Transcript Diagnosis of Pulmonary Embolism Using Fuzzy Inference System

Diagnosis of Pulmonary Embolism
Using
Fuzzy Inference System
Research Assistant: Vishwanath Acharya
Research Director: Dr. Gursel Serpen
Medical Expertise: Drs. Parsai, Coombs & Woldenberg of
Medical College of Ohio
Why Artificial Intelligence???
• It can offer a competent second opinion.
• It offers the expertise of an expert
radiologist in interpreting scans when an
expert radiologist is not available.
• It has the ability to make accurate and quick
diagnosis.
• It has the potential to reduce inter-observer
variability.
Artificial Intelligence in Practice
Artificial Intelligence
Expert Systems
ELIZA
MYCIN
Artificial Neural Networks
PATTERN RECOGNITION
Fuzzy Inference System
CAMERA
CARS
Groups Facing Higher
Probability of Pulmonary
Embolism
• Patients Undergoing
various types of
surgery - general,
urological, neurosurgical, and
gynecological.
• Patients with
orthopedic problems
and chronic diseases.
These groups face a
higher probability of
Pulmonary Embolism
due to the high risk of
developing deep
venous thrombosis.
Various Diagnostic Criteria’s
• PIOPED - Prospective Investigation of
Pulmonary Embolism Diagnosis [1995].
• Biello’s Criteria [1979].
• Inputs from Expert Radiologists.
Is Fuzzy Logic really Fuzzy?
Why Fuzzy Logic?
• Despite its name Fuzzy Logic is not nebulous, cloudy or vague.
• It provides a very precise approach for dealing with uncertainty which
is derived from complex human behavior.
• Fuzzy Logic is so powerful, mainly because it does not require a deep
understanding of a system or exact and precise numerical values.
• It uses abstraction that in human beings is arrived at from experience
or intuition.
• It allows intermediate values and representation of knowledge with
subjective concepts to be defined between conventional evaluation.
• It basically pays attention to the “excluded middle” gray areas.
• It attempts to apply a more human like way of thinking in
programming of computers.
Fuzzy Inference System
Input
Fuzzifier
Inference
Engine
Defuzzifier
Output
Fuzzy
Rule
Base
The three major components of the Fuzzy Inference System are:
• Fuzzifier - Converts the crisp input into appropriate fuzzy quantity.
• Inference Engine - Allows the application of the rule base to the input
parameters whereby producing the output.
• Defuzzifier - Converts the output produced by the Inference Engine
into user understandable terms.
Inputs to Fuzzy System
(According to PIOPED Criteria)
•
•
•
•
•
Number of Segmental Perfusions.
Number of Non-Segmental Perfusions.
Ventilation/Perfusion Mismatch.
Chest X-Ray Abnormality.
Presence of Pleural Effusion.
Inputs to Fuzzy System
(According to PIOPED Criteria)
Wt - Weight (pre-calculation of segmental and non-segmental perfusion
defects.
Vqdef - Ventilation-Perfusion Defect Mismatch.
Cxrab - Chest X-ray abnormality.
Peff - Presence of Pleural Effusion.
Rule Base of Fuzzy System
(Modeling of the PIOPED Criteria)
Outputs from Fuzzy Inference
System
(According to PIOPED Criteria)
Output of the Fuzzy System models the diagnostic
capabilities of the Fuzzy System. Hence, the
various classes are:
•
•
•
•
•
Normal.
Very Low.
Low.
Intermediate.
High
The output of the Fuzzy System are mapped to
one of these classes.
Outputs from Fuzzy Inference
System
(According to PIOPED Criteria)
Dia - Diagnosis, is the output of the Fuzzy System and
is divided into 5 classes.
What you see here is the tweaking that has to be given
to all the classes in order to implement the PIOPED
criteria to its best fit.
Testing/Simulation
To ensure accuracy and usability, the software has to pass stringent tests.
These tests were applied in two phases.
Alpha Testing
Beta Testing
• Output data was obtained
and passed to radiologists
to check for accuracy.
• Data developed by
radiologists was run
through the system and
checked to ensure that is
produced expected results.
• Currently being
implemented. In this
phase the radiologist will
have a hands on
experience. This will
ensure that the software
has a high degree of
usability and physicians
won’t be intimidated by it.
Conclusions
• Implementation of Artificial Intelligence software in the
diagnosis of medical diseases is feasible and can be very
easily extended to cover different diseases.
• It can be of help to medical practitioners.
• The alternative methods utilized to diagnose for Pulmonary
Embolism effectively capture the spirit of the PIOPED
criteria.
• This software has the ability to make accurate and quick
diagnosis.