Skip to content
View TarunSadarla2606's full-sized avatar

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Block or report TarunSadarla2606

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 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
TarunSadarla2606/README.md

Tarun Sadarla

Medical Imaging AI · Deep Learning · Healthcare ML

MS Artificial Intelligence (Biomedical) · University of North Texas · GPA 4.00 · Available June 2026

LinkedIn HuggingFace Portfolio Email Kaggle

About Me

I build deep learning systems for clinical imaging problems — from segmentation and classification to model compression and edge deployment. My work spans ultrasound biometry, histopathology, and neuroimaging, with a focus on models that are accurate, interpretable, and deployable in real-world clinical settings.

Currently completing my MS at UNT with a 4.00 GPA, actively seeking full-time roles in healthcare AI, medical image analysis, and applied ML.

Featured Projects

Project Task Key Result Deployed Stack
🤰 Fetal Head Circumference Clinical AI Segmentation + Compression Dice 97.75% · MAE 1.65mm · −43.7% params HF PyTorch, Streamlit, Structural Pruning
🧠 ASD Detection via Neuroimaging Classification 91% accuracy · AUC 0.98 · CNN vs ViT HF PyTorch, ViT, LIME
🔬 Histopathologic Cancer Detection Binary Classification ROC-AUC 0.81 · Flask + Docker deployment — PyTorch, Flask, Docker
❤️ WECARE — Cardiac & Fall Detection Edge AI / Signal F1 0.9864 (ECG) · F1 0.8133 (IMU) · <0.033ms — 1D CNN, TorchScript, ECG, IMU
✂️ CNN Structured Pruning (VGG16) Model Compression −43.7% params · +0.37% Top-1 accuracy — PyTorch, VGG16, Hybrid Crossover
🎭 Multimodal Emotion Recognition Multimodal Classification CNN + BiLSTM fusion · MELD dataset — PyTorch, VGG-16, BiLSTM

Technical Skills

Medical Imaging & Vision DICOM · Ultrasound · MRI/Radiology · U-Net Segmentation · OpenCV · CNNs · Vision Transformers · GradCAM++

ML & Deep Learning PyTorch · TensorFlow · Keras · Scikit-learn · Temporal Attention · Structural Pruning · Knowledge Distillation

Deployment & Cloud HuggingFace Spaces · Streamlit · AWS (S3, EMR) · Docker · Flask · FastAPI · TorchScript

Big Data & Tools PySpark · Hadoop · Hive · SQL · Git

Languages Python · MATLAB · SQL · C

Education

University of North Texas — MS Artificial Intelligence (Biomedical Concentration) · GPA 4.00 · May 2026

Manipal Institute of Technology — B.Tech Computer Science & Engineering · Minor: Data Analytics · Dec 2023

Actively seeking full-time roles in healthcare AI and medical image analysis · Available June 2026

📧 tarunsadarla26@gmail.com  ·  Portfolio

Pinned Loading

  1. fetal-head-clinical-ai fetal-head-clinical-ai Public

    End-to-end clinical AI for fetal head circumference measurement — 4-phase pipeline: Residual U-Net (Dice 97.75%), Pseudo-LDDM v2 cine synthesis, temporal attention, structured pruning. Deployed on …

    Jupyter Notebook 1

  2. histopathology-cancer-detection_1 histopathology-cancer-detection_1 Public

    Custom CNN for binary cancer detection on PCam histopathology patches — systematic study of training data volume impact across 4 stratified subsets (20%/40%/60%/100%)

    Jupyter Notebook

  3. multimodal-emotion-recognition multimodal-emotion-recognition Public

    Multimodal emotion and sentiment classification from video frames — custom CNN baseline vs pretrained VGG-16 on MELD dataset (Friends TV series)

    Jupyter Notebook

  4. TarunSadarla2606 TarunSadarla2606 Public