Deep learning uncertainty and confidence calibration for the five-class polyp classification from colonoscopy

A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods

The comprehensive integration of machine learning healthcare models within clinical practice remains suboptimal, notwithstanding the proliferation of high-performing solutions reported in the literature. A predominant factor hindering widespread adoption pertains to an insufficiency of evidence affirming the reliability of the aforementioned models. Recently, uncertainty quantification methods have been proposed as a potential solution to quantify the reliability of machine learning models and thus increase the interpretability and acceptability of the results. In this review, we offer a comprehensive overview of the prevailing methods proposed to quantify the uncertainty inherent in machine learning models developed for various medical image tasks. Contrary to earlier reviews that exclusively focused on probabilistic methods, this review also explores non-probabilistic approaches, thereby furnishing a more holistic survey of research pertaining to uncertainty quantification for machine learning models. Analysis of medical images with the summary and discussion on medical applications and the corresponding uncertainty evaluation protocols are presented, which focus on the specific challenges of uncertainty in medical image analysis. We also highlight some potential future research work at the end. Generally, this review aims to allow researchers from both clinical and technical backgrounds to gain a quick and yet in-depth understanding of the research in uncertainty quantification for medical image analysis machine learning models.

Trustworthy clinical AI solutions: A unified review of uncertainty quantification in Deep Learning models for medical image analysis

The full acceptance of Deep Learning (DL) models in the clinical field is rather low with respect to the quantity of high-performing solutions reported in the literature. End users are particularly reluctant to rely on the opaque predictions of DL models. Uncertainty quantification methods have been proposed in the literature as a potential solution, to reduce the black-box effect of DL models and increase the interpretability and the acceptability of the result by the final user. In this review, we propose an overview of the existing methods to quantify uncertainty associated with DL predictions. We focus on applications to medical image analysis, which present specific challenges due to the high dimensionality of images and their variable quality, as well as constraints associated with real-world clinical routine. Moreover, we discuss the concept of structural uncertainty, a corpus of methods to facilitate the alignment of segmentation uncertainty estimates with clinical attention. We then discuss the evaluation protocols to validate the relevance of uncertainty estimates. Finally, we highlight the open challenges for uncertainty quantification in the medical field.

Enhancing artificial intelligence-doctor collaboration for computer-aided diagnosis in colonoscopy through improved digital literacy

Establishing appropriate trust and maintaining a balanced reliance on digital resources are vital for accurate optical diagnoses and effective integration of computer-aided diagnosis (CADx) in colonoscopy. Active learning using diverse polyp image datasets can help in developing precise CADx systems. Enhancing doctors' digital literacy and interpreting their results is crucial. Explainable artificial intelligence (AI) addresses opacity, and textual descriptions, along with AI-generated content, deepen the interpretability of AI-based findings by doctors. AI conveying uncertainties and decision confidence aids doctors' acceptance of results. Optimal AI-doctor collaboration requires improving algorithm performance, transparency, addressing uncertainties, and enhancing doctors' optical diagnostic skills.

Trustworthy in silico cell labeling via ensemble-based image translation

Artificial intelligence (AI) image translation has been a valuable tool for processing image data in biological and medical research. To apply such a tool in mission-critical applications, including drug screening, toxicity study, and clinical diagnostics, it is essential to ensure that the AI prediction is trustworthy. Here, we demonstrate that an ensemble learning method can quantify the uncertainty of AI image translation. We tested the uncertainty evaluation using experimentally acquired images of mesenchymal stromal cells. We find that the ensemble method reports a prediction standard deviation that correlates with the prediction error, estimating the prediction uncertainty. We show that this uncertainty is in agreement with the prediction error and Pearson correlation coefficient. We further show that the ensemble method can detect out-of-distribution input images by reporting increased uncertainty. Altogether, these results suggest that the ensemble-estimated uncertainty can be a useful indicator for identifying erroneous AI image translations.

