Self-Ensembling Co-Training Framework for Semi-Supervised COVID-19 CT Segmentation

Li, Caizi; Li, Dong; Dou, Qi; Lin, Fan; Zhang, Kebao; Feng, Zuxin; Si, Weixin; Deng, Xiao-Dong; Deng, Zhe; Heng, Pheng‐Ann

doi:10.1109/jbhi.2021.3103646

Cited by 31 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Luo et al [56] employ a dual-task network that simultaneously predicts a pixel-wise segmentation map and a geometry-aware level set representation which is transformed into an approximate segmentation map through a differentiable task transform layer, between which the dual-task consistency regularization is ensured via CPS [16]. Li et al [57] propose a self-ensembled co-training framework for automatic COVID lesion segmentation, using collaborative models that teach via reciprocal pseudo-labeling of unlabeled data and self-ensembling for consistency regularization to mitigate noisy labels. Akin to these methods, our proposed methodology entails synthesizing dynamic thresholding and JS divergence as a decoder variance proxy to selectively modulate the loss contribution from pseudo-labeled data.…”

Section: Ssl In Medical Image Analysismentioning

confidence: 99%

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

Lyu,

Liu,

Lin

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Precise liver tumors and associated organ segmentation hold immense value for surgical and radiological intervention, enabling anatomical localization for pre-operative planning and intra-operative guidance. Modern deep learning models for medical image segmentation have evolved from convolution neural networks to transformer architectures, significantly boosting global context understanding. However, accurate delineation especially of hepatic lesions remains an enduring challenge due to models’ predominant focus solely on spatial feature extraction failing to adequately characterize complex medical anatomies. Moreover, the relative paucity of expertly annotated medical imaging data restricts model exposure to diverse pathological presentations. In this paper, we present a three-phrased cascaded segmentation framework featuring an X-Fuse model that synergistically integrates spatial and frequency domain’s complementary information in dual encoders to enrich latent feature representation. To enhance model generalizability, building upon X Fuse topology and taking advantage of additional unlabeled pathological data, our proposed integration of curriculum pseudo-labeling with Jensen-Shannon variance-based uncertainty rectification promotes optimized pseudo-supervision in the context of semi-supervised learning. We further introduce a tumor-focus augmentation technique including training-free copy-paste and knowledge-based synthesis that show efficacy in simplicity, contributing to the substantial elevation of model adaptability on diverse lesional morphologies. Extensive experiments and modular evaluations on a holdout test set demonstrate that our methods significantly outperform existing state-of-the-art segmentation models in both supervised and semi-supervised settings, as measured by the Dice similarity coefficient, achieving superior delineation of bones (95.42%), liver (96.26%), and liver tumors (89.53%) with 16.41% increase comparing to V-Net on supervised-only and augmented-absent scenario. Our method marks a significant step toward the realization of more reliable and robust AI-assisted diagnostic tools for liver tumor intervention. We have made the codes publicly available.

show abstract

Section: Ssl In Medical Image Analysismentioning

confidence: 99%

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

Lyu,

Liu,

Lin

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…"COVID-19," "lung CT scan," "diagnosis," "imaging," and "pneumonia" were some of the search keywords that were utilized. Studies were considered for inclusion if they were written in English and published in publications that had undergone peer reviews [21,22,23,24]. The chosen studies were discussed, and their most important conclusions were examined for clinical use cases.…”

Section: Literature Reviewmentioning

confidence: 99%

MXRFCS: Design of an augmented Multidomain XRay Feature representation model for identification of CoVID Severity levels

Thombre

Malik

Kumar

2023

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic has placed an enormous strain on healthcare systems worldwide, leading to a need for more efficient methods of identifying the severity of COVID-19 patients to efficiently allocate resources. Existing Xray processing models for identification of COVID-19 are either highly complicated or showcase lower efficiency when applied for real-time scenarios. To overcome these issues, this paper presents a novel approach for identifying the severity of COVID-19 patients using an augmented multimodal X-ray feature representation model. The proposed model combines X-ray images, clinical data, and demographic information to create a robust representation of individual patient condition. The collected information is converted into multidomain feature sets, including frequency, Gabor, Wavelet and entropy components. A customized deep neural network is trained on this representation to predict the severity level of COVID-19 patients. To evaluate the performance of the proposed model, we used a dataset of X-ray images and clinical data from COVID-19 patients. Our results demonstrate that the proposed model outperforms existing methods for identifying COVID-19 severity levels, achieving an accuracy of 98.5% on multiple dataset samples. The proposed model's performance was observed to be promising in terms of precision, recall and delay, thus has the potential to aid in the early identification and effective management of severe COVID-19 cases, thus contributing to the global effort to combat the COVID-19 pandemic under clinical use cases.

show abstract

“…In this co-training approach, learning was implemented among adversarial samples, so that the cross-model diversity was enhanced. A selfintegration co-training framework with U-Net as the benchmark model was proposed for COVID-9 (Li et al 2021). The consistent regularization was performed on the two synergistic models according to the selfintegration strategy, so that the adverse effects of noisy pseudo-labels were mitigated.…”

Section: Semi-supervised Image Segmentation Of Medical Imagesmentioning

confidence: 99%

MUE-CoT: multi-scale uncertainty entropy-aware co-training framework for left atrial segmentation

Hao,

Li,

Zhang

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Accurate left atrial segmentation is the basis of the recognition and clinical analysis of atrial fibrillation. Supervised learning has achieved some competitive segmentation results, but the high annotation cost often limits its performance. Semi-supervised learning is implemented from limited labeled data and a large amount of unlabeled data and shows good potential in solving practical medical problems. In this study, we proposed a collaborative training framework for multi-scale uncertain entropy perception (MUE-CoT) and achieved efficient left atrial segmentation from a small amount of labeled data. Based on the pyramid feature network, learning is implemented from unlabeled data by minimizing the pyramid prediction difference. In addition, novel loss constraints are proposed for co-training in the study. The diversity loss is defined as a soft constraint so as to accelerate the convergence and a novel multi-scale uncertainty entropy calculation method and a consistency regularization term are proposed to measure the consistency between prediction results. The quality of pseudo-labels cannot be guaranteed in the pre-training period, so a confidence-dependent empirical Gaussian function is proposed to weight the pseudo-supervised loss. The experimental results of a publicly available dataset and an in-house clinical dataset proved that our method outperformed existing semi-supervised methods.

show abstract

Self-Ensembling Co-Training Framework for Semi-Supervised COVID-19 CT Segmentation

Cited by 31 publications

References 37 publications

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

MXRFCS: Design of an augmented Multidomain XRay Feature representation model for identification of CoVID Severity levels

MUE-CoT: multi-scale uncertainty entropy-aware co-training framework for left atrial segmentation

Contact Info

Product

Resources

About