Medical image segmentation network with content-guided multi-angle feature fusion

doi:10.11772/j.issn.1001-9081.2024081188

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 3017-3025.DOI: 10.11772/j.issn.1001-9081.2024081188

• Multimedia computing and computer simulation • Previous Articles

Medical image segmentation network with content-guided multi-angle feature fusion

Fang WANG, Jing HU(), Rui ZHANG, Wenting FAN

College of Computer Science and Technology，Taiyuan University of Science and Technology，Taiyuan Shanxi 030024，China

Received:2024-08-21 Revised:2024-10-14 Accepted:2024-10-21 Online:2024-11-07 Published:2025-09-10
Contact: Jing HU
About author:WANG Fang， born in 1989， M. S.， lecturer. Her research interests include graphic and image processing， deep learning.
ZHANG Rui， born in 1987， Ph. D.， associate professor. His research interests include intelligent information processing.
FAN Wenting， born in 1988， M. S.， lecturer. Her research interests include natural language processing， computer vision.
Supported by:
Natural Science Foundation of Shanxi Province(20210302123216)

内容引导下多角度特征融合医学图像分割网络

王芳, 胡静(), 张睿, 范文婷

太原科技大学计算机科学与技术学院，太原 030024

通讯作者: 胡静
作者简介:王芳（1989—），女，山西太原人，讲师，硕士，主要研究方向：图形图像处理、深度学习
张睿（1987—），男，山西太原人，副教授，博士，CCF会员，主要研究方向：智能信息处理
范文婷（1988—），女，山西朔州人，讲师，硕士，主要研究方向：自然语言处理、计算机视觉。
基金资助:
山西省自然科学基金资助项目(20210302123216)

Abstract

Abstract:

In view of the lack of traditional image segmentation algorithms to guide Convolutional Neural Network （CNN） for segmentation in the current field of medical image segmentation， a medical image segmentation Network with Content-Guided Multi-Angle Feature Fusion （CGMAFF-Net） was proposed. Firstly， grayscale images and Otsu threshold segmentation images were used to generate lesion region guidance maps through a Transformer-based micro U-shaped feature extraction module， and Adaptive Combination Weighting （ACW） was used to weight them to the original medical images for initial guidance. Then， Residual Network （ResNet） was employed to extract downsampled features from the weighted medical images， and a Multi-Angle Feature Fusion （MAFF） module was used to fuse feature maps at 1/16 and 1/8 scales. Finally， Reverse Attention （RA） was applied to upsample and restore the feature map size gradually， so as to predict key lesion regions. Experimental results on CVC-ClinicDB， Kvasir-SEG， and ISIC 2018 datasets demonstrate that compared to the existing best-performing segmentation multiscale spatial reverse attention network MSRAformer， CGMAFF-Net increases the mean Intersection over Union （mIoU） by 0.97， 0.78， and 0.11 percentage points， respectively； compared to the classic network U-Net， CGMAFF-Net improves the mIoU by 2.66， 8.94， and 1.69 percentage points， respectively， fully verifying the effectiveness and advancement of CGMAFF-Net.

Key words: medical image segmentation, transfer learning, multi-angle feature fusion, adaptive combination weighting, Transformer

摘要：

针对当前医学图像分割领域缺乏使用传统图像分割算法引导卷积神经网络（CNN）进行分割的问题，提出内容引导下多角度特征融合医学图像分割网络（CGMAFF-Net）。首先，利用灰度图以及Otsu阈值分割图像通过基于Transformer的小微U型特征提取模块生成病变区域引导图，并使用自适应组合赋权（ACW）将它们赋权于原始医学图像以进行初始引导；其次，使用残差网络（ResNet）对赋权后的医学图像进行下采样特征提取，并使用多角度特征融合（MAFF）模块对1/16和1/8的特征图进行特征融合；最后，使用反向注意力（RA）上采样并逐步还原特征图的大小，从而实现对关键病变区域的预测。在CVC-ClinicDB、Kvasir-SEG和ISIC 2018数据集上的实验结果表明，与目前分割性能最好的多尺度空间反向注意力网络MSRAformer相比，CGMAFF-Net的平均交并比（mIoU）分别提升了0.97、0.78和0.11个百分点；与经典网络U-Net相比，CGMAFF-Net的mIoU则分别提升了2.66、8.94和1.69个百分点，充分验证了CGMAFF-Net的有效性与先进性。

