Goto

Collaborating Authors

Results


What is Artificial Intelligence? How does AI work, Types, Trends and Future of it?

#artificialintelligence

Let's take a detailed look. This is the most common form of AI that you'd find in the market now. These Artificial Intelligence systems are designed to solve one single problem and would be able to execute a single task really well. By definition, they have narrow capabilities, like recommending a product for an e-commerce user or predicting the weather. This is the only kind of Artificial Intelligence that exists today. They're able to come close to human functioning in very specific contexts, and even surpass them in many instances, but only excelling in very controlled environments with a limited set of parameters. AGI is still a theoretical concept. It's defined as AI which has a human-level of cognitive function, across a wide variety of domains such as language processing, image processing, computational functioning and reasoning and so on.


Artificial intelligence

#artificialintelligence

Deep learning[133] uses several layers of neurons between the network's inputs and outputs. The multiple layers can progressively extract higher-level features from the raw input. For example, in image processing, lower layers may identify edges, while higher layers may identify the concepts relevant to a human such as digits or letters or faces.[134] Deep learning has drastically improved the performance of programs in many important subfields of artificial intelligence, including computer vision, speech recognition, image classification[135] and others. Deep learning often uses convolutional neural networks for many or all of its layers.


AI Detects Osteoporosis With High Accuracy By Analyzing Dental X-Rays

#artificialintelligence

Scientists in Japan were able to identify osteoporosis with high accuracy using AI to analyze routine dental x-rays. The researchers at Kagawa Prefectural Central Hospital, Okayama University, and Matsumoto Dental University used deep learning to construct an osteoporosis classifier from dental x-rays. The study entitled Identification of osteoporosis using ensemble deep learning model with panoramic radiographs and clinical covariates was published in Scientific Reports on April 12, 2022. It's estimated that over 200 million people worldwide have osteoporosis. People with osteoporosis are at high risk for sudden bone fractures.


A new generative adversarial network for medical images super resolution - Scientific Reports

#artificialintelligence

For medical image analysis, there is always an immense need for rich details in an image. Typically, the diagnosis will be served best if the fine details in the image are retained and the image is available in high resolution. In medical imaging, acquiring high-resolution images is challenging and costly as it requires sophisticated and expensive instruments, trained human resources, and often causes operation delays. Deep learning based super resolution techniques can help us to extract rich details from a low-resolution image acquired using the existing devices. In this paper, we propose a new Generative Adversarial Network (GAN) based architecture for medical images, which maps low-resolution medical images to high-resolution images. The proposed architecture is divided into three steps. In the first step, we use a multi-path architecture to extract shallow features on multiple scales instead of single scale. In the second step, we use a ResNet34 architecture to extract deep features and upscale the features map by a factor of two. In the third step, we extract features of the upscaled version of the image using a residual connection-based mini-CNN and again upscale the feature map by a factor of two. The progressive upscaling overcomes the limitation for previous methods in generating true colors. Finally, we use a reconstruction convolutional layer to map back the upscaled features to a high-resolution image. Our addition of an extra loss term helps in overcoming large errors, thus, generating more realistic and smooth images. We evaluate the proposed architecture on four different medical image modalities: (1) the DRIVE and STARE datasets of retinal fundoscopy images, (2) the BraTS dataset of brain MRI, (3) the ISIC skin cancer dataset of dermoscopy images, and (4) the CAMUS dataset of cardiac ultrasound images. The proposed architecture achieves superior accuracy compared to other state-of-the-art super-resolution architectures.


