Abstract
Accurate segmentation ofs organs-at-risk (OARs) in computed tomography (CT) is the key to planning treatment in radiation therapy (RT). Manually delineating OARs over hundreds of images of a typical CT scan can be time-consuming and error-prone. Deep convolutional neural networks with specific structures like U-Net have been proven effective for medical image segmentation. In this work, we propose an end-to-end deep neural network for multiorgan segmentation with higher accuracy and lower complexity. Compared with several state-of-the-art methods, the proposed accuracy-complexity adjustment module (ACAM) can increase segmentation accuracy and reduce the model complexity and memory usage simultaneously. An attention-based multiscale aggregation module (MAM) is also proposed for further improvement. Experiment results on chest CT datasets show that the proposed network achieves competitive Dice similarity coefficient results with fewer float-point operations (FLOPs) for multiple organs, which outperforms several state-of-the-art methods.
Highlights
Radiation therapy is the main clinical method of treating various cancers [30]
Our contributions are summarized as follows: (i) We introduce an accuracy-complexity adjustment module throughout the encoder and decoder to increase the segmentation accuracy and reduce the model complexity and memory usage simultaneously (ii) We present an attention-based multiscale aggregation module after the encoder to enrich feature representation for further boosting the segmentation accuracy (iii) The proposed network achieves competitive results, which outperform several state-of-the-art methods on chest computed tomography (CT) segmentation datasets
An in-house dataset was used to evaluate the proposed method, which is provided by the Institute of Cancer and Basic Medicine (ICBM), Chinese Academy of Sciences, and Cancer Hospital of the University of Chinese Academy of Sciences
Summary
Radiation therapy is the main clinical method of treating various cancers [30]. It can be seen as a trade-off between sending maximum dose to the target-volume (TV) and minimum dose to the OARs [1, 31]. Oktay et al [5] proposed an attention gate in the skip connection layer of the U-Net to teach the decoder where to “look.” Selective Kernel [13] (SK) took advantage of the attention to guide the fusion of multiscale information It embeds multiple lightweight SE [14] attentions to dynamically select the receptive field size of each neuron in convolutional layers, which is consistent with the neuroscience cognition that the visual cortical neuron adaptively adjusts the size of its receptive field according to stimulus. (i) We introduce an accuracy-complexity adjustment module throughout the encoder and decoder to increase the segmentation accuracy and reduce the model complexity and memory usage simultaneously (ii) We present an attention-based multiscale aggregation module after the encoder to enrich feature representation for further boosting the segmentation accuracy (iii) The proposed network achieves competitive results, which outperform several state-of-the-art methods on chest CT segmentation datasets.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
