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 301–400 of 495
Dual attention fusion UNet for COVID-19 lesion segmentation from CT images
Ma, Y., Zhang, Y., Chen, L., Jiang, Q., & Wei, B. (2023) · Journal of X-Ray Science and Technology · doi:10.3233/xst-230001 · Cited by 5
“The segmenting results of the proposed DAF-UNet are compared with that of the state-of-the-art methods for medical image segmentation, including UNet [15], UNet++ [17], Dense-UNet [38], Gated-UNet [39], Inf-Net [20], and COPLE-Net [21].”
Unpaired Cross-Modal Interaction Learning for COVID-19 Segmentation on Limited CT Images
Guan, Q., Xie, Y., Yang, B., Zhang, J., Liao, Z., Wu, Q., & Xia, Y. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43898-1_58 · Cited by 5
Semi-supervised segmentation on medical images with pseudo label calibration and neural process
Zhang, T., Luo, Y., Wang, X., & Kwong, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107510 · Cited by 5
Automatic Sequence-Based Network for Lung Diseases Detection in Chest CT
Hao, J., Xie, J., Liu, R., Hao, H., Ma, Y., Yan, K., Liu, R., Zheng, Y., Zheng, J., Liu, J., et al. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.781798 · Cited by 5
“This body of work on COVID-19 has focused primarily on two problems: lesion segmentation (16, 21, 22), and automated screening (23 – 31).”
BackgroundQayyum, A., Lalande, A., & Mériaudeau, F. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.009 · Cited by 5
“[60] UNet + SegUNet 100 CT scans Guotai Wang et al.”
Segmentation-based context-aware enhancement network for medical images
Bao, H., Li, Q., & Zhu, Y. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01950-2 · Cited by 5
“Among various studies using visual technology to assist medical image analysis [1–5], medical image segmentation is one of the most significant areas of research.”
Zhao, C., Shen, Y., Su, N., Yan, Y., Feng, S., Xiang, W., Liu, Y., & Zhao, T. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3338977 · Cited by 5
“Specific comparative methods include NRL [48], GCE [49], TRI-NET [50], CFWS [35], ADELE [34].”
MethodMSAMS-Net: accurate lung lesion segmentation from COVID-19 CT images
Wang, Z., Zhu, H., & Gao, X. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18735-6 · Cited by 5
“A COPLE-Net [14] was developed using a novel noise-robust framework to deal with the COVID-19 pneumonia lesions with various scales and appearances.”
Self-citationPemmaraju, R., Kim, G., Mekki, L., Song, D. Y., & Lee, J. (2024) · Journal of medical imaging · doi:10.1117/1.jmi.11.2.024009 · Cited by 5
“Axial UNet has the same architecture as ACA-UNet but uses a 3D version of the original axial self-attention transformer as used in Wang et al. 41 in all transformer layers.”
MethodInfluentialAdaptive Semi-supervised Segmentation of Brain Vessels with Ambiguous Labels
Lin, F., Xia, Y., Ravikumar, N., Liu, Q., MacRaild, M., & Frangi, A. F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58171-7_11 · Cited by 5
Wang, L., Qu, Y., Luo, X., Liao, W., Zhang, S., & Wang, G. (2024) · The Journal of Machine Learning for Biomedical Imaging · doi:10.59275/j.melba.2024-489g · Cited by 5
“To ensure robustness against inaccurate annotations in segmentation tasks, Liu et al. (2022) enforced multi-scale cross-view consistency, and Wang et al. (2020a) introduced a noise-robust Dice loss.”
Self-citationDeep Reinforcement Learning Driven Weakly Supervised Lesion Segmentation in Lung CT Sequence Images
Lai, Y., Liu, X., Liang, X., Rong, C., Wu, Y., & Zheng, W. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3571146 · Cited by 5
Self-citationGao, Y., Wang, H., Liu, X., Huang, N., Wang, G., & Zhang, S. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630215 · Cited by 5
“After the outbreak of COVID-19, a lot of methods based on deep learning have been proposed for segmenting the CT images of COVID-19 [8], [9], [10].”