关键词: 医学图像分割, 迁移学习, 多角度特征融合, 自适应组合赋权, Transformer

CLC Number:

TP183

Fang WANG, Jing HU, Rui ZHANG, Wenting FAN. Medical image segmentation network with content-guided multi-angle feature fusion[J]. Journal of Computer Applications, 2025, 45(9): 3017-3025.

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, 2025, 45(9): 3017-3025.

Figures/Tables 14

References 31

[1]	GITE S， MISHRA A， KOTECHA K. Enhanced lung image segmentation using deep learning ［J］. Neural Computing and Applications， 2023， 35（31）： 22839-22853.
[2]	林荐壮，杨文忠，谭思翔，等. 融合滤波增强和反转注意力网络用于息肉分割［J］. 计算机应用， 2023， 43（1）： 265-272.
	LIN J Z， YANG W Z， TAN S X， et al. Fusing filter enhancement and reverse attention network for polyp segmentation ［J］. Journal of Computer Applications， 2023， 43（1）： 265-272.
[3]	HU B， ZHOU P， YU H， et al. LeaNet： lightweight U-shaped architecture for high-performance skin cancer image segmentation［J］. Computers in Biology and Medicine， 2024， 169： No.107919.
[4]	OTSU N. A threshold selection method from gray-level histograms［J］. IEEE Transactions on Systems， Man， and Cybernetics， 1979， 9（1）： 62-66.
[5]	TIZHOOSH H R. Image thresholding using type Ⅱ fuzzy sets ［J］. Pattern Recognition， 2005， 38（12）： 2363-2372.
[6]	刘少鹏，洪佳明，梁杰鹏，等. 面向医学图像分割的半监督条件生成对抗网络［J］. 软件学报， 2020， 31（8）： 2588-2602.
	LIU S P， HONG J M， LIANG J P， et al. Medical image segmentation using semi-supervised conditional generative adversarial nets ［J］. Journal of Software， 2020， 31（8）： 2588-2602.
[7]	徐蓬泉，梁宇翔，李英. 融合多尺度语义和剩余瓶颈注意力的医学图像分割［J］. 计算机工程， 2023， 49（10）： 162-170.
	XU P Q， LIANG Y X， LI Y. Medical image segmentation fusing multi-scale semantic and residual bottleneck attention ［J］. Computer Engineering， 2023， 49（10）：162-170.
[8]	HE K， ZHANG X， REN S， et al. Deep residual learning for image recognition ［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 770-778.
[9]	BASAK H， KUNDU R， SARKAR R. MFSNet： a multi focus segmentation network for skin lesion segmentation ［J］. Pattern Recognition， 2022， 128： No.108673.
[10]	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.
[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.
[12]	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/ 2018 International Workshop on Multimodal Learning for Clinical Decision Support， LNCS 11045. Cham： Springer， 2018： 3-11.
[13]	WU J， FU R， FANG H， et al. MedSegDiff： medical image segmentation with diffusion probabilistic model ［C］// Proceedings of the 2024 International Conference on Medical Imaging with Deep Learning. New York： JMLR.org， 2024： 1623-1639.
[14]	LI Z， LI Y， LI Q， et al. LViT： language meets Vision Transformer in medical image segmentation ［J］. IEEE Transactions on Medical Imaging， 2023， 43（1）： 96-107.
[15]	YUAN F， ZHANG Z， FANG Z. An effective CNN and Transformer complementary network for medical image segmentation ［J］. Pattern Recognition， 2023， 136： No.109228.
