Collaborating Authors


Mental instructions free up space for productive thoughts, study shows

Daily Mail - Science & tech

Giving yourself verbal or mental instructions to clear your mind can help make room in your brain for more productive thoughts, a new study reveals. US researchers used brain imaging scans and machine learning to investigate what happens to the brain when we try to stop thinking about something. Three instructions – to'clear' our mind, 'suppress' a thought and'replace' a thought with something else – all successfully removed and manipulated unwanted information in the'working memory'. The working memory is the mental'notepad' that contains fleeting thoughts and is responsible for the temporary holding and processing of information. Holding information in the working memory is essential for cognition, but removing unwanted thoughts is equally important, researchers say.

NIH is developing AI to help with COVID19


Artificial intelligence is a vital component in the fight against COVID-19. Healthcare benefits greatly from machine learning and artificial intelligence techniques that allow for better and faster mapping of the virus as well as for more comprehensive research to administrate the right treatment and create a vaccine. The National Institutes of Health has launched the Medical Imagining and Data Resource Center (MIDRC) to deliver AI-based solutions for the new type of problems the world is facing in the actual climate. The goal is to combine the power of AI and medical imaging to better understand and retaliate against COVID-19. Moreover, their goal is to be able to use medical imaging to create personalized treatments for patients with COVID-19.

A connection between the pattern classification problem and the General Linear Model for statistical inference Machine Learning

A connection between the General Linear Model (GLM) in combination with classical statistical inference and the machine learning (MLE)-based inference is described in this paper. Firstly, the estimation of the GLM parameters is expressed as a Linear Regression Model (LRM) of an indicator matrix, that is, in terms of the inverse problem of regressing the observations. In other words, both approaches, i.e. GLM and LRM, apply to different domains, the observation and the label domains, and are linked by a normalization value at the least-squares solution. Subsequently, from this relationship we derive a statistical test based on a more refined predictive algorithm, i.e. the (non)linear Support Vector Machine (SVM) that maximizes the class margin of separation, within a permutation analysis. The MLE-based inference employs a residual score and includes the upper bound to compute a better estimation of the actual (real) error. Experimental results demonstrate how the parameter estimations derived from each model resulted in different classification performances in the equivalent inverse problem. Moreover, using real data the aforementioned predictive algorithms within permutation tests, including such model-free estimators, are able to provide a good trade-off between type I error and statistical power.

Endotracheal Tube Position Assessment on Chest Radiographs Using Deep Learning


"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. To determine the efficacy of deep learning in assessing endotracheal tube (ETT) position on radiographs. Images were split into training (80%, 18368 images), validation (10%, 2296 images), and'internal test' (10%, 2296 images), derived from the same institution as the training data.

2020: The Year of Artificial Intelligence in Mammography


It is no secret that mammography services faced a significant set-back this year when the COVID-19 pandemic erupted. Eventually, the service line was able to rebound from the catastrophic 92-percent plummet it experienced during the summer months – but, that was not all that happened. That recovery was, without a doubt, a success, but it was by no means the only positive development with mammography during 2020. This was the year to watch advances in artificial intelligence tools in breast imaging. To pinpoint the ones that will be most impactful, Diagnostic Imaging spoke with Randy Miles, M.D., MPH, assistant professor of radiology at Harvard Medical School.

Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information Artificial Intelligence

As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks. In the medical domain, however, large-scale and multi-parties data training and analyses are infeasible due to the privacy and data security concerns. In this paper, we propose an extendable and elastic learning framework to preserve privacy and security while enabling collaborative learning with efficient communication. The proposed framework is named distributed Asynchronized Discriminator Generative Adversarial Networks (AsynDGAN), which consists of a centralized generator and multiple distributed discriminators. The advantages of our proposed framework are five-fold: 1) the central generator could learn the real data distribution from multiple datasets implicitly without sharing the image data; 2) the framework is applicable for single-modality or multi-modality data; 3) the learned generator can be used to synthesize samples for down-stream learning tasks to achieve close-to-real performance as using actual samples collected from multiple data centers; 4) the synthetic samples can also be used to augment data or complete missing modalities for one single data center; 5) the learning process is more efficient and requires lower bandwidth than other distributed deep learning methods.

Using MONAI Framework For Medical Imaging Research - Analytics India Magazine


Medical Imaging has been used in several applications in the healthcare industry. Deep Learning solutions have exceeded many healthcare tasks in detecting and diagnosing abnormalities in medical data. In January 2020, we noticed Google's DeepMind AI outperformed radiologists in detecting breast cancer, according to Nature's publication. Data management is one of the most critical steps in deep learning solutions. The size of healthcare data is reaching 2314 Exabytes of new data by 2020.

Pyramid-Focus-Augmentation: Medical Image Segmentation with Step-Wise Focus Artificial Intelligence

Segmentation of findings in the gastrointestinal tract is a challenging but also an important task which is an important building stone for sufficient automatic decision support systems. In this work, we present our solution for the Medico 2020 task, which focused on the problem of colon polyp segmentation. We present our simple but efficient idea of using an augmentation method that uses grids in a pyramid-like manner (large to small) for segmentation. Our results show that the proposed methods work as indented and can also lead to comparable results when competing with other methods.

Deep-learning model enables rapid lymphoma detection in PET/CT images


From left to right: Timothy Perk, Alison Roth, Peter Ferjančič, Robert Jeraj, Daniel Huff, Brayden Schott, Ali Deatsch, Victor Santoro Fernandes, Amy Weisman, Vince Streif. Whole-body positron emission tomography combined with computed tomography (PET/CT) is a cornerstone in the management of lymphoma (cancer in the lymphatic system). PET/CT scans are used to diagnose disease and then to monitor how well patients respond to therapy. However, accurately classifying every single lymph node in a scan as healthy or cancerous is a complex and time-consuming process. Because of this, detailed quantitative treatment monitoring is often not feasible in clinical day-to-day practice. Researchers at the University of Wisconsin-Madison have recently developed a deep-learning model that can perform this task automatically.

Attentional Biased Stochastic Gradient for Imbalanced Classification Machine Learning

In this paper~\footnote{The original title is "Momentum SGD with Robust Weighting For Imbalanced Classification"}, we present a simple yet effective method (ABSGD) for addressing the data imbalance issue in deep learning. Our method is a simple modification to momentum SGD where we leverage an attentional mechanism to assign an individual importance weight to each gradient in the mini-batch. Unlike existing individual weighting methods that learn the individual weights by meta-learning on a separate balanced validation data, our weighting scheme is self-adaptive and is grounded in distributionally robust optimization. The weight of a sampled data is systematically proportional to exponential of a scaled loss value of the data, where the scaling factor is interpreted as the regularization parameter in the framework of information-regularized distributionally robust optimization. We employ a step damping strategy for the scaling factor to balance between the learning of feature extraction layers and the learning of the classifier layer. Compared with exiting meta-learning methods that require three backward propagations for computing mini-batch stochastic gradients at three different points at each iteration, our method is more efficient with only one backward propagation at each iteration as in standard deep learning methods. Compared with existing class-level weighting schemes, our method can be applied to online learning without any knowledge of class prior, while enjoying further performance boost in offline learning combined with existing class-level weighting schemes. Our empirical studies on several benchmark datasets also demonstrate the effectiveness of our proposed method