Breaking News
April 21, 2018 - Developing cooking skills as young adult may have long-term health benefits
April 21, 2018 - Study compares survival outcomes of different drugs for type 2 diabetes
April 21, 2018 - More Than 40 Percent of Americans Breathe Dirty Air: Report
April 21, 2018 - Obstructive sleep apnea – Genetics Home Reference
April 21, 2018 - More evidence shows exposure to traffic and outdoor air pollution increases risk of asthma
April 21, 2018 - Novel gold nanoparticle technology could guide cancer treatment in real-time
April 21, 2018 - News coverage of Ebola impacted public’s perception on disease and survivors
April 21, 2018 - S.Africa’s DIY battle against HIV
April 21, 2018 - Children with autism have gastrointestinal and immune system deregulation, research finds
April 21, 2018 - Human brain processes sight and sound in the same way, shows study
April 21, 2018 - Evolutionary history of tumor helps predict severity of prostate cancer
April 21, 2018 - Pepper plant metabolizes antibiotic in personal care products
April 21, 2018 - Tradeshow Talks with Integra
April 21, 2018 - EPFL becomes part of Chan Zuckerberg’s project to develop Human Cell Atlas
April 21, 2018 - Pfizer Announces Positive Topline Results From Phase 3 ATTR-ACT Study Of Tafamidis In Patients With Transthyretin Cardiomyopathy
April 21, 2018 - Breaking through the HIV vaccine ‘logjam’
April 21, 2018 - IntelliCyt introduces new QSol buffer to enable robust, consistent sampling
April 21, 2018 - Scientists publish comprehensive lineage tree of whole adult animal in Science journal
April 21, 2018 - Innovative method based on FluidFM technology could revolutionize biological research
April 21, 2018 - Americans world’s biggest TV addicts, watching four hours a day
April 21, 2018 - Investigational drug may help increase protein levels in babies with spinal muscular atrophy
April 21, 2018 - Study shows distinctions between age groups in predicting and responding to stress at home
April 21, 2018 - Aziyo Biologics, BIOTRONIK enter into US co-distribution agreement
April 21, 2018 - Opiate Use Linked to Early Mortality in IBD Patients
April 21, 2018 - Online ads help pregnant smokers quit
April 21, 2018 - Opioid pain medications may not be safe for hemodialysis patients
April 21, 2018 - Rare variants in non-coding DNA inherited from parents heighten autism risk
April 21, 2018 - A needleless glucose monitor for diabetes patients
April 21, 2018 - BD introduces new informatics and automation solutions for clinical laboratories
April 21, 2018 - Turn Chores Into a Fitness Routine
April 21, 2018 - DNA methylation plays key role in stem cell differentiation
April 21, 2018 - Scientists find link between soil metals and cancer mortality
April 21, 2018 - Experts discuss implications of low calcium intake in global population
April 21, 2018 - GNA Biosolutions to display Pharos V8 Laser PCR instrument at Analytica trade fair
April 21, 2018 - People with vitamin D deficiency may be at greater risk of diabetes
April 21, 2018 - Study findings could open new possibilities for treating cancer with adenovirus
April 21, 2018 - People who use medical marijuana have higher rates of prescription drug use, study finds
April 21, 2018 - Study debunks ‘myth’ that strenuous exercise dampens immunity
April 21, 2018 - FDA approves marijuana based medication for epilepsy treatment
April 21, 2018 - Researchers find novel genes for longevity in mammals
April 21, 2018 - GNA Biosolutions and project partners launch new research project to develop TB diagnostic platform for POC applications
April 21, 2018 - $2 million funding boosts progress of UAB biomedical startup
April 21, 2018 - Scientists identify gene responsible for evolution of recombination rates
April 21, 2018 - UConn researchers develop new composite for healing broken load-bearing bones
April 21, 2018 - Study examines how higher-order gene combinations help maintain normal cell physiology
April 21, 2018 - Study challenges use of whole-brain radiation for small-cell lung cancer patients with brain metastases
April 21, 2018 - Researchers discover blood biomarkers that may help detect, confirm mild traumatic brain injury
April 21, 2018 - People who become physically active after heart attack more likely to live longer, shows research
April 21, 2018 - CPRIT awards $2 million grant to push forward breast cancer research in West Texas
April 21, 2018 - Unhealthy diet damages the development of immature fat cells, study shows
April 21, 2018 - Consumption of protein supplements with meals may provide better weight control
April 21, 2018 - 4 Types of Foods to Help Boost Your Memory
April 21, 2018 - How did gonorrhea become a drug-resistant superbug?
April 21, 2018 - DePuy Synthes announces clinical results related to use of CORAIL Hip System Femoral Stems
April 21, 2018 - New initiative launched to support goals of Human Cell Atlas
April 20, 2018 - Teen patient gets a new lease on life
April 20, 2018 - Cancer Australia launches new framework to improve outcomes for lung cancer patients
April 20, 2018 - ‘Gut-on-a-chip’ model recreates intestinal matrix critical for nutrient absorption
April 20, 2018 - Researchers develop new drug-testing platform for epilepsy
April 20, 2018 - FDA Alert: NxtGen Botanicals Maeng Da Kratom by NGB Corp.: Recall
April 20, 2018 - Pelizaeus-Merzbacher-like disease type 1 – Genetics Home Reference
April 20, 2018 - Tick-borne diseases reach epidemic levels, panel says
April 20, 2018 - A potential “male pill” without side effects
April 20, 2018 - Researchers discover new information related to rare form of leukemia
April 20, 2018 - Researchers find crucial links between dopamine and avoidance behavior
April 20, 2018 - UGA scientist creates system for efficient detection of foodborne pathogens
April 20, 2018 - Social Support of Autonomy Tied to Better Glycemic Control in DM
April 20, 2018 - Study reports use of nutritional ketosis with mobile app intervention could reverse Type 2 diabetes
April 20, 2018 - New microscopy techniques allow quasi-biochemical studies on living T cells
April 20, 2018 - Study shows connection between muscular strength and brain health
April 20, 2018 - Ecolab introduces Life Sciences cleanroom program in North America
April 20, 2018 - Normal weight people with fat belly may have more chance of heart problems
April 20, 2018 - Male fruit flies like sex and alcohol
April 20, 2018 - Meditation could help reduce anxiety levels and some heart health risk factors
April 20, 2018 - Improving job prospects unlikely to control opioid epidemic
April 20, 2018 - Skin Sensor Might Someday Track Alcoholics’ Booze Intake
April 20, 2018 - The relevance of GABA for diabetes highlighted in two new studies
April 20, 2018 - Novel method enables fast and noninvasive assessment of tumor status
April 20, 2018 - IU psychologist receives NIH grant to study earliest phases of language learning in children
April 20, 2018 - Walking fast lowers risk of hospitalization in heart patients, shows study
Deep learning enhances smartphone microscopes into laboratory-grade equipments

