《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (10): 3282-3289.DOI: 10.11772/j.issn.1001-9081.2022101545
所属专题: 多媒体计算与计算机仿真
收稿日期:
2022-10-14
修回日期:
2023-02-06
接受日期:
2023-02-08
发布日期:
2023-04-12
出版日期:
2023-10-10
通讯作者:
徐杨
作者简介:
卢小燕(1997—),女,河南南阳人,硕士研究生,主要研究方向:深度学习、图像处理基金资助:
Xiaoyan LU1, Yang XU1,2(), Wenhao YUAN1
Received:
2022-10-14
Revised:
2023-02-06
Accepted:
2023-02-08
Online:
2023-04-12
Published:
2023-10-10
Contact:
Yang XU
About author:
LU Xiaoyan, born in 1997, M. S. candidate. Her research interests include deep learning, image processing.Supported by:
摘要:
针对主流的深度学习网络难以完整分割肺部病灶、区域边界预测模糊的问题,提出一种基于U-Net的多尺度稠密融合网络(MDF-Net)。首先,引入多分支密集跳层连接以捕获多级上下文信息,并在网络末端引入信息加权融合(IWF)模块进行逐级融合,以解决网络中的特征损失问题;其次,设计一种自注意力金字塔模块,使用各金字塔层对特征图进行不同规模的切分处理,并使用自注意力机制计算像素关联度,从而增强局部与全局区域的感染特征显著性;最后,设计一种区别于传统U-Net的上采样模式的上采样残差(UR)模块,多分支的残差结构与通道特征激励使网络能够还原更加丰富的微小病灶特征。在两个公开数据集上的实验结果显示,与UNeXt相比,所提网络的准确度(ACC)分别提升了1.5%和1.4%,平均交并比(MIoU)分别提升了3.9%和1.9%,实验结果验证了MDF-Net具有更好的肺部病灶分割性能。
中图分类号:
卢小燕, 徐杨, 袁文昊. 用于肺部病灶图像分割的多尺度稠密融合网络[J]. 计算机应用, 2023, 43(10): 3282-3289.
Xiaoyan LU, Yang XU, Wenhao YUAN. Multiscale dense fusion network for lung lesion image segmentation[J]. Journal of Computer Applications, 2023, 43(10): 3282-3289.
数据集 | 网络 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | SegNet | 73.7 | 69.8 | 61.3 | 53.6 |
R2U-Net | 77.1 | 71.0 | 62.5 | 57.8 | |
Attention U-Net | 79.9 | 73.3 | 64.1 | 60.5 | |
U2-Net | 81.2 | 75.9 | 67.6 | 63.9 | |
CaraNet | 81.7 | 76.5 | 68.3 | 65.2 | |
UNeXt | 82.4 | 79.2 | 70.5 | 68.6 | |
MDF-Net | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | SegNet | 85.6 | 75.9 | 66.2 | 57.1 |
R2U-Net | 87.3 | 82.6 | 72.3 | 68.3 | |
Attention U-Net | 88.9 | 83.5 | 74.7 | 70.5 | |
U2-Net | 89.4 | 84.3 | 75.1 | 72.4 | |
CaraNet | 89.6 | 86.4 | 76.5 | 72.9 | |
UNeXt | 91.8 | 89.5 | 78.8 | 73.7 | |
MDF-Net | 93.1 | 91.2 | 79.9 | 75.2 |
表1 不同网络在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 1 Performance comparison of different networks on Lung dataset-1 and Lung dataset-2
数据集 | 网络 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | SegNet | 73.7 | 69.8 | 61.3 | 53.6 |
R2U-Net | 77.1 | 71.0 | 62.5 | 57.8 | |
Attention U-Net | 79.9 | 73.3 | 64.1 | 60.5 | |
U2-Net | 81.2 | 75.9 | 67.6 | 63.9 | |
CaraNet | 81.7 | 76.5 | 68.3 | 65.2 | |
UNeXt | 82.4 | 79.2 | 70.5 | 68.6 | |
MDF-Net | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | SegNet | 85.6 | 75.9 | 66.2 | 57.1 |
R2U-Net | 87.3 | 82.6 | 72.3 | 68.3 | |
Attention U-Net | 88.9 | 83.5 | 74.7 | 70.5 | |
U2-Net | 89.4 | 84.3 | 75.1 | 72.4 | |
CaraNet | 89.6 | 86.4 | 76.5 | 72.9 | |
UNeXt | 91.8 | 89.5 | 78.8 | 73.7 | |
MDF-Net | 93.1 | 91.2 | 79.9 | 75.2 |
数据集 | 模块 | ACC | MIoU | DSC | F1 | ||||
---|---|---|---|---|---|---|---|---|---|
