VISVESVARAYA TECHNOLOGICAL UNIVERSITY
IMPACT COLLEGE OF ENGINEERING AND APPLIED SCIENCES
Department of Data Science
PRESENTATION
PROJECT TITLE:
AI- Powered Medical Diagnosis System
UNDER THE GUIDANCE OF: Mr. Krishna Mehar
Assistant Professor
GROUP MEMBERS:
MOHAMMAD ISRAR - 1IC21CD001
MONICA K - 1IC21CD002
SANJAY G R - 1IC22CD400
MOHAMMAD SAAD KHAN - 1IC21AI019
CONTENTS
1. INTRODUCTION
2. LITERATURE SURVEY
3. PROBLEM STATEMENT
4. OBJECTIVES
5. SYSTEM REQUIREMENTS
6. USE CASE DIAGRAM
7. ACTIVITY DIAGRAM
8. ARCHITECTURE DIAGRAM
9. IMPLEMENTATION
10. TESTING
11. RESULTS
1. INTRODUCTION
● THIS TECHNOLOGY HAS THE POTENTIAL TO REVOLUTIONIZE
HEALTHCARE BY ENHANCING DIAGNOSTIC ACCURACY,
ENABLING EARLY DISEASE DETECTION, AND CONTRIBUTING TO
PERSONALIZED TREATMENT PLANS.
● THESE TECHNOLOGIES CAN PROCESS MEDICAL IMAGES,
RECOGNIZE PATTERNS, AND EVEN PREDICT DISEASE
OUTCOMES, REVOLUTIONIZING THE PRACTICE OF MEDICINE.
● AI-POWERED MEDICAL DIAGNOSIS IS POISED TO
REVOLUTIONIZE THE FIELD OF MEDICINE, PAVING THE WAY FOR
A FUTURE WHERE PRECISION AND PREVENTIVE CARE ARE
MORE ACCESSIBLE THAN EVER.
2. LITERATURE SURVEY
SL. TITLE AUTHOR Summary of Findings Relevance to Project
NO
1 AI-Driven Various Authors Discusses CNN and GAN models Relevant for
Diagnostic improving accuracy in medical enhancing diagnostic
Systems for imaging for cancer, cardiovascular accuracy in imaging
Medical Imaging diseases, and neurology. modalities like MRI
and CT scans, vital for
oncology and
neurology diagnostics.
2 Natural K. Liu et al. Examines the use of NLP for Crucial for projects
Language interpreting clinical notes and focused on automating
Processing in automating diagnosis of diseases like textbased diagnostic
Medical COVID-19 and diabetes. systems, especially for
Diagnostics structured and
unstructured clinical data.
SL.NO TITLE AUTHOR Summary of Findings Relevance to
Project
3 Artificial A. Patel et al. Highlights the use of AI in ECG and Key for developing
Intelligence in heart rate variability analysis to detect real-time monitoring
Cardiovascular arrhythmia and other cardiovascular systems using AI,
Diagnostics issues. especially in wearable
health technology for
heart conditions.
4 AI and M. Zhang, S. Explores AI's role in analyzing Highly relevant
Genomics: Gupta genomic data to predict disease risk, for integrating AI
Predictive particularly in personalized in genomic data
Models for medicine and oncology. analysis for
Disease Risk predictive
diagnostics.
2.1 LITERATURE OVERVIEW
● THE USE OF INTELLIGENCE (AI), IN TECHNOLOGY HAS GROWN
SIGNIFICANTLY ESPECIALLY IN SPECIALIZED FIELDS SUCH AS ONCOLOGY,
PULMONOLOGY, CARDIOVASCULAR MEDICINE ORTHOPEDICS, HEPATOLOGY
AND NEUROLOGY. THIS COMPREHENSIVE REVIEW AIMS TO EXPLORE THE
EMERGING TRENDS IN INCORPORATING AI INTO HEALTHCARE PRACTICES.
● THE REVIEW EMPHASIZES AREAS WHERE AI IS MAKING CONTRIBUTIONS.
THESE INCLUDE COLLECTING AND ANALYZING DATA FOR DISEASE
DIAGNOSIS WELL AS ASSISTING IN ACTIVE TREATMENT PROCESSES.
