Multi-scale and spatial frequency feature-based image segmentation network for pheochromocytoma

doi:10.11772/j.issn.1001-9081.2024121868

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (1): 280-288.DOI: 10.11772/j.issn.1001-9081.2024121868

• Multimedia computing and computer simulation • Previous Articles Next Articles

Multi-scale and spatial frequency feature-based image segmentation network for pheochromocytoma

Chaoyun MAI¹, Hongyi ZHANG¹, Chuanbo QIN¹(), Junying ZENG¹, Dong WANG²

^1.School of Electronics and Information Engineering，Wuyi University，Jiangmen Guangdong 529020，China
^2.Peking Union Medical College Hospital，Chinese Academy of Medical Sciences，Beijing 100730，China

Received:2025-01-03 Revised:2025-03-21 Accepted:2025-03-25 Online:2026-01-10 Published:2026-01-10
Contact: Chuanbo QIN
About author:MAI Chaoyun， born in 1989， Ph. D.， associate professor. His research interests include intelligent information processing， digital signal processing.
ZHANG Hongyi， born in 1999， M. S. candidate. His research interests include biometric identification， medical image analysis.
ZENG Junying， born in 1977， Ph. D.， professor. His research interests include computer image processing， biometric identification.
WANG Dong， born in 1981， Ph. D. His research interests include clinical diagnosis and treatment of complex pheochromocytoma.
Supported by:
Key Research Platform Project for Ordinary Universities in Guangdong Province(2024ZDZX1008);Guangdong Provincial Medical Research Fund Project(B2023100);Science and Technology Program in Healthcare Sector of Jiangmen City(2022YL01029)

基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络

麦超云¹, 张洪燚¹, 秦传波¹(), 曾军英¹, 王栋²

^1.五邑大学电子与信息工程学院，广东江门 529020
^2.中国医学科学院北京协和医院，北京 100730

通讯作者: 秦传波
作者简介:麦超云（1989—），男，广东江门人，副教授，博士，CCF会员，主要研究方向：智能信息处理、数字信号处理
张洪燚（1999—），男，河南洛阳人，硕士研究生，CCF会员，主要研究方向：生物特征识别、医学图像分析
曾军英（1977—），男，江西赣州人，教授，博士，主要研究方向：计算机图像处理、生物特征识别
王栋（1981—），男，山东日照人，博士，主要研究方向：复杂嗜铬细胞瘤临床诊疗。
基金资助:
广东省普通高校重点研究平台项目(2024ZDZX1008);广东省医学科研基金资助项目(B2023100);江门市医疗卫生领域科技计划项目(2022YL01029)

Abstract

Abstract:

To address the issue of insufficient learning of features between different organs in the segmentation of pheochromocytoma images from partially annotated abdominal datasets， which leads to difficulties in distinguishing tumor and surrounding organ boundaries accurately， a Multi-scale and spatial Frequency feature-based image segmentation Network for pheochromocytoma （MF-Net） was proposed. Firstly， a Multi-scale Spatial Frequency Channel Attention module （MSFCA） was constructed， which enhanced the capture of inter-organ texture and boundary features by weighting and fusing the frequency domain information of image and the multi-scale feature maps from adjacent encoders， thereby highlighting the feature representation ability of tumor regions. Then， an Upsampling Multi-Scale Feature Fusion module （UMFF） was introduced， which combined upsampled feature maps of different scales to enhance the model's ability to recognize objects of varying sizes in image. Finally， an Adaptive Objective loss function （AOb） was utilized， which calculated the loss for the annotated abdominal organ labels and adjusted the loss weights according to the annotated organ categories， thereby optimizing learning process of the segmentation network. Experimental results show that on the abdominal organ and pheochromocytoma datasets， MF-Net has the segmentation accuracy improved by 3.33 and 3.18 percentage points， respectively， compared to the separately trained nnU-Net （no new U-Net）， with Dice similarity coefficient （Dice） and Normalized Surface Dice （NSD） reached 89.07% and 92.85%， respectively. On the external datasets， MF-Net has the Dice and NSD of 84.66% and 90.55%， respectively. In addition visualization results indicate that MF-Net can handle complex backgrounds and blurred boundaries in pheochromocytoma images better， providing better technical support for accurate diagnosis and treatment of pheochromocytoma.