[16]	HOORALI F， KHOSRAVI H， MORADI B. IRUNet for medical image segmentation ［J］. Expert Systems with Applications， 2022， 191： No.116399.
[17]	QI Y， HU C， ZUO L， et al. Cardiac magnetic resonance image segmentation method based on multi-scale feature fusion and sequence relationship learning ［J］. Sensors， 2023， 23（2）： No.690.
[18]	RYU J， REHMAN M U， NIZAMI I F， et al. SegR-Net： a deep learning framework with multi-scale feature fusion for robust retinal vessel segmentation ［J］. Computers in Biology and Medicine， 2023， 163： No.107132.
[19]	ZHANG J， ZHANG Y， JIN Y， et al. MDU-Net： multi-scale densely connected U-Net for biomedical image segmentation ［J］. Health Information Science and Systems， 2023， 11： No.13.
[20]	YIN Y， HAN Z， JIAN M， et al. AMSUnet： a neural network using atrous multi-scale convolution for medical image segmentation ［J］. Computers in Biology and Medicine， 2023， 162： No.107120.
[21]	DING Z， LI H， GUO Y， et al. M⁴FNet： multimodal medical image fusion network via multi-receptive-field and multi-scale feature integration ［J］. Computers in Biology and Medicine， 2023， 159： No.106923.
[22]	REIS H C， TURK V. Transfer learning approach and nucleus segmentation with MedCLNet colon cancer database ［J］. Journal of Digital Imaging， 2023， 36（1）： 306-325.
[23]	TOMAR N K， JHA D， RIEGLER M A， et al. FANet： a feedback attention network for improved biomedical image segmentation ［J］. IEEE Transactions on Neural Networks and Learning Systems， 2023， 34（11）： 9375-9388.
[24]	JHA D， SMEDSRUD P H， RIEGLER M A， et al. ResUNet++： an advanced architecture for medical image segmentation ［C］// Proceedings of the 2019 IEEE International Symposium on Multimedia. Piscataway： IEEE， 2019： 225-230.
[25]	WU C， LONG C， LI S， et al. MSRAformer： multiscale spatial reverse attention network for polyp segmentation ［J］. Computers in Biology and Medicine， 2022， 151（Pt A）： No.106274.
[26]	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）： No.014005.
[27]	XU Q， MA Z， HE N， et al. DCSAU-Net： a deeper and more compact split-attention U-Net for medical image segmentation ［J］. Computers in Biology and Medicine， 2023， 154： No.106626.
[28]	IBTEHAZ N， KIHARA D. ACC-UNet： a completely convolutional UNet model for the 2020s ［C］// Proceedings of the 2023 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 14222. Cham： Springer， 2023： 692-702.
[29]	ZHOU T， ZHOU Y， HE K， et al. Cross-level feature aggregation network for polyp segmentation ［J］. Pattern Recognition， 2023， 140： No.109555.
[30]	HUANG X， DENG Z， LI D， et al. MISSFormer： an effective Transformer for 2D medical image segmentation ［J］. IEEE Transactions on Medical Imaging， 2023， 42（5）： 1484-1494.
[31]	LI Y， YAN B， HOU J， et al. UNet based on dynamic convolution decomposition and triplet attention ［J］. Scientific Reports， 2024， 14： No.271.

