MBA & Software Engineer Artificial Intelligence - Deep Learning Specialist
Projects
Kissing Bug Paper
Pneumothorax Segmentation
Kissing Bug image recognition
Skin Cancer lesion Classifier
Image classifier for AI projects
About me
Passionate about innovation and new business generation. Building highly motivated teams to develop industry break through solutions.
Software Engineer & MBA. Developing Deep Learning Models to create new business opportunities in the medical and the consumer market. Enjoy running, ski and tennis.
Contact Me
Kissing Bug Paper
A convolutional neural network to recognize Chagas disease vectors using mobile phone images. "Abstract There are several identification tools that can assist researchers, technicians and the community in the recognition of Chagas vector insects (triatomines), from other insects with similar morphologies. They involve using dichotomous keys, field guides, expert knowledge or, in more recent approaches, through the classification by a neural network of high quality photographs taken in standardized conditions. The aim of this research was to develop a deep neural network to recognize triatomines (insects associated with vectorial transmission of Chagas disease) directly from photos taken with any commonly available mobile device, without any other specialized equipment. To overcome the shortcomings of taking images using specific instruments and a controlled environment an innovative machine-learning approach was used Fastai with Pytorch, a combination of open-source software for deep learning. The Convolutional Neural Network (CNN) was trained with triatomine photos, reaching a correct identification in 94.3% of the cases. Results were validated using photos sent by citizen scientists from the GeoVin project, resulting in 91.4% of correct identification of triatomines. The CNN provides a lightweight, robust method that even works with blurred images, poor lighting and even with the presence of other subjects and objects in the same frame. Future steps include the inclusion of the CNN into the framework of the GeoVin science project, which will also allow to further train the network using the photos sent by the citizen scientists. This would allow the participation of the community in the identification and monitoring of the vector insects, particularly in regions where government-led monitoring programmes are not frequent due to their low accessibility and high costs."
From a thorax x-ray the neural network will highlight the pneumothorax affected zone. The model has been trained with images from the SIIM-ACR Pneumothorax Segmentations.
This neural network recognizes a Kissing Bug from an image taken in the natural habitat using mobile phone. It achieves 93,7% accuracy. The model has been trained with images from the GeoVin project. This project has been developed by the CEPAVE. The project has been published in Ecological Informatics Volume 68 May 2022.
From a skin image the model will classify the lesion as the most similar pathologies. The Deep Learning module has been trained with the HAM10000 2018 ISIC dermoscopic images, achieving 92,3% accuracy.