Peter Uzoho
A United Kingdom-based Nigerian synthetic intelligence (AI) analysis scientist and Founder of GenScan AI, Mary-Brenda Akoda, has disclosed plans to roll out her AI medical imaging answer in Nigeria and the UK by the second half of 2027 to assist fast-track scan outcomes and scale back affected person backlogs globally.
Akoda, a Google DeepMind Scholar, ex-Microsoft engineer and Imperial College London-trained researcher, mentioned her flagship innovation, GenMRI, is a first-of-its-kind AI imaging software program that makes MRI scans up to 90 per cent sooner on current scanners with out hospitals spending hundreds of thousands on new machines.
Speaking throughout an interactive session between 2026 NLNG Nigeria Prize Winners and journalists in Lagos, she defined that the software program can scale back a 20-minute scan to as little as two minutes and an hour-long scan to six minutes, permitting hospitals and imaging centres to scan considerably extra sufferers per day, lower ready lists, scale back repeat scans and sedation prices, significantly for aged sufferers, youngsters and infants.
According to her, the know-how was constructed and validated on over 8,800 Magnetic Resonance Imaging (MRI) pictures and later subjected to an early blinded evaluation with a advisor radiologist at Buckinghamshire Healthcare NHS Trust within the UK.
She mentioned the radiologist was not instructed which pictures have been standard and which have been GenMRI-enhanced.
“The results came back scoring the GenMRI images as diagnostically equivalent to the conventional MRI images in all the cases assessed,” she mentioned.
She famous that technical analysis earlier than the blinded evaluation had proven up to 99.7 per cent similarity to standard MRI pictures, with speed-ups starting from 4 occasions to ten occasions.
Akoda mentioned the system was developed on over 15,000 cardiac MRI pictures and validated on a separate set of over 7,700 pictures, with an extra out-of-distribution check on 1,125 knee MRI pictures it had by no means seen earlier than, the place it achieved up to 75 per cent shorter scans and outperformed state-of-the-art fashions in pace and picture high quality.
She mentioned the inspiration for the innovation got here from private loss and lived expertise of an overburdened well being system, noting that delays in analysis may be deadly in time-critical situations corresponding to stroke and most cancers.
She recounted how about three years in the past, an aged cherished one suffered a stroke and couldn’t get well timed imaging due to lengthy queues, main to deterioration and loss of life, an expertise compounded by her personal encounter with sluggish hospital processes.
“Every second counts and the difference between life and death can be how quickly a patient gets diagnosed,” she mentioned.
She mentioned stroke kills over 6.5 million folks yearly worldwide and most cancers over 10 million, with medical imaging usually step one to analysis, but MRI scans take quarter-hour to over an hour, require sufferers to lie nonetheless in noisy enclosed areas, and any motion leads to blurry pictures, repeat scans and sedation dangers.
