Lausanne, Switzerland, February 18, 2020 – Deep Cube SA, a Swiss-based artificial intelligence (AI) company, announced today that it has established a collaboration with University Hospital of Geneva (HUG) to use AI-based algorithms to better evaluate brain positron emission tomography (PET) scans measuring glucose metabolism to diagnose patients with Alzheimer’s disease. Deep Cube’s algorithms are able to help diagnose Alzheimer’s disease with 97.3 percent accuracy.
Alzheimer’s disease is a neurodegenerative disorder caused by neuronal death due to two misfolded proteins, beta amyloid (β-Amyloid) and hyperphosphorated tau (pTau). According to Deep Cube, their new AI diagnostics could also play a key role in measuring drug efficacy in Alzheimer’s clinical trials.
Alexandre Gouy, Deep Cube’s AI engineer on Alzheimer’s, commented, “Accurate early diagnosis is crucial in neurodegenerative diseases as it allows therapy to begin earlier. Additional benefits of the AI Model are to improve Alzheimer’s diagnostics at hospitals. Our neural networks architectures combined with imaging and biomarkers reach state-of-the-art AI performance using a minimal amount of data, approximately 200 PET scan images.”
Deep Cube CEO Chris Patris de Broe also commented, “The future of AI in neurosciences is a combination of three input sources: medical imaging, biomarkers and genomic data. At 97.3 percent accuracy, our AI team has been able to surpass two other Alzheimer’s AI diagnostic models, one at Google with 94.2 percent sensitivity and another at the Massachusetts Institute of Technology (MIT) with 85 percent sensitivity. Even if data is not comparable, in each of those AI models the results are tangible. So far, the best doctors have been able to do in analyzing Alzheimer’s PET images is 93 percent accuracy*, that is, 7 percent misdiagnoses. Our Deep Cube AI Alzheimer’s Model is demonstrating minimal misdiagnoses at 2.7 percent, significantly lower than human interpretations.”
About Deep Cube
Founded in 2018 and based in Lausanne Epalinges at BIOPOLE in Switzerland, Deep Cube SA specializes in developing innovative artificial intelligence (AI) technology based on Deep Learning. The company operates in two focus areas, one in analyzing skin disorders such as skin melanoma and skin non-melanoma and the other in diagnosing human brain PET scans for Alzheimer’s disease. Deep Cube is the recipient of several prestigious awards and industry prizes: 2017 Best AI Award at the Multimodal Emotion Recognition Challenge (MEC), best AI Award at the 2018 Convention on Computer Vision and Pattern Recognition (CVPR), First Prize at the 2019 Consumer Electronics Show (CES ASIA) and Second Prize at the 2019 World AI Conference (WAIC) and including a recent world record in mathematics with HPC computing on HPE’s APOLLO 6500 Server for the computation of Phi (the golden ratio) with 20,000,000,000 digits, executed in only 6.9 days.
More information is available at www.deepcube.ch
* Source Journal of Nuclear Medicine (JNN) Effectiveness and Safety of 18F-FDG PET in the Evaluation of Dementia: A Review of the Recent Literature
Nicolaas I. Bohnen, David S.W. Djang, Karl Herholz5, Yoshimi Anzai and Satoshi Minoshima http://jnm.snmjournals.org/content/53/1/59.long
For any country outside of the USA