Cancer Imaging Phenomics Toolkit (CaPTk)  1.8.1
Deep Learning Segmentation

For our Deep Learning based segmentation, we use DeepMedic [1,2] and users can do inference using a pre-trained models (trained on BraTS 2017 Training Data) with CaPTk for Brain Tumor Segmentation or Skull Stripping [3]. Users also have the option to train their own models using DeepMedic and using that model for their own tasks (be mindful of the preprocessing).

REQUIREMENTS:

  • For tumor segmentation model and multi-4 skull-stripping model:
    • The 4 basic MRI modalities (T1, T1-Gd, T2 and T2-FLAIR) for a subject which are co-registered.
  • For modality-agnostic skull-stripping model:
    • A single structural MRI modality (can be either T1, T1-Gd, T2 or T2-FLAIR).

USAGE:

  1. Load the images that you want to segment in CaPTk.
  2. [OPTIONAL] Load the brain mask - this is used for normalization.
  3. Select the appropriate pre-trained model folder (either brain tumor segmentation or skull stripping is available): for custom models, select appropriate option and browse to the model directory.
  4. Select the output folder.
  5. Click on 'Applications' -> 'Brain Tumor Segmentation' or 'Skull Stripping'
  6. This can also be used from the command line:
    ${CaPTk_InstallDir}/bin/DeepMedic.exe -md ${CaPTk_InstallDir}/data/deepMedic/saved_models/brainTumorSegmentation -i C:/data/t1.nii.gz,C:/data/t1ce.nii.gz,C:/data/t2.nii.gz,C:/data/fl.nii.gz -m C:/data/optionalMask.nii.gz -o C:/data/outputSegmentation.nii.gz
    ${CaPTk_InstallDir}/bin/DeepMedic.exe -i c:/t1_withSkull.nii.gz -o c:/output -md c:/CaPTk_install/data/deepMedic/saved_models/skullStripping_modalityAgnostic # modality-agnostic skull-stripping
    


References:

  1. K.Kamnitsas, C.Ledig, V.F.J.Newcombe, J.P.Simpson, A.D.Kane, D.K.Menon, D.Rueckert, B.Glocker, "Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation", Medical Image Analysis, 2016.
  2. K.Kamnitsas, L.Chen, C.Ledig, D.Rueckert, B.Glocker, "Multi-Scale 3D CNNs for segmentation of brain Lesions in multi-modal MRI", in proceeding of ISLES challenge, MICCAI 2015.
  3. S.P.Thakur, J.Doshi, S.Pati, S.M.Ha, C.Sako, S.Talbar, U.Kulkarni, C.Davatzikos, G.Erus, S.Bakas, "Skull-Stripping of Glioblastoma MRI Scans Using 3D Deep Learning", Springer - BrainLes 2019 - LNCS, Vol.11992, 57-68, 2020, DOI: 10.1007/978-3-030-46640-4_6
  4. S.P.Thakur, J.Doshi, S.Pati, S.M.Ha, C.Sako, S.Talbar, U.Kulkarni, C.Davatzikos, G.Erus, S.Bakas, "Brain Extraction on MRI Scans in Presence of Diffuse Glioma: Multi-institutional Performance Evaluation of Deep Learning Methods and Robust Modality-Agnostic Training", NeuroImage 2020 [Accepted]