Medical signal classification often focuses on one representation (raw signal or time frequency). In that context, recent works have shown the value of exploiting different representations simultaneously. We propose a regularized end-to-end trained model for classification in a medical context exploiting both the raw signal and a time-frequency representation (TFR). First, a 2D convolutional neural network (CNN) encoder and a 1D CNN-transformer encoder start by extracting embedded representations from the TFR and the raw signal, respectively. Then, the obtained embeddings are fused to form a common latent space that is used for classification. We propose to guide the training of each encoder by applying two iterated losses. Moreover, we propose to regularize the fused common latent space using deep embedded clustering. Extensive experiments on three medical datasets and ablation studies show the adaptability and good performance of our method for medical signal classification. Our method makes it possible to improve the classification performance from 4% to 12% MCC on a transcranial Doppler dataset, when compared with single-feature counterparts, while giving more stable models. The code is available at: https://github.com/gdec-submission/gdec/.

This paper addresses the detection of emboli from signals acquired with a new miniaturized and portable transcranial Doppler ultrasound device. The use of this device enables outpatient monitoring but increases the number of artifacts. These artifacts usually come from the patient voice and motion and can be superimposed to emboli. For this reason and because of the scarcity of emboli compared to artifacts, reliably detect emboli is a challenging task. As an example, the 11809 s of signal used in this study contained 0.06 % of embolic events and 10.14 % of artifacts. Herein, we propose an automatic and sequential approach. The method is based on sequential determination of high intensity transient signals. We also define efficient features to describe emboli in the time frequency representation. On our database, the number of artifacts detected as emboli is divided by more than 10 compared to the other algorithms reported in the literature.

This paper addresses the detection of a suddenly arriving dynamic profile of a finite duration often called a transient change. In contrast to the traditional abrupt change detection, where the post-change period is assumed to be infinitely long, the detection of a suddenly arriving transient change should be done before it disappears. The detection of transient changes after their disappearance is considered as missed. Hence, the traditional quickest change detection criterion, minimizing the average detection delays provided a prescribed false alarm rate, is compromised. The proposed optimality criterion minimizes the worst case probability of missed detection provided that the worst case probability of false alarm during a certain period is upper bounded. A suboptimal CUSUM-type transient change detection algorithm, based on a subclass of truncated Sequential Probability Ratio Tests, is proposed. The optimization of the proposed algorithm in this subclass leads to a specially designed Finite Moving Average Test. The proposed method is analyzed theoretically and by simulation. A special attention is paid to the case of Gaussian observations with a dynamic profile.

Detecting micro-emboli in the middle cerebral artery is a major challenge because these micro-emboli are related to the risk of stroke (cerebrovascular accident). Because micro-emboli are defined as High Intensity Transient Signals (HITS), their detection require the estimation of the blood flow background signal; i.e, the reference from which HITS have to be detected. In this paper, we propose an original micro-emboli detection procedure composed of two steps. Firstly, the background noise is isolated from the blood flow time-frequency image thanks to the log-likelihood segmentation method. Secondly, a HITS detection threshold is calculated from a blood flow statistic using the spectral kurtosis approach. Our procedure is used on the transcranial Doppler data from two patients and the results show that the mean percentage error of the velocity envelope estimation is reduced from 5% to 3% and the micro-emboli detection probability is 84% while only 49 artifacts are detected.