4650-6 pubmed: 27896471
Li L, Roth R, Germaine P et al (2017) Contrast-enhanced spectral mammography (CESM) versus breast magnetic resonance imaging (MRI): a retrospective comparison in 66 breast lesions. Diagn Interv Imaging 98:113–123. https://doi.org/10.1016/j.diii.2016.08.013
doi: 10.1016/j.diii.2016.08.013 pubmed: 27687829
Hobbs MM, Taylor DB, Buzynski S, Peake RE (2015) Contrast-enhanced spectral mammography (CESM) and contrast enhanced MRI (CEMRI): patient preferences and tolerance: CESM and CEMRI preferences and tolerance. J Med Imaging Radiat Oncol 59:300–305. https://doi.org/10.1111/1754-9485.12296
doi: 10.1111/1754-9485.12296 pubmed: 25900704
Patel BK, Gray RJ, Pockaj BA (2017) Potential cost savings of contrast-enhanced digital mammography. AJR Am J Roentgenol 208:W231–W237. https://doi.org/10.2214/AJR.16.17239
doi: 10.2214/AJR.16.17239 pubmed: 28379734
Lee-Felker SA, Tekchandani L, Thomas M et al (2017) Newly diagnosed breast cancer: comparison of contrast-enhanced spectral mammography and breast MR imaging in the evaluation of extent of disease. Radiology 285:389–400. https://doi.org/10.1148/radiol.2017161592
doi: 10.1148/radiol.2017161592 pubmed: 28654337
Iotti V, Ravaioli S, Vacondio R et al (2017) Contrast-enhanced spectral mammography in neoadjuvant chemotherapy monitoring: a comparison with breast magnetic resonance imaging. Breast Cancer Res 19:106. https://doi.org/10.1186/s13058-017-0899-1
doi: 10.1186/s13058-017-0899-1 pubmed: 28893303 pmcid: 5594558
Badr S, Laurent N, Régis C et al (2014) Dual-energy contrast-enhanced digital mammography in routine clinical practice in 2013. Diagn Interv Imaging 95:245–258. https://doi.org/10.1016/j.diii.2013.10.002
doi: 10.1016/j.diii.2013.10.002 pubmed: 24238816
Dromain C, Vietti-Violi N, Meuwly JY (2019) Angiomammography: a review of current evidences. Diagn Interv Imaging 100:593–605. https://doi.org/10.1016/j.diii.2019.01.011
doi: 10.1016/j.diii.2019.01.011 pubmed: 30962168
Sardanelli F, Fallenberg EM, Clauser P et al (2017) Mammography: an update of the EUSOBI recommendations on information for women. Insights Imaging 8:11–18. https://doi.org/10.1007/s13244-016-0531-4
doi: 10.1007/s13244-016-0531-4 pubmed: 27854006
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
doi: 10.1038/nature14539 pubmed: 26017442
Rajpurkar P, Irvin J, Ball RL et al (2018) Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 15:e1002686. https://doi.org/10.1371/journal.pmed.1002686
doi: 10.1371/journal.pmed.1002686 pubmed: 30457988 pmcid: 6245676
McKinney SM, Sieniek M, Godbole V et al (2020) International evaluation of an AI system for breast cancer screening. Nature 577: https://doi.org/10.1038/s41586-019-1799-6
Geras KJ, Mann RM, Moy L (2019) Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives. Radiology 293:246–259. https://doi.org/10.1148/radiol.2019182627
doi: 10.1148/radiol.2019182627 pubmed: 31549948
Parekh VS, Jacobs MA (2019) Deep learning and radiomics in precision medicine. Expert Rev Precis Med Drug Dev 4:59–72. https://doi.org/10.1080/23808993.2019.1585805
doi: 10.1080/23808993.2019.1585805 pubmed: 31080889 pmcid: 6508888
Boisserie-Lacroix M, Hurtevent-Labrot G, Ferron S et al (2013) Correlation between imaging and molecular classification of breast cancers. Diagn Interv Imaging 94:1069–1080. https://doi.org/10.1016/j.diii.2013.04.010
doi: 10.1016/j.diii.2013.04.010 pubmed: 23867597
Pardamean B, Cenggoro TW, Rahutomo R et al (2018) Transfer learning from chest X-ray pre-trained convolutional neural network for learning mammogram data. Procedia Computer Science 135:400–407. https://doi.org/10.1016/j.procs.2018.08.190
doi: 10.1016/j.procs.2018.08.190
Haghanifar A, Majdabadi MM, Choi Y, et al (2020) COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep Learning. arXiv:200613807 [cs, eess]
Yi M, Huo L, Koenig KB et al (2014) Which threshold for ER positivity? a retrospective study based on 9639 patients. Ann Oncol 25:1004–1011. https://doi.org/10.1093/annonc/mdu053
doi: 10.1093/annonc/mdu053 pubmed: 24562447 pmcid: 3999801
Penault-Llorca F, Vincent-Salomon A, MacGrogan G et al (2014) 2014 update of the GEFPICS’ recommendations for HER2 status determination in breast cancers in France. Ann Pathol 34:352–365. https://doi.org/10.1016/j.annpat.2014.08.018