Language Models

Communications of the ACM

A transformer has strong language representation ability; a very large corpus contains rich language expressions (such unlabeled data can be easily obtained) and training large-scale deep learning models has become more efficient. Therefore, pre-trained language models can effectively represent a language's lexical, syntactic, and semantic features. Pre-trained language models, such as BERT and GPTs (GPT-1, GPT-2, and GPT-3), have become the core technologies of current NLP. Pre-trained language model applications have brought great success to NLP. "Fine-tuned" BERT has outperformed humans in terms of accuracy in language-understanding tasks, such as reading comprehension.8,17 "Fine-tuned" GPT-3 has also reached an astonishing level of fluency in text-generation tasks.3


Neural network generates lung ventilation images from CT scans – Physics World

#artificialintelligence

Incorporating ventilation images into radiotherapy plans to treat lung cancer could reduce the incidence of debilitating radiation-induced lung injuries, such as radiation pneumonitis and radiation fibrosis. Specifically, ventilation imaging can be used to adapt radiation treatment plans to reduce the dose to high-functioning lung. Positron emission tomography (PET) and single-photon emission computed tomography (SPECT) scans are the gold standard of ventilation imaging. However, these modalities are not always readily available and the cost of such exams may be prohibitive. As such, researchers are investigating the feasibility of alternatives such as MR or CT ventilation imaging.


Neural Network News: How Deep Learning Predicts Traumatic Brain Injury Outcomes

#artificialintelligence

The algorithm, created by researchers at the University of Pittsburgh School of Medicine, was trained to predict outcomes for patients with traumatic brain injury (TBI). The algorithm was trained on a wide range of data including computed tomography (CT) scans, vital signs, blood tests, heart function, and coma severity estimates for the patient. The large and varied dataset lends itself well to a deep learning algorithm. The model was a fusion model that combined clinical input with a dataset of head CT scans predicting mortality and unfavorable outcomes. The researchers used transfer learning and curriculum learning applied to a convolutional neural network (CNN) in order to specialize the network to the CT scans.


Focus on machine learning models in medical imaging – Physics World

#artificialintelligence

Join the audience for an AI in Medical Physics Week live webinar at 3 p.m. BST on 23 June 2022 based on IOP Publishing's special issue, Focus on Machine Learning Models in Medical Imaging Want to take part in this webinar? An overview will be given of the role of artificial intelligence (AI) in automatic delineation (contouring) of organs in preclinical cancer research models. It will be shown how AI can increase efficiency in preclinical research. Speaker: Frank Verhaegen is head of radiotherapy physics research at Maastro Clinic, and also professor at the University of Maastricht, both located in the Netherlands. He is also a co-founder of the company SmART Scientific Solutions BV, which develops research software for preclinical cancer research.


Genome-wide mapping of somatic mutation rates uncovers drivers of cancer - Nature Biotechnology

#artificialintelligence

Identification of cancer driver mutations that confer a proliferative advantage is central to understanding cancer; however, searches have often been limited to protein-coding sequences and specific non-coding elements (for example, promoters) because of the challenge of modeling the highly variable somatic mutation rates observed across tumor genomes. Here we present Dig, a method to search for driver elements and mutations anywhere in the genome. We use deep neural networks to map cancer-specific mutation rates genome-wide at kilobase-scale resolution. These estimates are then refined to search for evidence of driver mutations under positive selection throughout the genome by comparing observed to expected mutation counts. We mapped mutation rates for 37 cancer types and applied these maps to identify putative drivers within intronic cryptic splice regions, 5′ untranslated regions and infrequently mutated genes. Our high-resolution mutation rate maps, available for web-based exploration, are a resource to enable driver discovery genome-wide. Cancer driver mutations are identified by predicting neutral mutation rates across the entire genome.


Artificial intelligence shows promise for interpreting dental X-rays

#artificialintelligence

A deep learning algorithm successfully detects periodontal disease from 2D bitewing radiographs, according to research presented at EuroPerio10, the world's leading congress in periodontology and implant dentistry organized by the European Federation of Periodontology (EFP). "Our study shows the potential for artificial intelligence (AI) to automatically identify periodontal pathologies that might otherwise be missed," said study author Dr. Burak Yavuz of Eskisehir Osmangazi University, Turkey. "This could reduce radiation exposure by avoiding repeat assessments, prevent the silent progression of periodontal disease, and enable earlier treatment." Previous studies have examined the use of AI to detect caries, root fractures and apical lesions but there is limited research in the field of periodontology. This study evaluated the ability of deep learning, a type of AI, to determine periodontal status in bitewing radiographs.