数据集	图像大小	样本总数	训练样本数	测试样本数
CVC-ClinicDB	384×288	612	551	61
Kvasir-SEG	变化	1 000	900	100
ISIC 2018	变化	2 594	2 335	259

数据集	图像大小	样本总数	训练样本数	测试样本数
CVC-ClinicDB	384×288	612	551	61
Kvasir-SEG	变化	1 000	900	100
ISIC 2018	变化	2 594	2 335	259

数据集	模型	Recall	Spe	Pre	F1	F2	Acc	mIoU
CVC-ClinicDB	backbone+RA	94.35	99.23	90.46	92.15	93.41	98.93	92.94
	backbone+Up	95.26	99.09	88.07	91.00	93.18	99.01	92.22
	backbone+RA+CGM	95.01	99.37	91.89	93.25	94.25	99.16	93.97
	backbone+RA+MAFF	94.58	99.36	92.61	91.85	92.85	99.12	93.25
	backbone+RA+CGM+MAFF	95.18	99.54	93.84	94.20	94.71	99.29	94.35
Kvasir-SEG	backbone+RA	88.30	98.71	92.83	88.25	88.03	96.12	88.35
	backbone+Up	92.01	97.68	89.45	87.93	89.38	95.99	88.37
	backbone+RA+CGM	91.20	98.36	92.53	90.40	90.63	96.38	89.72
	backbone+RA+MAFF	90.66	98.31	93.19	90.24	90.11	96.41	89.77
	backbone+RA+CGM+MAFF	92.25	98.18	92.96	91.37	91.67	96.89	90.73
ISIC 2018	backbone+RA	90.79	96.50	91.02	89.47	89.74	96.24	88.07
	backbone+Up	94.79	95.42	86.67	89.16	91.80	96.33	87.78
	backbone+RA+CGM	91.81	95.97	90.70	89.78	90.46	96.45	88.36
	backbone+RA+MAFF	91.31	96.53	91.19	89.93	90.43	96.45	88.58
	backbone+RA+CGM+MAFF	91.70	96.81	90.94	89.88	90.31	96.39	88.62

数据集	模型	Recall	Spe	Pre	F1	F2	Acc	mIoU
CVC-ClinicDB	backbone+RA	94.35	99.23	90.46	92.15	93.41	98.93	92.94
	backbone+Up	95.26	99.09	88.07	91.00	93.18	99.01	92.22
	backbone+RA+CGM	95.01	99.37	91.89	93.25	94.25	99.16	93.97
	backbone+RA+MAFF	94.58	99.36	92.61	91.85	92.85	99.12	93.25
	backbone+RA+CGM+MAFF	95.18	99.54	93.84	94.20	94.71	99.29	94.35
Kvasir-SEG	backbone+RA	88.30	98.71	92.83	88.25	88.03	96.12	88.35
	backbone+Up	92.01	97.68	89.45	87.93	89.38	95.99	88.37
	backbone+RA+CGM	91.20	98.36	92.53	90.40	90.63	96.38	89.72
	backbone+RA+MAFF	90.66	98.31	93.19	90.24	90.11	96.41	89.77
	backbone+RA+CGM+MAFF	92.25	98.18	92.96	91.37	91.67	96.89	90.73
ISIC 2018	backbone+RA	90.79	96.50	91.02	89.47	89.74	96.24	88.07
	backbone+Up	94.79	95.42	86.67	89.16	91.80	96.33	87.78
	backbone+RA+CGM	91.81	95.97	90.70	89.78	90.46	96.45	88.36
	backbone+RA+MAFF	91.31	96.53	91.19	89.93	90.43	96.45	88.58
	backbone+RA+CGM+MAFF	91.70	96.81	90.94	89.88	90.31	96.39	88.62

模型	Recall	Spe	Pre	F1	F2	Acc	mIoU
U-Net	92.19	99.27	89.94	90.61	91.45	98.80	91.69
UNet++	88.88	99.45	91.96	89.18	88.92	98.69	91.04
ResUNet++	80.94	98.94	84.53	79.39	80.04	97.96	84.41
MSRAformer	96.01	99.13	91.40	92.96	94.25	98.93	93.38
CaraNet	92.51	99.56	94.40	92.17	92.30	99.23	93.24
DCSAU-Net	81.39	99.25	89.34	82.52	81.66	98.08	86.41
ACC-UNet	78.54	98.56	80.08	75.98	77.20	97.15	82.04
CFANet	82.51	98.38	83.93	79.40	80.37	97.46	83.77
MISSFormer	90.89	99.31	91.85	90.43	90.57	98.88	91.40
DTA-UNet	91.06	99.37	92.67	90.34	90.53	98.88	91.62
CGMAFF-Net	95.18	99.54	93.84	94.20	94.71	99.29	94.35

Medical image segmentation network with content-guided multi-angle feature fusion

