results for au:Vaidya_V in:cs
Apr 21 2017 cs.CV
The ability to automatically learn task specific feature representations has led to a huge success of deep learning methods. When large training data is scarce, such as in medical imaging problems, transfer learning has been very effective. In this paper, we systematically investigate the process of transferring a Convolutional Neural Network, trained on ImageNet images to perform image classification, to kidney detection problem in ultrasound images. We study how the detection performance depends on the extent of transfer. We show that a transferred and tuned CNN can outperform a state-of-the-art feature engineered pipeline and a hybridization of these two techniques achieves 20\% higher performance. We also investigate how the evolution of intermediate response images from our network. Finally, we compare these responses to state-of-the-art image processing filters in order to gain greater insight into how transfer learning is able to effectively manage widely varying imaging regimes.
Dec 09 2016 cs.CV
Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them. In medical applications where training data is hard to come by, these sophisticated machine learning models are difficult to train. In this paper, we propose a method to reduce the inherent complexity of CNNs during training by exploiting the significant redundancy that is noticed in the learnt CNN filters. Our method relies on finding a small set of filters and mixing coefficients to derive every filter in each convolutional layer at the time of training itself, thereby reducing the number of parameters to be trained. We consider the problem of 3D lung nodule segmentation in CT images and demonstrate the effectiveness of our method in achieving good results with only few training examples.
We consider the problem of automatically prescribing oblique planes (short axis, 4 chamber and 2 chamber views) in Cardiac Magnetic Resonance Imaging (MRI). A concern with technologist-driven acquisitions of these planes is the quality and time taken for the total examination. We propose an automated solution incorporating anatomical features external to the cardiac region. The solution uses support vector machine regression models wherein complexity and feature selection are optimized using multi-objective genetic algorithms. Additionally, we examine the robustness of our approach by training our models on images with additive Rician-Gaussian mixtures at varying Signal to Noise (SNR) levels. Our approach has shown promising results, with an angular deviation of less than 15 degrees on 90% cases across oblique planes, measured in terms of average 6-fold cross validation performance -- this is generally within acceptable bounds of variation as specified by clinicians.
Aug 19 2005 cs.CR
In 1949, Shannon proved the perfect secrecy of the Vernam cryptographic system,also popularly known as the One-Time Pad (OTP). Since then, it has been believed that the perfectly random and uncompressible OTP which is transmitted needs to have a length equal to the message length for this result to be true. In this paper, we prove that the length of the transmitted OTP which actually contains useful information need not be compromised and could be less than the message length without sacrificing perfect secrecy. We also provide a new interpretation for the OTP encryption by treating the message bits as making True/False statements about the pad, which we define as a private-object. We introduce the paradigm of private-object cryptography where messages are transmitted by verifying statements about a secret-object. We conclude by suggesting the use of Formal Axiomatic Systems for investing N bits of secret.