Heterogeneous Collection of Learning Systems for Confident Pattern Recognition Joshua R. New Knowledge Systems Laboratory Jacksonville State University Knowledge Systems Lab JN 7/13/2017 Outline • • • • • Motivation Simplified Fuzzy ARTMAP (SFAM) Interactive Learning Interface System Demonstration Conclusions and Future Work Knowledge Systems Lab JN 7/13/2017 Motivation Knowledge Systems Lab JN 7/13/2017 Motivation • Doctors and radiologists spend several hours daily analyzing patient images (ie. MRI scans of the brain) • The patterns being searched for in the image are standard and well-known to doctors • Why not have the doctor teach the computer to find these patterns in the images? Knowledge Systems Lab JN 7/13/2017 Motivation • Doctors and radiologists who use supervised AI systems for image segmentation: – Usually can not interactively refine the computer’s segmentation performance – Must be able to precisely select regions/pixels of the image to train the computer – Often do not use an interface that facilitates accomplishment of their task – Can easily lose where they are looking in the image when using magnification Knowledge Systems Lab JN 7/13/2017 Simplified Fuzzy ARTMAP (SFAM) Knowledge Systems Lab JN 7/13/2017 SFAM • In order to “teach the computer” to find tumors in neuro-images, a supervised machine learning system must be used • Simplified Fuzzy ARTMAP (SFAM) is a neural network that was created by Grossberg in 1987 and uses a mathematical model of the way the human brain learns and encodes information • This AI system was utilized because it allows very fast learning for interactive training (ie. seconds instead of days to weeks) Knowledge Systems Lab JN 7/13/2017 SFAM • SFAM is a computer-based system capable of online, incremental learning • Two “vectors” are sent to this system for learning: – Input feature vector gives the data is available from which to learn – Supervisory signal indicates whether that vector is an example or counterexample Knowledge Systems Lab JN 7/13/2017 SFAM • Data from which to learn – Feature vector from slice pixel values from shunted and single-opponency images (Whole Brain Atlas) Knowledge Systems Lab JN 7/13/2017 SFAM • Vector-based graphic visualization of learning Category 1 - 2 members y Category 2 - 1 member Array of Pixel Values Category 4 - 3 members 0.35 0.90 x Knowledge Systems Lab JN 7/13/2017 SFAM • Only one tunable parameter – vigilance – Vigilance can be set from 0 to 1 and corresponds to the generality by which things are classified (ie. vig=0.3=>human, vig=0.6=>male, 0.9=>Joshua New) 0.675 0.75 0.825 Knowledge Systems Lab JN 7/13/2017 SFAM • SFAM is sensitive to the order of the inputs Vector 1 Category 1 - 2 members Vector 2 Category 2 - 1 member y Vector 3 Category 4 - 3 members x JN 7/13/2017 Knowledge Systems Lab SFAM • Voting scheme of 5 Heterogeneous SFAM networks to overcome vigilance and input order dependence – 3 networks: random input order, set vigilance – 2 networks: 3rd network order, vigilance ± 10% Knowledge Systems Lab JN 7/13/2017 SFAM Knowledge Systems Lab JN 7/13/2017 SFAM Threshold results Trans-slice results Overlay results Knowledge Systems Lab JN 7/13/2017 Interactive Learning Interface • Screenshot of Segmentation & Features Knowledge Systems Lab JN 7/13/2017 System Demonstration Knowledge Systems Lab JN 7/13/2017 Conclusions • Doctors and radiologists can teach the computer to recognize abnormal brain tissue • They can refine the learning systems results interactively • They can precisely select targets/non-targets • They can zoom for precision while maintaining context of the entire image • The interface developed facilitates task performance through display of segmentation results and interactive training Knowledge Systems Lab JN 7/13/2017 Future Work • Quantity of health-care can be increased by utilizing these trained “agents” to allow radiologists to only view the required images and directing their attention for the ones that are viewed • Quality of health care can be increased by using the agents to classify an entire database of images to highlight possibly overlooked or misdiagnosed cases Knowledge Systems Lab JN 7/13/2017
© Copyright 2026 Paperzz