内容引导下多角度特征融合医学图像分割网络

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 31

Related Articles 15

Recommended Articles

Metrics

模型	Recall	Spe	Pre	F1	F2	Acc	mIoU
U-Net	80.75	97.91	86.29	79.01	79.54	93.66	81.79
UNet++	82.49	98.22	88.60	81.41	81.48	94.02	82.93
ResUNet++	65.77	97.01	74.55	63.23	63.48	90.58	71.27
MSRAformer	92.34	98.35	89.20	89.46	90.71	97.22	89.95
CaraNet	90.38	98.07	90.46	87.89	88.99	96.08	88.15
DCSAU-Net	67.73	97.57	80.87	68.15	67.18	91.85	74.41
ACC-UNet	63.50	95.83	75.03	60.82	60.89	89.55	69.25
CFANet	69.05	96.19	78.10	65.47	66.11	91.21	72.32
MISSFormer	86.48	97.10	83.27	82.14	83.42	94.81	83.51
DTA-UNet	87.45	97.62	88.37	84.84	85.48	95.13	85.54
CGMAFF-Net	92.25	98.18	92.96	91.37	91.67	96.89	90.73

模型	Recall	Spe	Pre	F1	F2	Acc	mIoU
U-Net	89.73	97.31	90.17	88.25	88.55	95.32	86.93
UNet++	89.83	97.13	89.70	87.88	88.34	95.23	86.73
ResUNet++	89.12	97.43	88.34	86.13	87.31	94.59	85.69
MSRAformer	92.23	97.43	90.08	89.54	90.82	96.49	88.51
CaraNet	90.87	96.51	91.07	89.68	89.88	96.37	88.12
DCSAU-Net	87.07	97.62	91.95	87.24	86.55	94.64	86.34
ACC-UNet	87.29	97.28	90.43	86.55	86.13	94.89	85.58
CFANet	85.65	97.43	90.73	85.07	84.97	95.43	85.14
MISSFormer	88.22	97.77	91.98	88.14	87.72	95.98	87.28
DTA-UNet	89.05	96.61	89.74	86.71	87.36	95.37	86.23
CGMAFF-Net	91.70	96.81	90.94	89.88	90.31	96.39	88.62

模型	训练时长/s	参数量/10⁶	运算量/GFLOPs	帧率/（frame·s^-1）
U-Net^［10］	25	13.40	248.86	19.30
UNet++^［12］	33	9.16	279.23	18.07
ResUNet++^［24］	95	14.48	567.95	15.61
MSRAformer^［25］	26	68.03	170.34	16.07
CaraNet^［26］	26	44.59	92.11	17.61
DCSAU-Net^［27］	29	2.60	55.32	18.63
ACC-UNet^［28］	209	4.26	122.69	12.84
CFANet^［29］	32	25.24	234.25	15.63
MISSFormer^［30］	37	35.45	58.01	18.10
DTA-UNet^［31］	44	19.61	275.04	15.82
本文模型	21	33.94	127.31	24.71

实验	实验目的
实验1、实验2、实验7	验证直接引入Otsu阈值分割图像会降低分割准确率
实验3与实验4，实验5与实验6	验证精心设计特征提取模块的必要性
实验3与实验5，实验4与实验6	验证自适应组合赋权的有效性
实验1、实验5、实验7	验证引入原始数据灰度图像的有效性

数据集	实验	Recall	Spe	Pre	F1	F2	Acc	mIoU
CVC- ClinicDB	1	92.36	99.61	94.11	92.11	92.23	99.31	93.64
	2	85.80	98.77	86.62	83.21	84.48	97.91	86.79
	3	91.64	99.68	96.31	92.78	92.78	92.78	93.72
	4	92.10	99.56	94.68	94.68	91.92	99.28	93.31
	5	93.83	99.46	92.65	93.03	93.44	99.22	93.91
	6	94.49	99.49	92.57	92.83	93.65	99.26	93.67
	7	95.18	99.54	93.84	94.20	94.71	99.29	94.35
Kvasir- SEG	1	90.91	96.62	91.00	89.66	89.66	96.32	88.29
	2	82.39	97.32	87.11	80.39	81.13	94.24	82.36
	3	87.59	98.29	91.33	87.35	87.17	95.52	87.45
	4	85.60	98.43	92.17	85.75	85.43	95.85	86.99
	5	88.98	98.21	98.21	87.83	88.06	95.76	88.05
	6	88.06	98.03	98.03	87.24	87.38	95.76	87.63
	7	92.25	98.18	92.96	91.37	91.67	96.89	90.73
ISIC 2018	1	94.22	95.66	86.99	89.09	91.43	96.22	87.66
	2	91.12	96.41	89.71	88.77	89.50	95.78	87.43
	3	91.32	96.81	90.79	89.60	90.03	96.01	88.31
	4	92.06	96.44	89.67	89.38	90.29	96.17	88.08
	5	92.08	96.42	90.47	89.96	90.60	96.26	88.52
	6	93.27	95.25	89.18	90.08	91.54	96.34	88.40
	7	91.70	96.81	90.94	89.88	90.31	96.39	88.62

