{"references": ["Roth, H., Lu, L., Seff, A., Cherry, K. M., Hoffman, J., Wang, S., Liu, J., Turkbey, E., & Summers, R. M. (2015). A new 2.5 D representation for lymph node detection in CT [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2015.AQIIDCNM", "Roth, H. R., Lu, L., Seff, A., Cherry, K. M., Hoffman, J., Wang, S., Liu, J., Turkbey, E., & Summers, R. M. (2014). A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations. In Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2014 (pp. 520\u2013527). Springer International Publishing. https://doi.org/10.1007/978-3-319-10404-1_65", "Seff, A., Lu, L., Cherry, K.M., Roth, H.R., Liu, J., Wang, S., Hoffman, J., Turkbey, E.B., & Summers, R.M. 2D view aggregation for lymph node detection using a shallow hierarchy of linear classifiers. Medical Image Computing and Computer-Assisted Intervention--MICCAI 2014, p544-552, 2014. (http://arxiv.org/abs/1408.3337)", "Please cite the following paper when using the segmentation masks: Seff, A., Lu, L., Barbu, A., Roth, H., Shin, H.-C., & Summers, R. M. (2015). Leveraging Mid-Level Semantic Boundary Cues for Automated Lymph Node Detection. In Lecture Notes in Computer Science Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015 (pp. 53\u201361). Springer International Publishing. https://doi.org/10.1007/978-3-319-24571-3_7", "Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging, 26(6), 1045\u20131057. https://doi.org/10.1007/s10278-013-9622-7"]}

Down sampling of the CT Lymph Node dataset from the TCIA. The files were down sampled to a pixel spacing of 7 mm/pixel. Through zero padding and cropping, all images are provided in the size of 64px x 64 px. Moreover, the HU values were clipped between -1000 HU and 1500 HU and rescaled to -1 and 1. To avoid aliasing effects, an additional Gaussian smoothing filter was applied before down sampling. This dataset was created for a Body Part Regression tutorial.