Key words: abdominal organ segmentation, multi-scale feature, spatial frequency, partially annotated dataset, pheochromocytoma medical image

摘要：

针对腹部部分注释数据集的嗜铬细胞瘤图像分割缺乏不同器官间的特征学习，导致分割中难以准确区分肿瘤及周边器官边缘的问题，提出一种基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络（MF-Net）。首先，构建多尺度空间频率通道注意力模块（MSFCA）对图像频域信息和相邻编码器的多尺度特征图进行加权融合，以强化器官间纹理和边界特征的捕捉，从而突出肿瘤区域的特征表示能力；其次，引入上采样多尺度特征融合模块（UMFF）通过结合上采样得到的不同尺度特征图，增强模型对图像中不同大小对象的识别能力；最后，利用自适应目标损失函数（AOb）对有注释腹部器官标签进行损失计算，并根据注释器官类别调整损失权重大小，从而优化分割网络的学习过程。实验结果表明，在腹部器官和嗜铬细胞瘤数据集上， MF-Net的分割准确率相较于单独训练的nnU-Net （no new U-Net）分别提升了3.33和3.18个百分点，而Dice系数（Dice）和归一化表面距离（NSD）分别为89.07%和92.85%；在域外数据集上， MF-Net的Dice和NSD分别为84.66%和90.55%。此外，可视化结果表明， MF-Net能更好地处理嗜铬细胞瘤图像中的复杂背景和模糊边界，为嗜铬细胞瘤的精确诊断和治疗提供了更好的技术支持。

关键词: 腹部器官分割, 多尺度特征, 空间频率, 部分注释数据集, 嗜铬细胞瘤医学图像

CLC Number:

TP391.4

Chaoyun MAI, Hongyi ZHANG, Chuanbo QIN, Junying ZENG, Dong WANG. Multi-scale and spatial frequency feature-based image segmentation network for pheochromocytoma[J]. Journal of Computer Applications, 2026, 46(1): 280-288.

麦超云, 张洪燚, 秦传波, 曾军英, 王栋. 基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 280-288.