MethodSelf-citationC3D-UNET: A Comprehensive 3D Unet for Covid-19 Segmentation with Intact Encoding and Local Attention
Bao, Y., Zeng, H., Zhou, C., Liu, C., Zhang, L., Qian, D., Wang, J., & Lu, H. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629634 · Cited by 5
“[14] proposed a 2D segmentation model named COPLE-Net and a noise-robust self-ensemble strategy.”
MethodKillekar, A., Grodecki, K., Lin, A., Cadet, S. J., McElhinney, P. A., Razipour, A., Chan, C., Pressman, B. D., Julien, P. J., Chen, P., et al. (2022) · Journal of medical imaging · doi:10.1117/1.jmi.9.5.054001 · Cited by 5
“Because results of segmentation are presented to the human reader for visual inspection, eventual corrections enable the implementation of a human-in-the-loop strategy to reduce the annotation effort and provide high-volume training datasets to improve the performance of deep-learning models.(45) Furthermore, objectiv…”
BackgroundSotoudeh‐Paima, S., Hasanzadeh, N., Bashirgonbadi, A., Aref, A., Naghibi, M., Zoorpaikar, M., Arian, A., Gity, M., & Hamid Soltanian-zadeh, A. (2022) · Iranian Journal of Radiology · doi:10.5812/iranjradiol-117992 · Cited by 5
“(23) proposed a noise-robust learning framework based on a 2D convolutional neural network (CNN), combined with an adaptive self-ensembling framework for slice-by-slice image segmentation.”
BackgroundArtificial Intelligence and Big Data for COVID-19 Diagnosis
Sakly, H., Al-Sayed, A. A., Said, M., Loussaief, C., Seekins, J. M., & Sakly, R. (2022) · Integrated science · doi:10.1007/978-3-031-11199-0_6 · Cited by 5
Özcan, A. N. Ş., & Aslan, K. (2021) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405617666210806123720 · Cited by 5
Faruk, M. F. (2021) · International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI) · doi:10.1109/acmi53878.2021.9528285 · Cited by 5
“Wang et al. [17] proposed a noise-robust segmentation model named “COPLE-Net” for the fast and automated lung lesions localization due to COVID-19 pneumonia.”
BackgroundU-Net-based COVID-19 CT Image Semantic Segmentation: A Transfer Learning Approach
Ferdi, A., Benierbah, S., & Ferdi, Y. (2022) · International Conference on Image and Signal Processing and their Applications (ISPA) · doi:10.1109/ispa54004.2022.9786341 · Cited by 5
“Wang et al. [7] introduced a novel noise-robust dice loss function, which is a combination and generalization of mean absolute error loss that is robust against noisy labels and dice loss, to process the noisy annotations for training models.”
BackgroundCarré, A., Deutsch, É., & Robert, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09002-8_23 · Cited by 5
Grodecki, K., Killekar, A., Lin, A., Cadet, S. J., McElhinney, P. A., Razipour, A., Chan, C., Pressman, B. D., Julien, P. J., Simon, J., et al. (2021) · PubMed · doi:10.48550/arxiv.2104.00138 · Cited by 5
“reader for visual inspection, eventual corrections enable the implementation of a human-in-the-loop strategy to reduce the annotation effort and provide highvolume training datasets to improve the performance of deep-learning models [25].”
