My PhD Student Naji Khosravan (https://nkhosravan.github.io) ‘s latest research about automatic lung cancer detection from CT scans is accepted for publication in MICCAI 2018.
The work we have done does not require any additional postprocessing / refinement steps unlike all other available methods. More specifically, we propose a new deep learning based method, using a single feed forward pass of a single network for detection and provides better performance when compared to the current literature.
What does S4ND stand for? We use S4ND acronym here to represent Single-Shot Single Scale Lung Nodule Detection!
The whole detection pipeline is designed as a single 3 D Convolutional Neural Network (CNN) with dense connections, trained in an end-to-end manner. S4ND does not require any further post-processing or user guidance to refine detection results. Experimentally, we compared our network with the current state-of-the-art object detection network (SSD) in computer vision as well as the state-of-the-art published method for lung nodule detection (3D DCNN). We also provide an in-depth analysis of our proposed network to shed light on the unclear paradigms of tiny object detection.
Here is the paper in arxiv –> https://arxiv.org/pdf/1805.02279.pdf
Enjoy reading !