Breaking News
November 19, 2018 - Experts debate over whether gut or brain is more important in regulating appetite
November 19, 2018 - Playing on fear and fun, hospitals follow pharma in direct-to-consumer advertising
November 19, 2018 - Low-Carb Diets May Work By Boosting Calorie Burn
November 19, 2018 - Key molecule responsible for learning and memory discovered
November 19, 2018 - New blood test developed for early diagnosis of ovarian cancer
November 19, 2018 - Researchers identify molecule to fight myotubular myopathy
November 19, 2018 - Immune cells trigger OCD-like behaviour in multiple sclerosis, study finds
November 19, 2018 - Scientists equip new virus that kills carcinoma cells with protein
November 19, 2018 - Novel approach could provide painless, efficient alternative for treating eye diseases
November 19, 2018 - Protein in cell membranes of sperm plays key role in finding their way to eggs
November 19, 2018 - Parents who decline flu vaccination for their child may be exposed to limited information
November 19, 2018 - Mirati Presents Data From Ongoing Phase 2 Clinical Trial Of Mocetinostat In Combination With Durvalumab At The SITC 33rd Annual Meeting
November 19, 2018 - FDA warns of common diabetes meds’ link to dangerous genital infection
November 19, 2018 - New methods for preserving shoulder function, quality of life in breast cancer patients
November 19, 2018 - Surprising discovery about BH4 may rekindle interest in once-promising pathway
November 19, 2018 - Nabriva Therapeutics Completes Submission of New Drug Application to U.S. Food and Drug Administration for Intravenous Contepo to Treat Complicated Urinary Tract Infections
November 19, 2018 - Beating breast cancer only to die of opioid use – a sad Appalachian story
November 19, 2018 - Workplace bullying or violence linked to higher risk of cardiovascular problems
November 19, 2018 - Changes in Risk Indicators of MetS Severity Tied to T2DM Risk
November 19, 2018 - ‘Game-changing’ skin sensor could improve life for a million hydrocephalus patients
November 19, 2018 - Alcohol ads on social media sites with pro-drinking comments increase desire to drink
November 19, 2018 - Neural networks could replace marker genes in RNA sequencing
November 19, 2018 - Obese adolescents feel less food enjoyment than those with normal weight, study reveals
November 18, 2018 - Goodbye ‘Gluten-Free’? Celiac Disease Vaccine May Make It Possible
November 18, 2018 - Skin ages when the main cells in the dermis lose their identity and function
November 18, 2018 - Rainforest vine compound makes pancreatic cancer cells susceptible to nutrient starvation
November 18, 2018 - A new mechanism in the control of inflammation
November 18, 2018 - Age-related decline in abstract reasoning ability predicts depressive symptoms over time
November 18, 2018 - Scientists succeed in increasing stability, biocompatibility of light-transducing nanoparticles
November 18, 2018 - Sugar, a ‘sweet’ tool to understand brain injuries
November 18, 2018 - Pharmacist-Led Effort Cuts Inappropriate Rx in Older Adults
November 18, 2018 - Novel discovery could lead to new cancer, autoimmune disease therapy
November 18, 2018 - AHA and ADA launch new initiative to help people with type 2 diabetes reduce heart disease risk
November 18, 2018 - Balanced production of pro and anti-inflammatory cytokines at two years of age protects against malaria
November 18, 2018 - New pharmacological agent shows promise for prevention of heart rhythm disorders
November 18, 2018 - All That Social Media May Boost Loneliness, Not Banish It
November 18, 2018 - Scientists shine new light on link between obesity and cancer
November 18, 2018 - Risk factors for cardiovascular disease closely track with changes in diet patterns
November 18, 2018 - Biogen Scoops Sixth Prix Galien Award with UK Win for Life-Changing Rare Disease Medicine
November 18, 2018 - Detectable HIV-1 in treated human liver cells found to be inert
November 18, 2018 - Using light to control crucial step in embryonic development
November 18, 2018 - Unusual case of father-to-son HIV transmission reported
November 18, 2018 - FDA Approves Aemcolo (rifamycin) to Treat Travelers’ Diarrhea
November 18, 2018 - Poverty blamed on widening north-south gap in young adult deaths in England
November 18, 2018 - Progress in meningitis lags far behind other vaccine-preventable diseases, analysis shows
November 18, 2018 - Consensus Statement Issued on Management of Foot, Ankle Gout
November 18, 2018 - Fine particle air pollution is a public health emergency hiding in plain sight
November 18, 2018 - In-hospital mortality higher among patients with drug-resistant infections
November 17, 2018 - Research shines new, explanatory light on link between obesity and cancer
November 17, 2018 - FIND explores new diagnostic assays for confirmatory HCV diagnosis in community settings
November 17, 2018 - Tracking Preemies’ Head Size May Yield IQ Clues
November 17, 2018 - Scientists call for unified standards in 3-D genome and epigenetic data
November 17, 2018 - Lab Innovations 2018 has beaten all records by attracting 3,113 attendees
November 17, 2018 - New strategy to hinder emergence of antimicrobial-resistant pathogens
November 17, 2018 - Sexuality education before age 18 may reduce risk of sexual assault in college
November 17, 2018 - Reducing cellular proliferation could help deplete HIV reservoir and lead to a functional cure
November 17, 2018 - New model of FSHD could be useful to study effectiveness of experimental therapeutics
November 17, 2018 - FDA approves antibacterial drug to treat travelers’ diarrhea
November 17, 2018 - Lab Innovations 2018 confirmed as a major hit with visitors, exhibitors and speakers
November 17, 2018 - Largest parasitic worm genetic study hatches novel treatment possibilities
November 17, 2018 - UCLA biologists uncover how head injuries can lead to serious brain disorders
November 17, 2018 - Static and dynamic physical activities offer varying protection against heart disease
November 17, 2018 - Obesity significantly increases risk of Type 2 diabetes and coronary artery disease
November 17, 2018 - New method to analyze cell membrane complexes could revolutionize the way we study diseases
November 17, 2018 - Researchers show how proteins interact in hypoxic conditions to facilitate mitochondrial fission
November 17, 2018 - People with rare cancers can benefit from genomic profiling, shows research
November 17, 2018 - NIH awards over $1.8 million to husband-and-wife doctors to test new breast cancer approach
November 17, 2018 - Four-in-one antibody used to fight flu shows promise in mice
November 17, 2018 - New approach allows pathogens to be starved by blocking important enzymes
November 17, 2018 - Higher body mass index could cause depression even without health problems
November 17, 2018 - Protein which plays role in sensing cell damage serves as new target to treat pulmonary hypertension
November 17, 2018 - FDA Approves Adcetris (brentuximab vedotin) in Combination with Chemotherapy for Adults with Previously Untreated Systemic Anaplastic Large Cell Lymphoma or Other CD30-Expressing Peripheral T-Cell Lymphomas
November 17, 2018 - ID specialist input improves outcomes for outpatient parenteral antimicrobial therapy
November 17, 2018 - UT Southwestern scientists selected to receive 2019 Edith and Peter O’Donnell Awards
November 17, 2018 - New clinical algorithm to help individuals manage type 2 diabetes when fasting during Ramadan
November 17, 2018 - Researchers identify LZTR1 as evolutionarily conserved component of RAS pathway
November 17, 2018 - Heart Disease Leading Cause of Death in Low-Income Counties
November 17, 2018 - Estrogen Levels Test: MedlinePlus Lab Test Information
November 17, 2018 - Research reveals link between immunity, diabetes
November 17, 2018 - Research shows how to achieve improved smoking cessation outcomes within California’s Medicaid population
Novel system uses AI to detect abnormalities in fetal hearts