BackgroundOpen-source skull reconstruction with MONAI
Li, J., Ferreira, A., Puladi, B., Alves, V., Kamp, M., Kim, M., Nensa, F., Kleesiek, J., Ahmadi, S., & Egger, J. (2023) · SoftwareX · doi:10.1016/j.softx.2023.101432 · Cited by 5
CASC-AI: Consensus-aware Self-corrective Learning for Noise Cell SegmentationPreprint
Deng, R., Yang, Y., Pisapia, D. J., Liechty, B., Zhu, J., Xiong, J., Guo, J., Lu, Z., Wang, J., Yao, X., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.07302 · Cited by 5
Sujini, G. N., & Balakrishna, S. (2026) · Scientific Reports · doi:10.1038/s41598-025-34731-8 · Cited by 4
“Block 4 (Modified ASPP Block) 59 employs atrous convolutions to capture multi-scale contextual information without significantly increasing the number of parameters, which is beneficial for detecting nodules of varying sizes and echogenic patterns from ultrasound imaging.”
Review on Automatic Covid-19 Detection from Chest CT Images using Artificial Intelligence
Mali, D., & Patil, S. A. (2022) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic55036.2022.9848891 · Cited by 4
Shen, Y., Liao, E., Tai, T., Liao, Y., Sun, C., Lee, C., See, S. C. W., & Chen, H. (2023) · Journal of Biophotonics · doi:10.1002/jbio.202300285 · Cited by 4
GAN based approaches for self-supervised segmentation: A comparative study
Elmourabit, Z., & Banouar, O. (2024) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-1928 · Cited by 4
“In 2020, Guotai Wang et al. [1] proposed a novel noise-robust framework for ad-dressing noisy labels in the segmentation task.”
BackgroundLu, J., Wang, K., Ding, H., Shao, Z., Qin, R., & Huo, G. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01726-4 · Cited by 4
“In 2017, Chen et al. proposed the ASPP structure in the DeepLab V2 model [28].”
X-ray Images Detection of COVID-19 Based on Deepwise Separable DenseNet
Wang, Q., Yang, B. F., Liu, W., & Chen, G. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688876 · Cited by 4
“Although CT examination is an advanced medical imaging examination technology, which can help doctors carry out detailed analysis in medical imaging, X-ray plain film is cheaper than CT, and COVID-19 can be quickly diagnosed by doctor [8]-[9].”
BackgroundeSwin-UNet: A Collaborative Model for Industrial Surface Defect Detection
Cui, H., Xing, T., Ren, J., Chen, Y., Yu, Z., Guo, B., & Guo, X. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads56603.2022.00056 · Cited by 4
“[19] designed an ensemble model, COPLE-Net, and proposed a new noise-robust Dice loss function, which can obtain better segmentation results.”
MethodCOVID-19 monitoring system: in-browser face mask detection application using deep learning
Pham, T.-N., Nguyen, V.-H., & Huh, J. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15099-1 · Cited by 4
“According to these related studies [18, 32, 50], we decided to use a one-stage detector as YOLO which is one of the most widely used real-time object Fig.”
Murmu, A., & Kumar, P. (2024) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-024-03024-z · Cited by 4
“Additionally, according to some studies (Bougourzi et al. [16], Zhang et al. [18], Wang et al. [19], Liu et al. [20]) it could take substantially less time and effort.”
Lightweight SDENet Fusing Model-Based and Learned Features for Computational Histopathology
Bao, R., Zhao, Y., Srivastava, A., Frazier, S. R., & Palaniappan, K. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3470312 · Cited by 4
“Secondly, we explore several U-Net derivatives, specifically the Naylor et al. approach [22], the Attention U-Net [19], R2U-Net [23], COPLENet [98], CENet [99], and ResUNet.”
A Noise Robust Framework via Uncertainty Guidance for Medical Image Segmentation with Noisy Label
Huang, Z., Yang, Y., Zhao, T., & Yang, X. Y. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10687399 · Cited by 4
“(3) The proposed method was extensively evaluated on two public datasets: UESTC-COVID-19 [5] and AbdomenCT-1K [15].”
BackgroundMethodCOVID-19 Infection Segmentation from Chest CT Images Based on Scale Uncertainty
Oda, M., Zheng, T., Hayashi, Y., Otake, Y., Hashimoto, M., Akashi, T., Aoki, S., & Mori, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90874-4_9 · Cited by 4
“Other papers also employ 2D image-based process [5,6,7].”
BackgroundMethodHe, Z., Wong, A. N. N., & Yoo, J. S. (2023) · Bioengineering · doi:10.3390/bioengineering10080928 · Cited by 4
“[9] COPLE-Net • Noise-robust loss • Noise-robust dice loss Function to handle • The performance under a wider range of • Adaptive self-ensembling framework noisy annotations during the training process.”
Zhou, Z., Hayashi, Y., Oda, M., Kitasaka, T., & Mori, K. (2024) · Healthcare Technology Letters · doi:10.1049/htl2.12068 · Cited by 4
“To train a local model from this noisy dataset, we employ the noise-robust Dice (NR-Dice) loss nd [11], a generalization of dice loss and mean absolute error (MAE) loss.”
BackgroundMethodInfluentialInteractive Segmentation for COVID-19 Infection Quantification on Longitudinal CT Scans
Foo, M. X.-L., Kim, S. T., Paschali, M., Goli, L., Burian, E., Makowski, M. R., Braren, R., Navab, N., & Wendler, T. (2023) · IEEE Access · doi:10.1109/access.2023.3297506 · Cited by 4
“Numerous researchers utilized deep learning-based methods for this task [2]–[4].”
BackgroundMethodAdjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate
Öner, D., Koziński, M., Citraro, L., & Fua, P. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3193072 · Cited by 4
Semi-automatic Segmentation of COVID-19 Infection in Lung CT Scans
Shariaty, F., Mousavi, M., Moradi, A., Oshnari, M. N., Navvabi, S., Orooji, M., & Novikov, B. (2022) · Springer proceedings in physics · doi:10.1007/978-3-030-81119-8_7 · Cited by 4
Wang, Y., Yang, Q., Tian, L., Zhou, X., Rekik, I., & Huang, H. (2022) · Medical Physics · doi:10.1002/mp.15600 · Cited by 4
A Machine learning Classification approach for detection of Covid 19 using CT images
Chickaramanna, S. G., Veerabhadrappa, S. T., Tejas, A., Vaishnavi, P., Gowda, R., Udupa, P., Spoorthy, Reddy, S., & Sudarshan, E. (2022) · EMITTER International Journal of Engineering Technology · doi:10.24003/emitter.v10i1.672 · Cited by 4
Noisy Supervised Deep Learning for Remote Sensing Image Segmentation Using Electronic Maps
Zhang, Q., Pan, S., Min, F., Wu, Y., Zhang, Z., & Luo, H. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3285600 · Cited by 4
“Current approaches to noise supervision focus on designing noise-resistant deep learning models [19].”
BackgroundMS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images
Pan, X., Zhu, H., Du, J., Hu, G., Han, B., & Jia, Y. (2023) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s417068 · Cited by 4
“Wang et al 24 proposed COPLE-Net to mitigate down-sampling’s information loss problem by combining max-pooling and average pooling, using the bridge layer to mitigate the semantic gap between encoder and decoder.”
MethodSelf-citationDai, K., Zhou, Z., Qiu, S., Wang, Y., Zhou, M., Li, M., & Li, Q. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191749 · Cited by 4
“Other noise-robust training approaches like [31] perform co-training with a pair of studentteacher model and a new noise-robust loss function to their method.”
MethodLongitudinal Self-Supervision for COVID-19 Pathology QuantificationPreprint
Czempiel, T., Rogers, C., Keicher, M., Paschali, M., Braren, R., Burian, E., Makowski, M. R., Navab, N., Wendler, T., & Kim, S. T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.10804 · Cited by 4
A Review on Medical Image Segmentation TechniquesPreprint
Bahendwar, Y., & Thankachan, D. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4607754 · Cited by 4
Clean Label Disentangling for Medical Image Segmentation with Noisy LabelsPreprint
Wang, Z., Zhao, Z. W., Guo, E., & Zhou, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.16580 · Cited by 4
“The second category includes the methods that pro-pose noise-robust loss functions to mitigate the influence of the noisy labels [14, 36, 37], as shown in Fig.”