Deep learning enhances smartphone microscopes into laboratory-grade equipments

image_pdfDownload PDFimage_print

Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. The technique improves the resolution and color details of smartphone images so much that they approach the quality of images from laboratory-grade microscopes.

The advance could help bring high-quality medical diagnostics into resource-poor regions, where people otherwise do not have access to high-end diagnostic technologies. And the technique uses attachments that can be inexpensively produced with a 3-D printer, at less than $100 a piece, versus the thousands of dollars it would cost to buy laboratory-grade equipment that produces images of similar quality.

Cameras on today’s smartphones are designed to photograph people and scenery, not to produce high-resolution microscopic images. So the researchers developed an attachment that can be placed over the smartphone lens to increase the resolution and the visibility of tiny details of the images they take, down to a scale of approximately one millionth of a meter.

But that only solved part of the challenge, because no attachment would be enough to compensate for the difference in quality between smartphone cameras’ image sensors and lenses and those of high-end lab equipment. The new technique compensates for the difference by using artificial intelligence to reproduce the level of resolution and color details needed for a laboratory analysis.

The research was led by Aydogan Ozcan, Chancellor’s Professor of Electrical and Computer Engineering and Bioengineering, and Yair Rivenson, a UCLA postdoctoral scholar. Ozcan’s research group has introduced several innovations in mobile microscopy and sensing, and it maintains a particular focus on developing field-portable medical diagnostics and sensors for resource-poor areas.

“Using deep learning, we set out to bridge the gap in image quality between inexpensive mobile phone-based microscopes and gold-standard bench-top microscopes that use high-end lenses,” Ozcan said.

“We believe that our approach is broadly applicable to other low-cost microscopy systems that use, for example, inexpensive lenses or cameras, and could facilitate the replacement of high-end bench-top microscopes with cost-effective, mobile alternatives.”

He added that the new technique could find numerous applications in global health, telemedicine and diagnostics-related applications.

The researchers shot images of lung tissue samples, blood and Pap smears, first using a standard laboratory-grade microscope, and then with a smartphone with the 3D-printed microscope attachment. The researchers then fed the pairs of corresponding images into a computer system that “learns” how to rapidly enhance the mobile phone images. The process relies on a deep-learning-based computer code, which was developed by the UCLA researchers.

To see if their technique would work on other types of lower-quality images, the researchers used deep learning to successfully perform similar transformations with images that had lost some detail because they were compressed for either faster transmission over a computer network or more efficient storage.

The study was published in ACS Photonics, a journal of the American Chemical Society. It builds upon previous studies by Ozcan’s group that used deep learning to reconstruct holograms and improve microscopy.

Source:

Deep learning transforms smartphone microscopes into laboratory-grade devices

Tagged with:

About author

Related Articles