Intracranial hemorrhage (ICH) is a life-threatening emergency that can lead to brain damage or death, with high rates of mortality and morbidity. The fast and accurate detection of ICH is important for the patient to get an early and efficient treatment. To improve this diagnostic process, the application of Deep Learning (DL) models on head CT scans is an active area of research. Although promising results have been obtained, many of the proposed models require slice-level annotations by radiologists, which are costly and time-consuming. We formulate the ICH detection as a problem of Multiple Instance Learning (MIL) that allows training with only scan-level annotations. We develop a new probabilistic method based on Deep Gaussian Processes (DGP) that is able to train with this MIL setting and accurately predict ICH at both slice- and scan-level. The proposed DGPMIL model is able to capture complex feature relations by using multiple Gaussian Process (GP) layers, as we show experimentally. To highlight the advantages of DGPMIL in a general MIL setting, we first conduct several controlled experiments on the MNIST dataset. We show that multiple GP layers outperform one-layer GP models, especially for complex feature distributions. For ICH detection experiments, we use two public brain CT datasets (RSNA and CQ500). We first train a Convolutional Neural Network (CNN) with an attention mechanism to extract the image features, which are fed into our DGPMIL model to perform the final predictions. The results show that DGPMIL model outperforms VGPMIL as well as the attention-based CNN for MIL and other state-of-the-art methods for this problem. The best performing DGPMIL model reaches an AUC-ROC of 0.957 (resp. 0.909) and an AUC-PR of 0.961 (resp. 0.889) on the RSNA (resp. CQ500) dataset. The competitive performance at slice- and scan-level shows that DGPMIL model provides an accurate diagnosis on slices without the need for slice-level annotations by radiologists during training. As MIL is a common problem setting, our model can be applied to a broader range of other tasks, especially in medical image classification, where it can help the diagnostic process.

Machine learning (ML) methods often require large volumes of labeled data to achieve meaningful performance. The expertise necessary for labeling data in medical applications like pathology presents a significant challenge in developing clinical-grade tools. Crowdsourcing approaches address this challenge by collecting labels from multiple annotators with varying degrees of expertise. In recent years, multiple methods have been adapted to learn from noisy crowdsourced labels. Among them, Gaussian Processes (GPs) have achieved excellent performance due to their ability to model uncertainty. Deep Gaussian Processes (DGPs) address the limitations of GPs using multiple layers to enable the learning of more complex representations. In this work, we develop Deep Gaussian Processes for Crowdsourcing (DGPCR) to model the crowdsourcing problem with DGPs for the first time. DGPCR models the (unknown) underlying true labels, and the behavior of each annotator is modeled with a confusion matrix among classes. We use end-to-end variational inference to estimate both DGPCR parameters and annotator biases. Using annotations from 25 pathologists and medical trainees, we show that DGPCR is competitive or superior to Scalable Gaussian Processes for Crowdsourcing (SVGPCR) and other state-of-the-art deep-learning crowdsourcing methods for breast cancer classification. Also, we observe that DGPCR with noisy labels obtains better results (F1 = 81.91%) than GPs (F1 = 81.57%) and deep learning methods (F1 = 80.88%) with true labels curated by experts. Finally, we show an improved estimation of annotators’ behavior.

The automatic classification of volcano-seismic events is a key problem in volcanology. Due to its complexity, deep learning (DL) techniques have become the tool of choice for this problem, outperforming classical classifiers. The main drawback of this approach, when applied to the classification of volcano-seismic events, is its tendency to overfit because of the small-size available databases. In this work, we propose and analyze the use of the Gaussian processes (GPs) and Deep GPs (DGPs), and their hierarchical extension, for volcano-seismic event classification. We empirically prove the adequacy of the proposed modeling with an insightful and exhaustive comparison with state-of-the-art DL-based methods on a seismic database recorded at ``Volcán de Fuego,'' Colima, Mexico. The hierarchical structure of DGPs and the reduced number of parameters to be automatically estimated become essential to achieve excellent performance even on small databases, capturing well the complex patterns of seismic signals for all classes and, in particular, for those that have been hardly observed.