Thursday, December 10, 2020

Computerized Classification of Prostate Cancer Gleason Scores from Whole Slide Images

 H. Xu, S. Park and T. H. Hwang, "Computerized Classification of Prostate Cancer Gleason Scores from Whole Slide Images," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 6, pp. 1871-1882, 1 Nov.-Dec. 2020, doi: 10.1109/TCBB.2019.2941195.

Abstract: Histological Gleason grading of tumor patterns is one of the most powerful prognostic predictors in prostate cancer. However, manual analysis and grading performed by pathologists are typically subjective and time-consuming. In this paper, we present an automatic technique for Gleason grading of prostate cancer from H&E stained whole slide pathology images using a set of novel completed and statistical local binary pattern (CSLBP) descriptors. 

First, the technique divides the whole slide image (WSI) into a set of small image tiles, where salient tumor tiles with high nuclei densities are selected for analysis. The CSLBP texture features that encode pixel intensity variations from circularly surrounding neighborhoods are extracted from salient image tiles to characterize different Gleason patterns. Finally, the CSLBP texture features computed from all tiles are integrated and utilized by the multi-class support vector machine (SVM) that assigns patient slides with different Gleason scores such as 6, 7, or $\geq$≥ 8. 

Experiments have been performed on 312 different patient cases selected from the cancer genome atlas (TCGA) and have achieved superior performances over state-of-the-art texture descriptors and baseline methods including deep learning models for prostate cancer Gleason grading. 

keywords: {Tumors;Prostate cancer;Pathology;Feature extraction;Glands;Image segmentation;Prostate cancer;medical image analysis;texture features;image classification},

URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8836110&isnumber=9286984

Monday, December 7, 2020

NASA Webex on Li-ion cell calorimeter 12/8/20 at 2:00pm EST

NASA Webex Enterprise Site: 2


Date and time: Tuesday, December 8, 2020 2:00 pm
Eastern Standard Time (New York, GMT-05:00)
Change time zone
Duration: 1 hour
Description:
About the Event

Innovators at the NASA Johnson Space Center have developed a calorimeter that is able to measure the total heat generated when specific types of Lithium-ion (Li-ion) cells are driven into a thermal runaway condition. By understanding the behavior of a thermal runaway Li-ion battery, designers can improve the cell cases to contain or reduce damages experienced during thermal runaway. For this reason, this technology can benefit many different industries that depend on Li-ion batteries. Terrestrial applications include consumer electronics, battery safety, electric vehicles, and more!

During the webinar, you will learn much more about this novel technology, as well as how NASA’s technologies and capabilities are available to industry and other organizations through the NASA Technology Transfer Program.


About the Presenters

Dr. William Walker

Dr. William Q. Walker received a B.S. in Mechanical Engineering from West Texas A&M University and a Ph.D. in Materials Science and Engineering from the University of Houston. William is employed by NASA Johnson Space Center where his career primarily focuses on the safe design and optimization of lithium-ion (Li-ion) battery assemblies for human spaceflight applications. Specifically, William focuses on the thermal management of Li-ion battery assemblies, battery safety in general, and the development of new calorimetric techniques for thermal runaway characterization. Most recently, Dr. Walker has been involved with and supported the development of Fractional Thermal Runaway Calorimetry (FTRC) techniques which provide the capability to discern the fraction of thermal runaway energy ejected away from the Li-ion cell versus that which remains with the cell. Recently recognized with a NASA Trailblazer award and with the RNASA Stellar Award for his early career contributions to Li-ion battery thermal analysis and calorimetry methods, Dr. Walker continues to be engaged in the academic and professional communities focused on battery safety.

Dr. Eric Darcy

Eric C. Darcy, Ph.D, has spent his 33 year career at NASA in the areas of battery design, verification, and safety assessments for the rigors of manned spacecraft applications. As Battery Technical Discipline Lead at NASA JSC, his main objective has been the development of safe, while high performing, battery systems with a deep focus on understanding, preventing, and mitigating latent defects that could lead to catastrophic cell internal short circuits. With National Renewable Energy Laboratory (NREL) colleagues, he is co inventor of the patented On demand Internal Short Circuit Device that has provided significant design insights into the cell response during thermal runaway (TR), enabled valid battery TR propagation assessment, and received the prestigious R&D100 award in 2016 and Runner up NASA Invention of 2017.

He has led NASA’s design and test efforts for providing a path for developing safe, high performing Li ion spacecraft batteries using small commercial cells. He teaches a Li ion battery safety course with emphasis on design features and verification measures for achieving passive propagation resistance.

John Darst

John Jacob Darst is a Chemical Engineering BS graduate from Texas A&M University, and early career engineer at NASA Johnson Space Center. He is the lead mechanical designer behind the FTRC system, taking one of his first full time projects from early concept to fully successful in just a few years. In 2019 he was awarded the NASA Early Career Medal for outstanding performance. Jacob’s time at JSC has been primarily concerned with battery safety, with projects ranging from cell design feature analysis up to full pack design and integration. He has developed a number of novel thermal runaway initiation methods as well as devices for the calorimetric study of various sizes and formats of lithium ion cells.

 
 
By joining this event, you are accepting the Cisco Webex Terms of Service and Privacy Statement.

 

Novel AI System Achieves 90% Accuracy in Detecting Drone Jamming Attacks

Loss convergence analysis using test data under LoS and NLoS conditions     Novel AI System Achieves 90% Accuracy in Detecting Drone Jamming...