Upload README.md
Browse filesAdd README.md model card
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: pytorch
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- explainable-ai
|
| 7 |
+
- medical-imaging
|
| 8 |
+
- grad-cam
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# T1 MLOps Stack — ChestXplain Checkpoint
|
| 12 |
+
|
| 13 |
+
This repository contains the approved DenseNet121 checkpoint used by the ChestXplain research/demo application. The application performs multi-label classification of 14 thoracic conditions and provides Grad-CAM visual explanations.
|
| 14 |
+
|
| 15 |
+
## Training provenance
|
| 16 |
+
|
| 17 |
+
- **Architecture:** DenseNet121 with a multi-label classification head
|
| 18 |
+
- **Dataset:** NIH ChestX-ray14-derived training subset
|
| 19 |
+
- **Training subset:** 20,000 images
|
| 20 |
+
- **Checkpoint epoch:** 6
|
| 21 |
+
- **Validation AUC:** 0.813 (recorded in the checkpoint metadata)
|
| 22 |
+
- **Checkpoint SHA-256:** `5bf5e15396805ac85a5c1f1839813bc4ea3a66ff694f5ed6f12c1fd2eaee0cbf`
|
| 23 |
+
- **Artifact:** `densenet121_chestxray.pth`
|
| 24 |
+
|
| 25 |
+
The checkpoint is provided as a model artifact for the associated portfolio MLOps demonstration. NIH images and source data are not included in this repository.
|
| 26 |
+
|
| 27 |
+
## Intended use
|
| 28 |
+
|
| 29 |
+
Research, engineering evaluation, and educational/demo use only. This artifact is not validated for clinical deployment and must not be used to diagnose, treat, or make decisions about patients.
|
| 30 |
+
|
| 31 |
+
## Limitations
|
| 32 |
+
|
| 33 |
+
- The model was trained on a 20,000-image subset rather than the complete NIH ChestX-ray14 dataset.
|
| 34 |
+
- Dataset labels are noisy and may not represent definitive clinical diagnoses.
|
| 35 |
+
- Performance may vary across institutions, scanners, patient populations, acquisition protocols, and disease prevalence.
|
| 36 |
+
- Reported metrics are not evidence of clinical efficacy, safety, fairness, or regulatory approval.
|
| 37 |
+
- Grad-CAM highlights model attribution regions; it is not a clinical explanation or proof of pathology.
|
| 38 |
+
- The checkpoint has not undergone external validation, prospective evaluation, calibration analysis, or regulatory review.
|
| 39 |
+
|
| 40 |
+
## License and provenance
|
| 41 |
+
|
| 42 |
+
The model artifact is released under the repository's MIT license for research/demo purposes, subject to the terms and attribution requirements of the underlying NIH ChestX-ray14 dataset and its original publication. See the associated source project for inference code, evaluation context, and full citations:
|
| 43 |
+
|
| 44 |
+
<https://github.com/ajinkya-awari/t1-mlops-stack>
|