[ACM Tech Talk -1 ]Computer-Aided Assessment of Pulmonary Nodule Malignancy in from Low Dose Computed Tomography Screenings

Presented by :  

Dr. David Chapman Assistant Professor, Computer Science 11:30 PM – 12:30PM , Friday October 11th 2019 , ITE 346, UMBC

Abstract:
We propose to develop a novel quantitative algorithm to estimate the probability of malignancy of pulmonary nodules from a time series of successive LDCT screenings in patients with a high risk of developing lung cancer.  Lung cancer kills approximately 200,000 Americans annually and is responsible for 25% of all cancer-related deaths. Imaging with Low Dose Computed Tomography (LDCT) has been proven to reduce Non-Small Cell Lung Cancer (NSCLC) mortality by 20% and has become standard guidelines (NLST 2011a,b).  These new clinical guidelines have led to hospitals, including Mercy Medical Center in Baltimore, to collect an abundance of LDCT images of high risk individuals since 2014. These LDCT images along with additional CT/biopsy and PET/CT images collected by Mercy hospital in Baltimore have now been organized into an IRB exempt clinical research dataset to use anonymous radiology imagery for the purpose of training and evaluation of improved Computer Aided Diagnosis (CAD) algorithms.  Imaging biomarkers including cross-sectional diameter, calcification patterns, irregular margins, wall thickness all of which are known to have discriminating power to differentiate benign and malignant pulmonary nodules.  Furthermore, temporal changes in the size and biomarker characteristics of pulmonary nodules over multiple images are also highly informative and yield greater ability to differentiate malignancy.  The proposed CAD algorithm will be capable of detecting and quantifying temporal changes of imaging biomakers in order to estimate malignancy probability.  The algorithm will make use of convolutional neural networks for feature extraction as well as recurrent neural networks to analyze the temporal changes in extracted features.  The Mercy hospital dataset contains approximately 30,000 chest CT images. Training of the algorithm will incorporate semi-supervised learning using chest CT images from Mercy as well as the public portion of the NLST dataset.  A fraction of the Mercy images will be designated for evaluation of the sensitivity and specificity of the proposed algorithm for determining nodule malignancy.  Pulmonary nodules remain a challenging area for clinical management decision-making, and improved analysis of malignancy including temporal changes of imaging biomarkers have the potential to reduce patient morbidity and mortality through earlier and more accurate diagnosis.  

Hi -Tea Series -II

On behalf of the UMBC Association for Computing Machinery (ACM) Chapter you are invited to Second Hi-Tea for this Fall 2019 semester.
Date: Friday, October 11th, 2019
Time : 12:30 p.m. to 1:00 p.m.
Venue: ITE Building, 3rd Floor hallway outside of Suite 325
Refreshments, Meet with students, faculty and staff.

Hi – Tea Series -1

On behalf of the UMBC Association for Computing Machinery (ACM) Chapter you are invited to first Hi-Tea for this Fall 2019 semester.
Date: Friday, September 27, 2019
Time : 12:30 p.m. to 1:00 p.m.
Venue: ITE Building, 3rd Floor hallway outside of Suite 325
Refreshments, Meet with students, faculty and staff.

Call for abstracts – CSEE research symposium Friday May 4

The UMBC student chapters for ACM and IEEE are jointly organizing a one-day research symposium on Computer and Electrical Systems that will be held at bwtech@UMBC’s South Campus on Friday, May 4, 2018.

The goal of the symposium is to recognize and inspire student research by sharing cutting-edge ideas and achievements through presentations, posters, and demonstrations. It will bring students, faculty and collaborators from the Computer Science and Electrical Engineering department together to present their research ideas and results.

The symposium will be held on Friday, May 4, 2018, at the UMBC Technology Center South Campus from 9:00am to 5:00pm. Refreshments and lunch will be provided.

We invite proposals from graduate and undergraduate students and faculty in the following categories.
Faculty research talks
Student research talks
Student poster presentations, demonstrations and/or elevator pitch competition
The deadline to submit abstracts or proposals is April 27, 2018.