Estimating Patient-Level Uncertainty in Seizure Detection Using Group-Specific Out-of-Distribution Detection Technique

Epilepsy is a chronic neurological disorder affecting around 1% of the global population, characterized by recurrent epileptic seizures. Accurate diagnosis and treatment are crucial for reducing mortality rates. Recent advancements in machine learning (ML) algorithms have shown potential in aiding clinicians with seizure detection in electroencephalography (EEG) data. However, these algorithms face significant challenges due to the patient-specific variability in seizure patterns and the limited availability of high-quality EEG data for training, causing erratic predictions. These erratic predictions are harmful, especially for high-stake domains in healthcare, negatively affecting patients. Therefore, ensuring safety in AI is of the utmost importance. In this study, we propose a novel ensemble method for uncertainty quantification to identify patients with low-confidence predictions in ML-based seizure detection algorithms. Our approach aims to mitigate high-risk predictions in previously unseen seizure patients, thereby enhancing the robustness of existing seizure detection algorithms. Additionally, our method can be implemented with most of the deep learning (DL) models. We evaluated the proposed method against established uncertainty detection techniques, demonstrating its effectiveness in identifying patients for whom the model's predictions are less certain. Our proposed method managed to achieve 87%, 89% and 75% in accuracy, specificity and sensitivity, respectively. This study represents a novel attempt to improve the reliability and robustness of DL algorithms in the domain of seizure detection. This study underscores the value of integrating uncertainty quantification into ML algorithms for seizure detection, offering clinicians a practical tool to gauge the applicability of ML models for individual patients.

Application of uncertainty quantification to artificial intelligence in healthcare: A review of last decade (2013-2023)

Uncertainty estimation in healthcare involves quantifying and understanding the inherent uncertainty or variability associated with medical predictions, diagnoses, and treatment outcomes. In this era of Artificial Intelligence (AI) models, uncertainty estimation becomes vital to ensure safe decision-making in the medical field. Therefore, this review focuses on the application of uncertainty techniques to machine and deep learning models in healthcare. A systematic literature review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Our analysis revealed that Bayesian methods were the predominant technique for uncertainty quantification in machine learning models, with Fuzzy systems being the second most used approach. Regarding deep learning models, Bayesian methods emerged as the most prevalent approach, finding application in nearly all aspects of medical imaging. Most of the studies reported in this paper focused on medical images, highlighting the prevalent application of uncertainty quantification techniques using deep learning models compared to machine learning models. Interestingly, we observed a scarcity of studies applying uncertainty quantification to physiological signals. Thus, future research on uncertainty quantification should prioritize investigating the application of these techniques to physiological signals. Overall, our review highlights the significance of integrating uncertainty techniques in healthcare applications of machine learning and deep learning models. This can provide valuable insights and practical solutions to manage uncertainty in real-world medical data, ultimately improving the accuracy and reliability of medical diagnoses and treatment recommendations.

Adaptive Frequency Learning Network With Anti-Aliasing Complex Convolutions for Colon Diseases Subtypes

The automatic and dependable identification of colonic disease subtypes by colonoscopy is crucial. Once successful, it will facilitate clinically more in-depth disease staging analysis and the formulation of more tailored treatment plans. However, inter-class confusion and brightness imbalance are major obstacles to colon disease subtyping. Notably, the Fourier-based image spectrum, with its distinctive frequency features and brightness insensitivity, offers a potential solution. To effectively leverage its advantages to address the existing challenges, this article proposes a framework capable of thorough learning in the frequency domain based on four core designs: the position consistency module, the high-frequency self-supervised module, the complex number arithmetic model, and the feature anti-aliasing module. The position consistency module enables the generation of spectra that preserve local and positional information while compressing the spectral data range to improve training stability. Through band masking and supervision, the high-frequency autoencoder module guides the network to learn useful frequency features selectively. The proposed complex number arithmetic model allows direct spectral training while avoiding the loss of phase information caused by current general-purpose real-valued operations. The feature anti-aliasing module embeds filters in the model to prevent spectral aliasing caused by down-sampling and improve performance. Experiments are performed on the collected five-class dataset, which contains 4591 colorectal endoscopic images. The outcomes show that our proposed method produces state-of-the-art results with an accuracy rate of 89.82%.

DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images

Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.

