U-Net 变体在鼻咽癌肿瘤分割中的应用回顾

丁 宇欣
浙江中医药大学

摘要

鼻咽癌 (NPC) 是头颈部最常见的恶性肿瘤之一。U-Net 因其灵活性、优化的模块化设计以及在所有医学图像模式
中的成功而成为最广泛使用的图像分割架构。本文首先介绍了当前鼻咽癌现状和 U-Net 的工作原理，然后，根据时间线回
顾了 U-Net 及其变体在鼻咽癌肿瘤分割中的应用进展。最后，本文讨论了当前研究的不足以及 U-net 应用于鼻咽癌的未
来发展方向，并提出了一些建议。

关键词

U-Net；鼻咽癌；图像分割；深度学习

参考

[1] 吴伯恒 , 曹鸿斌 , 马永康等 . 基于多模态图像深度

学习局部晚期鼻咽癌肿瘤靶体积自动勾画的研究 [J]. 肿瘤 ,

2024, 43:1-10.

[2] Lee A W M, Ng W T, Chan L L K, et al. Evolution of

treatment for nasopharyngeal cancer–success and setback in

the intensity-modulated radiotherapy era[J]. Radiotherapy and

Oncology, 2014, 110(3): 377-384.

[3] 苏晓红 , 金观桥 . 基于 MRI 的深度学习在鼻咽癌中

的研究进展 [J]. 磁共振成像 ,2023,14(03):170-174+188.

[4] Tseng M, Ho F, Leong Y H, et al. Emerging radiotherapy

technologies and trends in nasopharyngeal cancer[J]. Cancer

Communications, 2020, 40(9): 395-405.

[5] Anwar S M, Majid M, Qayyum A, et al. Medical image

analysis using convolutional neural networks: a review[J]. Journal

of medical systems, 2018, 42: 1-13.

[6] 郗玉珍 , 周敏 , 丁忠祥 . 影像人工智能在鼻咽癌诊

疗中的应用 [J]. 临床放射学杂志 ,2022,41(11):2145-2148.

[7] Azad R, Aghdam E K, Rauland A, et al. Medical image

segmentation review: The success of u-net[J]. arXiv preprint,

2022.

[8] Recht M P, Dewey M, Dreyer K, et al. Integrating

artificial intelligence into the clinical practice of radiology:

challenges and recommendations[J]. European radiology, 2020,

30: 3576-3584.

[9] 李佳燨 , 刘红英 , 万亮 . 基于深度学习的医学图像

分析域自适应研究综述 [J/OL]. 计算机应用研究 , 2024, 1-12.

[10] Lin L, Dou Q, Jin Y M, et al. Deep learning for

automated contouring of primary tumor volumes by MRI for

nasopharyngeal carcinoma[J]. Radiology, 2019, 291(3): 677-686.

[11] Soffer S, Ben-Cohen A, Shimon O, et al. Convolutional

neural networks for radiologic images: a radiologist’s guide[J].

Radiology, 2019, 290(3): 590-606.

[12] Wang Y, Liu C, Zhang X, et al. Synthetic CT generation

based on T2 weighted MRI of nasopharyngeal carcinoma (NPC)

using a deep convolutional neural network (DCNN)[J]. Frontiers in

oncology, 2019, 9: 1333.

[13] Xue X, Qin N, Hao X, et al. Sequential and iterative

auto-segmentation of high-risk clinical target volume for

radiotherapy of nasopharyngeal carcinoma in planning CT

images[J]. Frontiers in oncology, 2020, 10: 1134.

[14] Bai X, Hu Y, Gong G, et al. A deep learning approach

to segmentation of nasopharyngeal carcinoma using computed

tomography[J]. Biomedical Signal Processing and Control, 2021,

64: 102246.

[15] Liu Y, Yuan X, Jiang X, et al. Dilated Adversarial

U-Net Network for automatic gross tumor volume segmentation of

nasopharyngeal carcinoma[J]. Applied Soft Computing, 2021, 111:

107722.

[16] Mei H, Lei W, Gu R, et al. Automatic segmentation

of gross target volume of nasopharynx cancer using ensemble

of multiscale deep neural networks with spatial attention[J].

Neurocomputing, 2021, 438: 211-222.

[17] Zhang J, Gu L, Han G, et al. AttR2U-Net: A fully

automated model for MRI nasopharyngeal carcinoma segmentation

based on spatial attention and residual recurrent convolution[J].

Frontiers in Oncology, 2022, 11: 816672.

[18] Hao Y, Jiang H, Diao Z, et al. MSU-Net: Multi-scale

Sensitive U-Net based on pixel-edge-region level collaborative

loss for nasopharyngeal MRI segmentation[J]. Computers in

Biology and Medicine, 2023, 159: 106956.

[19] Zeng Y, Zeng P H, Shen S D, et al. DCTR U-Net:

automatic segmentation algorithm for medical images of

nasopharyngeal cancer in the context of deep learning[J]. Frontiers

in Oncology, 2023, 13.

[20] 崔珂 , 田启川 , 廉露 . 基于 U-Net 变体的医学图像

分割算法综述 [J/OL]. 计算机工程与应用 , 2024, 1-18.