You are cordially invited to attend our next Computer Graphics and Visualization (CGV) Seminar/ Colloquium, which will be held on:
Friday, February 2nd, 2017, 13:45-15:45h, at EWI-Lecture Hall K.
The program features the following two presentations:
Presenter: Yin Yunchao
Title: Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
Abstract: Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation,CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
Presenter: Dirk Schut
Title: Automatic Initialization for US CT Registration During Liver Tumor Ablations
Abstract: Ablation is a medical procedure where a needle has to be inserted into a tumor. To guide the needle Ultrasound(US) imaging is used which shows the needle position in real time. However small tumors are often not visible on US images. Therefore a CT scan is acquired before the intervention. To make the information from the CT scan available during the intervention, the scans have to be aligned in such a way that the same parts of the body are visible in the same positions in both scans. To find the relative orientation between the scans, this technique tries to detect and match blood vessels and the liver surface while also taking into account that the US scanner should be on the skin of the patient. The technique is being developed specifically to find solutions over a wide search space, and to be robust to segmentation errors.