ARMO: automated and reliable multi-objective model for lymph node metastasis prediction in head and neck cancer

Objective. Accurate diagnosis of lymph node metastasis (LNM) is critical in treatment management for patients with head and neck cancer. Positron emission tomography and computed tomography are routinely used for identifying LNM status. However, for small or less fluorodeoxyglucose (FDG) avid nodes, there are always uncertainties in LNM diagnosis. We are aiming to develop a reliable prediction model is for identifying LNM.Approach. In this study, a new automated and reliable multi-objective learning model (ARMO) is proposed. In ARMO, a multi-objective model is introduced to obtain balanced sensitivity and specificity. Meanwhile, confidence is calibrated by introducing individual reliability, whilst the model uncertainty is estimated by a newly defined overall reliability in ARMO. In the training stage, a Pareto-optimal model set is generated. Then all the Pareto-optimal models are used, and a reliable fusion strategy that introduces individual reliability is developed for calibrating the confidence of each output. The overall reliability is calculated to estimate the model uncertainty for each test sample.Main results. The experimental results demonstrated that ARMO obtained more promising results, which the area under the curve, accuracy, sensitivity and specificity can achieve 0.97, 0.93, 0.88 and 0.94, respectively. Meanwhile, based on calibrated confidence and overall reliability, clinicians could pay particular attention to highly uncertain predictions.Significance. In this study, we developed a unified model that can achieve balanced prediction, confidence calibration and uncertainty estimation simultaneously. The experimental results demonstrated that ARMO can obtain accurate and reliable prediction performance.

DOMINO: Domain-aware loss for deep learning calibration

Deep learning has achieved the state-of-the-art performance across medical imaging tasks; however, model calibration is often not considered. Uncalibrated models are potentially dangerous in high-risk applications since the user does not know when they will fail. Therefore, this paper proposes a novel domain-aware loss function to calibrate deep learning models. The proposed loss function applies a class-wise penalty based on the similarity between classes within a given target domain. Thus, the approach improves the calibration while also ensuring that the model makes less risky errors even when incorrect. The code for this software is available at https://github.com/lab-smile/DOMINO.

Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review

Transparency in Machine Learning (ML), often also referred to as interpretability or explainability, attempts to reveal the working mechanisms of complex models. From a human-centered design perspective, transparency is not a property of the ML model but an affordance, i.e., a relationship between algorithm and users. Thus, prototyping and user evaluations are critical to attaining solutions that afford transparency. Following human-centered design principles in highly specialized and high stakes domains, such as medical image analysis, is challenging due to the limited access to end users and the knowledge imbalance between those users and ML designers. To investigate the state of transparent ML in medical image analysis, we conducted a systematic review of the literature from 2012 to 2021 in PubMed, EMBASE, and Compendex databases. We identified 2508 records and 68 articles met the inclusion criteria. Current techniques in transparent ML are dominated by computational feasibility and barely consider end users, e.g. clinical stakeholders. Despite the different roles and knowledge of ML developers and end users, no study reported formative user research to inform the design and development of transparent ML models. Only a few studies validated transparency claims through empirical user evaluations. These shortcomings put contemporary research on transparent ML at risk of being incomprehensible to users, and thus, clinically irrelevant. To alleviate these shortcomings in forthcoming research, we introduce the INTRPRT guideline, a design directive for transparent ML systems in medical image analysis. The INTRPRT guideline suggests human-centered design principles, recommending formative user research as the first step to understand user needs and domain requirements. Following these guidelines increases the likelihood that the algorithms afford transparency and enable stakeholders to capitalize on the benefits of transparent ML.

Uncertainty Estimation in Medical Image Classification: Systematic Review

Background

Deep neural networks are showing impressive results in different medical image classification tasks. However, for real-world applications, there is a need to estimate the network’s uncertainty together with its prediction.

Objective

In this review, we investigate in what form uncertainty estimation has been applied to the task of medical image classification. We also investigate which metrics are used to describe the effectiveness of the applied uncertainty estimation

Methods

Google Scholar, PubMed, IEEE Xplore, and ScienceDirect were screened for peer-reviewed studies, published between 2016 and 2021, that deal with uncertainty estimation in medical image classification. The search terms “uncertainty,” “uncertainty estimation,” “network calibration,” and “out-of-distribution detection” were used in combination with the terms “medical images,” “medical image analysis,” and “medical image classification.”

