Skip to content
View servasadolph's full-sized avatar
🫠
Focusing
🫠
Focusing

Block or report servasadolph

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
servasadolph/README.md

PhD Researcher in Future Convergence Technology / Big Data Engineering
Soonchunhyang University, South Korea

Portfolio University email Google Scholar ORCID LinkedIn


About

I am a PhD researcher in the Department of Future Convergence Technology / Big Data Engineering at Soonchunhyang University, South Korea. My work focuses on AI for healthcare, especially medical image analysis, domain adaptation, multimodal report generation, and practical LLM/RAG systems.

My research goal is to build AI systems that remain useful outside a single controlled dataset. I focus on models that can generalize across hospitals, imaging devices, and patient populations, with long-term interest in practical healthcare tools for Tanzania and other low-resource settings.


Current Research Focus

Area Status Focus
Domain Adaptation in Medical AI 2026 - Present Generalizing medical imaging and healthcare models across hospitals, clinical sites, imaging protocols, and patient populations.
Multimodal Report Generation for Blood Smear Analysis 2026 - Present Building systems that read microscopy blood-smear images and generate structured clinical reports using attention mechanisms and language models.

Completed Research Work

Area Period Focus
AI Systems with LLMs and RAG 2026, completed Retrieval-augmented systems that keep AI answers grounded in verified data, including Matokeo Yangu for Tanzanian academic guidance.
Blood Cell Classification & Domain Adaptation 2021.09 - 2024, completed White blood cell detection and classification across clinical settings using YOLO, Vision Transformers, augmentation, and domain adaptation methods.

Selected Publications

  1. Pancreas Segmentation Using a Two-Stage Pipeline of Faster R-CNN and TransUNet Applied Sciences, 2026. DOI

  2. WBC YOLO-ViT: 2-Way 2-Stage White Blood Cell Detection and Classification with a Combination of YOLOv5 and Vision Transformer Computers in Biology and Medicine, 2024. DOI

  3. Diffusion-based Wasserstein Generative Adversarial Network for Blood Cell Image Augmentation Engineering Applications of Artificial Intelligence, 2024. DOI

  4. Adapting YOLO-ViT for Differential Diagnosis of Myelodysplastic Syndromes and Normal Blood Cell Proceedings of the Korea Society of Computer and Information Conference, 2024.

  5. White Blood Cell Detection and Classification using YOLOv5 with Hybrid ResNet50-VGG16-SVM 6th International Conference on ICT for Smart Health & Home, 2022.


Projects

Project Status Summary
Domain Adaptation in Medical AI 2026 - Present Transfer learning and domain adaptation methods for robust medical AI across clinical sites.
Medical Report Generator 2026 - Present Multimodal clinical report generation for blood-smear analysis and decision-support workflows.
Matokeo Yangu 2026, completed Bilingual platform helping Tanzanian students check exam results and receive AI-guided university and career advice.
WBC Detection & Classification 2021.09 - 2024, completed Automated white blood cell detection, counting, and classification using YOLO and Vision Transformers.

Education

Ph.D. Student, Future Convergence Technology / Big Data Engineering
Soonchunhyang University, South Korea | 2023.09 - Present
Advisor: Prof. Woo Ji-Young | Lab: Advanced Data Mining Lab (ADM Lab)

M.Sc. Big Data Engineering
Soonchunhyang University, South Korea | 2021.09 - 2023.08
Dissertation: WBC YOLO-ViT: 2-Way 2-Stage White Blood Cell Detection and Classification with a Combination of YOLOv5 and Vision Transformer

B.Sc. Computer Engineering & Information Technology
United African University of Tanzania | 2017.01 - 2020.08


Work Experience

Research Assistant
Advanced Data Mining Lab (ADM Lab), Soonchunhyang University | 2021.09 - Present
Developing medical AI systems for blood-cell image analysis, domain adaptation, multimodal report generation, and RAG-based clinical decision-support workflows with Prof. Woo Ji-Young.


Technical Areas

Python, PyTorch, FastAPI, React

Medical AI Domain Adaptation Computer Vision LLM and RAG


Connect

Portfolio | University Email | Email | Google Scholar | ORCID | LinkedIn | GitHub | Instagram | X/Twitter | YouTube

Popular repositories Loading

  1. cv cv Public template

    Python

  2. Flowise Flowise Public

    Forked from FlowiseAI/Flowise

    Drag & drop UI to build your customized LLM flow

    JavaScript

  3. whaiautoreply whaiautoreply Public

    Python

  4. e-commerce e-commerce Public

    TypeScript

  5. project-template project-template Public

    Project Template

  6. test_pesapalAPI test_pesapalAPI Public