mibr_study - Multimodal Deep Learning for Predicting Recurrence in Non–muscle invasive bladder cancer: Comparison with Traditional Risk Models - v1.0.0-paper

This release includes the sample data and the frontend code used in the web demonstration accompanying the manuscript. It provides a minimal working example for recurrence prediction in NMIBC using our multimodal AI model (MIBR).

Contents:

Sample clinical records and image metadata (de-identified) Streamlit app frontend (home.py) Utility modules (preprocess.py, util.py) requirements.txt for dependency installation Note:

Model weights, backend training pipeline, and inference engine are excluded due to data protection regulations. This release is intended for code structure review, documentation purposes, and interactive demonstration. For access to model weights, full training code, or backend modules, please contact the corresponding author.

Full Changelog: https://github.com/leekj3133/MIBR_study/commits/v1.0.0-paper

- Python
Published by leekj3133 11 months ago

mibr_study - Multimodal Deep Learning for Predicting Recurrence in NMIBC: Comparison with Traditional Risk Models

This release includes the sample data and the frontend code used in the web demonstration accompanying the manuscript. It provides a minimal working example for recurrence prediction in NMIBC using our multimodal AI model (MIBR).

Contents:

Sample clinical records and image metadata (de-identified) Streamlit app frontend (home.py) Utility modules (preprocess.py, util.py) requirements.txt for dependency installation

Note:

Model weights, backend training pipeline, and inference engine are excluded due to data protection regulations. This release is intended for code structure review, documentation purposes, and interactive demonstration. For access to model weights, full training code, or backend modules, please contact the corresponding author.

- Python
Published by leekj3133 11 months ago

mibr_study - Multimodal Deep Learning for Predicting Recurrence in NMIBC: Comparison with Traditional Risk Models

This release includes the sample data and the frontend code used in the web demonstration accompanying the manuscript. It provides a minimal working example for recurrence prediction in NMIBC using our multimodal AI model (MIBR).

Contents: - Sample clinical records and image metadata (de-identified) - Streamlit app frontend (home.py) - Utility modules (preprocess.py, util.py) - requirements.txt for dependency installation

Note: - Model weights, backend training pipeline, and inference engine are excluded due to data protection regulations. - This release is intended for code structure review, documentation purposes, and interactive demonstration. - For access to model weights, full training code, or backend modules, please contact the corresponding author.

Full Changelog: https://github.com/leekj3133/MIBR_study/commits/v1.0-paper

- Python
Published by leekj3133 11 months ago

mibr_study - MIBR study - version 1.0(for publication)

MIBR Study – Version 1.0 (for publication)

This release includes the sample data and the frontend code used in the web demonstration accompanying the manuscript. It provides a minimal working example for recurrence prediction in NMIBC using our multimodal AI model (MIBR).

Contents:

Sample clinical records and image metadata (de-identified) Streamlit app frontend (home.py) Utility modules (preprocess.py, util.py) requirements.txt for dependency installation Note:

Model weights, backend training pipeline, and inference engine are excluded due to data protection regulations. This release is intended for code structure review, documentation purposes, and interactive demonstration. For access to model weights, full training code, or backend modules, please contact the corresponding author. Full Changelog: https://github.com/leekj3133/MIBR_study/commits/v1.0-paper

- Python
Published by leekj3133 11 months ago

mibr_study - MIBR study - version 1.0 (for publication)

MIBR Study – Version 1.0 (for publication)

This release includes the sample data and the frontend code used in the web demonstration accompanying the manuscript. It provides a minimal working example for recurrence prediction in NMIBC using our multimodal AI model (MIBR).

Contents: - Sample clinical records and image metadata (de-identified) - Streamlit app frontend (home.py) - Utility modules (preprocess.py, util.py) - requirements.txt for dependency installation

Note: - Model weights, backend training pipeline, and inference engine are excluded due to data protection regulations. - This release is intended for code structure review, documentation purposes, and interactive demonstration. - For access to model weights, full training code, or backend modules, please contact the corresponding author.

Full Changelog: https://github.com/leekj3133/MIBR_study/commits/v1.0-paper

- Python
Published by leekj3133 11 months ago