Search

Goal: Auscultation for neonates is a simple and non-invasive method of diagnosing cardiovascular and respiratory disease. However, obtaining high-quality chest sounds containing only heart or lung sounds is non-trivial. Hence, this study introduces a new deep-learning model named NeoSSNet and evaluates its performance in neonatal chest sound separation with previous methods. Methods: We propose a masked-based architecture similar to Conv-TasNet. The encoder and decoder consist of 1D convolution and 1D transposed convolution, while the mask generator consists of a convolution and transformer architecture. The input chest sounds were first encoded as a sequence of tokens using 1D convolution. The tokens were then passed to the mask generator to generate two masks, one for heart sounds and one for lung sounds. Each mask is then applied to the input token sequence. Lastly, the tokens are converted back to waveforms using 1D transposed convolution. Results: Our proposed model showed superior results compared to the previous methods based on objective distortion measures, ranging from a 2.01 dB improvement to a 5.06 dB improvement. The proposed model is also significantly faster than the previous methods, with at least a 17-time improvement. Conclusions: The proposed model could be a suitable preprocessing step for any health monitoring system where only the heart sound or lung sound is desired.

Content-based medical image retrieval is an important diagnostic tool that improves the explainability of computer-aided diagnosis systems and provides decision-making support to healthcare professionals. A common approach to content-based image retrieval is learning a distance metric by transforming images into a feature space where the distance between samples is a similarity measure. Proxy metric learning methods are effective at learning this transformation due to the use of proxy feature vectors that enable efficient learning. Training with a distance-based classification loss enables a single proxy model to be suitable for both retrieval and classification. However, these methods are designed only for single-label data, making them unsuitable for multimorbidity medical images. Addressing this, we propose a novel multi-label proxy metric learning method for content-based image retrieval and classification. Unlike existing proxy-based methods, training samples assign to multiple proxies that span multiple class labels. This results in a feature space that encodes the complex relationships between diseases. We introduce negative proxies to better encode the relationships between samples without detected diseases. The efficacy of our approach is demonstrated experimentally on two multimorbidity radiology datasets. Results show that our method outperforms state-of-the-art image retrieval systems and baseline approaches. Our method is clinically significant as it improves on two key factors shown to affect medical professionals’ willingness to use computer-aided diagnosis systems: accuracy and interpretability.

Lifelong learning portrays learning gradually in nonstationary environments and emulates the process of human learning, which is efficient, robust, and able to learn new concepts incrementally from sequential experience. To equip neural networks with such a capability, one needs to overcome the problem of catastrophic forgetting, the phenomenon of forgetting past knowledge while learning new concepts. In this work, we propose a novel knowledge distillation algorithm that makes use of contrastive learning to help a neural network to preserve its past knowledge while learning from a series of tasks. Our proposed generalized form of contrastive distillation strategy tackles catastrophic forgetting of old knowledge, and minimizes semantic drift by maintaining a similar embedding space, as well as ensures compactness in feature distribution to accommodate novel tasks in a current model. Our comprehensive study shows that our method achieves improved performances in the challenging class-incremental, task-incremental, and domain-incremental learning for supervised scenarios.