Automated lung tumor detection and diagnosis in CT Scans using texture feature analysis and SVM
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 17, Issue
Abstract
CT scans are an important tool in the diagnosis of lung tumors in medicine. This work presents an automated system for lung tumor diagnosis on CT scans. Scans are automatically segmented using marker-based watershed transformation, which enables to successfully segment hardly separable, lung wall adjunct tumors. The scans are further analyzed in a sliding window approach using Haralick features and a Support Vector Machine classifier to detect and classify benign and malignant tumors. This novel approach for classification was tested using the LUNGx Challenge dataset and achieved exceptional results while utilizing a minimal training set.
Authors and Affiliations
Tim Adams, Jens Dörpinghaus, Marc Jacobs, Volker Steinhage
Keywords
Related Articles
- EP ID EP568230
- DOI 10.15439/2018F176
- Views 20
- Downloads 0
Automatic Assessment of Student Understanding Level using Virtual Reality
The improvement of the efficiency in teaching re- quires knowing the understanding level of each student. However, it is difficult due to limited time in a class. We propose a Virtual Reality (VR) space imposing assignme...
Automated lung tumor detection and diagnosis in CT Scans using texture feature analysis and SVM
CT scans are an important tool in the diagnosis of lung tumors in medicine. This work presents an automated system for lung tumor diagnosis on CT scans. Scans are automatically segmented using marker-based watershed tran...
An ensemble of Deep Convolutional Neural Networks for Marking Hair Follicles on Microscopic Images
This paper presents an application of a Convolutional Neural Network as a solution for a task associated with ESENSEI Challenge: Marking Hair Follicles on Microscopic Images. As we show in this paper quality of classific...
Result Analysis Suite: A Completely Automated Result Analysis Solution
``What gets measured, gets managed''. The present paper intends to describe a one stop solution to analyze the student result data collected from the University Website automatically using the web automation technology,...
Vehicular Ad-Hoc Network for Smart Cities
The rapid increase in urban population is alleviating various kinds of problems such as long hours traffic-jams, pollution which is making cities life insecure and non-livable. The notion of a smart city is proposed to i...