Figures/Tables 12

References 31

[1]	NAIK N， HAMEED B M Z， SHETTY D K， et al. Legal and ethical consideration in artificial intelligence in healthcare： who takes responsibility？［J］. Frontiers in Surgery， 2022， 9： No.862322.
[2]	窦猛，陈哲彬，王辛，等.基于深度学习的多模态医学图像分割综述［J］.计算机应用， 2023， 43（11）： 3385-3395.
	DOU M， CHEN Z B， WANG X， et al. Review of multi-modal medical image segmentation based on deep learning ［J］. Journal of Computer Applications， 2023， 43（11）： 3385-3395.
[3]	LIU X， QU L， XIE Z， et al. Towards more precise automatic analysis： a systematic review of deep learning-based multi-organ segmentation ［J］. BioMedical Engineering OnLine， 2024， 23： No.52.
[4]	FANG X， YAN P. Multi-organ segmentation over partially labeled datasets with multi-scale feature abstraction ［J］. IEEE Transactions on Medical Imaging， 2020， 39（11）： 3619-3629.
[5]	YE Y， XIE Y， ZHANG J， et al. UniSeg： a prompt-driven universal segmentation model as well as a strong representation learner ［C］// Proceedings of the 2023 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 14222. Cham： Springer， 2023： 508-518.
[6]	ISENSEE F， JAEGER P F， KOHL S A A， et al. nnU-Net： A self-configuring method for deep learning-based biomedical image segmentation ［J］. Nature Methods， 2021， 18（2）： 203-211.
[7]	LIU Z， LIN Y， CAO Y， et al. Swin Transformer： hierarchical Vision Transformer using shifted windows ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 9992-10002.
[8]	HATAMIZADEH A， TANG Y， NATH V， et al. Unetr： Transformers for 3D medical image segmentation ［C］// Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway： IEEE， 2022： 574-584.
[9]	CHEN J， MEI J， LI X， et al. TransUNet： rethinking the U-Net architecture design for medical image segmentation through the lens of Transformers ［J］. Medical Image Analysis， 2024， 97： No.103280.
[10]	CHEN S， MA K， ZHENG Y. Med 3D： transfer learning for 3D medical image analysis ［EB/OL］. ［2024-12-30］. .
[11]	JI Z， GUO D， WANG P， et al. Continual segment： towards a single， unified and non-forgetting continual segmentation model of 143 whole-body organs in CT scans ［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 21140-21151.
[12]	ZHANG J， XIE Y， XIA Y， et al. DoDNet： learning to segment multi-organ and tumors from multiple partially labeled datasets ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 1195-1204.
[13]	LIU P， GU C， WU B， et al. 3D multi-organ and tumor segmentation based on re-parameterize diverse experts ［J］. Mathematics， 2023， 11（23）： No.4868.
[14]	LI L， LIAN S， LIN D， et al. Learning multi-organ and tumor segmentation from partially labeled datasets by a conditional dynamic attention network ［J］. Concurrency and Computation： Practice and Experience， 2024， 36（1）： No.e7869.
[15]	XIE Y， ZHANG J， XIA Y， et al. Learning from partially labeled data for multi-organ and tumor segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（12）： 14905-14919.
[16]	WU H， PANG S， SOWMYA A. Tgnet： a task-guided network architecture for multi-organ and tumour segmentation from partially labelled datasets ［C］// Proceedings of the IEEE 19th International Symposium on Biomedical Imaging. Piscataway： IEEE， 2022： 1-5.
[17]	LIU J， ZHANG Y， CHEN J N， et al. CLIP-driven universal model for organ segmentation and tumor detection ［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 21095-21107.
[18]	GAO Y. Training like a medical resident： context-prior learning toward universal medical image segmentation ［C］// Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2024： 11194-11204.
[19]	SRIVASTAVA A， JHA D， KELES E， et al. An efficient multi-scale fusion network for 3D Organs At Risk （OARs） segmentation ［C］// Proceedings of the 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway： IEEE， 2023： 1-4.
[20]	KOLAHI S G， CHAHARSOOGHI S K， KHATIBI T， et al. MSA²Net： multi-scale adaptive attention-guided network for medical image segmentation ［C］// Proceedings of the 2024 British Machine Vision Conference. Durham： BMVA Press， 2024： No.787.
[21]	CHANG A， ZENG J， HUANG R， et al. EM-Net： efficient channel and frequency learning with mamba for 3D medical image segmentation ［C］// Proceedings of the 2024 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 15009. Cham： Springer， 2024： 266-275.
[22]	ZHOU Z， HE A， WU Y， et al. Spatial-frequency dual domain attention network for medical image segmentation ［C］// Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway： IEEE， 2024： 4076-4081.
[23]	LEE H H， LIU Q， BAO S， et al. Scaling up 3D kernels with Bayesian frequency re-parameterization for medical image segmentation ［C］// Proceedings of the 2023 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 14223. Cham： Springer， 2023： 632-641.
[24]	刘慧，朱积成，王欣雨，等.面向医学图像融合的多尺度特征频域分解滤波［J］.软件学报， 2024， 35（12）： 5687-5709.
	LIU H， ZHU J C， WANG X Y， et al. Multi-scale feature frequency domain decomposition filtering for medical image fusion ［J］. Journal of Software， 2024， 35（12）： 5687-5709.
[25]	MA J， ZHANG Y， GU S， et al. AbdomenCT-1K： is abdominal organ segmentation a solved problem？［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2022， 44（10）： 6695-6714.
[26]	JI Y， BAI H， GE C， et al. AMOS： a large-scale abdominal multi-organ benchmark for versatile medical image segmentation ［C］// Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2022： 36722-36732.
[27]	MA J， ZHANG Y， GU S， et al. Fast and low-GPU-memory abdomen CT organ segmentation： the flare challenge ［J］. Medical Image Analysis， 2022， 82： No.102616.
[28]	LUO X， LIAO W， XIAO J， et al. WORD： a large scale dataset， benchmark and clinical applicable study for abdominal organ segmentation from CT image ［J］. Medical Image Analysis， 2022， 82： No.102642.
[29]	LANDMAN B， XU Z， IGELSIAS J， et al. MICCAI multi-atlas labeling beyond the cranial vault-workshop and challenge ［C］// Proceedings of the 2015 MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge. Cham： Springer， 2015， 5： 12.
[30]	MA J， ZHANG Y， GU S， et al. Unleashing the strengths of unlabeled data in pan-cancer abdominal organ quantification： the FLARE22 challenge ［J］. The Lancet Digital Health， 2024， 6（11）： e815-e826.
[31]	WANG D， ZENG J， HUANG G， et al. PheoSeg： a 3D transfer learning framework for accurate abdominal CT pheochromocytoma segmentation and surgical grade prediction ［J］. Knowledge-Based Systems， 2024， 301： 112202.

