Semi-automatic data annotation based on feature-space projection and local quality metrics: An application to cerebral emboli characterization.

We propose a semi-supervised learning approach to annotate a dataset with reduced requirements for manual annotation and with controlled annotation error. The method is based on feature-space projection and label propagation using local quality metrics. First, an auto-encoder extracts the features of the samples in an unsupervised manner. Then, the extracted features are projected by a t-distributed stochastic neighbor embedding algorithm into a two-dimensional (2D) space. A selection of the best 2D projection is introduced based on the silhouette score. The expert annotator uses the obtained 2D representation to manually label samples. Finally, the labels of the labeled samples are propagated to the unlabeled samples using a K-nearest neighbor strategy and local quality metrics. We compare our method against semi-supervised optimum-path forest and K-nearest neighbor label propagation (without considering local quality metrics). Our method achieves state-of-the-art results on three different datasets by labeling more than 96% of the samples with an annotation error from 7% to 17%. Additionally, our method allows to control the trade-off between annotation error and number of labeled samples. Moreover, we combine our method with robust loss functions to compensate for the label noise introduced by automatic label propagation. Our method allows to achieve similar, and even better, classification performances compared to those obtained using a fully manually labeled dataset, with up to 6% in terms of classification accuracy.

Sequential Emboli Detection From Ultrasound Outpatient Data.

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.

Discrimination between emboli and artifacts for outpatient transcranial Doppler ultrasound data.

This paper addresses the detection of emboli in transcranial Doppler ultrasound data acquired from an original portable device. The challenge is the removal of several artifacts (motion and voice) intrinsically related to long-duration (up to 1 h 40 mn per patient) outpatient signals monitoring from this device, as well as high intensities due to the stochastic nature of blood flow. This paper proposes an adapted removal procedure. This firstly consists of reducing the background noise and detecting the blood flow in the time-frequency domain using a likelihood method for contour detection. Then, a hierarchical extraction of features from magnitude and bounding boxes is achieved for the discrimination of emboli and artifacts. After processing of the long-duration outpatient signals, the number of artifacts predicted as emboli is considerably reduced (by 92% for some parameter values) between the first and the last step of our algorithm.