基础网络 | UR | M1 | M2 | IWF | |||||
Lung dataset-1 | √ | 74.7 | 74.1 | 67.2 | 67.4 | ||||
√ | √ | 75.6 | 75.2 | 68.9 | 68.2 | ||||
√ | √ | 77.2 | 76.1 | 70.5 | 68.4 | ||||
√ | √ | √ | √ | 79.9 | 78.2 | 71.3 | 69.5 | ||
√ | √ | √ | √ | √ | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-1 | √ | 84.9 | 82.3 | 72.5 | 72.8 | ||||
√ | √ | 85.6 | 83.5 | 74.4 | 73.5 | ||||
√ | √ | 86.1 | 84.9 | 76.7 | 73.6 | ||||
√ | √ | √ | √ | 89.7 | 87.3 | 78.2 | 74.1 | ||
√ | √ | √ | √ | √ | 93.1 | 91.2 | 79.9 | 75.2 |
表2 不同模块在Lung dataset-1和Lung dataset-2上对网络性能的影响 (%)
Tab. 2 Influence of different modules on network performance on Lung dataset-1 and Lung dataset-2
数据集 | 模块 | ACC | MIoU | DSC | F1 | ||||
---|---|---|---|---|---|---|---|---|---|
基础网络 | UR | M1 | M2 | IWF | |||||
Lung dataset-1 | √ | 74.7 | 74.1 | 67.2 | 67.4 | ||||
√ | √ | 75.6 | 75.2 | 68.9 | 68.2 | ||||
√ | √ | 77.2 | 76.1 | 70.5 | 68.4 | ||||
√ | √ | √ | √ | 79.9 | 78.2 | 71.3 | 69.5 | ||
√ | √ | √ | √ | √ | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-1 | √ | 84.9 | 82.3 | 72.5 | 72.8 | ||||
√ | √ | 85.6 | 83.5 | 74.4 | 73.5 | ||||
√ | √ | 86.1 | 84.9 | 76.7 | 73.6 | ||||
√ | √ | √ | √ | 89.7 | 87.3 | 78.2 | 74.1 | ||
√ | √ | √ | √ | √ | 93.1 | 91.2 | 79.9 | 75.2 |
数据集 | 采样方式 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | upsampling | 74.7 | 74.1 | 67.2 | 67.4 |
UR | 75.6 | 75.2 | 68.9 | 68.2 | |
Lung dataset-2 | upsampling | 84.9 | 82.3 | 72.5 | 72.8 |
UR | 85.6 | 83.5 | 74.4 | 73.5 |
表3 不同上采样方式在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 3 Performance comparison of different upsampling methods on Lung dataset-1 and Lung dataset-2
数据集 | 采样方式 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | upsampling | 74.7 | 74.1 | 67.2 | 67.4 |
UR | 75.6 | 75.2 | 68.9 | 68.2 | |
Lung dataset-2 | upsampling | 84.9 | 82.3 | 72.5 | 72.8 |
UR | 85.6 | 83.5 | 74.4 | 73.5 |
数据集 | UR模块组成 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 74.7 | 74.1 | 67.2 | 67.4 |
M3 | 75.2 | 74.8 | 68.4 | 67.9 | |
M4 | 74.9 | 74.5 | 67.7 | 67.6 | |
UR | 75.6 | 75.2 | 68.9 | 68.2 | |
Lung dataset-2 | 无 | 84.9 | 82.3 | 72.5 | 72.8 |
M3 | 85.3 | 83.1 | 73.8 | 73.3 | |
M4 | 85.1 | 82.6 | 73.2 | 73.0 | |
UR | 85.6 | 83.5 | 74.4 | 73.5 |
表4 UR模块不同组成部分在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 4 Performance comparison of different components of UR module on Lung dataset-1 and Lung dataset-2
数据集 | UR模块组成 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 74.7 | 74.1 | 67.2 | 67.4 |
M3 | 75.2 | 74.8 | 68.4 | 67.9 | |
M4 | 74.9 | 74.5 | 67.7 | 67.6 | |
UR | 75.6 | 75.2 | 68.9 | 68.2 | |
Lung dataset-2 | 无 | 84.9 | 82.3 | 72.5 | 72.8 |
M3 | 85.3 | 83.1 | 73.8 | 73.3 | |
M4 | 85.1 | 82.6 | 73.2 | 73.0 | |
UR | 85.6 | 83.5 | 74.4 | 73.5 |