数据集	训练集样本数	测试集样本数	注释类别数
AbdomenCT-1K^［25］	800	200	4
AMOS-CT^［26］	240	60	13
FLARE2021^［27］	361	30	4
WORD^［28］	120	30	11
BTCV^［29］	0	30	12
FLARE2022^［30］	0	50	13
PUMCH-PPGL	150	42	1

数据集	训练集样本数	测试集样本数	注释类别数
AbdomenCT-1K^［25］	800	200	4
AMOS-CT^［26］	240	60	13
FLARE2021^［27］	361	30	4
WORD^［28］	120	30	11
BTCV^［29］	0	30	12
FLARE2022^［30］	0	50	13
PUMCH-PPGL	150	42	1

评价指标	方法	肝脏	右肾	脾	胰腺	主动脉	下腔静脉	右肾上腺	左肾上腺	胆囊	食管	胃	十二指肠	左肾	PPGL	平均
Dice	Multi-Net^［5］	95.14	90.86	92.29	78.78	87.83	91.52	78.11	83.33	82.70	82.41	81.55	75.37	90.34	90.08	85.74
	TAL^［4］	94.47	92.39	93.04	82.03	90.33	91.03	78.28	79.69	83.59	82.82	84.84	82.08	91.71	86.57	86.63
	Multi-head^［10］	94.94	89.46	94.97	84.18	85.62	94.02	80.32	82.65	86.82	84.09	74.48	78.90	89.67	88.43	86.33
	CLIP-Driven^［17］	96.57	91.72	94.66	84.33	89.47	92.41	77.84	79.92	86.01	84.70	89.25	80.80	93.13	90.14	87.93
	DoDNet^［12］	96.80	92.15	94.54	86.13	90.12	92.66	77.05	80.10	83.57	84.06	90.39	82.77	92.26	90.02	88.04
	MF-Net	96.92	93.31	94.56	86.41	89.83	93.78	80.42	83.49	87.37	84.18	89.63	82.15	94.65	90.31	89.07
NSD	Multi-Net^［5］	95.32	92.41	93.44	87.21	94.69	90.27	84.39	87.71	86.20	83.93	90.27	88.56	88.86	92.08	89.67
	TAL^［4］	93.33	93.67	92.79	89.80	96.85	94.21	85.73	86.08	84.11	87.45	91.62	86.37	93.67	90.26	90.42
	Multi-head^［10］	95.12	92.46	94.68	88.08	97.83	94.15	87.36	86.83	85.45	84.08	88.68	89.61	86.08	88.37	89.91
	CLIP-Driven^［17］	97.44	93.15	95.83	89.62	96.46	93.83	86.11	85.24	87.74	91.37	92.52	92.32	90.64	92.14	91.74
	DoDNet^［12］	97.75	93.56	95.77	91.47	95.37	93.68	85.67	84.72	89.92	85.85	93.22	90.59	93.32	91.02	91.57
	MF-Net	97.79	94.36	96.28	91.86	97.36	94.32	87.54	88.21	91.42	91.13	93.62	91.52	92.15	92.40	92.85

评价指标	方法	肝脏	右肾	脾	胰腺	主动脉	下腔静脉	右肾上腺	左肾上腺	胆囊	食管	胃	十二指肠	左肾	PPGL	平均
Dice	Multi-Net^［5］	95.14	90.86	92.29	78.78	87.83	91.52	78.11	83.33	82.70	82.41	81.55	75.37	90.34	90.08	85.74
	TAL^［4］	94.47	92.39	93.04	82.03	90.33	91.03	78.28	79.69	83.59	82.82	84.84	82.08	91.71	86.57	86.63
	Multi-head^［10］	94.94	89.46	94.97	84.18	85.62	94.02	80.32	82.65	86.82	84.09	74.48	78.90	89.67	88.43	86.33
	CLIP-Driven^［17］	96.57	91.72	94.66	84.33	89.47	92.41	77.84	79.92	86.01	84.70	89.25	80.80	93.13	90.14	87.93
	DoDNet^［12］	96.80	92.15	94.54	86.13	90.12	92.66	77.05	80.10	83.57	84.06	90.39	82.77	92.26	90.02	88.04
	MF-Net	96.92	93.31	94.56	86.41	89.83	93.78	80.42	83.49	87.37	84.18	89.63	82.15	94.65	90.31	89.07
NSD	Multi-Net^［5］	95.32	92.41	93.44	87.21	94.69	90.27	84.39	87.71	86.20	83.93	90.27	88.56	88.86	92.08	89.67
	TAL^［4］	93.33	93.67	92.79	89.80	96.85	94.21	85.73	86.08	84.11	87.45	91.62	86.37	93.67	90.26	90.42
	Multi-head^［10］	95.12	92.46	94.68	88.08	97.83	94.15	87.36	86.83	85.45	84.08	88.68	89.61	86.08	88.37	89.91
	CLIP-Driven^［17］	97.44	93.15	95.83	89.62	96.46	93.83	86.11	85.24	87.74	91.37	92.52	92.32	90.64	92.14	91.74
	DoDNet^［12］	97.75	93.56	95.77	91.47	95.37	93.68	85.67	84.72	89.92	85.85	93.22	90.59	93.32	91.02	91.57
	MF-Net	97.79	94.36	96.28	91.86	97.36	94.32	87.54	88.21	91.42	91.13	93.62	91.52	92.15	92.40	92.85

