Assessfy Pvt. Ltd Moderate 7 milestones 60 marks

Lung Cancer Image Segmentation using Various Image Processing Techniques

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

Lung Cancer Image Segmentation using Various Image Processing Techniques

Objective: Segment lung cancer regions from CT scan images using advanced image processing techniques.

Context: Early detection of lung cancer is critical for improving patient outcomes, especially in India where access to radiologists and timely diagnosis can be limited. Automated segmentation assists clinicians in identifying cancerous regions efficiently and accurately.

What you'll build: You will develop a pipeline in Python that preprocesses CT scan images (denoising, contrast enhancement), applies thresholding and filtering, and performs segmentation using OpenCV and scikit-image. Optionally, you may extend the project to include basic machine learning-based segmentation. Visualization and validation will be done using tools like Matplotlib and DICOM viewers.

Deliverables: The project will produce a working segmentation prototype, annotated images, and a short technical report documenting methods and results.

Milestones

No submission required for this milestone.

2. Data collection (CT scan images, possibly from Kaggle or open medical datasets)

10 marks 30d

Collect a minimum of 200 chest CT scan images relevant to lung cancer from open-access sources such as Kaggle or public medical datasets. Submit a summary table listing dataset names, sources, number of images, and licensing terms. Acceptance requires clear documentation of dataset provenance and confirmation of medical relevance.

3. Data collection (CT scan images, possibly from Kaggle or open medical datasets)

10 marks 30d

Organize the collected CT scan images into a structured directory, separating images and any available annotations. Submit a zipped folder or repository link containing the organized data, along with a README file describing the directory structure. Done means all files are accessible, correctly labeled, and ready for preprocessing.

4. Preprocessing (denoising, contrast enhancement)

10 marks 30d

Apply denoising (e.g., median or Gaussian filtering) and contrast enhancement (e.g., histogram equalization) techniques to your CT images. Submit sample before-and-after images and the code used for preprocessing. Acceptance requires visible improvement in image clarity and contrast, with reproducible preprocessing steps.

5. Implementing segmentation algorithms (e.g., edge detection, watershed, thresholding)

10 marks 30d

Implement at least two segmentation algorithms (such as edge detection, watershed, or thresholding) on the preprocessed CT images. Submit the code, segmented output images, and a brief comparison of algorithm performance. Done means segmentation outputs are clearly visible and methods are correctly applied to lung regions.

6. Evaluation against annotated ground truth

10 marks 30d

Evaluate your segmentation results using annotated ground truth masks, calculating metrics such as Dice coefficient or IoU. Submit a table of quantitative results and a short analysis discussing strengths and weaknesses of each method. Acceptance requires clear metric calculations and critical comparison to ground truth.

7. Visualization and reporting

10 marks 30d

Create visualizations overlaying segmentation results on original CT images and compile a concise report summarizing your methodology, findings, and challenges. Submit annotated images and a PDF report. Done means visualizations are clear, the report is well-structured, and results are communicated effectively.

Open internships using this project -->

Upcoming sessions

Session	Window	Enrolled
Lung Cancer Image Segmentation using Various Image Proces...	11 Jun 2026 to 10 Jun 2028	0

Skills you'll learn

Image Processing (thresholdingfilteringsegmentation)Machine Learning basics (if extended to ML-based segmentation)Python ProgrammingKnowledge of medical imaging standards (DICOM)Data Annotation & Preprocessing

Tools used

Python with OpenCVscikit-imageNumPyMatplotlib MATLAB (for academic use) DICOM viewers (3D SlicerRadiAnt) Jupyter Notebook

Prerequisites

Understanding of digital image processing Basic knowledge of anatomy (lungstumors) Programming skills in Python or MATLAB

Available mentors

Priyang Kumar

Free

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

Lung Cancer Image Segmentation using Various Image Processi…

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Moderate

Lung Cancer Image Segmentation using …

Assessfy

Auto-issued on completion One-click LinkedIn add