Skull R-CNN: A CNN-based network for the skull fracture detection

Zhuo Kuang, Xianbo Deng, Li Yu, Hang Zhang, Xian Lin, Hui Ma
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:382-392, 2020.

Abstract

Skull fractures, following head trauma, may bring several complications and cause epidural hematomas. Therefore, it is of great significance to locate the fracture in time. However, the manual detection is time-consuming and laborious, and the previous studies for the automatic detection could not achieve the accuracy and robustness for clinical application. In this work, based on the Faster R-CNN, we propose a novel method for more accurate skull fracture detection results, and we name it as the Skull R-CNN. Guiding by the morphological features of the skull, a skeleton-based region proposal method is proposed to make candidate boxes more concentrated in key regions and reduced invalid boxes. With this advantage, the region proposal network in Faster R-CNN is removed for less computation. On the other hand, a novel full resolution feature network is constructed to obtain more precise features to make the model more sensitive to small objects. Experiment results showed that most of skull fractures could be detected correctly by the proposed method in a short time. Compared to the previous works on the skull fracture detection, Skull R-CNN significantly reduces the false positives, and keeps a high sensitivity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-kuang20a, title = {Skull R-CNN: A CNN-based network for the skull fracture detection}, author = {Kuang, Zhuo and Deng, Xianbo and Yu, Li and Zhang, Hang and Lin, Xian and Ma, Hui}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {382--392}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/kuang20a/kuang20a.pdf}, url = {https://proceedings.mlr.press/v121/kuang20a.html}, abstract = {Skull fractures, following head trauma, may bring several complications and cause epidural hematomas. Therefore, it is of great significance to locate the fracture in time. However, the manual detection is time-consuming and laborious, and the previous studies for the automatic detection could not achieve the accuracy and robustness for clinical application. In this work, based on the Faster R-CNN, we propose a novel method for more accurate skull fracture detection results, and we name it as the Skull R-CNN. Guiding by the morphological features of the skull, a skeleton-based region proposal method is proposed to make candidate boxes more concentrated in key regions and reduced invalid boxes. With this advantage, the region proposal network in Faster R-CNN is removed for less computation. On the other hand, a novel full resolution feature network is constructed to obtain more precise features to make the model more sensitive to small objects. Experiment results showed that most of skull fractures could be detected correctly by the proposed method in a short time. Compared to the previous works on the skull fracture detection, Skull R-CNN significantly reduces the false positives, and keeps a high sensitivity.} }
Endnote
%0 Conference Paper %T Skull R-CNN: A CNN-based network for the skull fracture detection %A Zhuo Kuang %A Xianbo Deng %A Li Yu %A Hang Zhang %A Xian Lin %A Hui Ma %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-kuang20a %I PMLR %P 382--392 %U https://proceedings.mlr.press/v121/kuang20a.html %V 121 %X Skull fractures, following head trauma, may bring several complications and cause epidural hematomas. Therefore, it is of great significance to locate the fracture in time. However, the manual detection is time-consuming and laborious, and the previous studies for the automatic detection could not achieve the accuracy and robustness for clinical application. In this work, based on the Faster R-CNN, we propose a novel method for more accurate skull fracture detection results, and we name it as the Skull R-CNN. Guiding by the morphological features of the skull, a skeleton-based region proposal method is proposed to make candidate boxes more concentrated in key regions and reduced invalid boxes. With this advantage, the region proposal network in Faster R-CNN is removed for less computation. On the other hand, a novel full resolution feature network is constructed to obtain more precise features to make the model more sensitive to small objects. Experiment results showed that most of skull fractures could be detected correctly by the proposed method in a short time. Compared to the previous works on the skull fracture detection, Skull R-CNN significantly reduces the false positives, and keeps a high sensitivity.
APA
Kuang, Z., Deng, X., Yu, L., Zhang, H., Lin, X. & Ma, H.. (2020). Skull R-CNN: A CNN-based network for the skull fracture detection. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:382-392 Available from https://proceedings.mlr.press/v121/kuang20a.html.

Related Material