Federated learning enables big data for rare cancer boundary detection

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

Temporal progress of gene expression analysis with RNA-Seq data: A review on the relationship between computational methods

Analysis of differential gene expression from RNA-seq data has become a standard for several research areas. The steps for the computational analysis include many data types and file formats, and a wide variety of computational tools that can be applied alone or together as pipelines. This paper presents a review of the differential expression analysis pipeline, addressing its steps and the respective objectives, the principal methods available in each step, and their properties, therefore introducing an organized overview to this context. This review aims to address mainly the aspects involved in the differentially expressed gene (DEG) analysis from RNA sequencing data (RNA-seq), considering the computational methods. In addition, a timeline of the computational methods for DEG is shown and discussed, and the relationships existing between the most important computational tools are presented by an interaction network. A discussion on the challenges and gaps in DEG analysis is also highlighted in this review. This paper will serve as a tutorial for new entrants into the field and help established users update their analysis pipelines.

A deep descriptor for cross-tasking EEG-based recognition

Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.

COVID-19 detection in CT images with deep learning: A voting-based scheme and cross-datasets analysis

Early detection and diagnosis are critical factors to control the COVID-19 spreading. A number of deep learning-based methodologies have been recently proposed for COVID-19 screening in CT scans as a tool to automate and help with the diagnosis. These approaches, however, suffer from at least one of the following problems: (i) they treat each CT scan slice independently and (ii) the methods are trained and tested with sets of images from the same dataset. Treating the slices independently means that the same patient may appear in the training and test sets at the same time which may produce misleading results. It also raises the question of whether the scans from the same patient should be evaluated as a group or not. Moreover, using a single dataset raises concerns about the generalization of the methods. Different datasets tend to present images of varying quality which may come from different types of CT machines reflecting the conditions of the countries and cities from where they come from. In order to address these two problems, in this work, we propose an Efficient Deep Learning Technique for the screening of COVID-19 with a voting-based approach. In this approach, the images from a given patient are classified as group in a voting system. The approach is tested in the two biggest datasets of COVID-19 CT analysis with a patient-based split. A cross dataset study is also presented to assess the robustness of the models in a more realistic scenario in which data comes from different distributions. The cross-dataset analysis has shown that the generalization power of deep learning models is far from acceptable for the task since accuracy drops from 87.68% to 56.16% on the best evaluation scenario. These results highlighted that the methods that aim at COVID-19 detection in CT-images have to improve significantly to be considered as a clinical option and larger and more diverse datasets are needed to evaluate the methods in a realistic scenario.

ECG-based heartbeat classification for arrhythmia detection: A survey

An electrocardiogram (ECG) measures the electric activity of the heart and has been widely used for detecting heart diseases due to its simplicity and non-invasive nature. By analyzing the electrical signal of each heartbeat, i.e., the combination of action impulse waveforms produced by different specialized cardiac tissues found in the heart, it is possible to detect some of its abnormalities. In the last decades, several works were developed to produce automatic ECG-based heartbeat classification methods. In this work, we survey the current state-of-the-art methods of ECG-based automated abnormalities heartbeat classification by presenting the ECG signal preprocessing, the heartbeat segmentation techniques, the feature description methods and the learning algorithms used. In addition, we describe some of the databases used for evaluation of methods indicated by a well-known standard developed by the Association for the Advancement of Medical Instrumentation (AAMI) and described in ANSI/AAMI EC57:1998/(R)2008 (ANSI/AAMI, 2008). Finally, we discuss limitations and drawbacks of the methods in the literature presenting concluding remarks and future challenges, and also we propose an evaluation process workflow to guide authors in future works.

Automatic cardiac arrhythmia detection and classification using vectorcardiograms and complex networks

This paper intends to bring new insights in the methods for extracting features for cardiac arrhythmia detection and classification systems. We explore the possibility for utilizing vectorcardiograms (VCG) along with electrocardiograms (ECG) to get relevant informations from the heartbeats on the MIT-BIH database. For this purpose, we apply complex networks to extract features from the VCG. We follow the ANSI/AAMI EC57:1998 standard, for classifying the beats into 5 classes (N, V, S, F and Q), and de Chazal's scheme for dataset division into training and test set, with 22 folds validation setup for each set. We used the Support Vector Machinhe (SVM) classifier and the best result we chose had a global accuracy of 84.1%, while still obtaining relatively high Sensitivities and Positive Predictive Value and low False Positive Rates, when compared to other papers that follows the same evaluation methodology that we do.

How the choice of samples for building arrhythmia classifiers impact their performances

Arrhythmia (i.e., irregular cardiac beat) classification in electrocardiogram (ECG) signals is an important issue for heart disease diagnosis due to the non-invasive nature of the ECG exam. In this paper, we analyze and criticize the results of some arrhythmia classification methods presented in the literature in terms of how the samples are chosen for training/testing the classifier and the impact this choice has on their performance (i.e., accuracy/sensitivity/specificity). From our implementation, we also report new accuracies for these methods, establishing a new state-of-the-art method, in terms of results.