NOTABLY DEEP LEARNING METHODS LIKE NETWORKS (CNNS) HAVE SHOWN
PROMISE, PARTICULARLY IN RADIOLOGY AND ONCOLOGY BY ENABLING
IMAGE RECOGNITION.
2.2 PROPOSED SYSTEM
OUR AI-POWERED MEDICAL DIAGNOSIS INITIATIVE RELIES ON
DIVERSE DATASETS THAT TRANSCEND MERE SYMPTOM RECORDS.
OUR DATASET IS NOT ONLY BROAD BUT ALSO REPRESENTATIVE,
STRENGTHENING THE EFFICIENCY AND RELIABILITY OF OUR AI
MODEL. THE GOAL IS TO EMPOWER OUR MODEL TO BE A VALUABLE
TOOL SUPPORTING USERS IN DIVERSE HEALTHCARE SITUATIONS.
3. PROBLEM STATEMENT
THE ACCURATE AND TIMELY DIAGNOSIS OF MEDICAL CONDITIONS IS
CRITICAL FOR EFFECTIVE TREATMENT AND IMPROVED PATIENT OUTCOMES.
HOWEVER, THE COMPLEXITY OF MEDICAL DATA, COUPLED WITH THE
INCREASING WORKLOAD ON HEALTHCARE PROFESSIONALS, CAN LEAD TO
DIAGNOSTIC ERRORS AND DELAYS. THE NUMBER OF PATIENTS, INTRICACY
AND COMPLEXITY, VOLUMES OF INFORMATION, SYMPTOMS, LAB RESULTS,
AND MEDICAL IMAGES ADD UP TO A DAUNTING CHALLENGE IN THE TIME
FRAME AS IMPORTANT AS IT IS TO GET DISEASE DIAGNOSIS ACCURATELY AS
FAST AS POSSIBLE. THE LACK OF CONNECTIVITY BETWEEN THE VARIOUS
TYPES OF DATA USED IN THE DIAGNOSIS PROCESS ALSO ADDS UP TO THE
ABOVE ISSUES. TRADITIONAL METHODS OF DIAGNOSIS RELY ON THE
MANUAL INTERPRETATION OF DATA, WHICH DELAYS AND BECOMES
INCONSISTENT AT WORST, AND INACCURATE AT BEST.
4. OBJECTIVES
● IMPROVED ACCUARACY: ENHANCE DIAGNOSTIC ACCUARACY BY
REDUCING HUMAN ERRORS AND PROVIDING PRECISE SYMPTOMS.
● ENHANCED ACCESSIBLITY: PROVIDE MEDICAL EXPERTISE TO REMOTE
AND UNDERSERVED AREAS.
● MODEL EDUCATION: TO TRAIN THE AI MODEL, USE SUPERVISED LEARNING
APPROACHES. BY INCLUDING LABELED INSTANCES IN THE TRAINING
DATASET, YOU MAY EMPHASIZE THE RELATIONSHIP BETWEEN PRESENTED
SYMPTOMS AND ACCURATE DIAGNOSES.
● MEASURES FOR EVALUATION: DEFINE AND MONITOR PERFORMANCE
MEASURES SUCH AS ACCURACY, SENSITIVITY, AND SPECIFICITY TO ASSESS
THE MODEL'S EFFECTIVENESS IN DISEASE DIAGNOSIS. CREATE A BASELINE
FOR FUTURE COMPARISON AND IMPROVEMENT.
● CREATE A USER-FRIENDLY INTERFACE: CREATE AN INTUITIVE AND USER-
FRIENDLY INTERFACE FOR INDIVIDUALS TO INTERACT WITH THE AI-BASED
DIAGNOSTIC SYSTEM.
NON-FUNCTIONAL REQUIREMENTS:
1. PERFORMANCE: RESULTS SHOULD BE RETURNED WITHIN SECONDS; MODEL
TRAINING SHOULD NOT OCCUR DURING USER INTERACTION.
2. SCALABILITY: SUPPORT INCREASING USER REQUESTS WITHOUT
PERFORMANCE LOSS.
3. USABILITY: SIMPLE, INTUITIVE INTERFACE WITH CLEAR INPUT PROMPTS.
4. MAINTAINABILITY: MODULAR, WELL-DOCUMENTED CODE FOR EASY
UPDATES.
5. ACCESSIBILITY: COMPATIBLE WITH COMMON BROWSERS AND DEVICES.
5. SYSTEM REQUIREMENTS
1. HARDWARE REQUIREMENTS:
● GPU: A HIGH-PERFORMANCE GPU IS RECOMMENDED FOR FASTER IMAGE
PROCESSING.
● INPUT DEVICES : KEYBOARD, MOUSE
● RAM : 8 GB
2. SOFTWARE REQUIREMENTS:
● OPERATING SYSTEM : WINDOWS 10.
● SOFTWARE :VS CODE
● CODING LANGUAGE : PYTHON, HTML, CSS
● DATA HANDLING: PANDAS, NUMPY
● FRAMEWORK: FLASK
6. USE CASE DIAGRAM
FIGURE 1
7. ACTIVITY DIAGRAM
FIGURE 2
8. ARCHITECTURE DIAGRAM
Figure 3
9. IMPLEMENTATION
4.1 TECHNOLOGIES USED:
● FRONTEND
• HTML/ CSS: FOR STRUCTURING AND STYLING WEB PAGES.
• FLASK: FOR DYNAMIC HTML RENDERING BASED ON USER INPUT AND MODEL
OUTPUT.
● BACKEND
• PYTHON WEB FRAMEWORK FOR APPLICATION LOGIC AND ROUTING.
● MACHINE LEARNING
• SCIKIT-LEARN: FOR TRADITIONAL CLASSIFIERS KERAS (WITH TENSORFLOW):
PANDAS & NUMPY: FOR NUMERIC OPERATIONS, DATA MANIPULATION AND
PREPROCESSING TASKS.
IMPEMENTATION
● BRAIN TUMOR DETECTION
○ INPUT: MRI IMAGES UPLOADED BY USERS.
○ PROCESS:
■ PREPROCESSING THE IMAGE.
■ USING A PRE-TRAINED CNN MODEL FOR PREDICTION.
○ OUTPUT:
■ PREDICTION: “TUMOR DETECTED” OR “NO TUMOR.”
● BONE FRACTURE DETECTION
○ INPUT: X-RAY IMAGES.
○ PROCESS:
■ PREPROCESSING THE IMAGE.
■ CLASSIFICATION USING A CNN MODEL.
○ OUTPUT:
■ PREDICTION: “FRACTURE DETECTED” OR “NO FRACTURE.”
• LUNG CANCER DETECTION
○ AIM:TO DETECT EARLY SIGNS OF LUNG CANCER FROM CT SCANS.
• TEXT GENERATOR
GENERATING TEXT BASED ON PROVIDED DATA
10. TESTING
• TEST SCENARIOS:UPLOADING MEDICAL IMAGES OF VARIOUS TYPES (E.G.,
BRAIN TUMOR, LUNG CANCER, AND BONE FRACTURE) TO VERIFY MODEL
ACCURACY.
• TESTING THE PERFORMANCE OF THE WEB APPLICATION UNDER DIFFERENT
NETWORK CONDITIONS.
• EVALUATION METRICS:ACCURACY, PRECISION, RECALL, F1-SCORE FOR
EACH DISEASE TYPE (BRAIN TUMOR, LUNG CANCER, BONE FRACTURE).
11. RESULTS
• BRAIN TUMOR DETECTION: PREDICTS IF THE GIVEN IMAGE IS DIAGNOSED WITH
BRAIN TUMOR OR NOT.
• BONE FRACTURE PREDICTION: PREDICTS IF THE GIVEN IMAGE OF THE BONE IS
FRACTURED OR NOT.
• LUNG CANCER DETECTION: DETECTS IF THE THE GIVEN IMAGE OF THE LUNGS IS
DIAGNOSED WITH CANCER OR NOT.
• TEXT GENERATOR: GENERATING TEXT BASED ON PROVIDED DATA.
THANK YOU
