DeepLesion: a large-scale and diverse CT lesion dataset

DeepLesion is a large-scale and diverse database of lesions in CT images. It was collected based on the bookmarks in the picture archiving and communication system of NIH. Currently, it contains 32,735 lesions from 32,120 axial CT slices of 4,427 patients. It can be used in studies of multi-class lesion detection, retrieval, segmentation, etc.DeepLesion has been released. Download it without any paperwork here:

visualization of the DeepLesion dataset

Please refer to our paper:

Other papers related with DeepLesion:

  • Lesion detection
    • Ke Yan, Mohammadhadi Bagheri, Ronald M. Summers, “3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection,” MICCAI, 2018
  • Lesion segmentation
    • Jinzheng Cai*, Youbao Tang*, Le Lu, Adam P. Harrison, Ke Yan, Jing Xiao, Lin Yang, Ronald M. Summers, “Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST,” MICCAI, 2018
  • Lesion measurement
    • Youbao Tang, Adam P. Harrison, Mohammadhadi Bagheri, Jing Xiao, Ronald M. Summers , “Semi-Automatic RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networks,” MICCAI, 2018


  • yeezy boost says:

    A lot of thanks for every one of your labor on this website. My aunt delights in working on internet research and it is obvious why. My spouse and i notice all of the dynamic ways you produce precious strategies via the web site and therefore attract response from website visitors on the topic so our daughter is really learning a great deal. Take advantage of the remaining portion of the new year. You are always performing a stunning job.

  • I want to convey my love for your kind-heartedness in support of all those that absolutely need help with this important concept. Your personal commitment to passing the solution throughout ended up being especially practical and has specifically enabled professionals just like me to get to their endeavors. Your entire interesting tips and hints indicates a whole lot to me and still more to my colleagues. Thanks a lot; from each one of us.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: