A.Y. Ng

Closing the Performance Gap between Generalists and Breast Imaging Specialists Using a Nationally Deployed AI Workflow for Screening Mammography

Matthew P. McCabe, Edgar A. Wakelin, Leeann Louis, A.Y. Ng et autres

A multistage artificial intelligence–driven workflow was associated with improved cancer detection rate and positive predictive value of recalls for general radiologists interpreting breast cancer screening mammograms, allowing them to perform on par with breast imaging specialists.

us (code pays fourni par la source)

Assessing artificial intelligence in breast screening with stratified results on 306 839 mammograms across geographic regions, age, breast density and ethnicity: A Retrospective Investigation Evaluating Screening (ARIES) study

Cary Oberije, Rachel Currie, Alice Leaver, Alan Redman et autres

OBJECTIVES: Evaluate an Artificial Intelligence (AI) system in breast screening through stratified results across age, breast density, ethnicity and screening centres, from different UK regions. METHODS: A large-scale retrospective study evaluating two variations of using AI as an independent second reader in …

gb, us (code pays fourni par la source)

Prospective implementation of AI-assisted screen reading to improve early detection of breast cancer

A.Y. Ng, Cary Oberije, Éva Ambrózay, Endre Szabó et autres

Artificial intelligence (AI) has the potential to improve breast cancer screening; however, prospective evidence of the safe implementation of AI into real clinical practice is limited. A commercially available AI system was implemented as an additional reader to standard double reading to …

gb, us, hu (code pays fourni par la source)

A prospective study to assess the impact and benefits of an artificial intelligence system in double reading for breast cancer screening

Nisha Sharma, A.Y. Ng

Multi-vendor evaluation of artificial intelligence as an independent reader for double reading in breast cancer screening on 275,900 mammograms

Nisha Sharma, A.Y. Ng, Jonathan J. James, Galvin Khara et autres

BACKGROUND: Double reading (DR) in screening mammography increases cancer detection and lowers recall rates, but has sustainability challenges due to workforce shortages. Artificial intelligence (AI) as an independent reader (IR) in DR may provide a cost-effective solution with the potential to improve …

gb, hu, de (code pays fourni par la source)

A proof of concept for a deep learning system that can aid embryologists in predicting blastocyst survival after thaw

Phil Marsh, Dahlia Radif, Pranav Rajpurkar, Z Wang et autres

The ability to understand whether embryos survive the thaw process is crucial to transferring competent embryos that can lead to pregnancy. The objective of this study was to develop a proof of concept deep learning model capable of assisting embryologist assessment of …

us (code pays fourni par la source)

Chlorhexidine versus povidone–iodine skin antisepsis before upper limb surgery (CIPHUR): an international multicentre prospective cohort study

Ryckie G. Wade, Gráinne Bourke, Justin C.R. Wormald, Joshua Totty et autres

INTRODUCTION: Surgical site infection (SSI) is the most common and costly complication of surgery. International guidelines recommend topical alcoholic chlorhexidine (CHX) before surgery. However, upper limb surgeons continue to use other antiseptics, citing a lack of applicable evidence, and concerns related to …

gb, au (code pays fourni par la source)

Grasping novel objects with depth segmentation

D. V. Rao, Quoc V. Le, Thanathorn Phoka, Martin Quigley et autres

We consider the task of grasping novel objects and cleaning fairly cluttered tables with many novel objects. Recent successful approaches employ machine learning algorithms to identify points on the scene that the robot should grasp. In this paper, we show that the …

us, th (code pays fourni par la source)

Learning to open new doors

Ellen Klingbeil, Ashutosh Saxena, A.Y. Ng

We consider the problem of enabling a robot to autonomously open doors, including novel ones that the robot has not previously seen. Given the large variation in the appearances and locations of doors and door handles, this is a challenging perception and …

us (code pays fourni par la source)

Low-cost accelerometers for robotic manipulator perception

Martin Quigley, Rubell Brewer, Sai Prashanth Soundararaj, Vijay Pradeep et autres

We present a series of experiments which explore the use of consumer-grade accelerometers as joint position sensors for robotic manipulators. We show that 6- and 7-dof joint angle estimation is possible by using one 3-d accelerometer for each pair of joints. We …

us (code pays fourni par la source)

Policy search via the signed derivative

J. Zico Kolter, A.Y. Ng

We consider policy search for reinforcement learning: learning policy parameters, for some fixed policy class, that optimize performance of a system.In this paper, we propose a novel policy gradient method based on an approximation we call the Signed Derivative; the approximation is …

us (code pays fourni par la source)

Learning sound location from a single microphone

Ashutosh Saxena, A.Y. Ng

We consider the problem of estimating the incident angle of a sound, using only a single microphone. The ability to perform monaural (single-ear) localization is important to many animals; indeed, monaural cues are also the primary method by which humans decide if …

us (code pays fourni par la source)