Results

A total of 22 papers were chosen for detailed analysis through the systematic review process. This paper provides a table for a systematic comparison of the included works with respect to the applied method for estimating the uncertainty.

Conclusions

The applied methods for estimating uncertainties are diverse, but the sampling-based methods Monte-Carlo Dropout and Deep Ensembles are used most frequently. We concluded that future works can investigate the benefits of uncertainty estimation in collaborative settings of artificial intelligence systems and human experts.

International Registered Report Identifier (IRRID)

RR2-10.2196/11936

WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification

The early detection and timely treatment of breast cancer can save lives. Mammography is one of the most efficient approaches to screening early breast cancer. An automatic mammographic image classification method could improve the work efficiency of radiologists. Current deep learning-based methods typically use the traditional softmax loss to optimize the feature extraction part, which aims to learn the features of mammographic images. However, previous studies have shown that the feature extraction part cannot learn discriminative features from complex data using the standard softmax loss. In this paper, we design a new architecture and propose respective loss functions. Specifically, we develop a double-classifier network architecture that constrains the extracted features' distribution by changing the classifiers' decision boundaries. Then, we propose the double-classifier constraint loss function to constrain the decision boundaries so that the feature extraction part can learn discriminative features. Furthermore, by taking advantage of the architecture of two classifiers, the neural network can detect the difficult-to-classify samples. We propose a weighted double-classifier constraint method to make the feature extract part pay more attention to learning difficult-to-classify samples' features. Our proposed method can be easily applied to an existing convolutional neural network to improve mammographic image classification performance. We conducted extensive experiments to evaluate our methods on three public benchmark mammographic image datasets. The results showed that our methods outperformed many other similar methods and state-of-the-art methods on the three public medical benchmarks. Our code and weights can be found on GitHub.

Judgment of benign and early malignant colorectal tumors from ultrasound images with deep multi-View fusion

BACKGROUND AND OBJECTIVE

Colorectal cancer (CRC) is currently one of the main cancers world-wide, with a high incidence in the elderly. In the diagnosis of CRC, endorectal ultrasound plays an important role in judging benign and early malignant tumors. However, malignant tumors in the early-stage are not easy to identify visually and experts usually seek help from multi-view images, which increases the workload and also exists a certain probability of misdiagnosis. In recent years, with the widespread use of deep learning methods in the analysis of medical images, it becomes necessary to design an effective computer-aided diagnosis (CAD) system of CRC based on multi-view endorectal ultrasound images.

METHOD

In this study, we proposed a CAD system for judging benign and early malignant colorectal tumors, and constructed the first multi-view ultrasound image dataset of CRC to validate our algorithm. Our system is an end-to-end model based on a deep neural network (DNN) which includes a feature extraction module based on dense blocks, a multi-view fusion module, and a Multi-Layer Perception-based classifier. A center loss was used for the first time in CAD tasks, to optimize our model.

RESULT

On the constructed dataset, the proposed system surpasses expert diagnosis in accuracy, sensitivity, specificity, and F1-score. Compared with the popular deep classification networks and other CAD methods, the algorithm has reached the best performance. Comparative experiments using different feature extraction methods, different view fusion strategies, and different classifiers verify the effectiveness of each part of the algorithm.

CONCLUSION

We propose a CAD system for judging benign and early malignant colorectal tumors based on DNN, which combines information of ultrasound images from different views for comprehension. On the first CRC multi-view ultrasound image dataset which we constructed, our method outperforms expert diagnosis results and all other methods, and the effectiveness of each part of the system has been verified. Our system has application value in future medical practice on early diagnosis of CRC.