Novel system uses AI to detect abnormalities in fetal hearts

image_pdfDownload PDFimage_print

A research group led by scientists from the RIKEN Center for Advanced Intelligence Project (AIP) have developed a novel system that can automatically detect abnormalities in fetal hearts in real-time using artificial intelligence (AI). This technology could help examiners to avoid missing severe and complex congenital heart abnormalities that require prompt treatments, leading to early diagnosis and well-planned treatment plans, and could contribute to the development of perinatal or neonatal medicine.

Congenital heart problems — which can involve abnormalities of the atrium, ventricle, valves or blood vessel connections — can be very serious, and account for about 20% of all newborn deaths. Diagnosis of such problems before the baby is born, allowing for prompt treatment within a week after birth, is known to markedly improve the prognosis, so there have been many attempts to develop technology to enables accurate and rapid diagnosis. However, today, fetal diagnosis depends heavily on observations by experienced examiners using ultrasound imaging, so it is unfortunately not uncommon for children to be born without having been properly diagnosed.

In recent years, machine learning techniques such as deep learning have been developing rapidly, and there is great interest in the adoption of machine learning for medical applications. Machine learning can allow diagnostic systems to detect diseases more rapidly and accurately than human beings, but this requires the availability of adequate datasets on normal and abnormal subjects for a certain disease. Unfortunately, however, since congenital heart problems in children are relatively rare, there are no complete datasets, and up until now, prediction based on machine learning was not accurate enough for practical use in the clinic. However, the RIKEN AIP-led group, which also involves collaborators from Fujitsu Ltd. and Showa University, decided to take on this challenge, and has successfully developed new machine learning technology that can accurately predict diseases using relatively small and incomplete datasets.

In general, experts of fetal heart diagnosis seek to find whether certain parts of the heart, such as valves and blood vessels, are in incorrect positions, by comparing normal and abnormal fetal heart images based on their own judgement. The researchers found that this process is similar to the “object detection” technique, which allows AIs to distinguish the position and classify multiple objects appearing in images.

A set of “teacher” data — meaning data from which the AI is to learn — is prepared through “annotation” — the attachment of meanings of objects — and used to train the object detection system. To develop the current system, the researchers used normal heart images to annotate correct positions of 18 different parts of the heart and peripheral organs, and developed a novel “Fetal Heart Screening System,” which allows the automatic detection of heart abnormalities from ultrasound images. When there are differences between the test and learned data, the system judges that there is an abnormality if the difference is greater than some confidence value. The process is quick and can be performed in real-time, with the results appearing immediately on the examination screen. The system can also help harmonize diagnoses among different hospitals with different levels of medical expertise or equipment.

“This breakthrough was possible thanks to the accumulated discussions among the experts on machine learning and fetal heart diagnosis. RIKEN AIP has many AI experts and opportunities for collaboration like this project. We hope that the system will go into wide-spread use by means of the successful cooperation among clinicians, academia, and the company,” says Masaaki Komatsu, a RIKEN AIP researcher who led the project.

The researchers now plan to carry out clinical trials at university hospitals in Japan, adding larger number of fetal ultrasound images to allow the AI to learn more in order to improve the screening accuracy and expand its target. Implementing this system could help correct medical disparities between regions through the training of examiners or by remote diagnosis using cloud-based systems.

Source:

http://www.riken.jp/en/pr/press/2018/20180918_3/

Tagged with:

About author

Related Articles