Scribd
Upload
74 views16 pages

Lung Cancer Detection

The project titled 'Lung Cancer Detection using CT Image Processing & ML' focuses on utilizing advanced machine learning and image processing techniques to improve early detection of lung cancer through CT scans. It outlines a proposed system involving data collection, lung segmentation, feature extraction, and model training, emphasizing the advantages of automation, accuracy, and cost-effectiveness. The conclusion highlights the potential of this approach to enhance diagnosis and treatment planning while addressing challenges related to computational requirements and ethical concerns.

Uploaded by

Pramod Parit
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
74 views16 pages

Lung Cancer Detection

The project titled 'Lung Cancer Detection using CT Image Processing & ML' focuses on utilizing advanced machine learning and image processing techniques to improve early detection of lung cancer through CT scans. It outlines a proposed system involving data collection, lung segmentation, feature extraction, and model training, emphasizing the advantages of automation, accuracy, and cost-effectiveness. The conclusion highlights the potential of this approach to enhance diagnosis and treatment planning while addressing challenges related to computational requirements and ethical concerns.

Uploaded by

Pramod Parit
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Department of Computer Science & Engineering

Project Title :
"Lung Cancer Detection using CT(Computed Tomography) Image
Processing & ML“
Under the Guidance of :
Prof. M. G. Ganachari
Presented By :
Mr. Aftab I Yaragatti USN : 2HN22CS005
Miss. Bhagyashree S Poojari USN : 2HN22CS013
Miss. Kavita K Dodagoudanavar USN : 2HN22CS024
Miss. Laxmi A Bilur USN : 2HN22CS026
Agenda
• Introduction
• Proposed System
• Data flow diagram
• System Requirements
• Snapshots.
• Advantages
• Conclusion.
• References.
Introduction
Lung cancer is one of the leading causes of cancer-
related deaths worldwide. Early detection plays a crucial role in
improving survival rates, as treatment is more effective in the initial
stages of the disease. Computed Tomography (CT) scans provide
detailed imaging of lung structures, enabling better analysis for cancer
detection.
With advancements in Machine Learning (ML) and
Image Processing, automated lung cancer detection systems are being
developed to assist radiologists in diagnosing cancer with higher
accuracy and efficiency. These systems utilize deep learning models,
convolutional neural networks (CNNs), and image processing
techniques to analyze CT scan images, identify abnormalities, and
classify cancer stages.
Proposed System
1. Data Collection & Preprocessing
2. Lung Segmentation & Feature Extraction
3. Machine Learning Model Training
4. Prediction & Classification
DataFlow Diagram

Fig 1.1 : Data Flow


Diagram
Fig 1.2 : Data Flow
System Requirements
Hardware Requirement Software Requirements
Computer : A PC or Laptop with Operating System: Windows 10/11
moderate to high performance. Code Editors : Visual Studio Code
Processor : Intel i5/i7. or Sublime text.
RAM : 8GB (Minimum) or Python Libraries: Libraries such as
16GB(Recommended) to handle OpenCV, TensorFlow, Keras, NumPy
large datasets. and Pandas, Matplotlib/Seaborn.
Storage : SSD with at least 256GB AI & ML Frameworks: Darknet &
or 500GB(for faster file access) YOLO
Storage.
Expected Outcome of this Project

Fig 2.1 : Lung Cancer Detection


Outcome
Expected Outcome of this Project

Fig 2.2 : Lung Cancer Detection


Outcome
Expected Outcome of this Project

Fig 2.3 : Lung Cancer Detection


Expected Outcome of this Project

Fig 2.4 : Lung Cancer Detection


Advantages
1. Early Detection & Improved Survival
Rates
2. Automated & Faster Diagnosis
3. Higher Accuracy with Deep Learning
4. Reduced False Positives & False
Negatives
5. Cost-Effective Solution
6. Scalability & Integration
Conclusion
Lung cancer detection using CT image processing and
machine learning has the potential to revolutionize early diagnosis
and treatment planning. It offers high accuracy, automation, and
efficiency, reducing the burden on radiologists and improving
patient outcomes.
However, challenges such as high computational
requirements, data availability, and ethical concerns must be
carefully addressed. Despite these limitations, continuous
advancements in AI and medical imaging are making this
approach increasingly reliable, cost-effective, and non-invasive
cancer detection in the future.
References
1. S. Saxena, S. N. Prasad, A. M. Polnaya, and S.
“Hybrid Deep Convolution
Agarwala, Lun Canc
Detecti wit Model for g er
arXiv:2501.02785,
on h TransferJan. [Online].
Learning,” arXiv prepri
https://arxiv.org/abs/2501.02785
2025. Available: nt
2. A. Chaudhari, A. Singh, S. Gajbhiye, and P. Agrawal,
Cancer
“Lung Using Deep Learning,”
arXiv:2501.071
Detection arXiv preprint Jan.
https://arxiv.org/abs/2501.0
97, 2025. [Online]. Available:
7197

You might also like