2024-03-29T02:39:20Z
https://nagoya.repo.nii.ac.jp/oai
oai:nagoya.repo.nii.ac.jp:00026376
2023-01-16T04:16:54Z
312:313:314
An application of cascaded 3D fully convolutional networks for medical image segmentation
Roth, Holger R.
85339
Oda, Hirohisa
85340
Zhou, Xiangrong
85341
Shimizu, Natsuki
85342
Yang, Ying
85343
Hayashi, Yuichiro
85344
Oda, Masahiro
85345
Fujiwara, Michitaka
85346
Misawa, Kazunari
85347
Mori, Kensaku
85348
Fully convolutional networks
Deep learning
Medical imaging
Computed tomography
Multi-organ segmentation
Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures (ranging from the large organs to thin vessels) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models. To this end, we propose a two-stage, coarse-to-fine approach that will first use a 3D FCN to roughly define a candidate region, which will then be used as input to a second 3D FCN. This reduces the number of voxels the second FCN has to classify to ∼10% and allows it to focus on more detailed segmentation of the organs and vessels. We utilize training and validation sets consisting of 331 clinical CT images and test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans, targeting three anatomical organs (liver, spleen, and pancreas). In challenging organs such as the pancreas, our cascaded approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset. We compare with a 2D FCN method on a separate dataset of 240 CT scans with 18 classes and achieve a significantly higher performance in small organs and vessels. Furthermore, we explore fine-tuning our models to different datasets. Our experiments illustrate the promise and robustness of current 3D FCN based semantic segmentation of medical images, achieving state-of-the-art results.
ファイル公開:2019-06-01
journal article
Elsevier
2018-06
application/pdf
Computerized Medical Imaging and Graphics
66
90
99
0895-6111
https://nagoya.repo.nii.ac.jp/record/26376/files/cmig2018_rothhr_cascaded_fcn_final.pdf
eng
https://doi.org/10.1016/j.compmedimag.2018.03.001
© 2018. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/