A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images
Open accessThe DOI matches its Crossref record; 55 of the 57 references it cites were found in a registry or an index.
Abstract
Segmentation of pneumonia lesions from CT scans of COVID-19 patients is important for accurate diagnosis and follow-up. Deep learning has a potential to automate this task but requires a large set of high-quality annotations that are difficult to collect. Learning from noisy training labels that are easier to obtain has a potential to alleviate this problem. To this end, we propose a novel noise-robust framework to learn from noisy labels for the segmentation task. We first introduce a noise-robust Dice loss that is a generalization of Dice loss for segmentation and Mean Absolute Error (MAE) loss for robustness against noise, then propose a novel COVID-19 Pneumonia Lesion segmentation network (COPLE-Net) to better deal with the lesions with various scales and appearances. The noise-robust Dice loss and COPLE-Net are combined with an adaptive self-ensembling framework for training, where an Exponential Moving Average (EMA) of a student model is used as a teacher model that is adaptively updated by suppressing the contribution of the student to EMA when the student has a large training loss. The student model is also adaptive by learning from the teacher only when the teacher outperforms the student. Experimental results showed that: (1) our noise-robust Dice loss outperforms existing noise-robust loss functions, (2) the proposed COPLE-Net achieves higher performance than state-of-the-art image segmentation networks, and (3) our framework with adaptive self-ensembling significantly outperforms a standard training process and surpasses other noise-robust training approaches in the scenario of learning from noisy labels for COVID-19 pneumonia lesion segmentation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Recently, the Automatic segmentation of COVID-19 Lung Infection from CT Images helps to detect the development of COVID-19 infection by employing several deep learning techniques [309–312].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [310]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“In addition, in each convolutional block, we use residual connection [27] to facilitate the training and add a Squeeze-and-Excitation (SE) block [40] to calibrate different channels for better performance.”
MethodU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · cited 3×
“They were also compared with: standard CE loss L CE , Dice loss L Dice proposed by Milletari et al. [18], L CE + L Dice , L MAE + L Dice , Sørensen-Dice [44], focal CE loss [43] and focal Dice loss [45].”
BackgroundMethodInfluentialA novel coronavirus from patients with pneumonia in China, 2019
Zhu, N., Zhang, D., Wang, W., Li, X., Yang, B., Song, J., Zhao, X., Huang, B., Shi, W., Lu, R., et al. (2020) · New England Journal of Medicine · doi:10.1056/nejmoa2001017 · Cited by 28,244 · cited 2×
“T HE coronavirus disease 2019 (COVID-19) has become a global pandemic since the beginning of 2020 [1]–[3].”
BackgroundEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063 · cited 2×
“ASPP [35] block is used at the bottleneck to better deal with lesions at multiple scales. bilinear interpolation, where the former reduces the number of feature channels to match that of the output of the bridge layer, and the latter improves the spatial resolution before the concatenation of the…”
MethodEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · cited 10×
“…noisy annotations for training CNNs to segment COVID-19 pneumonia lesions, we propose a novel noise-robust Dice loss function, which is a combination and generalization of MAE loss [14] that is robust against noisy labels and Dice loss [18] that is insensitive to foreground-background imbalance.”
BackgroundMethodInfluentialUNet++: A Nested U-Net Architecture for Medical Image Segmentation
Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., & Liang, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00889-5_1 · Cited by 9,610
Research works printed but not linked: 1
- [41].Isensee F., Kickingereder P., Wick W., Bendszus M., and Maier-Hein K. H., “No new-net,” in Proc. Int. MICCAI Brainlesion Workshop, 2018, pp. 234–244. [Google Scholar]
Cited by
Items 401–495 of 495
Localization Graph Generation Based Matrix Factorization for Incomplete Multi-View Clustering
Liang, N., Yang, Z., Xiang, D., Xu, J., Zhou, G., & Xie, S. (2026) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2026.3655898 · Cited by 1
“In some medical applications, e.g., CT scans of the coronavirus disease[42], since every high-quality sample is difficult to obtain, a sample tends to be more important when the corresponding data point suffers from a larger number of missing views.”
Wang, W., Mao, Q., Tian, Y., Wang, J., Xiang, Z., & Zhang, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109485 · Cited by 1
Peng, Y. L., Lee, W., & Juan, C.-Y. (2026) · Journal of Data and Information Quality · doi:10.1145/3802916 · Cited by 1
“For deep learning applications, particularly in vision tasks, researchers have explored robustness to label noise by designing noise-tolerant loss functions or adaptive sample weighting schemes [7, 21].”
Revisiting long-range dependency modeling in CNNs for medical image segmentation
Shen, Z., Li, S. B., & Xiao, Q. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133668 · Cited by 1
Ding, H., Niu, Q., Nie, Y., Shang, Y., Chen, N., & Liu, R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89029-2_27 · Cited by 1
COVID Pneumonia Severity Detection of Chest CT-Scan Images based on Robust Semantic Segmentation
Al-Saaidah, B. (2024) · WSEAS TRANSACTIONS ON BIOLOGY AND BIOMEDICINE · doi:10.37394/23208.2024.21.24 · Cited by 1
Symptom Tracking and Experimentation Platform for Covid-19 or Similar Infections
Petrellis, N., & Adam, G. K. (2021) · Computers · doi:10.3390/computers10020022 · Cited by 1
“The classification of the lesions appearing in pneumonia chest Coaxial Tomography (CT) has been recently proposed in [7,8].”
BackgroundChen, F., Wei, C., Ren, S., Zhou, Z. X., Xu, L., & Liang, J. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434025 · Cited by 1
“[12] proposed a novel noise-robust Dice loss and a teacher-student adaptive self-ensembling framework to cope with the noisy labels.”
BackgroundPerformance Measures of Respiratory Disease Classification using Deep Learning
Janani, G. R. (2021) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2021.35109 · Cited by 1
Learning from pseudo-lesion: a self-supervised framework for COVID-19 diagnosis
Li, Z., Li, X., Jin, Z., & Shen, L. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08259-9 · Cited by 1
“UESTC-COVID-19 dataset [56], where lesions of COVID-19 CT images are manually labeled.”
MethodEffective Early Stage Detection of COVID-19 Using Deep Learning
Swetha.M, & Rajendiran, M. (2021) · Advances in parallel computing · doi:10.3233/apc210037 · Cited by 1
Optimizing Radiologic Detection of COVID-19: Test Set Technologies and Artificial Intelligence
Gandomkar, Z., Brennan, P., & Suleiman, M. E. (2022) · Springer eBooks · doi:10.1007/978-3-030-64573-1_285 · Cited by 1
Wang, J., Li, B., Huang, J., Wei, M., Song, M., & Wang, Z. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897957 · Cited by 1
“1. demonstrates that varying degrees of lesions from people infected with Recently, several segmentation algorithms for COVID-19 have been proposed [3][4][5][6], which are mostly based on variations made on encoder-decoder architecture.”
BackgroundCAE-UNet: An Effective Automatic Segmentation Model for CT Images of COVID-19
Xingfei, F., & Huang, C. (2022) · International Conference on Communication and Information Systems (ICCIS) · doi:10.1109/iccis56375.2022.9998131 · Cited by 1
“Guotai Wang et al [3] proposed COPLE-Net to embed the atrous spatial pyramid pooling[4] module between the coding and decoding regions, which enables the network to improve the effect of COVID-19 CT image segmentation.”
MethodCovid-19 Infection Segmentation Using Deep Learning Techniques
Arya, R. S., & Deepak, S. (2022) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs55517.2022.10028743 · Cited by 1
“Guotai Wang [12] They first provide a novel COVID-19 Pneumonia Lesion segmentation network (COPLE-Net) to better handle the lesions with different scales and appearances, which is a generalisation of the Dice loss for segmentation and Mean Absolute Error (MAE) loss for robustness against noise.”
BackgroundKeerthana, R., Divakaran, S., & Nisha, A. S. A. (2022) · International Conference on Power, Energy, Control and Transmission Systems (ICPECTS) · doi:10.1109/icpects56089.2022.10047728 · Cited by 1
Development of a Decentralized Web App (D-App) for Covid-19 using AI
Nair, D., Kurakula, B. T., Harish, A., & Latha (2022) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi56455.2022.10119433 · Cited by 1
Segmentação de Infecções Pulmonares de COVID-19 com a Rede Mask R-CNN
Sousa, H. S., Neto, A. A. P., Júnior, I. C. D. P., & de Melo, C. R. (2023) · Journal of Health Informatics · doi:10.59681/2175-4411.v15.iespecial.2023.1100 · Cited by 1
Unsupervised Adaptive Lesion Segmentation with Similarity Based Cross Pseudo Supervision
Zhu, Y., Li, S., Yang, A., Feng, M., Pu, X., & Ren, Y. (2023) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait60137.2023.10528594 · Cited by 1
“To reduce the sensitivity of the model to noise pseudo label and improve the quality of pseudo label in cross pseudo super-vision, the NR-Dice loss [30] is applied in the unsupervised loss.”
MethodHou, Z., Meng, M., Zhou, G., Zhang, X., Cao, M., Qian, J., Li, N., Huang, Y., Wu, L., & Xie, L. (2024) · Remote Sensing Letters · doi:10.1080/2150704x.2024.2359096 · Cited by 1
“When γ = 2.0, L NR-Dice equals L Dice ; When γ = 1.0, L NR-Dice equals L MAE ; When γ is taken to be 1.5 the anti-noise and anti-imbalance effect is best (Wang et al. 2020).”
BackgroundInfluentialMupra, P. R., Ashok, B., & Bindulal, T. S. (2024) · OPSEARCH · doi:10.1007/s12597-024-00836-3 · Cited by 1
“Wang et al. [16] introduced a robust framework designed to automatically segment COVID-19 pneumonia lesions in CT scans.”
Zhao, L., Li, J., Zhao, Q. Y., & Xu, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126806 · Cited by 1
Qayyum, A., Razzak, I., Mazher, M., & Puig, D. (2022) · medRxiv · doi:10.1101/2022.02.25.22271520 · Cited by 1
“In another work, Wang et al. proposed noise robust dice loss approach for lesion segmentation ensemble networks (COPLE-Net) for the segmentation of COVID19 [13].”
BackgroundMethodLiu, M., Liu, Y., Yi-dong, Y., Liu, A., Li, S., Qu, C., Qiu, X., Li, Y., Lv, W., Zhang, P., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.05900 · Cited by 1
“To reduce the heavy annotation burden, we employed a human-in-the-loop strategy, similar to what other researchers did in (18, 22).”
MethodEnshaei, N., Rafiee, M. J., Mohammadi, A., & Naderkhani, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.08726 · Cited by 1
“To overcome this challenge, extracting pathology labels of large-scale medical images from radiology reports with the help of text mining [1], human-machine collaborative techniques [2, 3], and the use of non-expert annotators are some of the proposed solutions in the literature [4].”
BackgroundMethodAutomatic segmentation of metal surface defects with noise labelPreprint
Xu, Y., Zhu, J., Xu, S., Liu, W., & Bian, X. (2024) · Research Square · doi:10.21203/rs.3.rs-4787816/v1 · Cited by 1
Voxel-level forecast system for lesion development in patients with COVID-19Preprint
Jin, C., Duan, Y., Cao, Y., Yu, J., Xu, Z., Chen, W., Han, X., Liu, J., Zhou, J., Shi, H., et al. (2020) · medRxiv · doi:10.1101/2020.12.17.20248377
Self-citationCOVID-19 Classification Using Staked Ensembles: A Comprehensive AnalysisPreprint
Lb, B., Boddeda, R., & Sv, K. (2021) · arXiv (Cornell University)
Optimizing Radiologic Detection of COVID-19: Test Set Technologies and Artificial Intelligence
Gandomkar, Z., Brennan, P., & Suleiman, M. E. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_285-1
A review of emerging innovations in COVID-19
Saggi, S. (2021) · International Journal of Community Medicine and Public Health · doi:10.18203/2394-6040.ijcmph20214808
Wang, H., Mu, N., Zhang, Y., & Yang, H. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9659170
“[17] presented a noise-robust deep segmentation network to learn the pneumonia lesion of COVID-19.”
BackgroundNoisy Dense Label Prediction with Noise-Robust Loss Functions
Alvi, R. H., & Rahman, R. M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-6309-3_64
Shen, Y., Liao, E., Tai, T., Liao, Y., Sun, C., Lee, C., See, S. C. W., & Chen, H. (2021) · Frontiers in Optics · doi:10.1364/fio.2021.jw7a.126
LCFNet: A lightweight context fusion network for COVID-19 segmentation
Wang, Q., Hu, W., Wang, J., Luo, L., Ge, X., Chen, J., & Chen, L. (2022) · International Conference on Electronic Information Technology (EIT) · doi:10.1117/12.2640063
Meghana, A. S., Rao, K. T., & Sarada, N. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-8554-5_19
Lu, X., Xu, Y., & Yuan, W. (2022) · Evolving Systems · doi:10.1007/s12530-022-09466-w
“In contrast with COPLE-Net, DBF-Net improved sensitivity by 4.1%, specificity by 8.9%, the Dice coefficient by 5.0% and precision by 5.6%.”
BackgroundInfluentialTakuya, G. O. T. O., NAKANO, H., Asama, H., & Yamashita, A. (2022) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.88.919
P2P-COVID-GAN: Classification and Segmentation of COVID-19 Lung Infections From CT Images Using GAN
Abirami, R. N., Vincent, P. M. D. R., & Kadry, S. (2022) · IGI Global eBooks · doi:10.4018/978-1-6684-7544-7.ch037
COVID-19 Detection Using Deep Learning Based Medical Image Segmentation
Walvekar, S., & Shinde, S. V. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-22405-8_10
Liu, Q., Chu, J., Yu, H., Wang, X., & Li, T. (2022) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis57298.2022.10016338
Challenges and Opportunity for Salient Object Detection in COVID-19 Era: A Study
Singh, V. K., & Kumar, N. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0236-1_1
Automatic detection of infected areas of CT images in COVID-19 patients using Inf-Seg-Net
(2023) · International Journal of Advanced Technology and Engineering Exploration · doi:10.19101/ijatee.2022.10100457
A Survey on COVID-19 Lesion Segmentation Techniques from Chest CT Images
Roy, K., Bhattacharjee, D., & Krejcar, O. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-2680-0_50
Detection of COVID-19 lesions based on computed tomography using U-Net 2.5D and GAN
Landim, J. A. G. S., Carvalho, E. D., Diniz, J. O. B., de Sousa, A. D., Luz, D. D. S., & Filho, A. (2023) · doi:10.5753/sbcas.2023.229466
“All works analyzed, with the exception of Wang et al. [Wang et al. 2020], Ha-sanzadeh et al. [Hasanzadeh et al. 2020] and Xu et al. [Xu et al. 2020], perform a segmentation step of the lung parenchyma.”
Method[Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function].
Xiao, H., Li, H., Ran, Z., Zhang, Q., Zhang, B., Wei, Y.-J., & Zhu, X. (2023) · PubMed Central · doi:10.7507/1001-5515.202206051
Liu, K., Chen, M., Xie, J., Mao, J., & Liu, W. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10239887
Thaseen, A., & Kothandaraman, D. (2023) · International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · doi:10.1109/icaiss58487.2023.10250591
Kvasnytsia, M., Berenguer, A. D., Hichem Sahli, B., & Vandemeulebroucke, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44917-8_7
Prabakaran, G., & B, J. K. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-230312
“Since December 2019, SARS-CoV-2 has been the origin of a new disease that disturbs people of all ages and can produce symptoms of asthma [1], acute respiratory failure, and even irreversible alterations to the biology of the lungs [2].”
Optimizing Segmentation Strategies: Self-Supervised Methods for COVID-19 ImagingPreprint
Gao, Y., Geng, D., Xu, L., Hua, Q., & Wang, P. (2023) · Research Square · doi:10.21203/rs.3.rs-3795779/v1
A Comparative Study on Image Segmentation Models in COVID-19 Diagnosis
Xu, S. Y., Chen, S., & Chen, M. (2024) · Mechanisms and machine science · doi:10.1007/978-3-031-44947-5_19
Pan, X., & Jia, Y. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10393874
Artificial intelligence-based quantification of COVID-19 pneumonia burden using chest CT
Nardocci, C., Simon, J., & Budai, B. K. (2024) · Imaging · doi:10.1556/1647.2024.00167
Chen, J., Chen, R., Qiu, J., Jin, Y., & Zhang, L. (2024) · PubMed Central · doi:10.12182/20240360605
Liang, Y., Wu, H., & Wei, X. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1374373
Noise‐robust neural networks for medical image segmentation by dual‐strategy sample selection
Shi, J., Yang, Y., & Zhang, K. (2024) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.8271
COVID-19 lesions image segmentation method based on UniFormer
Geng, P., Tan, Z., Cao, X., Wang, X., Wang, Y., Zhao, D., & Wang, C. (2024) · Imaging and Radiation Research · doi:10.24294/irr7128
“In response to the slight differences among healthy tissues. infected tissues and noise, Wang et al. [10] proposed COPLE-NET for segmenting COVID-19 infected lesions, which introduced maximum pooling and average pooling together in the encoding stage.”
A deep-learning-based diagnostic system for lobar, lobular, and interstitial pneumonia CT patterns
Li, J., Che, P., Yin, W., Wang, X., & Chen, X. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110818
Oliveira, A. D. S., Costa, M. G. F., Cósta, J., & Filho, C. F. F. C. (2024) · Diagnostics · doi:10.3390/diagnostics14242791
Weighted ensemble learning for accurate COVID-19 CT image segmentation
Fang, H., Luo, G., Peng, Y. K., & Luó, X. (2025) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.3047279
DECE-Net: a dual-path encoder network with contour enhancement for pneumonia lesion segmentation
Wang, T., Li, X., Liu, R., Wang, M., & Sun, J. (2025) · Journal of medical imaging · doi:10.1117/1.jmi.12.3.034503
Deep Learning-Driven COVID-19 Lesion Segmentation in CT Scans with R-EDNet
Kujur, A., & Raza, Z. (2025) · International Conference on Communication, Security and Artificial Intelligence (ICCSAI) · doi:10.1109/iccsai64074.2025.11064039
“Multi-class segmentation [4], CNN-based frameworks [18], and noisy-label learning techniques [19] further refine segmentation accuracy.”
Wang, L., Ye, P., Liao, W., Zhang, S., Zhang, S., & Wang, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05169-1_49
Self-citationCNN-based segmentation methods in medical imaging
Тангиров, Х. Э., Alimov, M., Mengliyev, I., & Aminov, B. (2025) · AIP conference proceedings · doi:10.1063/5.0299537
Xiang, Y., Wu, N., Yu, L., Cheng, K.-T. T., & Yan, Z. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3625260
“…to prevent model over-fitting to noise; (cid:2) RMD [38] mitigates annotation noise in medical imaging through mutual distillation; (cid:2) NR-Dice [39] introduces a noise-robust Dice loss and utilizes a teacher-student model to combat noise; (cid:2) FedNoRo [25] proposes per-class noise…”
Deep-Learning based Identification of Suspicious Areas in Breast MRIs
Röthlin, B. E. (2024) · reposiTUm (TU Wien) · doi:10.34726/hss.2024.117627
Mithun Raja, P., Sujitha, S., Vishal, K., & Gowri.S (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308660
A survey: AI Techniques for Medical Image Analysis
Mohammed, S. J., Ahmed, R. I., & Mohsin, R. M. (2025) · Basrah Researches Sciences · doi:10.56714/bjrs.51.2.17
“Cople-Net now passes through U-Net variables, which contain encoder and decoder structures [37].”
Motta, P. C. (2023) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
Rolling convolution filters for lightweight neural networks in medical image analysis
Paluru, N., Arora, M., & Yalavarthy, P. K. (2026) · Journal of medical imaging · doi:10.1117/1.jmi.13.2.024501
Abd-Ellah, M. K., Mohamed, A., & Salama, G. M. (2026) · Neural Computing and Applications · doi:10.1007/s00521-025-11772-8
Anton, V. J. J., Nehemiah, H. K., & Kannan, A. (2026) · Intelligent Data Analysis · doi:10.1177/1088467x261424996
HFSUNet: A UNet architecture optimized for precise segmentation of pneumonia lesion boundaries
Zhang, Z., Zhao, Y., Wu, X., Yao, Z., Jia, L., Yao, C., & Ma, F. H. (2026) · iScience · doi:10.1016/j.isci.2026.115364
“Wang et al. 10 proposed a noise-robust framework integrated with a noise-resistant Dice loss function for the automatic segmentation of pneumonia lesions from COVID-19 patients’ CT images.”
Li, H., Liu, J., huang, Z., Li, Z., Ma, X., Schüffler, P. J., Navab, N., & Zhou, S. K. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104036
Dual Annotation Learning with Selective Uncertainty for medical image segmentation with noisy labels
Han, Q., Yang, G., Chen, X., Liu, A. L. A., & Yu, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110088
Privacy-preserving and data-efficient deep learning for medical image segmentation
ZHENG, Z. (2024) · Institutional Repositories DataBase (IRDB)
Li, X., Ju, F., Xu, Y., & Chen, H. (2026) · Journal of medical imaging · doi:10.1117/1.jmi.13.3.034002
Polynomial Dice Loss for Medical Image Segmentation
Aizawa, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38407-2_41
Li, X. N., Huang, X., Zhan, J. M., Liu, Z., Yi, Y., Luo, Y., & 谢永明 (2026) · BMC Medical Imaging · doi:10.1186/s12880-026-02517-7
“…represented by the U-shaped structure and its attention-enhanced or nested variants such as SwinUNet [12], AttentionUNet [13], and Unet++ [14], have achieved remarkable segmentation accuracy in medical imaging tasks due to their efficient cross-level feature fusion mechanisms [15–18].”
Elnashar, A., Elnashar, N., & Elemam, A. (2026) · Research Square · doi:10.21203/rs.3.rs-10255012/v1
Li, H., Liu, J., Schüffler, P. J., Han, H., & Zhou, S. K. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104209
Das, A., Banik, D., Roy, K., Krejcar, O., & Bhattacharjee, D. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3712909
“COPLE-Net [26] registers the best precision but falls marginally short of CAD-UNet [32] by 0.08 % mean DSC. Closely following COPLE-Net [26] is the TransAttUNet [30], which falls short of CResPIE-SegViT by a margin of 1.66 % DSC. TransUNet [27] records the highest recall while CResPIE-SegViT ranks…”
InfluentialYao, X., Xu, L., Li, Q., Yang, K., Ren, C., & Gu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3410-3_32
Li, H., Guo, R., & Li, C. (2026) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi69079.2026.00257
“: Since medical images exhibit hierarchical spectral characteristics where low-frequency components encode global structures while high-frequency components preserve boundaries [21], [24], and traditional fixed methods cannot adapt to modality-specific characteristics [22], we design LFD.”
Self-citationLi, H., Xing, W., & Li, C. (2026) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi69079.2026.00068
“Accurate pulmonary infection segmentation represents a critical biomedical pattern recognition challenge for respiratory diseases like COVID-19, where complex pathologies, ambiguous boundaries, and multi-scale lesions present significant analytical challenges [3]–[6].”
Self-citationA multi-resolution dual-path network with domain separated attention for medical image segmentation
Zhu, S., Li, Y., Wang, C., Mao, T., & Dai, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116222
Intelligent outlier detection under imperfect industrial data conditions
Fang, J. (2026) · Brunel University Research Archive (BURA) (Brunel University London)
Kusuma, B. N., Neupane, R. B., Li, K., Ma, X., & Hariyanto, T. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134068
Self-citationHybrid deep features for COVID-19 lung CT image segmentation
Parandakh, P., & Fotouhi, A. M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02145-8
“Wang et al. [21] tackled limited annotated data by combining Dice and MAE losses for robustness and introducing COPLE-Net, which adapts to lesions of varying sizes and appearances.”
Metadata
- Authors
- Wang, G., Liu, X., Li, C., Xu, Z., Ruan, J., Zhu, H., Meng, T., Li, K., Huang, N., & Zhang, S.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- Sensetime (China) (CN)
- Pingliang People's Hospital (CN)
- Dingxi City People's Hospital (CN)
- Aviation General Hospital (CN)
- Sichuan University (CN)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2020-08
- Volume
- 39
- Issue
- 8
- Pages
- 2653-2663
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- PMC
- PMC8544954
- OpenAlex
- W3033272814
- Cited by
- 469
- References
- 57
- Citations by year
- 2026: 23 · 2025: 36 · 2024: 68 · 2023: 88 · 2022: 112 · 2021: 122 · 2020: 20
- FWCI
- 41.62
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (81771921, 61901084)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- COVID-19 pneumonia, lesion segmentation, CT images, label noise, self-ensembling, exponential moving average, medical image segmentation
- MeSH terms
- Betacoronavirus, Deep Learning, COVID-19, SARS-CoV-2, Algorithms, Humans, Lung, Pneumonia, Viral, Tomography, X-Ray Computed, Coronavirus Infections, Pandemics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.