Automatic liver tumor segmentation using multi-scale features and reverse attention

ZHANG Rui; TANG Qiaozhan; LI Sihui; SONG Jiangling

doi:10.16152/j.cnki.xdxbzr.2023-06-007

您当前的位置：

首页 >

文章列表页 >

Automatic liver tumor segmentation using multi-scale features and reverse attention

更新时间：2024-01-03

- Automatic liver tumor segmentation using multi-scale features and reverse attention
- Journal of Northwest University (Natural Science Edition) Vol. 53, Issue 6, Pages: 964-973(2023)
- 作者机构：
  
  西北大学　医学大数据研究中心，陕西　西安　710127
- 作者简介：
- 基金信息：
- DOI：10.16152/j.cnki.xdxbzr.2023-06-007
  CLC：
扫描看全文
ZHANG Rui, TANG Qiaozhan, LI Sihui, et al. Automatic liver tumor segmentation using multi-scale features and reverse attention. [J]. Journal of Northwest University (Natural Science Edition) 53(6):964-973(2023)
DOI：

ZHANG Rui, TANG Qiaozhan, LI Sihui, et al. Automatic liver tumor segmentation using multi-scale features and reverse attention. [J]. Journal of Northwest University (Natural Science Edition) 53(6):964-973(2023) DOI： 10.16152/j.cnki.xdxbzr.2023-06-007.

摘要

肝脏肿瘤分割旨在定位肝脏肿瘤区域，以辅助医生进行精准诊治。鉴于深度学习能自动学习医学图像中复杂的特征和结构，已成为肝脏肿瘤分割的主流方法之一。但肝脏肿瘤的大小、形态存在显著差异及边缘模糊等问题，限制了深度学习模型的分割性能。基于此，该文提出了一种融合多尺度特征和反向注意力机制的深度网络，并用于肝脏肿瘤的自动分割。具体地，基于U-Net模型的框架，分别设计了多尺度特征提取模块和基于深度监督的反向注意力模块，使得网络能根据分割目标的大小自适应地选择不同尺度的特征，并引导网络关注分割目标的边缘特征，进而提高网络的边缘分割能力。此外，设计了一种新的混合损失，以解决医学图像分割中的类别不平衡问题。最后，在MICCAI2017 LiTS挑战赛数据集的数值实验结果表明，所提方法的Dice系数、平均对称表面距离ASSD分别为76.12%和3.25 mm。

Abstract

The objective of liver tumor segmentation is to pinpoint the region containing the liver tumor, aiding medical professionals in delivering precise diagnosis and treatment. Owing to its capacity to automatically learn intricate features and structures from medical images, deep learning has emerged as one of the mainstream approaches to liver tumor segmentation. Nonetheless, the size, shape, and blurred edges of liver tumor exhibit significant variations, which constrain the segmentation performance of deep learning models. Consequently, we introduce a deep network that incorporates multi-scale features and a reverse attention mechanism for the automatic segmentation of liver tumor. Specifically, drawing upon the U-Net model framework, this study designs a multi-scale feature extraction module and a reverse attention module based on deep supervision. This enables the network to adaptively select features of varying scales according to the size of the segmented target and direct the network’s attention towards the edge features of the segmented object, thereby enhancing the network’s edge segmentation capability. Furthermore, a novel hybrid loss is devised to address the issue of class imbalance in medical image segmentation.The recent numerical experiments conducted on the MICCAI2017 LiTS Challenge dataset have demonstrated that the proposed method achieves a Dice coefficient of 76.12% and an average symmetric surface distance (ASSD) of 3.25 mm.

关键词

肝脏肿瘤分割多尺度特征提取反向注意力

Keywords

liver tumor segmentationmulti-scale feature extractionreverse attention

references

曹毛毛, 李贺, 孙殿钦, 等. 全球肝癌2020年流行病学现状[J]. 中华肿瘤防治杂志, 2022, 29(5): 322-328.

CAO M M, LI H, SUN D Q, et al. Global epidemiology of liver cancer in 2020 [J]. Chinese Journal of Cancer Prevention and Treatment, 2022, 29(5): 322-328.

夏永祥, 张峰, 李相成, 等. 原发性肝癌10 966例外科治疗分析[J]. 中华外科杂志, 2021, 59(1): 6-17.

XIA Y X, ZHANG F, LI X C, et al. Surgical treatment of primary liver cnacer: A report of 10 966 cases [J]. Chinese Journal of Surgery, 2021, 59(1): 6-17.

郑永昌, 毛一雷. 早诊早治，提高我国肝癌5年生存率[J]. 肝胆胰外科杂志, 2022, 34(6): 321-324.

ZHENG Y C, MAO Y L. Improve the 5-year survival rate of hepatocellular carcinoma in China via early diagnosis and treatment [J]. Journal of Hepatopancreatobiliary Surgery, 2022, 34(6): 321-324.

QURESHI I, YAN J, ABBAS Q, et al. Medical image segmentation using deep semantic-based methods: A review of techniques, applications and emerging trends[J]. Information Fusion, 2023, 90: 316-352.

