Seismic horizon detection with neural networks

Over the last few years, Convolutional Neural Networks (CNNs) were successfully adopted in numerous domains to solve various image-related tasks, ranging from simple classification to fine borders annotation. Tracking seismic horizons is no different, and there are a lot of papers proposing the usage of such models to avoid time-consuming hand-picking. Unfortunately, most of them are (i) either trained on synthetic data, which can't fully represent the complexity of subterranean structures, (ii) trained and tested on the same cube, or (iii) lack reproducibility and precise descriptions of the model-building process. With all that in mind, the main contribution of this paper is an open-sourced research of applying binary segmentation approach to the task of horizon detection on multiple real seismic cubes with a focus on inter-cube generalization of the predictive model.

Benchmarks of ResNet Architecture for Atrial Fibrillation Classification

In this work we apply variations of ResNet architecture to the task of atrial fibrillation classification. Variations differ in number of filter after first convolution, ResNet block layout, number of filters in block convolutions and number of ResNet blocks between downsampling operations. We have found a range of model size in which models with quite different configurations show similar performance. It is likely that overall number of parameters plays dominant role in model performance. However, configuration parameters like layout have values that constantly lead to better results, which allows to suggest that these parameters should be defined and fixed in the first place, while others may be varied in a reasonable range to satisfy any existing constraints.

A Simple Probabilistic Model for Uncertainty Estimation

The article focuses on determining the predictive uncertainty of a model on the example of atrial fibrillation detection problem by a single-lead ECG signal. To this end, the model predicts parameters of the beta distribution over class probabilities instead of these probabilities themselves. It was shown that the described approach allows to detect atypical recordings and significantly improve the quality of the algorithm on confident predictions.

Clearing noisy annotations for computed tomography imaging

One of the problems on the way to successful implementation of neural networks is the quality of annotation. For instance, different annotators can annotate images in a different way and very often their decisions do not match exactly and in extreme cases are even mutually exclusive which results in noisy annotations and, consequently, inaccurate predictions. To avoid that problem in the task of computed tomography (CT) imaging segmentation we propose a clearing algorithm for annotations. It consists of 3 stages: - annotators scoring, which assigns a higher confidence level to better annotators; - nodules scoring, which assigns a higher confidence level to nodules confirmed by good annotators; - nodules merging, which aggregates annotations according to nodules confidence. In general, the algorithm can be applied to many different tasks (namely, binary and multi-class semantic segmentation, and also with trivial adjustments to classification and regression) where there are several annotators labeling each image.

Not quite unreasonable effectiveness of machine learning algorithms

State-of-the-art machine learning algorithms demonstrate close to absolute performance in selected challenges. We provide arguments that the reason can be in low variability of the samples and high effectiveness in learning typical patterns. Due to this fact, standard performance metrics do not reveal model capacity and new metrics are required for the better understanding of state-of-the-art.