MethodA Comprehensive Review on Deep Learning With Noisy Labels: Challenges, Solutions, and Frontiers
Fang, J., Wang, Z., Liu, W., Zhang, Y. J., He, Y., & liu, X. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3683790 · Cited by 3
“A noise-robust framework has been developed in [110] for segmenting COVID-19 pneumonia lesions from CT scans, which has improved segmentation performance under noisy label conditions.”
Self-citationZhai, J., Tian, F., Li, A., Qian, S., Wang, R., & Zou, X. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23035 · Cited by 3
“Of course, several other research works 46,47 also combined different pooling layers to learn image effective features.”
BackgroundA dense pyramid convolutional neural network for MRI brain tumor segmentation
Xiong, W., Song, H., Xie, H., & Li, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07805-7 · Cited by 3
Dmbg-Net: Dilated multiresidual boundary guidance network for COVID-19 infection segmentation
Xiang, Z., Mao, Q., Wang, J., Tian, Y., Zhang, Y., & Wang, W. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2023892 · Cited by 3
“The infected areas in lung CT images are usually scattered with complex backgrounds [30,31].”
BackgroundYue, G., Yang, C., Zhao, Z., An, Z., & Yang, Y. (2023) · Frontiers in Physiology · doi:10.3389/fphys.2023.1296185 · Cited by 3
“Different from the skip connection methods of UNet and COPLE-Net, ERGPNet uses spatial attention for optimization in the connection process, which increases the weight of target area information while reducing the semantic gap between codecs.”
BackgroundInfluentialNoise Robust Training of Segmentation Model Using Knowledge Distillation
Raipuria, G., Bonthu, S., & Singhal, N. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68763-2_8 · Cited by 3
Modified U-Net Based Covid-19 Lesion Segmentation Using CT Scans
Gopika Gopan, K., Peruru, P. S., & Sinha, N. (2022) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom55316.2022.9840780 · Cited by 3
Semi-Supervised Segmentation of COVID-19 Infection on CT-Scan Lung Using Dynamic Mutual Training
(2022) · International journal of intelligent engineering and systems · doi:10.22266/ijies2022.1031.47 · Cited by 3
“Milletari et al. [23] have proven effective in equaling this problem by implicitly establishing a balance between foreground and background classes.”
Background2D Medical Image Segmentation Combining Multi-Scale Channel Attention and Boundary Enhancement
Chen, D., Zhang, F., Hao, P., Wu, F., & Dong, T. (2022) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2022.19185 · Cited by 3
“…COPLENet [22] 72.64 a. 输入图像 b. 真实标注 c. U-Net [6] d. UNet++ [11] e. CENet [13] f. COPLENet [22] g. 本文 U-Net [6] 87.94 83.58 94.25 UNet++ [11] 88.57 85.66 94.43 CENet [13] 88.62 85.74 94.71 COPLENet [22] 87 a. 输入图像 b. 真实标注 c. U-Net U-Net [6] d. UNet++ [11] e. CENet [13] f. COPLENet [22] g. 本文 图 12”
InfluentialCOVID-19 Lungs CT Scan Lesion Segmentation
Shoaib, M. S., & Suhail, Z. (2024) · Foundation University Journal of Engineering and Applied Sciences · doi:10.33897/fujeas.v4i2.782 · Cited by 3
A Novel Strategy for COVID-19 Classification from Chest X-ray Images Using Deep Stacked-Ensembles.
Baru, L. B., Boddeda, R., Sai Vardhan, K., Sai Mohan, G., Deepak, S., & Patel, S. A. (2020) · Cited by 3
Neuron Segmentation using Incomplete and Noisy Labels via Adaptive Learning with Structure Priors
Park, C., Lee, K., Kim, S. Y., Cecen, F. S. C., Kwon, S., & Jeong, W. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434102 · Cited by 3
“Active and Passive Loss (APL) [9], and Noise-Robust Dice (NR-Dice) [10].”
BackgroundAmeliorating the Accuracy & Dimensional Reduction of Multi-modal Biometrics by Deep Learning
Raiu, V., Vidyasree, P., & Patel, A. (2021) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero50100.2021.9438214 · Cited by 3
“GuotaiWang.et.al. developed a framework for segmenting the infection from CT images of various sizes and provides robustness towards noise [5].”
BackgroundPneumonia Classification using Gabor-Convolutional Neural Networks and Image Enhancement
Minarno, A. E., Alfarizy, M. R., Hendryawan, A., Syaifuddin, S., & Munarko, Y. (2021) · doi:10.1109/icoict52021.2021.9527427 · Cited by 3
A game theory-based COVID-19 close contact detecting method with edge computing collaboration
Shen, Y., Liu, B., Xia, X., Qi, L., Xu, X., & Dou, W. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.04.029 · Cited by 3
“Therefore, the use of cientific methods to detect the spread of the epidemic has important ractical significance [6].”
Using Deep Learning-based Features Extracted from CT scans to Predict Outcomes in COVID-19 PatientsPreprint
Nuthalapati, S. V., Vizcaychipi, M. P., Shah, P. L., Chudzik, P., Leow, C. H., Yousefi, P., Selim, A., Tait, K., & Irving, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.05009 · Cited by 3
Open-Source Skull Reconstruction with MONAIPreprint
Li, J., Ferreira, A., Puladi, B., Alves, V., Kamp, M., Kim, M., Nensa, F., Kleesiek, J., Ahmadi, S., & Egger, J. (2022) · RWTH Publications (RWTH Aachen) · doi:10.48550/arxiv.2211.14051 · Cited by 3
“Another MONAI research contribution example is COPLENet [11], which is a noise-robust framework for the automatic segmentation of COVID-19 [12] pneumonia lesions from CT images.”
BackgroundRethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image SegmentationPreprint
Zhao, Z. W., Liu, Y., Zhao, M., Yin, D., Yuan, Y., & Zhou, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.11903 · Cited by 3
“Nevertheless, the majority of these approaches heavily depend on extensively annotated medical image datasets, which necessitates significant effort from expert annotators to obtain precise annotations [29].”
BackgroundCOVID-19 Classification Using Staked Ensembles: A Comprehensive AnalysisPreprint
Lalith Bharadwaj, B., Boddeda, R., Sai Vardhan, K., & Madhu, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05690 · Cited by 3
“G.wang et al. [15] (2020), has segmented the COVID-19 pneumonia lesions from CT image, proposed a COPEL-Net for segmentation task and novel dice loss which is noise robust (combined a MAEloss for generalisation) to fore and background imbalance.”
BackgroundCOVID-19 chest CT scan image segmentation based on chaotic gravitational search algorithm
Rather, S. A., Das, S. R., & Çiftçioğlu, A. Ö. (2024) · Evolving Systems · doi:10.1007/s12530-024-09634-0 · Cited by 2
“This methodological rigor, particularly indispensable for medical procedures like MRI and CT scans, facilitates the precise identification and analysis of areas of interest within the images (Sarkar et al. 2021; Liu et al. 2021; Wang et al. 2020; Luo et al. 2022).”
MCC: Multi-Cluster Contrastive Semi-Supervised Segmentation Framework for Echocardiogram Videos
Chen, Y.-J., Lin, S.-S., Shi, Y., Ho, T.-Y., & Xu, X. (2025) · IEEE Access · doi:10.1109/access.2025.3541173 · Cited by 2
COVID-19 Lung Infection Segmentation With Cascaded Aggregation Network
Tang, J., Zhou, X., Gao, Y., Chu, X., Li, Z., Yan, C. C., & Zhang, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551576 · Cited by 2
“First, most existing methods [20], [21], [22], [23] only utilize same-level features in the skip connections, which neglects the complementary information in different-level features.”