数据集 | 注意力模块 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 74.7 | 74.1 | 67.2 | 67.4 |
SCSE | 74.9 | 74.3 | 67.6 | 67.7 | |
ECA | 74.6 | 73.5 | 66.3 | 59.8 | |
自注意力金字塔模块 | 77.2 | 76.1 | 70.5 | 68.4 | |
Lung dataset-2 | 无 | 84.9 | 82.3 | 72.5 | 72.8 |
SCSE | 85.2 | 84.1 | 75.9 | 72.4 | |
ECA | 84.5 | 81.6 | 71.2 | 62.9 | |
自注意力金字塔模块 | 86.1 | 84.9 | 76.7 | 73.6 |
表5 不同注意力模块在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 5 Performance comparison of different attention modules on Lung dataset-1 and Lung dataset-2
数据集 | 注意力模块 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 74.7 | 74.1 | 67.2 | 67.4 |
SCSE | 74.9 | 74.3 | 67.6 | 67.7 | |
ECA | 74.6 | 73.5 | 66.3 | 59.8 | |
自注意力金字塔模块 | 77.2 | 76.1 | 70.5 | 68.4 | |
Lung dataset-2 | 无 | 84.9 | 82.3 | 72.5 | 72.8 |
SCSE | 85.2 | 84.1 | 75.9 | 72.4 | |
ECA | 84.5 | 81.6 | 71.2 | 62.9 | |
自注意力金字塔模块 | 86.1 | 84.9 | 76.7 | 73.6 |
数据集 | 特征融合模块 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 79.9 | 78.2 | 71.3 | 69.5 |
FFM | 80.3 | 78.8 | 71.6 | 69.8 | |
MAFF | 81.2 | 80.1 | 72.5 | 70.2 | |
IWF | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | 无 | 89.7 | 87.3 | 78.2 | 74.1 |
FFM | 90.6 | 88.5 | 78.6 | 74.3 | |
MAFF | 92.5 | 89.7 | 79.2 | 74.8 | |
IWF | 93.1 | 91.2 | 79.9 | 75.2 |
表6 IWF模块与其他特征融合模块在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 6 Performance comparison of IWF module and other feature fusion modules on Lung dataset-1 and Lung dataset-2
数据集 | 特征融合模块 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | 无 | 79.9 | 78.2 | 71.3 | 69.5 |
FFM | 80.3 | 78.8 | 71.6 | 69.8 | |
MAFF | 81.2 | 80.1 | 72.5 | 70.2 | |
IWF | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | 无 | 89.7 | 87.3 | 78.2 | 74.1 |
FFM | 90.6 | 88.5 | 78.6 | 74.3 | |
MAFF | 92.5 | 89.7 | 79.2 | 74.8 | |
IWF | 93.1 | 91.2 | 79.9 | 75.2 |
数据集 | 网络 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | UNet++ | 80.9 | 79.4 | 70.1 | 66.3 |
MDF-Net | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | UNet++ | 89.1 | 88.7 | 76.9 | 71.4 |
MDF-Net | 93.1 | 91.2 | 79.9 | 75.2 |
表7 两种网络的密集连接方式在Lung dataset-1和Lung dataset-2上的性能对比 (%)
Tab. 7 Performance comparison of dense connection methods of two networks on Lung dataset-1 and Lung dataset-2
数据集 | 网络 | ACC | MIoU | DSC | F1 |
---|---|---|---|---|---|
Lung dataset-1 | UNet++ | 80.9 | 79.4 | 70.1 | 66.3 |
MDF-Net | 83.6 | 82.3 | 73.4 | 70.3 | |
Lung dataset-2 | UNet++ | 89.1 | 88.7 | 76.9 | 71.4 |
MDF-Net | 93.1 | 91.2 | 79.9 | 75.2 |
1 | 陈树越,晁亚,邹凌. 基于几何特征的孤立性肺结节检测[J]. 生物医学工程学杂志, 2016, 33(4):680-685. |
CHEN S Y, CHAO Y, ZOU L. Detection of solitary pulmonary nodules based on geometric features[J]. Journal of Biomedical Engineering, 2016, 33(4): 680-685. | |