CIECHOLEWSKI M, OGIELA M R. Automatic segmentation of single and multiple neoplastic hepatic lesions in CT images[C]//International Work-conference on the Interplay between Natural and Artificial Computation. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007: 63-71.

YANG X P, DO YANG J, HWANG H P, et al. Segmentation of liver and vessels from CT images and classification of liver segments for preoperative liver surgical planning in living donor liver transplantation[J]. Computer Methods and Programs in Biomedicine, 2018, 158: 41-52.

宋红, 王勇, 黄小川, 等. 基于动态自适应区域生长的肝脏CT图像肿瘤分割算法[J]. 北京理工大学学报, 2014, 34(1): 72-76.

SONG H, WANG Y, HUANG X C, et al. A dynamic adaptive region growing segmentation algorithm for tumor of liver CT images [J]. Transactions of Beijing Institute of Technology, 2014, 34(1): 72-76.

MASSOPTIER L, CASCIARO S. A new fully automatic and robust algorithm for fast segmentation of liver tissue and tumors from CT scans[J]. European Radiology, 2008, 18(8): 1658-1665.

VORONTSOV E, ABI-JAOUDEH N, KADOURY S. Metastatic liver tumor segmentation using texture-based omni-directional deformable surface models[C]//Abdominal Imaging. Computational and Clinical Applications: 6th International Workshop, ABDI 2014. Cambridge, MA, USA: Springer International Publishing, 2014: 74-83.

LI Y, HARA S, SHIMURA K. A machine learning approach for locating boundaries of liver tumors in CT images[C]//18th International Conference on Pattern Recognition (ICPR’06). Hong Kong, China: IEEE, 2006, 1: 400-403.

LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE, 2015: 3431-3440.

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention. MICCAI 2015: 18th International Conference. Munich, Germany: Springer International Publishing, 2015: 234-241.

LI X, CHEN H, QI X, et al. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes[J]. IEEE Transactions on Medical Imaging, 2018, 37(12): 2663-2674.

ZHOU Z, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: Redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Transactions on Medical Imaging, 2020, 39(6): 1856-1867.

LV P, WANG J, WANG H. 2.5 D lightweight RIU-Net for automatic liver and tumor segmentation from CT[J]. Biomedical Signal Processing and Control, 2022, 75: 103567.

CHEN Y, ZHENG C, ZHANG W, et al. MS-FANet: Multi-scale feature attention network for liver tumor segmentation[J]. Computers in Biology and Medicine, 2023, 163: 107208.

GAO S H, CHENG M M, ZHAO K, et al. Res2Net: A new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662.

LI B, XIAO C, WANG L, et al. Dense nested attention network for infrared small target detection[J]. IEEE Transactions on Image Processing, 2022, 32: 1745-1758.

WANG K, ZHANG X, ZHANG X, et al. EANet: Iterative edge attention network for medical image segmentation[J]. Pattern Recognition, 2022, 127: 108636.

FU Z, ZHANG R. ω-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution[J]. Neurocomputing, 2022, 500: 177-190.

CHEN S, TAN X, WANG B, et al. Reverse attention for salient object detection[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 234-250.

LOU A, GUAN S, LOEW M. Caranet: Context axial reverse attention network for segmentation of small medical objects[J]. Journal of Medical Imaging, 2023, 10(1): 014005-014005.

DI S, ZHAO Y Q, LIAO M, et al. TD-Net: A hybrid end-to-end network for automatic liver tumor segmentation from CT images[J]. IEEE Journal of Biomedical and Health Informatics, 2023, 27(3): 1163-1172.

GAO H, LYU M, ZHAO X, et al. Contour-aware network with class-wise convolutions for 3D abdominal multi-organ segmentation[J]. Medical Image Analysis, 2023, 87: 102838.

ZHOU Z, BIAN Y, PAN S, et al. A dual branch and fine-grained enhancement network for pancreatic tumor segmentation in contrast enhanced CT images[J]. Biomedical Signal Processing and Control, 2023, 82: 104516.

SUDRE C H, LI W, VERCAUTEREN T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017. Quebec City, Canada: Springer International Publishing, 2017: 240-248.

SALEHI S S M, ERDOGMUS D, GHOLIPOUR A. Tversky loss function for image segmentation using 3D fully convolutional deep networks[C]//International Workshop on Machine Learning in Medical Imaging. Cham: Springer International Publishing, 2017: 379-387.

BILIC P, CHRIST P, LI H B, et al. The liver tumor segmentation benchmark (lits)[J]. Medical Image Analysis, 2023, 84: 102680.

MILLETARI F, NAVAB N, AHMADI S A. V-net: Fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3D Vision (3DV). Stanford, CA, USA: IEEE, 2016: 565-571.

JACCARD P. Étude comparative de la distribution florale dans une portion des Alpes et des Jura[J]. Bull Soc Vaudoise Sci Nat, 1901, 37: 547-579.

HEIMANN T, VAN GINNEKEN B, STYNER M A, et al. Comparison and evaluation of methods for liver segmentation from CT datasets[J]. IEEE Transactions on Medical Imaging, 2009, 28(8): 1251-1265.

HUTTENLOCHER D P, KLANDERMAN G A, RUCKLIDGE W J. Comparing images using the Hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850-863.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