[1]	Chuang WANG, Lu YU, Jianwei CHEN, Cheng PAN, Wenbo DU. Review of open set domain adaptation [J]. Journal of Computer Applications, 2025, 45(9): 2727-2736.
[2]	Jinggang LYU, Shaorui PENG, Shuo GAO, Jin ZHOU. Speech enhancement network driven by complex frequency attention and multi-scale frequency enhancement [J]. Journal of Computer Applications, 2025, 45(9): 2957-2965.
[3]	Zhixiong XU, Bo LI, Xiaoyong BIAN, Qiren HU. Adversarial sample embedded attention U-Net for 3D medical image segmentation [J]. Journal of Computer Applications, 2025, 45(9): 3011-3016.
[4]	Jiaxiang ZHANG, Xiaoming LI, Jiahui ZHANG. Few-shot object detection algorithm based on new category feature enhancement and metric mechanism [J]. Journal of Computer Applications, 2025, 45(9): 2984-2992.
[5]	Li LI, Han SONG, Peihe LIU, Hanlin CHEN. Named entity recognition for sensitive information based on data augmentation and residual networks [J]. Journal of Computer Applications, 2025, 45(9): 2790-2797.
[6]	Yiming LIANG, Jing FAN, Wenze CHAI. Multi-scale feature fusion sentiment classification based on bidirectional cross attention [J]. Journal of Computer Applications, 2025, 45(9): 2773-2782.
[7]	Jin LI, Liqun LIU. SAR and visible image fusion based on residual Swin Transformer [J]. Journal of Computer Applications, 2025, 45(9): 2949-2956.
[8]	Jin ZHOU, Yuzhi LI, Xu ZHANG, Shuo GAO, Li ZHANG, Jiachuan SHENG. Modulation recognition network for complex electromagnetic environments [J]. Journal of Computer Applications, 2025, 45(8): 2672-2682.
[9]	Jing WANG, Jiaxing LIU, Wanying SONG, Jiaxing XUE, Wenxin DING. Few-shot skin image classification model based on spatial transformer network and feature distribution calibration [J]. Journal of Computer Applications, 2025, 45(8): 2720-2726.
[10]	Haoyu LIU, Pengwei KONG, Yaoli WANG, Qing CHANG. Pedestrian detection algorithm based on multi-view information [J]. Journal of Computer Applications, 2025, 45(7): 2325-2332.
[11]	Bo FENG, Haizheng YU, Hong BIAN. Domain adaptive semantic segmentation based on masking enhanced self-training [J]. Journal of Computer Applications, 2025, 45(7): 2132-2137.
[12]	Yuyang SUN, Minjie ZHANG, Jie HU. Zero-shot dialogue state tracking domain transfer model based on semantic prefix-tuning [J]. Journal of Computer Applications, 2025, 45(7): 2221-2228.
[13]	Yongpeng TAO, Shiqi BAI, Zhengwen ZHOU. Neural architecture search for multi-tissue segmentation using convolutional and transformer-based networks in glioma segmentation [J]. Journal of Computer Applications, 2025, 45(7): 2378-2386.
[14]	Dehui ZHOU, Jun ZHAO, Jinfeng CHENG. Tiny defect detection algorithm for bearing surface based on RT-DETR [J]. Journal of Computer Applications, 2025, 45(6): 1987-1997.
[15]	Sheping ZHAI, Yan HUANG, Qing YANG, Rui YANG. Multi-view entity alignment combining triples and text attributes [J]. Journal of Computer Applications, 2025, 45(6): 1793-1800.