Update README.md

README.md

@@ -115,7 +115,7 @@ else:
 🚨 Not for clinical diagnosis! This model should not be used in real-world medical decision-making without further validation & regulatory approval. It is intended for research and educational purposes only.
 
 ## Bias, Risks, and Limitations
-- Dataset Bias: The model is trained on CBIS-DDSM, which may not fully represent all patient demographics.
+- Dataset Bias: The model is trained on Breast Histopathology Images, which may not fully represent all patient demographics.
 - False Positives/Negatives: Misclassification can occur, highlighting the need for human review in medical practice.
 - Limited Generalization: Performance may degrade on datasets from different imaging devices or institutions.
 - Ethical Concerns: AI in medical imaging should be deployed transparently and with clinical oversight to avoid unintended harm.
@@ -129,7 +129,7 @@ else:
 ## Training Details
 
 ### Training Data
-- Dataset: CBIS-DDSM (Curated Breast Imaging Subset of DDSM)
+- Dataset: Breast Histopathology Images
 - Image Types: High-resolution mammograms
 - Classes: Cancerous (Malignant), Non-Cancerous (Benign/Normal)
 - Annotations: Region of Interest (ROI) bounding boxes & BI-RADS assessments
@@ -153,7 +153,7 @@ else:
 
 #### Training Hyperparameters
 
-- **Epochs:** Coming soon...
+- **Epochs:** 20
 - **Batch Size:** 75
 - **Learning Rate:** 0.001
 - **Optimizer:** Adam
@@ -163,7 +163,7 @@ else:
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
-- Total Training Time: Coming soon...
+- Total Training Time: 33m
 - Hardware Used: Tesla P100
 
 ### Testing Data, Factors & Metrics
@@ -180,13 +180,11 @@ The model was evaluated on the test split of the CBIS-DDSM dataset
 
 The following metrics were computed for evaluation:
 - Accuracy
-- Precision & Recall
 - Confusion Matrix
-- AUC-ROC Curve
 
 ### Results
 
-- Accuracy: Coming soon...
+- Accuracy: 0.9789
 
 #### Summary
 
@@ -199,9 +197,9 @@ The model achieves strong performance on explicit misogyny detection, with poten
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
 - **Hardware Type:** Tesla P100
-- **Hours used:** Coming soon...
+- **Hours used:** 0.33
 - **Cloud Provider:** Kaggle
-- **Carbon Emitted:** Coming soon...
+- **Carbon Emitted:** 0.04
 
 ## Citation