Deep learning model calibration for improving performance in class-imbalanced medical image classification tasks

In medical image classification tasks, it is common to find that the number of normal samples far exceeds the number of abnormal samples. In such class-imbalanced situations, reliable training of deep neural networks continues to be a major challenge, therefore biasing the predicted class probabilities toward the majority class. Calibration has been proposed to alleviate some of these effects. However, there is insufficient analysis explaining whether and when calibrating a model would be beneficial. In this study, we perform a systematic analysis of the effect of model calibration on its performance on two medical image modalities, namely, chest X-rays and fundus images, using various deep learning classifier backbones. For this, we study the following variations: (i) the degree of imbalances in the dataset used for training; (ii) calibration methods; and (iii) two classification thresholds, namely, default threshold of 0.5, and optimal threshold from precision-recall (PR) curves. Our results indicate that at the default classification threshold of 0.5, the performance achieved through calibration is significantly superior (p < 0.05) to using uncalibrated probabilities. However, at the PR-guided threshold, these gains are not significantly different (p > 0.05). This observation holds for both image modalities and at varying degrees of imbalance. The code is available at https://github.com/sivaramakrishnan-rajaraman/Model_calibration.

Uncertainty-aware deep learning in healthcare: A scoping review

Mistrust is a major barrier to implementing deep learning in healthcare settings. Entrustment could be earned by conveying model certainty, or the probability that a given model output is accurate, but the use of uncertainty estimation for deep learning entrustment is largely unexplored, and there is no consensus regarding optimal methods for quantifying uncertainty. Our purpose is to critically evaluate methods for quantifying uncertainty in deep learning for healthcare applications and propose a conceptual framework for specifying certainty of deep learning predictions. We searched Embase, MEDLINE, and PubMed databases for articles relevant to study objectives, complying with PRISMA guidelines, rated study quality using validated tools, and extracted data according to modified CHARMS criteria. Among 30 included studies, 24 described medical imaging applications. All imaging model architectures used convolutional neural networks or a variation thereof. The predominant method for quantifying uncertainty was Monte Carlo dropout, producing predictions from multiple networks for which different neurons have dropped out and measuring variance across the distribution of resulting predictions. Conformal prediction offered similar strong performance in estimating uncertainty, along with ease of interpretation and application not only to deep learning but also to other machine learning approaches. Among the six articles describing non-imaging applications, model architectures and uncertainty estimation methods were heterogeneous, but predictive performance was generally strong, and uncertainty estimation was effective in comparing modeling methods. Overall, the use of model learning curves to quantify epistemic uncertainty (attributable to model parameters) was sparse. Heterogeneity in reporting methods precluded the performance of a meta-analysis. Uncertainty estimation methods have the potential to identify rare but important misclassifications made by deep learning models and compare modeling methods, which could build patient and clinician trust in deep learning applications in healthcare. Efficient maturation of this field will require standardized guidelines for reporting performance and uncertainty metrics.

Artificial intelligence (AI) real-time detection vs. routine colonoscopy for colorectal neoplasia: a meta-analysis and trial sequential analysis

GOALS AND BACKGROUND

Studies analyzing artificial intelligence (AI) in colonoscopies have reported improvements in detecting colorectal cancer (CRC) lesions, however its utility in the realworld remains limited. In this systematic review and meta-analysis, we evaluate the efficacy of AI-assisted colonoscopies against routine colonoscopy (RC).

STUDY

We performed an extensive search of major databases (through January 2021) for randomized controlled trials (RCTs) reporting adenoma and polyp detection rates. Odds ratio (OR) and standardized mean differences (SMD) with 95% confidence intervals (CIs) were reported. Additionally, trial sequential analysis (TSA) was performed to guard against errors.

RESULTS

Six RCTs were included (4996 participants). The mean age (SD) was 51.99 (4.43) years, and 49% were females. Detection rates favored AI over RC for adenomas (OR 1.77; 95% CI: 1.570-2.08) and polyps (OR 1.91; 95% CI: 1.68-2.16). Secondary outcomes including mean number of adenomas (SMD 0.23; 95% CI: 0.18-0.29) and polyps (SMD 0.23; 95% CI: 0.17-0.29) detected per procedure favored AI. However, RC outperformed AI in detecting pedunculated polyps. Withdrawal times (WTs) favored AI when biopsies were included, while WTs without biopsies, cecal intubation times, and bowel preparation adequacy were similar.

CONCLUSIONS

Colonoscopies equipped with AI detection algorithms could significantly detect previously missed adenomas and polyps while retaining the ability to self-assess and improve periodically. More effective clearance of diminutive adenomas may allow lengthening in surveillance intervals, reducing the burden of surveillance colonoscopies, and increasing its accessibility to those at higher risk. TSA ruled out the risk for false-positive results and confirmed a sufficient sample size to detect the observed effect. Currently, these findings suggest that AI-assisted colonoscopy can serve as a useful proxy to address critical gaps in CRC identification.