评价指标	方法	肝脏	右肾	脾	胰腺	主动脉	下腔静脉	右肾上腺	左肾上腺	胆囊	食管	胃	十二指肠	左肾	平均
Dice	Multi-Net^［5］	94.25	87.24	83.38	74.66	85.81	83.63	75.94	77.72	79.87	78.40	72.47	70.01	87.21	80.81
	TAL^［4］	95.66	86.62	86.64	77.58	83.91	83.73	73.93	75.99	79.52	78.14	81.50	78.27	86.99	82.19
	Multi-head^［10］	95.60	86.40	88.65	79.35	88.21	82.26	79.77	75.62	81.97	78.04	73.12	73.91	86.85	82.29
	CLIP-Driven^［17］	95.25	86.58	89.73	80.34	86.37	84.18	74.48	76.10	82.15	81.00	78.90	76.10	88.98	83.09
	DoDNet^［12］	95.38	87.61	90.59	79.56	87.27	84.76	76.23	76.72	81.23	79.67	80.73	76.90	87.94	83.43
	MF-Net	95.88	88.73	90.21	79.33	88.31	85.88	79.84	78.61	83.36	82.47	79.62	78.83	89.52	84.66
NSD	Multi-Net^［5］	95.28	91.08	91.28	79.37	87.85	89.89	81.47	82.12	85.24	85.50	83.87	84.97	89.24	86.70
	TAL^［4］	94.25	92.50	91.34	82.49	90.91	91.10	82.94	81.78	85.09	86.97	86.83	90.19	90.73	88.24
	Multi-head^［10］	95.34	89.99	93.54	83.33	88.15	92.90	84.92	84.32	87.83	86.59	78.59	86.04	88.51	87.70
	CLIP-Driven^［17］	97.05	91.80	93.60	83.88	90.43	92.17	82.57	81.46	87.89	89.99	90.28	89.28	92.28	89.44
	DoDNet^［12］	97.25	92.44	93.71	85.71	90.27	92.21	82.03	81.54	87.33	87.20	91.19	91.40	91.33	89.51
	MF-Net	97.34	93.28	93.38	86.07	91.36	92.30	84.97	84.46	88.15	89.81	90.77	91.21	93.99	90.55

Multi-scale and spatial frequency feature-based image segmentation network for pheochromocytoma

基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 31

Related Articles 15

Recommended Articles

Metrics

MSFCA	UMFF	AOb	AbdomenCT-1K		AMOS-CT		FLARE2021		WORD		PUMCH-PPGL		加权平均
MSFCA	UMFF	AOb	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD
			90.02	93.33	32.85	34.69	80.97	83.64	41.25	43.95			65.31	67.89
		√	90.36	93.78	88.27	91.95	81.36	83.95	81.64	86.89	88.65	92.78	88.35	91.98
√		√	90.86	93.89	88.62	92.74	81.61	84.26	81.97	87.49	89.36	93.62	88.81	92.34
	√	√	90.78	93.86	88.76	93.25	81.58	84.78	82.08	87.56	89.41	93.47	88.80	92.44
√	√	√	91.03	94.29	88.83	93.85	81.66	85.22	82.21	87.75	90.31	93.68	89.07	92.85