InfluentialSedaghat, S., Nazernejad, M., & Jahromi, M. S. S. (2025) · Computing · doi:10.1007/s00607-025-01453-8 · Cited by 2
Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation
Guo, Z., Wu, D., Gao, C., & Sang, N. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70042 · Cited by 2
MLAANet: A multi-level attention-aware network for pathological nuclei segmentation
Zhu, S., Li, Y., Lu, L., Mao, T., Yan, Y., & Dai, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108716 · Cited by 2
Rather, S. A., & Roy, P. P. (2026) · Evolutionary Intelligence · doi:10.1007/s12065-026-01146-x · Cited by 2
Application of transformer models in medical image segmentation: a narrative review
Xu, Y., Peng, Y., Zhang, C., Jiang, K., She, X., & Feng, L. (2026) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-2025-aw-2381 · Cited by 2
A Review on Effectiveness of Artificial Intelligence Techniques in the Detection of COVID-19
Swetha, M., & Rajendiran, M. (2020) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart50582.2020.9336798 · Cited by 2
“In a framework for automatically classifying the pneumonia lesions [11] from covid-19, a noise robust method is proposed to segment the CAP lesions from the CT scans.”
MethodExtraction Method of Target Region for HIFU Therapy Based on Ultrasonic Image Semantic Segmentation
Huang, Z., Yan, S., Xiao, Z., Wang, R., & Qian, S. (2022) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2022.18988 · Cited by 2
BPCN: bilateral progressive compensation network for lung infection image segmentation
Wang, X., Yang, B., Pan, X., Liu, F., & Zhang, S. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acaf21 · Cited by 2
“Dataset A (Wang et al 2020): all the clinical CT scanswere collected fromof 120 patients withCOVID-19 pneumonia.”
BackgroundMethodInfluentialSelf-citationVisvanathan, M., Balasubramanian, V., Sathish, R., Balasubramaniam, S., & Sheet, D. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629591 · Cited by 2
“To facilitate learning from noisy labels [8] designed a 2D CNN model called COPLE-Net, which is trained using a noise-robust Dice loss.”
MethodLiu, J., WU, J., Gong, S., Hu, W., Zhou, Y., & Hu, S. (2023) · Fractals · doi:10.1142/s0218348x23401084 · Cited by 2
Segmentation of CT-Scan Images Using UNet Network for Patients Diagnosed with COVID-19
Gois, F. N. B., & Marques, J. A. L. (2023) · Springer eBooks · doi:10.1007/978-3-031-30788-1_3 · Cited by 2
Doppler Image-Based Weakly-Supervised Vascular Ultrasound Segmentation with Transformer
Ning, G., Liang, H., Chen, F., Zhang, X., & Liao, H. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230548 · Cited by 2
CovLIS-MUnet segmentation model for Covid-19 lung infection regions in CT images
Devi, M., Singh, S., & Tiwari, S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09459-7 · Cited by 2
Kalaivani, J., Arunachalam, A. S., & Gobinath, R. (2024) · International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT) · doi:10.1109/tqcebt59414.2024.10545304 · Cited by 2
Cutting-Edge AI Technologies in Neurological Diagnosis Current Trends and Future Perspectives
Kanagamalliga, S., & Rajappriadharshine, S. (2024) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa64454.2024.00064 · Cited by 2
“6) Hybrid Imaging: PET/MRI combines both the functional image obtained by PET and anatomical image obtained from MRI in order to analyse a variety of neurological disorder and various types of cancer [7].”
