See more.
Smarter skin checks with Kāhu AI
We believe Kāhu AI has the power to help clinicians discover skin cancer, both easily and effectively.
What we do
Support healthcare professionals
Zongyuan Ge, Sergey Demyanov, Rajib Chakravorty, Adrian Bowling, Rahil Garnavi
Next-generation A.I. technology
Combining one of the largest known databases of skin lesions and next-generation technology, we're designing products with patient safety at the heart of what we do.
Evidence-backed AI
Backed by clinical validation, Kāhu AI achieves 98% sensitivity and 54% specificity for melanoma detection, and 94% sensitivity and 81% specificity for malignant skin cancer detection. Our comprehensive AI governance framework helps ensure our technology is deployed safely, responsibly, and transparently.
Catches nearly all melanomas, some false positives get referred on
Customer-centric approach
We work closely with clinical experts in Australia & New Zealand to ensure our products are not only safe and effective, but fit-for-purpose and easy to use.
Our purpose
Kāhu A.I. is a clinical decision support tool, not a replacement for clinical decisions. It gives clinicians more information about skin lesions to help them make more informed decisions.
Kāhu's mission is to put instant skin cancer detection in the hands of every clinicians. Its first product, Skin Assist, is already being introduced into MoleMap's workflows, using a convolutional neural network to analyse a lesion photograph against hundreds of thousands of others.
Why Kahu AI?
Unlike other technologies in this space, Kāhu technology is being developed by leveraging MoleMap's world-leading database of high-quality dermatological images.
We can confidently say that Kāhu will have seen more skin lesions and melanomas than most healthcare professionals.
Dermatologist shortage
Kāhu supports nurses to assess and triage lesions, which frees dermatologists to focus on the lesions that need specialist review, so more patients get through the pathway than a dermatologist-led model allows.
Featured publications
We partner with world leading research groups to further our technology and evidence of safety and effectiveness.
Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images
Zongyuan Ge, Sergey Demyanov, Rajib Chakravorty, Adrian Bowling, Rahil Garnavi
Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging
Zongyuan Ge, Sergey Demyanov, Behzad Bozorgtabar, Mani Abedini, Rajib Chakravorty, Adrian Bowling, Rahil Garnavi
Artificial Intelligence in Skin Cancer Diagnostics: The Patients' Perspective
Zongyuan Ge, Sergey Demyanov, Rajib Chakravorty, Adrian Bowling, Rahil Garnavi
Tree-loss function for training neural networks on weakly-labelled datasets
Sergey Demyanov, Rajib Chakravorty, Zongyuan Ge, Seyedbehzad Bozorgtabar, Michelle Pablo, Adrian Bowling, Rahil Garnavi
Improving Skin cancer Management with ARTificial Intelligence (SMARTI)
Claire Felmingham, Samantha MacNamara, William Cranwell, Narelle Williams, Miki Wada, Nikki R Adler, Zongyuan Ge, Alastair Sharfe, Adrian Bowling, Martin Haskett, Rory Wolfe, Victoria Mar
News
Diversity as an advantage
Why age diversity is the key to solving staff shortages post-COVID
$3M funding round
Meet Kāhu, the Kiwi AI cancer-detection startup that just secured $3 million
Book your skin check with Kāhu A.I.
Book a MoleMap skin check and your images are assessed with Kāhu A.I. supporting the clinical team.