doi: 10.1016/j.annpat.2014.08.018 pubmed: 25439988
Gnant M, Thomssen C, Harbeck N (2015) St. Gallen/Vienna 2015: A brief summary of the consensus discussion. Breast Care (Basel) 10:124–130. https://doi.org/10.1159/000430488
doi: 10.1159/000430488
Yamamoto Y, Iwase H (2010) Clinicopathological features and treatment strategy for triple-negative breast cancer. Int J Clin Oncol 15:341–351. https://doi.org/10.1007/s10147-010-0106-1
doi: 10.1007/s10147-010-0106-1 pubmed: 20632057
Schneider CA, Rasband WS, Eliceiri KW (2012) NIH Image to ImageJ: 25 years of image analysis. Nat Meth 9:671–675. https://doi.org/10.1038/nmeth.2089
doi: 10.1038/nmeth.2089
Zhou J, Zhang Y, Chang K-T et al (2020) Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue. J Magn Reson Imaging 51:798–809. https://doi.org/10.1002/jmri.26981
doi: 10.1002/jmri.26981 pubmed: 31675151
Rajpurkar P, Irvin J, Zhu K et al (2017) CheXNet: radiologistlevel pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 2261–2269
Patel BK, Ranjbar S, Wu T et al (2018) Computer-aided diagnosis of contrast-enhanced spectral mammography: a feasibility study. Eur J Radiol 98:207–213. https://doi.org/10.1016/j.ejrad.2017.11.024
doi: 10.1016/j.ejrad.2017.11.024 pubmed: 29279165
Massafra R, Bove S, Lorusso V et al (2021) Radiomic feature reduction approach to predict breast cancer by contrast-enhanced spectral mammography images. Diagnostics 11:684. https://doi.org/10.3390/diagnostics11040684
doi: 10.3390/diagnostics11040684 pubmed: 33920221 pmcid: 8070152
Fanizzi A, Losurdo L, Basile TMA et al (2019) Fully automated support system for diagnosis of breast cancer in contrast-enhanced spectral mammography images. J Clin Med 8:E891. https://doi.org/10.3390/jcm8060891
doi: 10.3390/jcm8060891 pubmed: 31234363
Danala G, Patel B, Aghaei F et al (2018) Classification of breast masses using a computer-aided diagnosis scheme of contrast enhanced digital mammograms. Ann Biomed Eng 46:1419–1431. https://doi.org/10.1007/s10439-018-2044-4
doi: 10.1007/s10439-018-2044-4 pubmed: 29748869 pmcid: 6097613
Perek S, Kiryati N, Zimmerman-Moreno G et al (2019) Classification of contrast-enhanced spectral mammography (CESM) images. Int J Comput Assist Radiol Surg 14:249–257. https://doi.org/10.1007/s11548-018-1876-6
doi: 10.1007/s11548-018-1876-6 pubmed: 30367322
Gao F, Wu T, Li J et al (2018) SD-CNN: a shallow-deep CNN for improved breast cancer diagnosis. Comput Med Imaging Graph 70:53–62. https://doi.org/10.1016/j.compmedimag.2018.09.004
doi: 10.1016/j.compmedimag.2018.09.004 pubmed: 30292910
Marino MA, Pinker K, Leithner D et al (2020) Contrast-enhanced mammography and radiomics analysis for noninvasive breast cancer characterization: initial results. Mol Imaging Biol 22:780–787. https://doi.org/10.1007/s11307-019-01423-5
doi: 10.1007/s11307-019-01423-5 pubmed: 31463822 pmcid: 7047570
Krizmanich-Conniff KM, Paramagul C, Patterson SK et al (2012) Triple receptor–negative breast cancer: imaging and clinical characteristics. AJR Am J Roentgenol 199:458–464. https://doi.org/10.2214/AJR.10.6096
doi: 10.2214/AJR.10.6096 pubmed: 22826413 pmcid: 3638984
Youk JH, Son EJ, Chung J et al (2012) Triple-negative invasive breast cancer on dynamic contrast-enhanced and diffusion-weighted MR imaging: comparison with other breast cancer subtypes. Eur Radiol 22:1724–1734. https://doi.org/10.1007/s00330-012-2425-2
doi: 10.1007/s00330-012-2425-2 pubmed: 22527371

Auteurs

Caroline Dominique (C)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France.

Françoise Callonnec (F)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France.

Anca Berghian (A)

Department of Pathology, Henri Becquerel Cancer Centre, Rouen, France.

Diana Defta (D)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France.

Pierre Vera (P)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France.
QuantIF-LITIS EA4108, University of Rouen, Rouen, France.

Romain Modzelewski (R)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France.
QuantIF-LITIS EA4108, University of Rouen, Rouen, France.

Pierre Decazes (P)

Department of Radiology and Nuclear Medicine, Henri Becquerel Cancer Centre, Rouen, France. pierre.decazes@chb.unicancer.fr.
QuantIF-LITIS EA4108, University of Rouen, Rouen, France. pierre.decazes@chb.unicancer.fr.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH