no code implementations • 20 Apr 2022 • Kelly Payette, Hongwei Li, Priscille de Dumast, Roxane Licandro, Hui Ji, Md Mahfuzur Rahman Siddiquee, Daguang Xu, Andriy Myronenko, Hao liu, Yuchen Pei, Lisheng Wang, Ying Peng, Juanying Xie, Huiquan Zhang, Guiming Dong, Hao Fu, Guotai Wang, ZunHyan Rieu, Donghyeon Kim, Hyun Gi Kim, Davood Karimi, Ali Gholipour, Helena R. Torres, Bruno Oliveira, João L. Vilaça, Yang Lin, Netanell Avisdris, Ori Ben-Zvi, Dafna Ben Bashat, Lucas Fidon, Michael Aertsen, Tom Vercauteren, Daniel Sobotka, Georg Langs, Mireia Alenyà, Maria Inmaculada Villanueva, Oscar Camara, Bella Specktor Fadida, Leo Joskowicz, Liao Weibin, Lv Yi, Li Xuesong, Moona Mazher, Abdul Qayyum, Domenec Puig, Hamza Kebiri, Zelin Zhang, Xinyi Xu, Dan Wu, Kuanlun Liao, Yixuan Wu, Jintai Chen, Yunzhi Xu, Li Zhao, Lana Vasung, Bjoern Menze, Meritxell Bach Cuadra, Andras Jakab
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
1 code implementation • 5 Apr 2022 • Lucas Fidon, Michael Aertsen, Florian Kofler, Andrea Bink, Anna L. David, Thomas Deprest, Doaa Emam, Fr/'ed/'eric Guffens, András Jakab, Gregor Kasprian, Patric Kienast, Andrew Melbourne, Bjoern Menze, Nada Mufti, Ivana Pogledic, Daniela Prayer, Marlene Stuempflen, Esther Van Elslander, Sébastien Ourselin, Jan Deprest, Tom Vercauteren
Our method automatically discards the voxel-level labeling predicted by the backbone AI that are likely to violate expert knowledge and relies on a fallback atlas-based segmentation method for those voxels.
Label-set loss functions allow to train deep neural networks with partially segmented images, i. e. segmentations in which some classes may be grouped into super-classes.
1 code implementation • 9 Aug 2021 • Lucas Fidon, Michael Aertsen, Nada Mufti, Thomas Deprest, Doaa Emam, Frédéric Guffens, Ernst Schwartz, Michael Ebner, Daniela Prayer, Gregor Kasprian, Anna L. David, Andrew Melbourne, Sébastien Ourselin, Jan Deprest, Georg Langs, Tom Vercauteren
The performance of deep neural networks typically increases with the number of training images.
2 code implementations • 8 Jul 2021 • Lucas Fidon, Michael Aertsen, Doaa Emam, Nada Mufti, Frédéric Guffens, Thomas Deprest, Philippe Demaerel, Anna L. David, Andrew Melbourne, Sébastien Ourselin, Jan Deprest, Tom Vercauteren
Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images.
To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects.
Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object.
Experimental results show that: (1) our proposed CNN obtains uncertainty estimation in real time which correlates well with mis-segmentations, (2) the proposed interactive level set is effective and efficient for refinement, (3) UGIR obtains accurate refinement results with around 30% improvement of efficiency by using uncertainty to guide user interactions.
1 code implementation • 8 Jan 2020 • Lucas Fidon, Michael Aertsen, Thomas Deprest, Doaa Emam, Frédéric Guffens, Nada Mufti, Esther Van Elslander, Ernst Schwartz, Michael Ebner, Daniela Prayer, Gregor Kasprian, Anna L. David, Andrew Melbourne, Sébastien Ourselin, Jan Deprest, Georg Langs, Tom Vercauteren
In order to improve the robustness of machine learning systems, Distributionally Robust Optimization (DRO) has been proposed as a generalization of Empirical Risk Minimization (ERM).
In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks.
no code implementations • 11 Oct 2017 • Guotai Wang, Wenqi Li, Maria A. Zuluaga, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sebastien Ourselin, Tom Vercauteren
Experimental results show that 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine-tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.
1 code implementation • 3 Jul 2017 • Guotai Wang, Maria A. Zuluaga, Wenqi Li, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sebastien Ourselin, Tom Vercauteren
We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy.