When to Use Advanced Sequences & AI
Katja Pinker-Domenig1
1Memorial Sloan Kettering Cancer Center, New York, NY, United States

Synopsis

This presentation will explain the concept and methodology of AI-enhanced multiparametric MRI, summarize the current applications in breast cancer and address its challenges and limitations.

Abstract

Magnetic resonance imaging (MRI) is an essential tool in breast imaging, with multiple established indications. Dynamic contrast-enhanced MRI (DCE-MRI) is the backbone of any breast MRI protocol and has an excellent sensitivity and good specificity for breast cancer diagnosis. To overcome limitations in specificity, several other functional MRI parameters have been investigated and the application of these combined parameters is defined as multiparametric breast MRI. Multiparametric breast MRI includes both established [diffusion-weighted imaging (DWI), MR spectroscopic imaging (MRSI)] and novel MRI parameters such as [sodium imaging (23Na-MRI), chemical exchange saturation transfer (CEST) imaging, blood oxygen level–dependent (BOLD) MRI]. One of the most promising areas of health innovation is the application of AI in biomedical imaging. Medical imaging has always been an integral part of disease diagnosis and treatment decisions. With the possibility to use AI for image, i.e radiomics analysis to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Out of the myriad proposed use-cases for AI in radiology, breast cancer is one of the most researched. Advances in radiomics analysis, i.e. the extraction and correlation of multiple imaging parameters with different variables of interest (patients’ characteristics, histopathologic, genomic, molecular or outcome data) and machine learning (such as deep learning) are on the cusp of providing more effective, more efficient, and even more patient-centric breast cancer care support than ever before. Radiogenomics aims to correlate imaging characteristics (i.e., the imaging phenotype) with gene expression patterns, such as molecular subtypes, gene mutations, and other genome-related characteristics. Radiogenomics is designed to facilitate a deeper understanding of molecular tumor biology through the extraction of parameters derived from image processing and analyses of medical images that are linked to the geno- and phenotypic characteristics of the tissue. Due to the non-invasive nature of medical imaging and its ubiquitous use in clinical practice, the field of AI-enhanced multiparametric MRI is rapidly evolving and initial results are encouraging. This presentation will explain the concept and methodology of AI-enhanced multiparametric MRI, summarize the current applications in breast cancer and address its challenges and limitations.

Acknowledgements

No acknowledgement found.

References

The potential of multiparametric MRI of the breast. Pinker K, Helbich TH, Morris EA. Br J Radiol. 2017 Jan;90(1069):20160715. doi: 10.1259/bjr.20160715. Epub 2016 Nov 2.

Diffusion-weighted imaging of the breast-a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group. Baltzer P, Mann RM, Iima M, Sigmund EE, Clauser P, Gilbert FJ, Martincich L, Partridge SC, Patterson A, Pinker K, Thibault F, Camps-Herrero J, Le Bihan D; EUSOBI international Breast Diffusion-Weighted Imaging working group.

Accuracy of multiparametric MRI in distinguishing the breast malignant lesions from benign lesions: a meta-analysis. Zhu CR, Chen KY, Li P, Xia ZY, Wang B. Acta Radiol. 2020 Oct 15:284185120963900. doi: 10.1177/0284185120963900.

Breast MRI: State of the Art. Mann RM, Cho N, Moy L. Radiology. 2019 Sep;292(3):520-536. doi: 10.1148/radiol.2019182947. Epub 2019 Jul 30. Eur Radiol. 2020 Mar;30(3):1436-1450. doi: 10.1007/s00330-019-06510-3. Epub 2019 Nov 30.

Morris EA, Comstock CE, Lee CH, et al. ACR BI-RADS® Magnetic Resonance Imaging. In: ACR BI-RADS® Atlas, Breast Imaging Reporting and Data System. Reston, VA, American College of Radiology; 2013. Eur Radiol. 2015 Dec;25(12):3669-78. doi: 10.1007/s00330-015-3807-z. Epub 2015 May 23.

Breast MRI: EUSOBI recommendations for women's information. Mann RM1, Balleyguier C2, Baltzer PA3, Bick U4, Colin C5, Cornford E6, Evans A7, Fallenberg E4, Forrai G8, Fuchsjäger MH9, Gilbert FJ10, Helbich TH3, Heywang-Köbrunner SH11, Camps-Herrero J12, Kuhl CK13, Martincich L14, Pediconi F15, Panizza P16, Pina LJ17, Pijnappel RM18, Pinker-Domenig K3, Skaane P19, Sardanelli F20; European Society of Breast Imaging (EUSOBI), with language review by Europa

Diffusion-weighted MRI for Unenhanced Breast Cancer Screening.Amornsiripanitch N, Bickelhaupt S, Shin HJ, Dang M, Rahbar H, Pinker K, Partridge SC.Radiology. 2019 Dec;293(3):504-520. doi: 10.1148/radiol.2019182789. Epub 2019 Oct 8.PMID: 31592734

Development of a Non-invasive Assessment of Hypoxia and Neovascularization with Magnetic Resonance Imaging in Benign and Malignant Breast Tumors: Initial Results.Stadlbauer A, Zimmermann M, Bennani-Baiti B, Helbich TH, Baltzer P, Clauser P, Kapetas P, Bago-Horvath Z, Pinker K.Mol Imaging Biol. 2019 Aug;21(4):758-770. doi: 10.1007/s11307-018-1298-4.PMID: 30478507

Current Status and Future Perspectives of Artificial Intelligence in Magnetic Resonance Breast Imaging.Meyer-Bäse A, Morra L, Meyer-Bäse U, Pinker K.Contrast Media Mol Imaging. 2020 Aug 28;2020:6805710. doi: 10.1155/2020/6805710. eCollection 2020.PMID: 32934610

AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer.Meyer-Base A, Morra L, Tahmassebi A, Lobbes M, Meyer-Base U, Pinker K.J Magn Reson Imaging. 2020 Aug 30. doi: 10.1002/jmri.27332. Online ahead of print.PMID: 32864782

Combining molecular and imaging metrics in cancer: radiogenomics.Lo Gullo R, Daimiel I, Morris EA, Pinker K.Insights Imaging. 2020 Jan 3;11(1):1. doi: 10.1186/s13244-019-0795-6.PMID: 31901171

Imaging and the completion of the omics paradigm in breast cancer.Leithner D, Horvat JV, Ochoa-Albiztegui RE, Thakur S, Wengert G, Morris EA, Helbich TH, Pinker K.Radiologe. 2018 Nov;58(Suppl 1):7-13. doi: 10.1007/s00117-018-0409-1.PMID: 29947931 Free PMC article. Review.

Precision Medicine and Radiogenomics in Breast Cancer: New Approaches toward Diagnosis and Treatment.Pinker K, Chin J, Melsaether AN, Morris EA, Moy L.Radiology. 2018 Jun;287(3):732-747. doi: 10.1148/radiol.2018172171.PMID: 29782246

Proc. Intl. Soc. Mag. Reson. Med. 29 (2021)