3D Lung Cancer Segmentation and Representation Learning for Few-Shot Classification

Manno, Galleria 1, 2nd floor @12h00
The recent advances in Deep Learning made many tasks in Computer Vision much easier to tackle. However, working with a small amount of data, and highly imbalanced real-world datasets can still be very challenging. In this talk, I will present two of my recent projects, where modelling and training occur under those circumstances. Firstly, I will introduce a novel 3D UNet-like model for fast volumetric segmentation of lung cancer nodules in Computed Tomography (CT) imagery. This model highly relied on kernel factorisation and other architectural improvements to reduce the number of parameters and computational load, allowing its successful use in production. Secondly, I will discuss the use of representation learning or similarity metric learning for few-shot classification tasks, and more specifically its use in a competition at NeurIPS 2019 and Kaggle. This competition aimed to detect the effects of over 1000 different genetic treatments to 4 types of human cells, and published a dataset composed of 6-channel fluorescent microscopy images with only a handful of samples per target class.

The speaker

Henrique Mendonça got a MSc at the University of Zurich in 2015 and has 10+ years experience in designing and developing systems in areas from real-time embedded systems to high performance distributed applications, computer vision and machine learning.