方法	Multi_BCE+Dice Loss	AOb	AbdomenCT-1K		AMOS-CT		FLARE2021		WORD		PUMCH-PPGL		加权平均
方法	Multi_BCE+Dice Loss	AOb	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD	Dice	NSD
DoDNet	√		88.24	92.91	88.13	92.16	82.29	83.25	81.12	83.34	90.03	91.17	87.35	90.99
DoDNet		√	89.45	93.80	88.35	92.23	82.37	83.77	80.73	83.38	90.14	91.46	88.04	91.57
CLIP-Driven	√		88.86	93.05	88.14	92.16	81.63	83.24	81.26	85.91	90.21	92.27	87.67	91.41
CLIP-Driven		√	89.21	93.03	88.39	92.32	81.44	83.27	81.81	86.23	90.15	92.43	87.93	91.47
MF-Net	√		90.37	93.63	88.26	93.35	81.48	84.82	81.89	86.98	90.22	92.51	88.56	92.17
MF-Net		√	91.03	94.29	88.83	93.85	81.66	85.22	82.21	87.75	90.31	93.68	89.07	92.85

[1]	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.
[2]	Liang CHEN, Xuan WANG, Kun LEI. Helmet wearing detection algorithm for complex scenarios based on cross-layer multi-scale feature fusion [J]. Journal of Computer Applications, 2025, 45(7): 2333-2341.
[3]	Xiang WANG, Qianqian CUI, Xiaoming ZHANG, Jianchao WANG, Zhenzhou WANG, Jialin SONG. Wireless capsule endoscopy image classification model based on improved ConvNeXt [J]. Journal of Computer Applications, 2025, 45(6): 2016-2024.
[4]	Shiyue GUO, Jianwu DANG, Yangping WANG, Jiu YONG. 3D hand pose estimation combining attention mechanism and multi-scale feature fusion [J]. Journal of Computer Applications, 2025, 45(4): 1293-1299.
[5]	Zhongwei ZHANG, Jun WANG, Shudong LIU, Zhiheng WANG. Object detection in remote sensing image based on multi-scale feature fusion and weighted boxes fusion [J]. Journal of Computer Applications, 2025, 45(2): 633-639.
[6]	Ziyi WANG, Weijun LI, Xueyang LIU, Jianping DING, Shixia LIU, Yilei SU. Image caption method based on Swin Transformer and multi-scale feature fusion [J]. Journal of Computer Applications, 2025, 45(10): 3154-3160.
[7]	Xuehui YIN, Linlin FU, Shangbo ZHOU. Concrete pavement crack detection network with progressive context interaction and attention mechanism [J]. Journal of Computer Applications, 2025, 45(10): 3353-3362.
[8]	Shang LIU, Yuwei ZHOU, Rao DAI, Linfang DONG, Meng LIU. Small target detection algorithm in remote sensing images integrating attention and contextual information [J]. Journal of Computer Applications, 2025, 45(1): 292-300.
[9]	Yan RONG, Jiawen LIU, Xinlei LI. Adaptive hybrid network for affective computing in student classroom [J]. Journal of Computer Applications, 2024, 44(9): 2919-2930.
[10]	Tong CHEN, Fengyu YANG, Yu XIONG, Hong YAN, Fuxing QIU. Construction method of voiceprint library based on multi-scale frequency-channel attention fusion [J]. Journal of Computer Applications, 2024, 44(8): 2407-2413.
[11]	Hongtian LI, Xinhao SHI, Weiguo PAN, Cheng XU, Bingxin XU, Jiazheng YUAN. Few-shot object detection via fusing multi-scale and attention mechanism [J]. Journal of Computer Applications, 2024, 44(5): 1437-1444.
[12]	Zhanjun JIANG, Baijing WU, Long MA, Jing LIAN. Faster-RCNN water-floating garbage recognition based on multi-scale feature and polarized self-attention [J]. Journal of Computer Applications, 2024, 44(3): 938-944.
[13]	Hao YANG, Yi ZHANG. Feature pyramid network algorithm based on context information and multi-scale fusion importance awareness [J]. Journal of Computer Applications, 2023, 43(9): 2727-2734.
[14]	Hong WANG, Qing QIAN, Huan WANG, Yong LONG. Lightweight image tamper localization algorithm based on large kernel attention convolution [J]. Journal of Computer Applications, 2023, 43(9): 2692-2699.
[15]	Shuai ZHENG, Xiaolong ZHANG, He DENG, Hongwei REN. 3D liver image segmentation method based on multi-scale feature fusion and grid attention mechanism [J]. Journal of Computer Applications, 2023, 43(7): 2303-2310.