Yoo, S., Goo, J. M., & Yoon, S. H. (2020) · Journal of the Korean Society of Radiology · doi:10.3348/jksr.2020.0138 · Cited by 2
“소수의 출판 연구에서 흉부 CT 폐렴 분할 및 중증도 평가 인공지 능을 보고하였는데 U-Net 기반 인공지능의 Dice score는 80% 내외였으며 다만 정량화된 값이 실 제 환자의 임상 소견과 어떤 관련이 있는지는 평가하지 않았다(56, 57).”
A REVIEW OF DEEP LEARNING IN MEDICAL PRACTICE
Vasile, C. M., Udriștoiu, Ș., Ghenea, A. E., Ungureanu, A. M., Gheonea, C., NICULESCU, C.-E., Siminel, M. A., Udriștoiu, Ș., Iana, O., Cioboată, R., et al. (2021) · Research and Science Today Supplement · doi:10.38173/rst.2021.21.1.6:67-77 · Cited by 2
Enshaei, N., Rafiee, M. J., Mohammadi, A., & Naderkhani, F. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746044 · Cited by 2
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images
de Sousa, P. M., Carneiro, P. C., Pereira, G. M., Oliveira, M. M., da Costa, C. A., de Moura, L. V., Mattjie, C., da Silva, A. M. M., Macedo, T. A. A., & Patrocínio, A. C. (2022) · Research Society and Development · doi:10.33448/rsd-v11i5.27919 · Cited by 2
A Semantic Segmentation Method for High-resolution Remote Sensing Images Based on Encoder-Decoder
Jing-yu, Y., Zhao, L., Dang, J., Wang, Y., Yue, B., & Gu, Z. (2022) · International Conference on Advanced Cloud and Big Data · doi:10.1109/cbd58033.2022.00026 · Cited by 2
“Compared with the single pooling approach used in general semantic segmentation models, dual pooling can better preserve the information of the previous module and reduce the information loss in the pooling process[16].”
MethodJeevitha, S., & Valarmathi, K. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22862 · Cited by 2
“The COVID-19 Pneumonia Lesion Segmentation Network (COPLE-Net) 38 is trained on a noise-robust Dice loss to handle noisy labels.”
MethodZhou, W. J., Wang, J., Wang, Y., Liu, Z., & Yang, C. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23021 · Cited by 2
Adversarially Residual U$$^2$$Net for COVID-19 Lung Infection Segmentation from CT Images
Xu, Y., Ju, F., Li, J., & Zu, B. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-4182-3_30 · Cited by 2
Dynamic Loss Decay Based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels
Liu, G., Liu, T., Yuan, M., Pang, T., Yang, G., Fu, H., Wang, T., & Liao, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78110-0_27 · Cited by 2
Distribution-aware Margin Calibration for Medical Image SegmentationPreprint
Li, Z., Yu, L., & Zhang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01462 · Cited by 2
“…deep learning-based image segmentation, the encoder-decoder like convolutional segmentation models, such as U-net (Ronneberger, Fischer, and Brox 2015) and its variants (Wang et al. 2020; Zhou et al. 2019), can well handle the visual-semantic consistencies and have achieved very promising results.”
InfluentialSegmentation of Lungs COVID Infected Regions by Attention Mechanism and Synthetic DataPreprint
Yazdekhasty, P., Zindari, A., Nabizadeh, Z., Khadivi, P., Karimi, N., & Samavi, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.08895 · Cited by 2
Wu, H., Liu, J., Xiao, F., Wen, Z., Cheng, L., & Qin, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.03.022 · Cited by 1
RetractedJiang, X., Yang, D., Feng, L., Zhu, Y. M., Wang, M., Feng, Y., Bai, C., & Fang, H. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1360143 · Cited by 1
“In addition, several works (24–26) also used segmentation techniques for detection.”
A Novel Feature-Prioritized Dice Loss Function for Enhanced Pneumonia Segmentation in Chest X-rays
Shaikh, M., Arain, Q. A., & Jaffari, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98691-8_5 · Cited by 1
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.