AHA: AI-guided tool for the quantification of venom-induced haemorrhage in mice

Abstract

Venom-induced haemorrhage constitutes a severe pathology in snakebite envenomings, especially those inflicted by viperid species. To both explore venom activity accurately and evaluate the efficacy of viperid antivenoms for the neutralisation of haemorrhagic activity it is essential to have available a precise, quantitative tool for empirically determining venom-induced haemorrhage. Thus, we have built on our prior approach and developed a new AI-guided tool (AHA) for the quantification of venom-induced haemorrhage in mice. Using a smartphone, it takes less than a minute to take a photo, upload the image, and receive accurate information on the magnitude of a venom-induced haemorrhagic lesion in mice. This substantially decreases analysis time, reduces human error, and does not require expert haemorrhage analysis skills. Furthermore, its open access web-based graphical user interface makes it easy to use and implement in laboratories across the globe. Together, this will reduce the resources required to preclinically assess and control the quality of antivenoms, whilst also expediting the profiling of haemorrhagic activity in venoms for the wider toxinology community.

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

“…Therefore, we first developed a simple computational tool to improve accuracy of quantifying haemorrhage severity, which has since been implemented by different groups within the field 23 – 31 . This encouraged us to build a more sophisticated machine learning guided tool that further increased the accuracy, accessibility, and reproducibility of snake venom haemorrhage assessment 32 .…”

“…Whilst the tool brings many advantages, it does come with some of the same limitations as our prior tool 32 . These include potential decreases in white balancing accuracy in very poorly or unevenly lit environments, as well as a heavily damaged template sheet.…”

“…To allow for standardised analysis of the dermonecrotic lesions, as well as to support the image analysis algorithms, we used the same A4 printout sheet as in our prior publication 32 (c.f. Supplementary Fig.…”

“…First, the input images were white balanced and scaled, as described in our prior publication 32 . Thereafter, to identify and segment the dermonecrotic lesions, we applied a deep learning method based on the U-Net architecture 33 , which we have previously also applied to snake venom induced haemorrhage identification 32 .…”

Dermonecrosis caused by spitting cobra snakebite results from toxin potentiation and is prevented by the repurposed drug varespladib

“…Thereafter, experimental animals were humanely euthanised via inhalational CO 2 , and the skins around the injection site dissected. The height and width of the lesions on the inner side of the skin were measured in two directions with digital calipers, placed on A4 printout sheets to standardise the AI-lesion analyser which are available in Jenkins, et al(79), and photographed using a Sony DSC-W800 camera. Excised lesions were cut into cross-sections down the centre of the lesions,…”