2 | LITJENS G, KOOI T, EHTESHAMI BEJNORDI B, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis, 2017, 42: 60-88. 10.1016/j.media.2017.07.005 |
3 | MUNUSAMY H, KARTHIKEYAN J M, SHRIRAM G, et al. FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image Segmentation[J]. Biocybernetics and Biomedical Engineering, 2021, 41(3): 1025-1038. 10.1016/j.bbe.2021.06.011 |
4 | RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer, 2015: 234-241. |
5 | ZHAN X, ZHANG P, SONG F, et al. D2A U-Net: automatic segmentation of COVID-19 CT slices based on dual attention and hybrid dilated convolution[J]. Computers in Biology and Medicine, 2021, 135: No.104526. 10.1016/j.compbiomed.2021.104526 |
6 | WANG B, JIN S, YAN Q, et al. AI-assisted CT imaging analysis for COVID-19 screening: building and deploying a medical AI system[J]. Applied Soft Computing, 2021, 98: No.106897. 10.1016/j.asoc.2020.106897 |
7 | FAN D P, ZHOU T, JI G P, et al. Inf-Net: automatic COVID-19 lung infection segmentation from CT images[J]. IEEE Transactions on Medical Imaging, 2020, 39(8): 2626-2637. 10.1109/tmi.2020.2996645 |
8 | KUMAR SINGH V, ABDEL-NASSER M, PANDEY N, et al. LungINFseg: segmenting COVID-19 infected regions in lung CT images based on a receptive-field-aware deep learning framework[J]. Diagnostics, 2021, 11(2): No.158. 10.3390/diagnostics11020158 |
9 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
10 | FU J, LIU J, TIAN H, et al. Dual attention network for scene segmentation[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 3141-3149. 10.1109/cvpr.2019.00326 |
11 | MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]// Proceedings of the 4th International Conference on 3D Vision. Piscataway: IEEE, 2016: 565-571. 10.1109/3dv.2016.79 |
12 | BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495. 10.1109/tpami.2016.2644615 |
13 | ALOM M Z, YAKOPCIC C, HASAN M, et al. Recurrent residual U-Net for medical image segmentation[J]. Journal of Medical Imaging, 2019, 6(1): No.014006. 10.1117/1.jmi.6.1.014006 |
14 | OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL]. (2018-03-20) [2022-08-15].. |
15 | QIN X, ZHANG Z, HUANG C, et al. U2-Net: going deeper with nested U-structure for salient object detection[J]. Pattern Recognition, 2020, 106: No.107404. 10.1016/j.patcog.2020.107404 |
16 | LOU A, GUAN S, KO H, et al. CaraNet: context axial reverse attention network for segmentation of small medical objects[C]// Proceedings of the SPIE 12032, Medical Imaging 2022: Image Processing. Bellingham, WA: SPIE, 2022: No.120320D. 10.1117/12.2611802 |
17 | VALANARASU J M J, PATEL V M. UNeXt: MLP-based rapid medical image segmentation network[C]// Proceedings of the 2022 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 13435. Cham: Springer, 2022: 23-33. |
