IEEE Journal of Biomedical and Health Informatics最新文献

In the field of diagnosing lung diseases, the application of neural networks (NNs) in image classification exhibits significant potential. However, NNs are considered "black boxes," making it difficult to discern their decision-making processes, thereby leading to skepticism and concern regarding NNs. This compromises model reliability and hampers intelligent medicine's development. To tackle this issue, we introduce the Evolutionary Neural Architecture Search (EvoNAS). In image classification tasks, EvoNAS initially utilizes an Evolutionary Algorithm to explore various Convolutional Neural Networks, ultimately yielding an optimized network that excels at separating between redundant texture features and the most discriminative ones. Retaining the most discriminative features improves classification accuracy, particularly in distinguishing similar features. This approach illuminates the intrinsic mechanics of classification, thereby enhancing the accuracy of the results. Subsequently, we incorporate a Differential Evolution algorithm based on distribution estimation, significantly enhancing search efficiency. Employing visualization techniques, we demonstrate the effectiveness of EvoNAS, endowing the model with interpretability. Finally, we conduct experiments on the diffuse lung disease texture dataset using EvoNAS. Compared to the original network, the classification accuracy increases by 0.56%. Moreover, our EvoNAS approach demonstrates significant advantages over existing methods in the same dataset.

Cancer is a pressing public health problem and one of the main causes of mortality worldwide. The development of advanced computational methods for predicting cancer survival is pivotal in aiding clinicians to formulate effective treatment strategies and improve patient quality of life. Recent advances in survival prediction methods show that integrating diverse information from various cancer-related data, such as pathological images and genomics, is crucial for improving prediction accuracy. Despite promising results of existing approaches, there are great challenges of modality gap and semantic redundancy presented in multiple cancer data, which could hinder the comprehensive integration and pose substantial obstacles to further enhancing cancer survival prediction. In this study, we propose a novel agnostic-specific modality learning (ASML) framework for accurate cancer survival prediction. To bridge the modality gap and provide a comprehensive view of distinct data modalities, we employ an agnostic-specific learning strategy to learn the commonality across modalities and the uniqueness of each modality. Moreover, a cross-modal fusion network is exerted to integrate multimodal information by modeling modality correlations and diminish semantic redundancy in a divide-and-conquer manner. Extensive experiment results on three TCGA datasets demonstrate that ASML reaches better performance than other existing cancer survival prediction methods for multiple data.

Semi-supervised learning effectively mitigates the lack of labeled data by introducing extensive unlabeled data. Despite achieving success in respiratory sound classification, in practice, it usually takes years to acquire a sufficiently sizeable unlabeled set, which consequently results in an extension of the research timeline. Considering that there are also respiratory sounds available in other related tasks, like breath phase detection and COVID-19 detection, it might be an alternative manner to treat these external samples as unlabeled data for respiratory sound classification. However, since these external samples are collected in different scenarios via different devices, there inevitably exists a distribution mismatch between the labeled and external unlabeled data. For existing methods, they usually assume that the labeled and unlabeled data follow the same data distribution. Therefore, they cannot benefit from external samples. To utilize external unlabeled data, we propose a semi-supervised method based on Joint Energy-based Model (JEM) in this paper. During training, the method attempts to use only the essential semantic components within the samples to model the data distribution. When non-semantic components like recording environments and devices vary, as these non-semantic components have a small impact on the model training, a relatively accurate distribution estimation is obtained. Therefore, the method exhibits insensitivity to the distribution mismatch, enabling the model to leverage external unlabeled data to mitigate the lack of labeled data. Taking ICBHI 2017 as the labeled set, HF_Lung_V1 and COVID-19 Sounds as the external unlabeled sets, the proposed method exceeds the baseline by 12.86.

Automatic extraction of valuable, structured evidence from the exponentially growing clinical trial literature can help physicians practice evidence-based medicine quickly and accurately. However, current research on evidence extraction has been limited by the lack of generalization ability on various clinical topics and the high cost of manual annotation. In this work, we address these challenges by constructing a PICO-based evidence dataset PICO-DS, covering five clinical topics. This dataset was automatically labeled by a distant supervision based on our proposed textual similarity algorithm called ROUGE-Hybrid. We then present an Aceso-DSAL model, an extension of our previous supervised evidence extraction model - Aceso. In Aceso-DSAL, distantly-labelled and multi-topic PICO-DS was exploited as training corpus, which greatly enhances the generalization of the extraction model. To mitigate the influence of noise unavoidably-introduced in distant supervision, we employ TextCNN and MW-Net models and a paradigm of active learning to weigh the value of each sample. We evaluate the effectiveness of our model on the PICO-DS dataset and find that it outperforms state-of-the-art studies in identifying evidential sentences.