Dilated densely connected U-Net with uncertainty focus loss for 3D ABUS mass segmentation

BACKGROUND AND OBJECTIVE

Accurate segmentation of breast mass in 3D automated breast ultrasound (ABUS) images plays an important role in qualitative and quantitative ABUS image analysis. Yet this task is challenging due to the low signal to noise ratio and serious artifacts in ABUS images, the large shape and size variation of breast masses, as well as the small training dataset compared with natural images. The purpose of this study is to address these difficulties by designing a dilated densely connected U-Net (D²U-Net) together with an uncertainty focus loss.

METHODS

A lightweight yet effective densely connected segmentation network is constructed to extensively explore feature representations in the small ABUS dataset. In order to deal with the high variation in shape and size of breast masses, a set of hybrid dilated convolutions is integrated into the dense blocks of the D²U-Net. We further suggest an uncertainty focus loss to put more attention on unreliable network predictions, especially the ambiguous mass boundaries caused by low signal to noise ratio and artifacts. Our segmentation algorithm is evaluated on an ABUS dataset of 170 volumes from 107 patients. Ablation analysis and comparison with existing methods are conduct to verify the effectiveness of the proposed method.

RESULTS

Experiment results demonstrate that the proposed algorithm outperforms existing methods on 3D ABUS mass segmentation tasks, with Dice similarity coefficient, Jaccard index and 95% Hausdorff distance of 69.02%, 56.61% and 4.92 mm, respectively.

CONCLUSIONS

The proposed method is effective in segmenting breast masses on our small ABUS dataset, especially breast masses with large shape and size variations.

Deep Learning Models for Colorectal Polyps

Colorectal cancer is one of the main causes of cancer incident cases and cancer deaths worldwide. Undetected colon polyps, be them benign or malignant, lead to late diagnosis of colorectal cancer. Computer aided devices have helped to decrease the polyp miss rate. The application of deep learning algorithms and techniques has escalated during this last decade. Many scientific studies are published to detect, localize, and classify colon polyps. We present here a brief review of the latest published studies. We compare the accuracy of these studies with our results obtained from training and testing three independent datasets using a convolutional neural network and autoencoder model. A train, validate and test split was performed for each dataset, 75%, 15%, and 15%, respectively. An accuracy of 0.937 was achieved for CVC-ColonDB, 0.951 for CVC-ClinicDB, and 0.967 for ETIS-LaribPolypDB. Our results suggest slight improvements compared to the algorithms used to date.

Uncertainty Aware Temporal-Ensembling Model for Semi-Supervised ABUS Mass Segmentation

Accurate breast mass segmentation of automated breast ultrasound (ABUS) images plays a crucial role in 3D breast reconstruction which can assist radiologists in surgery planning. Although the convolutional neural network has great potential for breast mass segmentation due to the remarkable progress of deep learning, the lack of annotated data limits the performance of deep CNNs. In this article, we present an uncertainty aware temporal ensembling (UATE) model for semi-supervised ABUS mass segmentation. Specifically, a temporal ensembling segmentation (TEs) model is designed to segment breast mass using a few labeled images and a large number of unlabeled images. Considering the network output contains correct predictions and unreliable predictions, equally treating each prediction in pseudo label update and loss calculation may degrade the network performance. To alleviate this problem, the uncertainty map is estimated for each image. Then an adaptive ensembling momentum map and an uncertainty aware unsupervised loss are designed and integrated with TEs model. The effectiveness of the proposed UATE model is mainly verified on an ABUS dataset of 107 patients with 170 volumes, including 13382 2D labeled slices. The Jaccard index (JI), Dice similarity coefficient (DSC), pixel-wise accuracy (AC) and Hausdorff distance (HD) of the proposed method on testing set are 63.65%, 74.25%, 99.21% and 3.81mm respectively. Experimental results demonstrate that our semi-supervised method outperforms the fully supervised method, and get a promising result compared with existing semi-supervised methods.