18 | ROY A G, NAVAB N, WACINGER C. Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks[C]// Proceedings of the 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 11070. Cham: Springer, 2018: 421-429. |
19 | WANG Q, WU B, ZHU P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020:11531-11539. 10.1109/cvpr42600.2020.01155 |
20 | 傅双杰,陈玮,尹钟. 结合自注意力和特征自适应融合的语义分割算法[J]. 信息与控制, 2022, 51(6):680-687, 698. |
FU S J, CHEN W, YIN Z. Semantic segmentation algorithm combining self-attention and feature adaptive fusion[J]. Information and Control, 2022, 51(6):680-687, 698. | |
21 | 梁礼明,詹涛,雷坤,等. 多级自适应尺度的U型视网膜血管分割算法[J]. 电子测量技术, 2022, 45(13):130-140. |
LIANG L M, ZHAN T, LEI K, et al. Multi-level adaptive scale U-shaped retinal blood vessel segmentation algorithm[J]. Electronic Measurement Technology, 2022, 45(13):130-140. | |
22 | ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]// Proceedings of the 2018 International Workshop on Deep Learning in Medical Image Analysis/ International Workshop on Multimodal Learning for Clinical Decision Support, LNCS 11045. Cham: Springer, 2018: 3-11. 10.1007/978-3-030-00889-5_1 |
[1] | 沈嫣然, 温昕, 张瑾昊, 张帅, 曹锐, 高保禄. 轻量级多尺度卷积网络的功能磁共振成像脑龄预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3949-3957. |
[2] | 蒋权 黄文清 苟志勇. 基于等变图神经网络的拉格朗日粒子流模拟[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[3] | 李岚皓 严皓钧 周号益 孙庆赟 李建欣. 基于神经网络的多尺度信息融合时间序列长期预测模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[4] | 陈丹阳 张长伦. 多尺度去相关的图卷积网络[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[5] | 蒋沛宇 王永光 任亚亭 李硕晨 谭火彬. 基于测量不确定度表示指南的目标检测不确定度测量方案[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[6] | 胡能兵, 蔡彪, 李旭, 曹旦华. 基于图池化对比学习的图分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3327-3334. |
[7] | 林滏, 石稼晟, 高泽, 楚遵康, 马琼敏, 余海燕, 饶卫雄. 基于3D几何特征深度表达学习的物理系统仿真[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3548-3555. |
[8] | 范艺扬, 张洋, 曾尚, 曾渝, 付茂栗. 基于分解和频域特征提取的多变量长时间序列预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3442-3448. |
[9] | 刘文博, 于连飞, 谢冬梅, 蔡闯, 曲志坚, 任崇广. 基于多尺度特征融合的时间序列长期预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3435-3441. |
[10] | 王芳 胡静 张睿 范文婷. 内容引导下多角度特征融合医学图像分割网络[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[11] | 王翔 陈志祥 毛国君. 融合局部和全局相关性的多变量时间序列预测方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
[12] | 蒋汶娟, 过弋, 付娇娇. 融合图注意力的复杂时序知识图谱推理问答模型[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3047-3057. |
[13] | 黄华, 杨子仪, 李小龙, 李闯. 基于概念漂移的预测性业务流程监控方法[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3167-3176. |
[14] | 张睿, 潘俊铭, 白晓露, 胡静, 张荣国, 张鹏云. 面向深度分类模型超参数自优化的代理模型[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3021-3031. |
[15] | 陈满 杨小军 杨慧敏. 基于图卷积网络和终点诱导的行人轨迹预测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||