Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@Kirti-Pant
Kirti-Pant
Follow

Kirti Pant Kirti-Pant

Block or report Kirti-Pant

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Kirti-Pant /README.md

Hi 👋, I'm Kirti Pant

AI/ML Engineer | Healthcare AI & Medical Imaging Researcher

Typing SVG


🌟 About Me

  • 🎓 B.Tech in Computer Science & Engineering — BTKIT, Uttarakhand (2021–2025)
  • 🧠 AI/ML Engineer specializing in Healthcare AI and Medical Imaging
  • 📊 Research focus on brain tumor classification & segmentation using MRI
  • 🔍 Strong interest in explainable AI, clinical reliability, and cross-dataset generalization
  • 🌍 Open to relocation and visa sponsorship

📰 Publications & Research

📘 Published Journal Paper

  • Pant, K., Pramanik, P. K. D., Zhao, Z.
    A Robust ConvNeXt-Based Framework for Efficient, Generalizable, and Explainable Brain Tumor Classification on MRI
    Bioengineering (MDPI), 2026
    🔗 https://doi.org/10.3390/bioengineering13020157

📄 Communicated / Under Review

  • Clinically Explainable Hybrid CNN–Transformer Model for Efficient Brain Tumor Segmentation Using MRI
    The Visual Computer (Springer), 2025

  • Global–Local Feature Fusion: A Robust Hybrid Deep Learning Model for Multiclass Brain Tumor Classification
    Egyptian Informatics Journal (Elsevier), 2025


🧰 Technical Skills

Languages & Tools

  • Python · Git · GitHub

Deep Learning & CV

  • PyTorch · TensorFlow · CNNs · ConvNeXt · Transformers

Medical Imaging & Explainability

  • OpenCV · Grad-CAM++ · SHAP · timm

Healthcare AI

  • Medical image classification & segmentation
  • Model validation · Explainable AI · Reproducibility

Generative AI

  • LLMs · RAG · LangChain · Hugging Face

MLOps & Experimentation

  • Weights & Biases · TensorBoard

Platforms

  • Google Colab · Kaggle

🚀 Research & Applied Projects

🧠 ConvNeXt-Based Brain Tumor Classification (Multi-Dataset)

  • Achieved 99.86%, 99.69%, and 99.83% cross-dataset accuracy
  • Conducted ablation studies, statistical validation, and Grad-CAM++ explainability
    🔗 https://github.com/ConvNeXt-Base

🧬 Hybrid CNN–Transformer Models for MRI

  • Developed global–local feature fusion models for multi-class classification & segmentation
  • Achieved up to 99.64% accuracy with strong generalization

🤖 MathAIAssistant

🏥 HealthAIAssistant


💼 Experience

👩‍💻 AI/ML Intern — ONGC India Ltd. (June–July 2024)

  • Developed PDF-based Retrieval-Augmented Generation (RAG) system
  • Designed a two-stage retrieval pipeline achieving ~85% accuracy
  • Worked on LLM integration, system scalability, and enterprise AI workflows
  • Exposure to GenAI, DevOps, and SAS-based AI systems

🌐 Open Source Contributor — Hacktoberfest 2025

  • Merged 5+ PRs across C, Java, and AI/ML repositories
  • Built agentic AI systems and contributed to DSA and system design projects

📫 Connect With Me

LinkedIn GitHub Email


💬 "Building reliable and explainable AI systems for real-world healthcare."

Pinned Loading

  1. CreditCardFraudDetectionProject CreditCardFraudDetectionProject Public

    I've predicted a model which classifies whether a transaction is Legit or Fraudulent .

    Python

  2. MindfulAI-Chat MindfulAI-Chat Public

    Built to combat online harassment and promote digital well-being

    TypeScript

  3. -Optimizing-POS-Tagging-using-HMM-A-Comparison-of-Algorithmic-Approaches -Optimizing-POS-Tagging-using-HMM-A-Comparison-of-Algorithmic-Approaches Public

    Conducted a comparative analysis of POS tagging algorithms—Viterbi, Posterior Decoding, Greedy, and Beam Search—within an HMM model across Hindi, English, Spanish, and Sanskrit, revealing key insig...

    Python

  4. cpp-dsa-sheet-testing cpp-dsa-sheet-testing Public

    Forked from saumyayadav25/cpp-dsa-sheet-testing

    Open-source template of DSAMate UI – built with Next.js, Tailwind CSS & TypeScript. For GSSoC '25 contributions.

    TypeScript

  5. CustomerSegmentationMLProject CustomerSegmentationMLProject Public

    I've predicted a model which segments the customers based on some features.

    Jupyter Notebook

  6. DisasterAI DisasterAI Public

    DisasterAI is an advanced disaster management and early warning system that leverages artificial intelligence to predict, prevent, and respond to natural disasters.

    TypeScript

AltStyle によって変換されたページ (->オリジナル) /