Automatic Deep Learning-Based Consolidation/Collapse Classification in Lung Ultrasound Images for COVID-19 Induced Pneumonia

<div>Our automated deep learning-based approach identifies consolidation/collapse in LUS images to aid in the diagnosis of late stages of COVID-19 induced pneumonia, where consolidation/collapse is one of the possible associated pathologies. A common challenge in training such models is that annotating each frame of an ultrasound video requires high labelling effort. This effort in practice becomes prohibitive for large ultrasound datasets. To understand the impact of various degrees of labelling precision, we compare labelling strategies to train fully supervised models (frame-based method, higher labelling effort) and inaccurately supervised models (video-based methods, lower labelling effort), both of which yield binary predictions for LUS videos on a frame-by-frame level. We moreover introduce a novel sampled quaternary method which randomly samples only 10% of the LUS video frames and subsequently assigns (ordinal) categorical labels to all frames in the video based on the fraction of positively annotated samples. This method outperformed the inaccurately supervised video-based method of our previous work on pleural effusions. More surprisingly, this method outperformed the supervised frame-based approach with respect to metrics such as precision-recall area under curve (PR-AUC) and F1 score that are suitable for the class imbalance scenario of our dataset despite being a form of inaccurate learning. This may be due to the combination of a significantly smaller data set size compared to our previous work and the higher complexity of consolidation/collapse compared to pleural effusion, two factors which contribute to label noise and overfitting; specifically, we argue that our video-based method is more robust with respect to label noise and mitigates overfitting in a manner similar to label smoothing. Using clinical expert feedback, separate criteria were developed to exclude data from the training and test sets respectively for our ten-fold cross validation results, which resulted in a PR-AUC score of 73% and an accuracy of 89%. While the efficacy of our classifier using the sampled quaternary method must be verified on a larger consolidation/collapse dataset, when considering the complexity of the pathology, our proposed classifier using the sampled quaternary video-based method is clinically comparable with trained experts and improves over the video-based method of our previous work on pleural effusions.</div>

Automatic Deep Learning-Based Consolidation/Collapse Classification in Lung Ultrasound Images for COVID-19 Induced Pneumonia

<div>Our automated deep learning-based approach identifies consolidation/collapse in LUS images to aid in the diagnosis of late stages of COVID-19 induced pneumonia, where consolidation/collapse is one of the possible associated pathologies. A common challenge in training such models is that annotating each frame of an ultrasound video requires high labelling effort. This effort in practice becomes prohibitive for large ultrasound datasets. To understand the impact of various degrees of labelling precision, we compare labelling strategies to train fully supervised models (frame-based method, higher labelling effort) and inaccurately supervised models (video-based methods, lower labelling effort), both of which yield binary predictions for LUS videos on a frame-by-frame level. We moreover introduce a novel sampled quaternary method which randomly samples only 10% of the LUS video frames and subsequently assigns (ordinal) categorical labels to all frames in the video based on the fraction of positively annotated samples. This method outperformed the inaccurately supervised video-based method of our previous work on pleural effusions. More surprisingly, this method outperformed the supervised frame-based approach with respect to metrics such as precision-recall area under curve (PR-AUC) and F1 score that are suitable for the class imbalance scenario of our dataset despite being a form of inaccurate learning. This may be due to the combination of a significantly smaller data set size compared to our previous work and the higher complexity of consolidation/collapse compared to pleural effusion, two factors which contribute to label noise and overfitting; specifically, we argue that our video-based method is more robust with respect to label noise and mitigates overfitting in a manner similar to label smoothing. Using clinical expert feedback, separate criteria were developed to exclude data from the training and test sets respectively for our ten-fold cross validation results, which resulted in a PR-AUC score of 73% and an accuracy of 89%. While the efficacy of our classifier using the sampled quaternary method must be verified on a larger consolidation/collapse dataset, when considering the complexity of the pathology, our proposed classifier using the sampled quaternary video-based method is clinically comparable with trained experts and improves over the video-based method of our previous work on pleural effusions.</div>

When Speaker Recognition Meets Noisy Labels: Optimizations for Front-ends and Back-ends

A typical speaker recognition system often involves two modules: a feature extractor front-end and a speaker identity back-end. Despite the superior performance that deep neural networks have achieved for the front-end, their success benefits from the availability of large-scale and correctly labeled datasets. While label noise is unavoidable in speaker recognition datasets, both the front-end and back-end are affected by label noise, which degrades the speaker recognition performance. In this paper, we first conduct comprehensive experiments to help improve the understanding of the effects of label noise on both the front-end and back-end. Then, we propose a simple yet effective training paradigm and loss correction method to handle label noise for the front-end. We combine our proposed method with the recently proposed Bayesian estimation of PLDA for noisy labels, and the whole system shows strong robustness to label noise. Furthermore, we show two practical applications of the improved system: one application corrects noisy labels based on an utterance’s chunk-level predictions, and the other algorithmically filters out high-confidence noisy samples within a dataset. By applying the second application to the NIST SRE0410 dataset and verifying filtered utterances by human validation, we identify that approximately 1% of the SRE04-10 dataset is made up of label errors.<br>