Holistic Modeling In Medical Image Segmentation Using Spatial Recurrence

João BS Carvalho, João Santinha, Djordje Miladinovic, Carlos Cotrini, Joachim M Buhmann
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:199-218, 2022.

Abstract

In clinical practice, regions of interest in medical imaging (MI) often need to be identified through a process of precise image segmentation. For MI segmentation to generalize, we need two components: to identify local descriptions, but at the same time to develop a holistic representation of the image that captures long-range spatial dependencies. Unfortunately, we demonstrate that the start of the art does not achieve the latter. In particular, it does not provide a modeling that yields a global, contextual model. To improve accuracy, and enable holistic modeling, we introduce a novel deep neural network architecture endowed with spatial recurrence. The implementation relies on gated recurrent units that directionally traverse the feature map, greatly increasing each layers receptive field and explicitly modeling non-adjacent relationships between pixels. Our method is evaluated in four different segmentation tasks: nuclei segmentation in microscopy images, colorectal polyp segmentation in colonoscopy videos, liver segmentation in abdominal CT scans, and aorta artery segmentation in thoracic CT scans. Our experiments demonstrate an average increase in performance of 4.72 Dice points and 0.68 Hausdorff distance units comparing to U-Net and U-Net++, and a performance better or on par when compared to transformer-based architectures. Code available at https://github.com/JoaoCarv/holistic-seg.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-carvalho22a, title = {Holistic Modeling In Medical Image Segmentation Using Spatial Recurrence}, author = {Carvalho, Jo{\~a}o BS and Santinha, Jo{\~a}o and Miladinovic, Djordje and Cotrini, Carlos and Buhmann, Joachim M}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {199--218}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/carvalho22a/carvalho22a.pdf}, url = {https://proceedings.mlr.press/v172/carvalho22a.html}, abstract = {In clinical practice, regions of interest in medical imaging (MI) often need to be identified through a process of precise image segmentation. For MI segmentation to generalize, we need two components: to identify local descriptions, but at the same time to develop a holistic representation of the image that captures long-range spatial dependencies. Unfortunately, we demonstrate that the start of the art does not achieve the latter. In particular, it does not provide a modeling that yields a global, contextual model. To improve accuracy, and enable holistic modeling, we introduce a novel deep neural network architecture endowed with spatial recurrence. The implementation relies on gated recurrent units that directionally traverse the feature map, greatly increasing each layers receptive field and explicitly modeling non-adjacent relationships between pixels. Our method is evaluated in four different segmentation tasks: nuclei segmentation in microscopy images, colorectal polyp segmentation in colonoscopy videos, liver segmentation in abdominal CT scans, and aorta artery segmentation in thoracic CT scans. Our experiments demonstrate an average increase in performance of 4.72 Dice points and 0.68 Hausdorff distance units comparing to U-Net and U-Net++, and a performance better or on par when compared to transformer-based architectures. Code available at https://github.com/JoaoCarv/holistic-seg.} }
Endnote
%0 Conference Paper %T Holistic Modeling In Medical Image Segmentation Using Spatial Recurrence %A João BS Carvalho %A João Santinha %A Djordje Miladinovic %A Carlos Cotrini %A Joachim M Buhmann %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-carvalho22a %I PMLR %P 199--218 %U https://proceedings.mlr.press/v172/carvalho22a.html %V 172 %X In clinical practice, regions of interest in medical imaging (MI) often need to be identified through a process of precise image segmentation. For MI segmentation to generalize, we need two components: to identify local descriptions, but at the same time to develop a holistic representation of the image that captures long-range spatial dependencies. Unfortunately, we demonstrate that the start of the art does not achieve the latter. In particular, it does not provide a modeling that yields a global, contextual model. To improve accuracy, and enable holistic modeling, we introduce a novel deep neural network architecture endowed with spatial recurrence. The implementation relies on gated recurrent units that directionally traverse the feature map, greatly increasing each layers receptive field and explicitly modeling non-adjacent relationships between pixels. Our method is evaluated in four different segmentation tasks: nuclei segmentation in microscopy images, colorectal polyp segmentation in colonoscopy videos, liver segmentation in abdominal CT scans, and aorta artery segmentation in thoracic CT scans. Our experiments demonstrate an average increase in performance of 4.72 Dice points and 0.68 Hausdorff distance units comparing to U-Net and U-Net++, and a performance better or on par when compared to transformer-based architectures. Code available at https://github.com/JoaoCarv/holistic-seg.
APA
Carvalho, J.B., Santinha, J., Miladinovic, D., Cotrini, C. & Buhmann, J.M.. (2022). Holistic Modeling In Medical Image Segmentation Using Spatial Recurrence. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:199-218 Available from https://proceedings.mlr.press/v172/carvalho22a.html.

Related Material