Unified medical image segmentation by learning from uncertainty in an end-to-end manner

Pin, Tang; Yang, Pinli; Nie, Dong; Wu, Xi; Zhou, Jiliu; Wang, Yan

doi:10.1016/j.knosys.2022.108215

Cited by 69 publications

(22 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models that provide predictive estimates of uncertainty could be widely integrated into clinical practice to flag clinicians for alternate opinions, thereby imparting trust, and improving patient care. Research is ongoing in proposing novel methods for quantifying and explaining uncertainties in model predictions [ 34 , 35 ]. With the advent of high-performance computing and storage solutions, several models with deep and diverse architectures can be trained to construct ensembles with reduced prediction uncertainty and deployed in the cloud to be used for real-time clinical applications.…”

Section: Discussionmentioning

confidence: 99%

Uncertainty Quantification in Segmenting Tuberculosis-Consistent Findings in Frontal Chest X-rays

et al. 2022

View full text Add to dashboard Cite

Deep learning (DL) methods have demonstrated superior performance in medical image segmentation tasks. However, selecting a loss function that conforms to the data characteristics is critical for optimal performance. Further, the direct use of traditional DL models does not provide a measure of uncertainty in predictions. Even high-quality automated predictions for medical diagnostic applications demand uncertainty quantification to gain user trust. In this study, we aim to investigate the benefits of (i) selecting an appropriate loss function and (ii) quantifying uncertainty in predictions using a VGG16-based-U-Net model with the Monto–Carlo (MCD) Dropout method for segmenting Tuberculosis (TB)-consistent findings in frontal chest X-rays (CXRs). We determine an optimal uncertainty threshold based on several uncertainty-related metrics. This threshold is used to select and refer highly uncertain cases to an expert. Experimental results demonstrate that (i) the model trained with a modified Focal Tversky loss function delivered superior segmentation performance (mean average precision (mAP): 0.5710, 95% confidence interval (CI): (0.4021,0.7399)), (ii) the model with 30 MC forward passes during inference further improved and stabilized performance (mAP: 0.5721, 95% CI: (0.4032,0.7410), and (iii) an uncertainty threshold of 0.7 is observed to be optimal to refer highly uncertain cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Uncertainty Quantification in Segmenting Tuberculosis-Consistent Findings in Frontal Chest X-rays

et al. 2022

View full text Add to dashboard Cite

show abstract

“…After that, many segmentation algorithms for medical images were adapted from U-Net. Some scholars combined mechanisms such as attention mechanism and residual connectivity with U-Net to improve segmentation performance and segment the nasopharyngeal carcinoma [40][41][42]. In order to accommodate the volume segmentation of medical images, many U-Net-based 3D models have been developed as well [43,44].…”

Section: Fully-supervisedmentioning

confidence: 99%

CAFS: An Attention-Based Co-Segmentation Semi-Supervised Method for Nasopharyngeal Carcinoma Segmentation

Chen

Han

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Accurate segmentation of nasopharyngeal carcinoma is essential to its treatment effect. However, there are several challenges in existing deep learning-based segmentation methods. First, the acquisition of labeled data are challenging. Second, the nasopharyngeal carcinoma is similar to the surrounding tissues. Third, the shape of nasopharyngeal carcinoma is complex. These challenges make the segmentation of nasopharyngeal carcinoma difficult. This paper proposes a novel semi-supervised method named CAFS for automatic segmentation of nasopharyngeal carcinoma. CAFS addresses the above challenges through three mechanisms: the teacher–student cooperative segmentation mechanism, the attention mechanism, and the feedback mechanism. CAFS can use only a small amount of labeled nasopharyngeal carcinoma data to segment the cancer region accurately. The average DSC value of CAFS is 0.8723 on the nasopharyngeal carcinoma segmentation task. Moreover, CAFS has outperformed the state-of-the-art nasopharyngeal carcinoma segmentation methods in the comparison experiment. Among the compared state-of-the-art methods, CAFS achieved the highest values of DSC, Jaccard, and precision. In particular, the DSC value of CAFS is 7.42% higher than the highest DSC value in the state-of-the-art methods.

show abstract

“…Yu et al ( 2019 ) present a novel uncertainty-aware semi-supervised learning framework for left atrium segmentation from 3D MR images by additionally leveraging the unlabeled data. Tang et al ( 2022 ) propose an uncertainty guided network referred to as UG-Net for automatic medical image segmentation.…”

Section: Related Workmentioning

confidence: 99%

Ensemble learning via supervision augmentation for white matter hyperintensity segmentation

Guo

Yang

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

Since the ambiguous boundary of the lesion and inter-observer variability, white matter hyperintensity segmentation annotations are inherently noisy and uncertain. On the other hand, the high capacity of deep neural networks (DNN) enables them to overfit labels with noise and uncertainty, which may lead to biased models with weak generalization ability. This challenge has been addressed by leveraging multiple annotations per image. However, multiple annotations are often not available in a real-world scenario. To mitigate the issue, this paper proposes a supervision augmentation method (SA) and combines it with ensemble learning (SA-EN) to improve the generalization ability of the model. SA can obtain diverse supervision information by estimating the uncertainty of annotation in a real-world scenario that per image have only one ambiguous annotation. Then different base learners in EN are trained with diverse supervision information. The experimental results on two white matter hyperintensity segmentation datasets demonstrate that SA-EN gets the optimal accuracy compared with other state-of-the-art ensemble methods. SA-EN is more effective on small datasets, which is more suitable for medical image segmentation with few annotations. A quantitative study is presented to show the effect of ensemble size and the effectiveness of the ensemble model. Furthermore, SA-EN can capture two types of uncertainty, aleatoric uncertainty modeled in SA and epistemic uncertainty modeled in EN.

show abstract

Unified medical image segmentation by learning from uncertainty in an end-to-end manner

Cited by 69 publications

References 41 publications

Uncertainty Quantification in Segmenting Tuberculosis-Consistent Findings in Frontal Chest X-rays

Uncertainty Quantification in Segmenting Tuberculosis-Consistent Findings in Frontal Chest X-rays

CAFS: An Attention-Based Co-Segmentation Semi-Supervised Method for Nasopharyngeal Carcinoma Segmentation

Ensemble learning via supervision augmentation for white matter hyperintensity segmentation

Contact Info

Product

Resources

About