batch 14.ppt aitam useful ppt for students
- 1. (Approved by AICTE ,Permanently Affiliated to JNTUV , Vizianagaram) K.KOTTURU,TEKKALI-532201 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
- 2. Dugana Lakshmi Prasanna -20A51A0520 Borra Yeshoda Venkata Bhavani -20A51A0512 Pallela Kashyapu -20A51A0529 Yabaji Kiran -20A51A0549 Presented by: SriTippana.Chalapathi Rao MTech. Sr.Asst.Professor Dept of CSE Under the esteemed Guidance of BRAIN TUMOR DETECTION USING HYBRID DEEP LEARNING MODELS
- 3. 01 ABSTRACT 02 INTRODUCTION 03 LITERATURE SURVEY 04 PROBLEM IDENTIFICATION Contents 05 EXISTING SYSTEM AND PROPOSED SYSTEM 06 07 08 09 OVERVIEW AND METHODOLOGY REQUIREMENTS AND EVALUATION REFERENCES PLAN OF ACTION
- 4. ABSTRACT Brain is one of the vital organs in the human body. Brain related diagnosis demands utmost care and a minute error in judgment may be disastrous. Brain tumor is one of the most life-threatening diseases at its highest grade. Generally, Magnetic resonance imaging (MRI) is widely used imaging technique to assess the tumors in brain, liver…etc. The large amount of data produced by MRI prevents manual classification in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, it is not an optimistic method to use to detect brain tumors. Hence trusted and automatic classification schemes are essential to prevent the death rate of human. On using deep learning models like vgg19, Resnet101,denseNet 121 Hence an MRI brain tumor image will be classified as either a High-Grade Gliomas (HGG) or Low-Grade Gliomas (LGG). Finally, performance analysis of these models will be compared.
- 5. Brain tumors are one of the deadliest forms of cancer. Early detection and treatment can improve outcomes and save lives. The importance of early detection We have developed a hybrid deep learning method that combines several techniques to improve accuracy and reduce false positives. Our approach Brain tumors can be difficult to detect because they often have irregular shapes and can be in sensitive areas of the brain. Challenges in Brain Tumor Detection Deep learning is a powerful tool for analyzing medical images and detecting abnormalities that might not be visible to the human eye. The role of deep learning Introduction
- 6. Problem Identification • Discover the critical challenges in brain tumor detection and the limitations of traditional methods. • Learn how hybrid deep learning methods have revolutionized the accuracy and efficiency of tumor identification.
- 7. Title Authors Publication Year Summary "A MRI based CNN Approach for Brain Tumor Image Detection" Chattopadhyay, A., & Maitra, M. 2022 The major goal of this study is to create a convolutional neural network-based algorithm for segmenting brain tumors from 2D magnetic resonance imaging (MRI) data. This algorithm will be used in combination with conventional classifiers and deep learning techniques. The objective is to develop a very precise automatic tumor detection technique for use in medical diagnosis. The Precision, recall, and F1 score are performance indicators used to assess the algorithm's accuracy. These measures assess how accurately the system can detect tumors in MRI images while minimizing false positives or false negatives. Literature Survey
- 8. “Adaptive fuzzy deformable fusion and optimized CNN with ensemble classification for automated brain tumor diagnosis" Murthy, M. Y. B., Koteswararao, A., & Babu, M. S 2020 This study's goal is to create a brand-new brain tumor classification model based on sophisticated segmentation and classification techniques. This model combines the use of fuzzy deformable fusion, optimized convolutional neural networks, and ensemble classifiers to accurately identify brain tumors from MRI images. The main advantage of this method is that it can provide more accurate results than manual identification by medical professionals. Additionally, the use of fuzzy deformable fusion and optimized convolutional neural networks allows for a more efficient segmentation and classification process.
- 9. Time-Consuming Procedures Learn about the extensive time and effort required to analyze complex medical images and the need for more efficient solutions. Manual Detection Discover the current reliance on manual interpretation of medical images and the drawbacks of human error and subjectivity. Traditional Algorithms Explore the limitations of conventional image processing and machine learning algorithms in identifying brain tumors effectively. Existing System
- 10. Hybrid deep learning Discover the power of combining VGG19 and ResNet101 deep learning models to enhance brain tumor detection accuracy, precision, and speed. Automated Diagnosis Learn how our proposed system automates the process of tumor identification, reducing human effort and minimizing diagnostic errors. Proposed System
- 11. Preprocessing We preprocess the medical images to enhance contrast and reduce noise. Segmentation We use a segmentation algorithm to identify the tumor region of interest. Classification We use an ensemble of CNNs and auto encoders to classify the tumor as benign or malignant. Overview of Hybrid Deep Learning Methods
- 12. High quality medical images Accurate medical image analysis requires high-quality images. We need good resolution and contrast to identify tumor regions. Expertise in Medical Imaging Developing a hybrid deep learning method requires expertise in both deep learning and medical imaging. Powerful computing resources Deep learning algorithms require a lot of computing power. We need powerful CPUs or GPUs to train and run our models. Requirements for Implementing Hybrid Deep Learning Methods for Brain Tumor Detection Magnetic resonance imaging Once MRI shows that there is a tumor in the brain, the most common way to determine the type of brain tumor is to look at the results from a sample of tissue after a biopsy or surgery.
- 13. SOURCE REQUIREMENTS Operating system Windows 11-64bit Programming languages Python Tools Jupyter Notebook, Visual studio code Libraries Tensorflow, seaborn, pandas, numpy, cv2, sklearn Software Requirements
- 14. We believe that our method has the potential to be used in clinical settings to improve patient outcomes. Clinical Applications We aim to make our method more accessible to healthcare providers by developing user- friendly software. Improved Accessibility We plan to explore the use of reinforcement learning in brain tumor detection to improve decision-making. Future Research ADVANTAGES
- 21. References On the Performance of Deep Transfer Learning Networks for Brain Tumor Detection Using MR Images https://ieeexplore.ieee.org/abstract/document/9785791 A Hybrid Deep Learning Model for Brain Tumor Classification https://doi.org/10.3390/e24060799 Two-phase multi-model automatic brain tumor diagnosis system from magnetic resonance images using convolutional neural networks https://link.springer.com/article/10.1186/s13640-018-0332-4 A VGG Net-Based Deep Learning Framework for Brain Tumor Detection on MRI Images https://ieeexplore.ieee.org/abstract/document/9515947 Brain tumor detection and multi-classification using advanced deep learning techniques https://doi.org/10.1002/jemt.23688 A. B. Hamida, Histogram equalization-based techniques for contrast enhancement of MRI brain glioma tumor images: comparative study, in 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), IEEE, 2018,pp. 1. 6.510
- 22. PLAN OF ACTION 12-10 2023 17-11 2023 10-12-2023 19-01-2024 10-02-2024 15-03-2024 Abstract Literature survey Problem identification Algorithm Implementation Results Analysis
- 23. Conclusion • In conclusion, this study demonstrates the effectiveness of deep learning models, specifically VGG19, ResNet101, and DenseNet121, in the automatic classification of MRI brain tumor images into High-Grade Gliomas (HGG) and Low-Grade Gliomas (LGG). The research addresses the critical need for accurate and efficient diagnosis of brain tumors, considering the life- threatening nature of these conditions and the challenges posed by the large volume of MRI data. Through rigorous performance analysis, each model's ability to accurately classify brain tumor images was evaluated, shedding light on their respective strengths and weaknesses. The findings of this study offer valuable insights into the potential applications of deep learning in medical imaging, highlighting opportunities for further optimization and refinement of these models to enhance diagnostic accuracy and ultimately improve patient outcomes.