There will be awards and cash prizes for
Best emerging Women Research student
Best undergraduate research
Best MS research
Best Ph.D. research
Best poster
Best elevator pitch
Location: The symposium will be held at the bwtech@UMBC South Campus (1450 S Rolling Road, Halethorpe, MD 21227) main building. Parking is free and the UMBC Halethorpe shuttle stops there (stop #18).

More information, including information on submitting an abstract, can be found at https://acm.umbc.edu/rsce2018/cfp/. If you have any questions, please contact acmumbc@csee.umbc.edu.

[ACM Tech Talk ]A Practitioner’s Introduction to Deep Learning

Presented by :  Ashwinkumar Ganesan, PhD student

1 pm – 2 pm Friday, November 17 2017 , ITE 325 UMBC

In recent years, Deep Neural Networks have been highly successful at performing a number of tasks in computer vision, natural language processing and artificial intelligence in general. The remarkable performance gains have led to universities and industries investing heavily in this space. This investment creates a thriving open source ecosystem of tools & libraries that aid the design of new architectures, algorithm research as well as data collection.

 

This talk (and hands-on session) introduce people to some of the basics of machine learning, neural networks and discusses some of the popular neural network architectures. We take a dive into one of the popular libraries, Tensorflow, and an associated abstraction library Keras.

Workshop requirements: Laptop

Following are the list of libraries to be installed:
1. numpy, scipy & scikit-learn.
2. tensorflow / tensoflow-gpu. (The first one is the GPU version).
3. matplotlib for visualizations (if necessary).
4. jupyter & ipython. (We will use python2.7 in our experiments).
 
Following are helpful links:
 
All of the above can be installed using pip. In case of windows or (any other OS) consider doing an installation of anaconda that has all the necessary libraries.

[ACM Career Workshop] How to crack a coding interview? – 2

 
Presented by: Nikhil Kumar, 2nd year MS 
ITE 229, November 17, 2017, 4.00 PM – 5.00 PM
 
 
In this workshop series, we plan to assist the students on the tough problems in coding interviews. 
Topic: LinkedLists

Hi – Tea Series – 5

The UMBC ACM Student Chapter welcomes you to the HiTea event. 
 
Date: Friday, November 17, 2017
Time: 2.00 pm-2.30 pm
Venue: CSEE hallway outside ITE 325
Hosted by: Maithilee Joshi

[Career Workshop]How to crack a coding interview – 1

How to crack a coding interview?
 
In this workshop series, we plan to assist the students on the tough problems in coding interviews. 
 
Date/Time : November 10, 2017, 4.00 PM – 5.00 PM
Tutor: Naveen Bansal
Topic: HashMaps
Room:  ITE 233

[Tech Talk] Understanding What We Read and Share: Event Processing from Text and Images

Dr. Frank Ferraro, Assistant Professor, CSEE 
1 pm – 2 pm Friday, November 10, 2017, ITE 325, UMBC
   
A goal of natural language processing (NLP) is to design machines with human-like communication and language understanding skills. NLP systems able to represent knowledge and synthesize domain-appropriate responses have the potential to improve many tasks and human-facing applications, like virtual assistants such as Google Now or question answering systems like IBM’s Watson.
 
In this talk, I will present some of my work—past, on-going, and future—in developing knowledge-aware NLP models. I will discuss how to better (1) encode linguistic- and cognitive science-backed meanings within learned word representations, (2) learn high-level representations for document and discourse understanding, and (3) how to generate compelling, human-like stories from sequences of images.
 
Dr. Frank Ferraro is an assistant professor in the CSEE department at UMBC. His research focuses on natural language processing, computational event semantics, and unlabeled, structured probabilistic modeling over very large corpora. He has published basic and applied research on a number of cross-disciplinary projects, and has papers in areas such as multimodal processing and information extraction, latent-variable syntactic methods and applications, and the induction and evaluation of frames and scripts.

Hi-Tea Series IV

The UMBC ACM Student Chapter welcomes you to the Hi-Tea event. 
 
Date: Friday, November 10, 2017
Time: 2.00 pm-2.30 pm
Venue: CSEE hallway outside ITE 325
Hosted by: Sai Sree Laya Chukkapalli
« Older posts