Breast MRI molecular cancer subtype

<p>This data set is part of the public development data for&nbsp;the&nbsp;<a href="http://auc23.grand-challenge.org/">2023 Automated Universal Classification Challenge</a> (AUC23). The data set concerns&nbsp;the classification of breast cancer molecular subtypes on dynamic contrast-enhanced magnetic resonance imaging (MRI) and was derived from <a href="https://sites.duke.edu/mazurowski/resources/breast-cancer-mri-dataset/">Duke Hospital</a>. The data set is a subset of the data originally introduced and described by&nbsp;<a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6134102/">Saha et al. (2018)</a>, with no additional images or patient information.&nbsp;Data was&nbsp;restructured in compliance with the&nbsp;<a href="https://auc23.grand-challenge.org/">AUC23</a>&nbsp;challenge format. The dataset is a single-institutional, retrospective collection of 737 biopsy-confirmed&nbsp;patients from 1 January 2000 to 23 March 2014 with invasive breast cancer and available pre-operative MRI at Duke Hospital.</p> <p>Images are&nbsp;3D tensors:</p> <ul> <li>0:&nbsp;3D T1-subtraction dynamic contrast-enhanced&nbsp;MRI</li> </ul> <p>Classification labels:</p> <ul> <li>0: Luminal A, estrogen-receptor (ER) and/or progesterone-receptor (PR) positive<strong>,</strong> human epidermal growth factor receptor 2 (HER2) negative</li> <li>1: Luminal B, ER and/or PR negative, HER2 positive</li> <li>2: HER2, ER and PR negative, HER2 positive</li> <li>3: Triple negative, ER, PR, and HER2 negative</li> </ul> <p>Folder structure:</p> <p>imagesTr (root folder with all patients and studies)<br> &nbsp; &nbsp; ├── Breast_MRI_0001_0000.mha &nbsp;(3D T1-subtraction MRI imaging for study 0001)<br> &nbsp;&nbsp; &nbsp;├── Breast_MRI_0003_0000.mha &nbsp;(3D T1-subtraction MRI imaging for study 0003)<br> &nbsp; &nbsp; ├──&nbsp;...</p> <p>Please cite the following article if you are using the <a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=70226903">Duke-Breast-Cancer-MRI&nbsp;Dataset</a>:</p> <pre><code>A. Saha, M. R. Harowicz, L. J. Grimm, C. E. Kim, S. V. Ghate, R. Walsh, M. A. Mazurowski, "A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features". Br J Cancer. 2018 Aug;119(4):508-516. doi: 10.1038/s41416-018-0185-8. Epub 2018 Jul 23. PMID: 30033447; PMCID: PMC6134102. </code></pre>