M1.4 | Use of prior knowledge for interventional MRI

This sub-project aims at the reconstruction of dynamic time series from fast acquisitions.

Typically, these fast acquisitions are of lower quality (e.g. wrt resolution, contrast, or artefacts) compared to slower scans with higher resolution, the latter being acquired for the purpose of planning. At the same time we know that the object is mainly left unchanged apart from potential non-linear deformations and the presence of an interventional tool (e.g. a needle) with its position being precisely known.

Consequently, a lot is known about the object expecting this prior knowledge to enable the reconstruction of dynamic high resolution and high contrast images.
Therefore, different approaches may be applied including image-based matching and deformation, model-based reconstruction using prior knowledge to support regularisation, or even machine learning methods.

(1) Chatterjee, S., Sciarra, A., Dünnwald, M., Talagini Ashoka, A. B., Cheepinahalli Vasudeva, M. G., Saravanan, S., Thirugnana Sambandham, V., Oeltze-Jafra, S., Speck, O., and Nürnberger, A. (2022): Uncertainty quantification for ground-truth free evaluation of deep learning reconstructions.
>> ABSTRACT
>> VIDEO PRESENTATION

(2) Chatterjee, S., Bajaj, H., Siddiquee, I., Nandish, B. S., Simon, S., Shashidhar, S., Speck, O., and Nürnberger, A. (2022): Multi-scale UNet with Self-Constructing Graph Latent for Deformable Image Registration.
>> ABSTRACT
>> CODE
>> VIDEO PRESENTATION

(3) Chatterjee, S., Sciarra, A., Dünnwald, M., Tummala, P., Agrawal, S., Jauhari, A., Kalra, A., Oeltze-Jafra, S., Speck, O., and Nürnberger, A. (2022): StRegA: Unsupervised Anomaly Detection in Brain MRIs using Compact Context-encoding Variational Autoencoder.
>>ABSTRACT
>> CODE
>> VIDEO PRESENTATION

(4) Chatterjee, S., Yassin, H., Dubost, F., Nürnberger, A., and Speck, O. (2022): Learning to segment brain tumours using an explainable classifier.
>>ABSTRACT
>> CODE
>> VIDEO PRESENTATION

 (ISMRM-ESMRMB & ISMRT 31st Annual Meeting,
7-12 May 2022 @London, UK)

VIDEO PRESENTATION by Soumick Chatterjee (MEMoRIAL) on
Ernst, P., Chatterjee, S., Rose, G., Speck, O., and Nürnberger, A. (2022): Sinogram upsampling using Primal-Dual UNet for undersampled CT and radial MRI reconstruction.
Further information...
(IEEE ISBI 2022 / Mar 28-31, 2022)

VIDEO PRESENTATION by Soumick Chatterjee (MEMoRIAL) on
Chatterjee, S., Sciarra, A., Dünnwald, M., Mushunuri, R. V., Podishetti, R., Rao, R. N., Gopinath, G. D., Oeltze-Jafra, S., Speck, O., and Nürnberger, A. (2021): ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning.
(IEEE EUSIPCO 2021 / Aug 26, 2021)

  1. Chatterjee, S., Sarasaen, C., Sciarra, A., Breitkopf, M., Oeltze-Jafra, S., Nürnberger, A., and Speck, O. (2021): Going beyond the image space: undersampled MRI reconstruction directly in the k-space using a complex valued residual neural network.
    >> VIDEO PRESENTATION
  2. Chatterjee, S., Das, A., Mandal, C., Mukhopadhyay, B., Vipinraj, M., Shukla, A., Speck, O., and Nürnberger, A. (2021): Interpretability Techniques for Deep Learning based Segmentation Models.
    >> VIDEO PRESENTATION
  3. Chatterjee, S., Bajaj, H., Shashidhar, S. B., Indushekar S. B., Simon, S., Siddiquee, I. H., Subbarayappa, N. B., Speck, O., and Nürnberger, A. (2021): A Comparative Study of Deep Learning Based Deformable Image Registration Techniques.
    >> VIDEO PRESENTATION
  4. Chatterjee, S., Sciarra, A., Dünnwald, M., Agrawal, S. K., Tummala, P., Setlur, D., Kalra, A., Jauhari, A., Oeltze-Jafra, S., Speck, O., and Nürnberger, A. (2021): Unsupervised reconstruction based anomaly detection using a Variational Auto Encoder.
    >> ABSTRACT + DIGITAL POSTER
  5. Sarasaen, C., Chatterjee, S., Saad, F., Breitkopf, M., Nürnberger, A., and Speck, O. (2021): Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge.
    >> ABSTRACT
  6. Nath, V., Pizzolato, M., Palombo, M., Gyori, N., Schilling, K., Hansen, C., Yang, Q., Kanakaraj, P., Landman, B., Chatterjee, S., Sciarra, A., Dünnwald, M., Oeltze-Jafra, S., Nürnberger, A., Speck, O., Pieciak, T., Baranek, M., Bartocha, K., Ciupek, D., and Hutter, J. (2021): Resolving to super resolution multi-dimensional diffusion imaging (Super-MUDI).
    >> ABSTRACT

 (ISMRM & SMRT Virtual Conference & Exhibition / May 15-20, 2021)

VIDEO PRESENTATION by Soumick Chatterjee (MEMoRIAL) on
Chatterjee, S., Prabhu, K., Pattadkal, M., Bortsova, G., Sarasaen, C., Dubost, F., Mattern, H., De Bruijne, M., Speck, O., and Nürnberger, A. (2021):
DS6, Deformation-aware Semi-supervised Learning: Application to Vessel Segmentation with Noisy Data.
Further information ...
(Invited talk at Stanford University, Contrastive & Semi-Supervised Learning Group, CA, US / Mar 12, 2021)

VIDEO PRESENTATION by Soumick Chatterjee (MEMoRIAL) on
Chatterjee, S., Sciarra, A., Dünnwald, M., Oeltze-Jafra, S., Nürnberger, A., and Speck, O. (2020): Retrospective Motion Correction of MR Images using Prior-Assisted Deep Learning.
(Medical Imaging Meets NeurIPS 2020 / Dec 12, 2020)

VIDEO PRESENTATION by Soumick Chatterjee (MEMoRIAL) on
Chatterjee, S., Putti, P., Nürnberger, A., and Speck, O. (2020): Wavelet filtering of undersampled MRI using trainable wavelets and CNN.
(ESMRMB 2020 ONLINE / Sep 30 - Oct 02, 2020)

  1. Mitta, D., Chatterjee, S., Speck, O., and Nürnberger, A. (2020): Unsupervised learning for Abdominal MRI Segmentation using 3D Attention W-Net.
    >> VIDEO PRESENTATION
  2. Sciarra, A., Chatterjee, S., Dünnwald, M., Speck, O., and Oeltze-Jafra, S. (2020): Evaluation of Deep Learning Techniques for Motion Artifacts Removal.
    >>
    ABSTRACT + DIGITAL POSTER
  3. Mattern, H., Sciarra, A., Dünnwald, M., Chatterjee, S., Müller, U., Oeltze-Jafra, S., and Speck, O. (2020): Contrast prediction-based regularization for iterative reconstructions (PROSIT).
    >> ABSTRACT

 (ISMRM & SMRT Virtual Conference & Exhibition / Aug 08-14, 2020)

Last Modification: 03.05.2022 - Contact Person:

Sie können eine Nachricht versenden an: Dipl.-Ing Anke Ryll
Sicherheitsabfrage:
Captcha
 
Lösung: