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 201–300 of 495
Islam, M. S., Farid, F. A., Shamrat, F. M. J. M., Islam, M. N., Rashid, M., Bari, B. S., Abdullah, J., Islam, M. N., Akhtaruzzaman, M., Kabir, M. N., et al. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2517 · Cited by 15
Multi-Mode Interactive Image Segmentation
Zheng, L. L., Zhang, Z., Han, L.-H., & Lu, S.-P. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548096 · Cited by 15
“In real-world annotation tasks, such as the COVID-19 annotating, interacting based on automatic prediction [14, 52, 59] will reduce the manual annotating burden.”
MethodReza, S. M. S., Chu, W. T., Homayounieh, F., Blain, M., Firouzabadi, F. D., Anari, P. Y., Lee, J. H., Worwa, G., Finch, C. L., Kuhn, J. H., et al. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.02.027 · Cited by 15
“Indeed, this subjectivity is demonstrated as wide inconsistency in manual outlines among experts and from the same expert [1].”
A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images
Yu, F., Zhu, Y. M., Qin, X., Xin, Y., Yang, D., & Xu, T. (2021) · IET Image Processing · doi:10.1049/ipr2.12249 · Cited by 16
“[40] proposed a new model called COPLE-Net, it exploited a self-ensembling framework and a noise-robust Dice loss to improve the segmentation capability.”
MethodEarly diagnosis of COVID-19 patients using deep learning-based deep forest model
Singh, D., Kumar, V., Kaur, M., & Kumari, R. (2022) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2021.2021300 · Cited by 15
“The results from RT-PCR can be obtained within a few hours to 2 days (J. Wang et al., 2020).”
BackgroundInfluentialFully feature fusion based neural network for COVID-19 lesion segmentation in CT images
Li, W., Cao, Y., Wang, S., & Wan, B. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104939 · Cited by 14
Wei, J., Wang, G., & Zhang, S. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111401 · Cited by 14
Self-citationRobust T-Loss for medical image segmentation
González-Jiménez, Á., Lionetti, S., Gottfrois, P., Gröger, F., Navarini, A. A., & Pouly, M. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103735 · Cited by 15
ASMM-Net: A Hybrid CNN with Adaptive Scale Modulation for Robust Ischemic Stroke Lesion Segmentation
Paçal, İ., & Kunduracıoğlu, İ. (2025) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-025-00940-0 · Cited by 14
“Some of the methods, like COPLE-Net (Wang et al. 2020 ), employed atrous spatial pyramid pooling (ASPP) modules to reconstruct numerous feature maps that contain multi - scale information; this is a beneficial strategy to improve segmentation because it greatly enhances feature map detail and restricts spatial and bou…”
MIC-Net: A deep network for cross-site segmentation of COVID-19 infection in the fog-assisted IoMT
Ding, W., Abdel‐Basset, M., Hawash, H., & Pedrycz, W. (2022) · Information Sciences · doi:10.1016/j.ins.2022.12.017 · Cited by 14
“In [41], the authors developed a noise-robust dice loss as a generalized variant of dice loss and mean absolute error (MAE) loss to make the segmentation network more robust against noisy COVID-19 originating from different scales and presences.”
Multi-Modal COVID-19 Discovery With Collaborative Federated Learning
Chen, X., Shao, Y., Xue, Z., & Yu, Z. (2021) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis53392.2021.9754623 · Cited by 13
Unveiling the Influence of AI on Advancements in Respiratory Care: Narrative Review
Alqahtani, M. Μ., Alanazi, A., Algarni, S. S., Aljohani, H., Alenezi, F. K., Alotaibi, T. F., Alotaibi, M. M., Alqahtani, M. K., Alahmari, M. A., Alwadeai, K. S., et al. (2024) · Interactive Journal of Medical Research · doi:10.2196/57271 · Cited by 13
DEA-UNet: a dense-edge-attention UNet architecture for medical image segmentation
Zeng, Z., Fan, C., Xiao, L., & Qu, X. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.4.043032 · Cited by 13
“Wang et al.(9) proposed a novel noise-robust-Dice loss function and a noise robust learning framework based on CNNs self-integration, which is robust to noise labels and Dice losses.”
BackgroundInfluentialA novel full-convolution UNet-transformer for medical image segmentation
Zhu, T., Ding, D., Wang, F., Liang, W. F., & Wang, B. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105772 · Cited by 13
Liu, Z., Sun, C., Wang, H., Li, Z., Gao, Y., Lei, W., Zhang, S., Wang, G., & Zhang, S. (2021) · Medical Physics · doi:10.1002/mp.15260 · Cited by 13
Self-citationBartoli, A., Fournel, J., Maurin, A., Marchi, B., Habert, P., Castelli, M., Gaubert, J., Cortaredona, S., Lagier, J., Million, M., et al. (2022) · Research in Diagnostic and Interventional Imaging · doi:10.1016/j.redii.2022.100003 · Cited by 13
“Our DSC calculation method was identical to those from [20] and [21].”
Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs
Kim, S. T., Goli, L., Paschali, M., Khakzar, A., Keicher, M., Czempiel, T., Burian, E., Braren, R., Navab, N., & Wendler, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87234-2_26 · Cited by 13
Cao, Y., Wu, S., Liu, C., Lin, N., Wang, Y., Yang, C., & Li, J. (2021) · Journal of Computer Science and Technology · doi:10.1007/s11390-021-0782-5 · Cited by 12
“Deeplabv3, CE-Net, and UNet++ are newly proposed FCN-based image segmentation models and have shown their potential in medical image segmentation.”
BackgroundMethodInfluentialJu, Z., Ying, C., Ye, Z., Ma, D., Wang, B., & Cheng, Y. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.105970 · Cited by 12
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. (2021) · International Journal of Data Warehousing and Mining · doi:10.4018/ijdwm.2021100105 · Cited by 12
Supervised segmentation with domain adaptation for small sampled orbital CT images
Suh, S., Cheon, S., Choi, W., Chung, Y. W., Cho, W., Paik, J., Kim, S. E., Chang, D.-J., & Lee, Y. O. (2022) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwac029 · Cited by 12
do Carmo, D. S., Ribeiro, J. A., Comellas, A. P., Reinhardt, J. M., Gerard, S. E., Rittner, L., & Lotufo, R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.02365 · Cited by 12
“CopleNet (Wang et al., 2020) uses a noise-robust Dice (Sudre et al., 2017a) loss modification and an exponential moving average of a novel architecture as a teacher network that is only updated when the student has a low loss.”
MethodShi, Y., Ma, J., Yang, J., Wang, S., & Zhang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.13239 · Cited by 13
Fully Automated Spleen Segmentation in Patients using Convolutional Neural Network on CT Images
Ramkumar, G., Prabu, R. T., Anitha, G., Mohanavel, V., & Tamilselvi, M. (2022) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac55078.2022.9987387 · Cited by 11
Cai, G.-W., Liu, Y., Feng, Q., Liang, R.-H., Zeng, Q., Deng, Y., & Yang, W. (2023) · Bioengineering · doi:10.3390/bioengineering10070830 · Cited by 11
Xu, Z., Lu, D., Luo, J., Zheng, Y., & Tong, R. K. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103095 · Cited by 11
Self-citationSegmenting lung lesions of COVID-19 from CT images via pyramid pooling improved Unet
Ma, Y., Feng, P., He, P., Ren, Y., Guo, X., Yu, X., & Wei, B. (2021) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ac008a · Cited by 11
FCF: Feature complement fusion network for detecting COVID-19 through CT scan images
Liang, S. Y., Nie, R., Cao, J., Wang, X., & Zhang, G. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109111 · Cited by 11
“…lesion and organ manually until CNN was involved in and support doctors to segment their interest part automatically for the succeeding diagnose [17–19]; multimodal medical image fusion: image imaging from different apparatus stores various information, whereas CNN fused images can reduce…”
Sun, Y., Liang, D., Li, S.-Y., Chen, S., & Huang, S.-J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3562073 · Cited by 10
“Recent studies addressed this problem by explicitly considering systematic human labeling errors [34] and modifying the segmentation loss to increase robustness [35], [36].”
Qi, K., Yan, C., Niu, D., Zhang, B., Liang, D., & Long, X. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108451 · Cited by 10
Abbas, T., Linjawi, M., Iqbal, I. A., Alghushairy, O., Alsini, R. A. I., & Daud, A. Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108391 · Cited by 10
Fang, C., Liu, Y., Liu, Y., Liu, M., Qiu, X., Li, Y., Wen, J., & Yang, Y. (2022) · Medical Physics · doi:10.1002/mp.15661 · Cited by 10
Dhruv, B., Mittal, N., & Modi, M. (2022) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2022.2061376 · Cited by 10
“For the segmentation challenge, Wang et al. (2020)”
Computer Vision-Based Prognostic Modelling of COVID-19 from Medical Imaging
Fayyaz, A. M., Kolivand, M., Alyami, J., Roy, S. S., & Rehman, A. U. (2022) · Studies in big data · doi:10.1007/978-981-19-2057-8_2 · Cited by 11
Xiao, Z., Zhang, X., Liu, Y., Geng, L., Wu, J., Wang, W., & Zhang, F. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-022-02446-2 · Cited by 10
Bougourzi, F., Distante, C., Dornaika, F., & Ahmed, A. T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.15576 · Cited by 10
“Table 4: Performance evaluation of our proposed approach (D-TrAttUnet), Unet [23], Att-Unet [24], Unet++ [25], CopleNet [12], AnamNet [13], and SCOATNet [10] The aim of this section is to examine the significance of each element of the proposed D-TrAttUnet architecture.”
BackgroundMethodInfluentialFedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness
Xiang, Y., Wu, N., Yu, L., Yang, X., Cheng, K.-T. T., & Yan, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72117-5_35 · Cited by 9
He, L. T., Fu, J., Li, Y., Xiong, X., & Zhang, J. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3209941 · Cited by 9
Loop Residual Attention Network for Automatic Segmentation of COVID-19 Chest X-Ray Images
Yue, G., Lin, J., An, Z., & Yang, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3227798 · Cited by 9
“Self-attention mechanism [43] is widely used in various fields of deep learning to improve the discriminative ability of network models [28], [32].”
BackgroundMethodLizzi, F., Postuma, I., Brero, F., Cabini, R. F., Fantacci, M. E., Lascialfari, A., Oliva, P., Rinaldi, L. M., & Retico, A. (2023) · The European Physical Journal Plus · doi:10.1140/epjp/s13360-023-03896-4 · Cited by 9
PARADISE: Personalized and regional adaptation for HIE disease identification and segmentation
Bao, R., Weiss, R. J., Bates, S. V., Song, Y., he, S. T., Li, J., Bjørnerud, A., Hirschtick, R., Grant, P. E., & Ou, Y. (2025) · Medical Image Analysis · doi:10.1016/j.media.2024.103419 · Cited by 9
AI-Empowered Computational Examination of Chest Imaging for COVID-19 Treatment: A Review
Deng, H., & Li, X. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.612914 · Cited by 9
“Wang et al. (2020) have introduced a noise-robust Dice loss to improve the robustness of the model against noise labels.”
BackgroundCough Sound Classification Based on Similarity Metrics
Petrellis, N., & Adam, G. K. (2021) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp52935.2021.9522595 · Cited by 9
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Xuan, W., Zhao, S., Yao, Y., Liu, J., Liu, T., Chen, Y., Du, B., & Tao, D. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612136 · Cited by 9
“Inspired by the success of label-noise learning in classification, researchers took similar heuristics such as proposing robust loss functions [28] or algorithms for noisy label detection and correction [23, 27].”
MethodCOMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation
Shin, W., Lee, M. S., & Han, S. W. (2022) · Applied Sciences · doi:10.3390/app12042114 · Cited by 9
Dynamic feature learning for COVID-19 segmentation and classification
Zhang, X., Jiang, R., Huang, P., Wang, T., Hu, M., Scarsbrook, A. F., & Frangi, A. F. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106136 · Cited by 9
Lin, M., & Wang, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131125 · Cited by 8
PDRF-Net: a progressive dense residual fusion network for COVID-19 lung CT image segmentation
Lu, X., Xu, Y., & Yuan, W. (2023) · Evolving Systems · doi:10.1007/s12530-023-09489-x · Cited by 8
“To reduce external interference, Wang et al. (2020b) proposed a novel network (COPLE-Net) for COVID-19 lesion segmentation.”
InfluentialCovid-19 Diagnosis using Deep Learning Approaches: A Systematic Review
Abdullah, T. H., & Abdullah, B. H. (2024) · Mesopotamian Journal of Artificial Intelligence in Healthcare · doi:10.58496/mjaih/2024/012 · Cited by 8
Mustapha, B., Zhou, Y., Nawel, B., Chunyan, S., & Xiao, Z. (2025) · Journal of Radiation Research and Applied Sciences · doi:10.1016/j.jrras.2025.101650 · Cited by 8
Hurtado, R., Barrera, J. C. B., & Barrera, K. M. B. (2020) · IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) · doi:10.1109/ropec50909.2020.9258765 · Cited by 8
“Artı́culos presentan modelos basados en red neuronal convolucional (4) (6) para la detección de pacientes con COVID-19 que utilizan imágenes de rayos X, igualmente del tórax CXR.”
BackgroundU-Net-based medical image segmentation algorithm
Yan, W., Chen, C., & Zhang, D. (2021) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp52459.2021.9613447 · Cited by 8
FAM: focal attention module for lesion segmentation of COVID-19 CT images
Wu, X., Zhang, Z., Guo, L., Chen, H., Luo, Q., Jin, B., Gu, W., Lu, F., & Chen, J. (2022) · Journal of Real-Time Image Processing · doi:10.1007/s11554-022-01249-5 · Cited by 8
“[18] proposed noise-robust dice loss to solve the problem of poor training results caused by low-quality labels, and the DSC of the model is 80.”
BackgroundHe, T., Liu, H., Zhang, Z., Li, C., & Zhou, Y. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20021158 · Cited by 8
“Other methods applying semi-supervised [14,15] and unsupervised learning [16,17] fail to achieve good performance due to the large variations of infection on CT images, such as irregular shapes and ambiguous boundaries [18].”
MethodSelf-citationFang, C., Yan, W., Chen, Y., Dou, Z., Liu, T., Luo, F., Chen, W., Li, X., Chen, Y., Wu, W., et al. (2023) · Journal of Medical Virology · doi:10.1002/jmv.29036 · Cited by 8
Xu, Z., Lu, D., Yan, J., Sun, J., Luo, J., Wei, D., Frisken, S. F., Li, Q., Zheng, Y., & Tong, R. K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43901-8_1 · Cited by 8
Self-citationAdaptive Multi-scale Online Likelihood Network for AI-Assisted Interactive Segmentation
Asad, M., Williams, H., Mandal, I., Ather, S., Deprest, J. A., D’hooge, J., & Vercauteren, T. K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43895-0_53 · Cited by 8
Xiao, J., Cheng, T., Chen, D., Chen, H., Li, N., Lu, Y., & Cheng, L. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3360458 · Cited by 8
“…problems: first, when the training set contains a large amount of anomalous data, it increases the training complexity and risks overfitting [30], [31]; second, there is a discrepancy in the noise distribution between the training samples and the actual scene, which challenges the generalization…”
BackgroundA Novel Weakly Supervised Framework Based On Noisy-Label Learning For Medical Image Segmentation
Wu, H., Wang, H., He, H., He, Z., & Wang, G. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9433883 · Cited by 8
“…structures, additional modules such as a concatenation of max-pooling and avg-pooling and Atrous Spatial Pyramid Pooling (ASPP) are introduced to enable the network to extract features at various levels and scales [5] from the images and generate precise segmentation with limited annotations.”
BackgroundMethodInfluentialSelf-citationAn Ensemble Learning Framework For Multi-Class Covid-19 Lesion Segmentation From Chest Ct Images
Enshaei, N., Afshar, P., Heidarian, S., Mohammadi, A., Rafiee, M. J., Oikonomou, A., Fard, F. B., Plataniotis, K. N., & Naderkhani, F. (2021) · IEEE International Conference on Autonomous Systems (ICAS) · doi:10.1109/icas49788.2021.9551169 · Cited by 8
Xie, H., Gao, X., & Guoyan Zheng, A. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103913 · Cited by 7
Learning with less: A survey of deep learning in medical imaging under varying supervision levels
Kumari, S., & Singh, P. P. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103375 · Cited by 8
Context-aware and local-aware fusion with transformer for medical image segmentation
Xiao, H., Li, L., Liu, Q., Zhang, Q., Liu, J., & Liu, Z. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad14c6 · Cited by 7
Bougourzi, F., Distante, C., Dornaika, F., Taleb-Ahmed, A., Hadid, A., Chaudhary, S., Yang, W., Qiang, Y., Anwar, T., Breabăn, M., et al. (2024) · Italian National Conference on Sensors · doi:10.3390/s24051557 · Cited by 7
The role of advanced machine learning in COVID-19 medical imaging: A technical review
Fayyaz, A. M., Abdulkadir, S. J., Hassan, S. U., Al-Selwi, S. M., Sumiea, E. H., & Talib, L. F. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.105154 · Cited by 7
Gampala, V., Rathan, K., Selvin, C. N., Shajin, F. H., & Rajesh, P. (2022) · Electromagnetic Biology and Medicine · doi:10.1080/15368378.2022.2065679 · Cited by 7
Towards smart diagnostic methods for COVID-19: Review of deep learning for medical imaging
Moghaddam, M. J., & Ghavipour, M. (2022) · IPEM-Translation · doi:10.1016/j.ipemt.2022.100008 · Cited by 7
A Deep Learning Method for Pneumonia Detection Based on Fuzzy Non-Maximum Suppression
Wu, H., Lu, H., Ping, M., Zhu, W., & Li, Z. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3247483 · Cited by 7
“In recent years, CNN has achieved excellent performance in the image classification [11], [12], [13], object detection [14], [15], [16], and instance segmentation [17], [18], [19] tasks.”
BackgroundShanthi, A., & Koppu, S. (2023) · Sensors · doi:10.3390/s23115316 · Cited by 7
“Many deep convolutional neural networks such as COPLE-Net [15] have been developed and proved their capabilities in offering the best performance on infection segmentation of COVID-19 from lung CT images [16].”
MethodZhu, Q., Che, P., Li, M., Guo, W., Ye, K., Yin, W., Chu, D., Wang, X., & Li, S. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-23-945 · Cited by 7
CHDNet: A lightweight weakly supervised segmentation network for lung CT image
Lu, F., Liu, T., Zhang, T., Jin, B., & Gu, W. (2024) · Displays · doi:10.1016/j.displa.2024.102650 · Cited by 7
AĞRALI, M., & Kılıç, V. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106167 · Cited by 7
Xu, Z., Chen, C., Lu, D., Sun, J., Wei, D., Zheng, Y., Li, Q., & Tong, R. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72111-3_28 · Cited by 7
“5 and ϵ = 10 − 5 due to demonstrated noise-robustness [18].”
Self-citationHuang, Z., Wang, Z., Zhao, T., Ding, X., & Yang, X. Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106850 · Cited by 7
[Research progress in lung parenchyma segmentation based on computed tomography].
Xiao, H., Ran, Z., Huang, J., Ren, H., Liu, C., Zhang, B., Zhang, B., & Dang, J. (2021) · PubMed · doi:10.7507/1001-5515.202008032 · Cited by 7
COVID-19 Imaging-based AI Research - A Literature Review
Chang, S., Ge, C., Zhang, L., Xie, L., Kong, R., & Zhang, H. (2021) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405617666210902103729 · Cited by 7
RETRACTED: A Survey on Techniques used in Medical Imaging Processing
Chatterjee, P., & Rani, D. S. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2089/1/012013 · Cited by 7
““Flexible Prediction of CT Images from MRI Data Through Improved Neighborhood Anchored Regression for PET Attenuation Corrections [53]” by Liming Zhong et al, in IEEE journal of biomedical and health informatics, April 2020 deals with attenuation correction in PET/MRI images.”
RetractedAbdel‐Basset, M., Hawash, H., & Chang, V. I. C. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3146175 · Cited by 7
“Moreover, Wang et al. [8] introduced a noise-robust seg-mentationnetwork(COPLE-Net)tolearntosegmentCOVID-19 lesionsfromnoisyannotated2-Ddatausingnoise-robustdice loss(NRD).”
BackgroundMethodInfluentialA Deep Ensemble Learning Approach to Lung CT Segmentation for Covid-19 Severity Assessment
Ben-Haim, T., Sofer, R. M., Ben‐Arie, G., Shelef, I., & Raviv, T. R. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897656 · Cited by 7
Combined Cloud-Based Inference System for the Classification of COVID-19 in CT-Scan and X-Ray Images
Dubey, A. K., & Mohbey, K. K. (2022) · New Generation Computing · doi:10.1007/s00354-022-00195-x · Cited by 7
“Researchers use X-ray images to find the absence or presence of COVID-19 in given images [19].”
Li, B., Wang, J., Wang, B., Shao, Z., Li, W., Huang, J., & Li, P. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108939 · Cited by 7
Xie, X., Ma, S.-X., Luo, X., Liao, D.-Y., Han, D., Huang, Z.-P., Chen, Z., Li, X.-P., Li, B., Hu, S., et al. (2025) · Annals of Medicine · doi:10.1080/07853890.2025.2540596 · Cited by 6
“Several metrics were employed to quantify the performance of the segmentation model, including the DSC (Dice similarity coefficient) [27], IOU (intersection over union) [28], RVE (relative volume error) [29] and HD (Hausdorff distance) [30].”
A Deep Learning Approach For Improved Segmentation Of Lesions Related To Covid-19 Chest CT Scans
Vasilescu, V., Neacsu, A., Chouzenoux, É., Pesquet, J.-C., & Burileanu, C. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434139 · Cited by 6
“For other CT slice-based approaches, we refer the reader to [12, 13, 14].”
COVID-19 Imaging Detection in the Context of Artificial Intelligence and the Internet of Things
Gu, X.-W., Chen, S., Zhu, H., & Brown, M. (2022) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2022.018948 · Cited by 6
Self-citationWei, J., & Wang, G. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230433 · Cited by 6
“The chest CT images used in this study are obtained from public datasets [14, 15, 16], and they are approved by the corresponding institutional review board.”
MethodSelf-citationCap2Seg: leveraging caption generation for enhanced segmentation of COVID-19 medical images
Zhao, W., Li, F., Diao, Y., Fan, P., & Chen, Z. (2024) · Frontiers in Physics · doi:10.3389/fphy.2024.1439122 · Cited by 6
Automatic COVID-19 and Common-Acquired Pneumonia Diagnosis Using Chest CT Scans
Motta, P. C., Cortez, P. C., Silva, B. R. D. S., Yang, G., & de Albuquerque, V. H. C. (2023) · Bioengineering · doi:10.3390/bioengineering10050529 · Cited by 6
“[26] Encoder–decoderbased X Private X DSC, RVE, and HD95”
BackgroundMethodOptimal Synergic Deep Learning for COVID-19 Classification Using Chest X-Ray Images
Escorcia‐Gutierrez, J., Gamarra, M., Soto-Díaz, R., Alsafari, S., Yafoz, A., & Mansour, R. F. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.033731 · Cited by 6
Deep Stacked Ensemble Learning Model for COVID-19 Classification
Madhu, G., Baru, L. B., Boddeda, R., Vardhan, S., Kautish, S., Alnowibet, K. A., Alrasheedi, A. F., & Mohamed, A. W. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.020455 · Cited by 6
“[15] proposed the use of COPEL-Net to segment COVID-19 pneumonia lesions from CT images.”
MethodCOVID ‐19 lung infection segmentation from chest CT images based on CAPA‐ResUNet
Ma, L., Song, S., Guo, L., Tan, W., & Xu, L. (2022) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22819 · Cited by 6
“Wang et al. 24 proposed a noise-robust learning algorithm for the segmentation of COVID-19 lung lesions.”
BackgroundInfluentialA COVID-19 Multipurpose Platform
Petrellis, N. (2020) · Digital Biomarkers · doi:10.1159/000511704 · Cited by 6
“Lung ultrasonography images can also reveal signs of COVID-19 [3].”
BackgroundMethodology to create 3D models of COVID-19 pathologies for virtual clinical trials
Pérez, S. R., Coolen, J., Struelens, L., Marshall, N., Cockmartin, L., Biebaû, C., Desmet, J., Bosmans, H., & Wever, W. D. (2021) · Journal of medical imaging · doi:10.1117/1.jmi.8.s1.013501 · Cited by 6
“ation of the models is using automatic segmentation software to identify the pathology in the CT images.(34,36) A study using a similar methodology has been recently published by Abadi et al.”
MethodAutomatic Segmentation of COVID-19 Pneumonia Lesions and its Classification from CT images: A Survey
Rathod, S. R., & Khanuja, H. K. (2021) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit51480.2021.9498350 · Cited by 6
“The training process of Deep learning technique needs huge amount of clean data, so it is necessary to learn from noisy annotations [13].”
BackgroundWeakly-supervised lesion analysis with a CNN-based framework for COVID-19
Wu, K., Jelfs, B., Ma, X., Ke, R., Tan, X., & Fang, Q. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac4316 · Cited by 6
“Naturally, for x-ray images 2-dimensional CNNmodels are used (Wang et al 2020c, Duran-Lopez et al 2020, Narin et al 2021).”
BackgroundMethodInfluentialMA-Net:Mutex attention network for COVID-19 diagnosis on CT images
Zheng, B., Zhu, Y. M., Shi, Q., Yang, D., Shao, Y., & Xu, T. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03431-5 · Cited by 6
Attention-based Automated Chest CT Image Segmentation Method of COVID-19 Lung Infection
Lee, B. J., Martirosyan, S. T., Khan, Z., Chiu, H. Y., Wang, Z., Shi, W., Giuste, F., Zhong, Y., Sun, J., & Wang, M. D. (2022) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe55377.2022.00042 · Cited by 6
“3) COPLE U-Net: COPLE U-Net [7] is an architecture modified from U-Net to focus on data with noisy labels.”
BackgroundMethodInfluentialPathological Image Segmentation with Noisy LabelsPreprint
Xiao, L., Li, Y., Qv, L., Tian, X., Peng, Y., & Zhou, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02602 · Cited by 6
“In [9,11,20], a teacher-student structure is utilized to overcome the negative impact of noisy labels, but they only deal with the situation where one image corresponds to only one label.”
BackgroundMobarakeh, S. A. M., Kazemi, K., Aarabi, A., & Danyal, H. (2024) · HAL · doi:10.48550/arxiv.2401.07020 · Cited by 6
“In an effort to deal with this matter, Wang et al. [66] addressed the issue of learning from noisy labels They introduced a noise-robust Dice loss function that able to handle noisy labels and the Non-uniform distribution of foreground and background pixels.”
BackgroundLiu, J., Junqi, Z., Cen, L., Wu, X., Wu, J., Zhang, K., & Zhou, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3400352 · Cited by 5
“Although great efforts have been conducted to study the diagnosis and treatment of COVID-19, the virus mutates too quickly and is too transmissible to be effective in stopping it [1].”
BackgroundSA-Seg: Annotation-Efficient Segmentation for Airway Tree Using Saliency-Based Annotation
Zhou, K., Chen, N., Zhang, Y., & Xu, X. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3568855 · Cited by 5
“MAE [44] + Dice and NR-Dice [46] improve the DSC metrics but yield a decrease in TD and BD in both datasets.”
Influential
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.