Citizen neuroscience: Wearable technology and open software to study the human brain in its natural habitat.

Citizen science allows the public to participate in various stages of scientific research, including study design, data acquisition, and data analysis. Citizen science has a long history in several fields of the natural sciences, and with recent developments in wearable technology, neuroscience has also become more accessible to citizen scientists. This development was largely driven by the influx of minimal sensing systems in the consumer market, allowing more do-it-yourself (DIY) and quantified-self (QS) investigations of the human brain. While most subfields of neuroscience require sophisticated monitoring devices and laboratories, the study of sleep characteristics can be performed at home with relevant noninvasive consumer devices. The strong influence of sleep quality on waking life and the accessibility of devices to measure sleep are two primary reasons citizen scientists have widely embraced sleep research. Their involvement has evolved from solely contributing to data collection to engaging in more collaborative or autonomous approaches, such as instigating ideas, formulating research inquiries, designing research protocols and methodology, acting upon their findings, and disseminating results. In this article, we introduce the emerging field of citizen neuroscience, illustrating examples of such projects in sleep research. We then provide overviews of the wearable technologies for tracking human neurophysiology and various open-source software used to analyse them. Finally, we discuss the opportunities and challenges in citizen neuroscience projects and suggest how to improve the study of the human brain outside the laboratory.

A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework.

The field of Medicine and Healthcare has attained revolutionary advancements in the last forty years. Within this period, the actual reasons behind numerous diseases were unveiled, novel diagnostic methods were designed, and new medicines were developed. Even after all these achievements, diseases like cancer continue to haunt us since we are still vulnerable to them. Cancer is the second leading cause of death globally; about one in every six people die suffering from it. Among many types of cancers, the lung and colon variants are the most common and deadliest ones. Together, they account for more than 25% of all cancer cases. However, identifying the disease at an early stage significantly improves the chances of survival. Cancer diagnosis can be automated by using the potential of Artificial Intelligence (AI), which allows us to assess more cases in less time and cost. With the help of modern Deep Learning (DL) and Digital Image Processing (DIP) techniques, this paper inscribes a classification framework to differentiate among five types of lung and colon tissues (two benign and three malignant) by analyzing their histopathological images. The acquired results show that the proposed framework can identify cancer tissues with a maximum of 96.33% accuracy. Implementation of this model will help medical professionals to develop an automatic and reliable system capable of identifying various types of lung and colon cancers.

A Novel Method to Identify Pneumonia through Analyzing Chest Radiographs Employing a Multichannel Convolutional Neural Network.

Pneumonia is a virulent disease that causes the death of millions of people around the world. Every year it kills more children than malaria, AIDS, and measles combined and it accounts for approximately one in five child-deaths worldwide. The invention of antibiotics and vaccines in the past century has notably increased the survival rate of Pneumonia patients. Currently, the primary challenge is to detect the disease at an early stage and determine its type to initiate the appropriate treatment. Usually, a trained physician or a radiologist undertakes the task of diagnosing Pneumonia by examining the patient's chest X-ray. However, the number of such trained individuals is nominal when compared to the 450 million people who get affected by Pneumonia every year. Fortunately, this challenge can be met by introducing modern computers and improved Machine Learning techniques in Pneumonia diagnosis. Researchers have been trying to develop a method to automatically detect Pneumonia using machines by analyzing and the symptoms of the disease and chest radiographic images of the patients for the past two decades. However, with the development of cogent Deep Learning algorithms, the formation of such an automatic system is very much within the realms of possibility. In this paper, a novel diagnostic method has been proposed while using Image Processing and Deep Learning techniques that are based on chest X-ray images to detect Pneumonia. The method has been tested on a widely used chest radiography dataset, and the obtained results indicate that the model is very much potent to be employed in an automatic Pneumonia diagnosis scheme.

A Pneumonia Diagnosis Scheme Based on Hybrid Features Extracted from Chest Radiographs Using an Ensemble Learning Algorithm.

Pneumonia is a fatal disease responsible for almost one in five child deaths worldwide. Many developing countries have high mortality rates due to pneumonia because of the unavailability of proper and timely diagnostic measures. Using machine learning-based diagnosis methods can help to detect the disease early and in less time and cost. In this study, we proposed a novel method to determine the presence of pneumonia and identify its type (bacterial or viral) through analyzing chest radiographs. We performed a three-class classification based on features containing diverse information of the samples. After using an augmentation technique to balance the dataset's sample sizes, we extracted the chest X-ray images' statistical features, as well as global features by employing a deep learning architecture. We then combined both sets of features and performed the final classification using the RandomForest classifier. A feature selection method was also incorporated to identify the features with the highest relevance. We tested the proposed method on a widely used (but relabeled) chest radiograph dataset to evaluate its performance. The proposed model can classify the dataset's samples with an 86.30% classification accuracy and 86.03% F-score, which assert the model's efficacy and reliability. However, results show that the classifier struggles while distinguishing between viral and bacterial pneumonia samples. Implementing this method will provide a fast and automatic way to detect pneumonia in a patient and identify its type.