Complete medical imaging workspace dump (weights, deliverables, papers, notebooks, code, figures)
eded815 verified |
Download README.md from unknownBrain/BioHCL-SSSM-Complete-Workspace: direct link, hf CLI and curl.
- Browser
- Download file 7.16 kB
-
https://huggingface.co/unknownBrain/BioHCL-SSSM-Complete-Workspace/resolve/main/README.md
- Command line
-
hf download hf://unknownBrain/BioHCL-SSSM-Complete-Workspace/README.md
-
curl -L -o README.md https://huggingface.co/unknownBrain/BioHCL-SSSM-Complete-Workspace/resolve/main/README.md
7.16 kB
| language: | |
| - en | |
| license: mit | |
| tags: | |
| - medical-imaging | |
| - chest-xray | |
| - pneumonia-detection | |
| - state-space-models | |
| - mamba | |
| - sssm | |
| - pediatric | |
| - physics-informed-neural-networks | |
| pipeline_tag: image-classification | |
| datasets: | |
| - paultimothymooney/chest-xray-pneumonia | |
| metrics: | |
| - accuracy | |
| - f1 | |
| - precision | |
| - recall | |
| - roc_auc | |
| model-index: | |
| - name: BioHCL-SSSM | |
| results: | |
| - task: | |
| type: image-classification | |
| name: Pediatric Pneumonia Classification | |
| dataset: | |
| name: Guangzhou Pediatric Chest X-Ray Cohort (Cell 2018) | |
| type: paultimothymooney/chest-xray-pneumonia | |
| metrics: | |
| - type: accuracy | |
| value: 99.37 | |
| name: 10-Fold Cross-Validation Accuracy | |
| - type: f1 | |
| value: 0.9957 | |
| name: 10-Fold Cross-Validation F1 | |
| - type: roc_auc | |
| value: 0.9929 | |
| name: 10-Fold Cross-Validation AUC | |
| # BioHCL-SSSM: Complete Medical Imaging Workspace & Model Hub | |
| **Author:** unknownBrain | |
| **Project:** BioHCL-SSSM: Hierarchical Convolutional State-Space Hybrid Architecture for Pediatric Pneumonia Diagnosis | |
| **Dataset:** Guangzhou Women and Childrenβs Medical Center Pediatric Chest X-Ray Cohort (Kermany et al., *Cell* 2018; 5,856 images, 624 official held-out test split) | |
| --- | |
| ## π Complete Repository Contents | |
| This public repository contains the complete end-to-end workspace for the BioHCL-SSSM project, including all pre-trained checkpoints, raw experimental sweeps, modular source code, deliverable packages, evaluation figures, and peer-reviewed reference literature: | |
| ``` | |
| BioHCL-SSSM-Complete-Workspace/ | |
| β | |
| βββ deliverables/ # π OFFICIAL SUPERVISOR DELIVERABLE PACKAGES | |
| β βββ 1_sota_benchmarks_master.csv # 15-Model SOTA Benchmark (Literature baselines + Ours) | |
| β βββ 2_table1_component_ablation.csv # Table 1: Macro Component Ablation (SSSM vs Attention vs CNN) | |
| β βββ 3_table2_layer_hyperparameter_deduction.csv # Table 2: Proposed SSSM Layer Hyperparameter Deduction | |
| β βββ 4_table3_loss_function_weighting.csv # Table 3: Loss Function & Class Weighting Dynamics | |
| β βββ 5_10_fold_cross_validation_metrics.csv # Approved 10-Fold CV metrics (Folds 1 to 10 + Mean/Std) | |
| β βββ remaining_ablations_plan.md # Comprehensive scientific audit & execution plan | |
| β βββ tathagat_sir_revision_report.md # Full revision report formatted for Tathagat Sir | |
| β βββ v2/ # Clean v2 supervisor release package | |
| β βββ raw_sweeps/ # Raw 64-run ablation search & hardware profiling logs | |
| β βββ figures/ # Publication-ready ROC, PR, and Confusion Matrix plots | |
| β | |
| βββ medical imaging/ # π FULL ORIGINAL TRAINING CODE & WEIGHTS | |
| β βββ best_student_cv.pt # Best Model Checkpoint (Fold 2: 99.81% Val Acc, 0.9987 F1) | |
| β βββ model_fold_1.pt β¦ model_fold_10.pt # All 10 trained cross-validation model weights (54 MB each) | |
| β βββ ablation.csv # Raw 64 empirical ablation sweep runs | |
| β βββ extracted_code.py # Original full pipeline code extracted from Colab | |
| β βββ build_benchmark.py # Benchmark runner | |
| β βββ build_ablations.py # Ablation engine runner | |
| β βββ build_eval.py # Test evaluation engine | |
| β βββ build_xai.py # Explainability generator (Attention, GradCAM, LIME, SHAP) | |
| β βββ *.ipynb / *.ipynb.txt # Full Colab training notebooks | |
| β | |
| βββ hf_repo_staging/ # π CLEAN MODULARIZED SOURCE & ARTIFACTS | |
| β βββ src/ # Clean modular Python package (models, dataset, loss, eval) | |
| β βββ checkpoints/ # Reorganized weights (cross_validation/ and ablations/) | |
| β βββ results/ # CSV deliverables | |
| β βββ figures/ # Complete high-res figures & XAI heatmaps | |
| β | |
| βββ papers to refer/ # π 12 PEER-REVIEWED REFERENCE PAPERS | |
| β βββ IBMED-S-26-01139.pdf # Bio-HCLSSSM Reference Paper (Computers in Biology and Medicine) | |
| β βββ CMPB-D-26-01992_R1_reviewer.pdf # Computer Methods and Programs in Biomedicine | |
| β βββ EAAI-26-17234_reviewer.pdf # Engineering Applications of Artificial Intelligence | |
| β βββ TCIV-2026-0179.pdf # Computer Methods in Biomechanics and Biomedical Engineering | |
| β βββ IJIG-D-26-00102_R1_reviewer.pdf # International Journal of Image and Graphics | |
| β βββ JBHI-04026-2026_Proof_hi.pdf # IEEE Journal of Biomedical and Health Informatics | |
| β βββ ... (6 additional reviewer proofs) | |
| β | |
| βββ run_colab_remaining_ablations.py # π STANDALONE RUNNER FOR REMAINING EXPERIMENTS | |
| β # Executes the 4 remaining core runs (lambda_bio in [0.2, 0.5, 1.0] and MHSA Attention baseline) | |
| β # Takes ~10 mins on GPU and logs directly to CSV | |
| β | |
| βββ 10_fold_metrics.csv # Exact 10-fold cross-validation metrics | |
| βββ benchmark_master.csv # Consolidated SOTA benchmarks | |
| βββ remaining_ablations_plan.md # Scientific audit & plan | |
| βββ tathagat_sir_revision_report.md # Comprehensive revision report | |
| ``` | |
| --- | |
| ## π Key Performance Highlights | |
| 1. **Approved 10-Fold Cross-Validation:** | |
| * **Mean Accuracy:** **99.37% Β± 0.33%** | |
| * **Mean F1-Score:** **0.9957 Β± 0.0022** | |
| * **Mean ROC-AUC:** **0.9929 Β± 0.0039** | |
| * **Pooled Errors:** Only 33 errors across 5,232 images (3,862 TP, 1,337 TN, 12 FP, 21 FN). | |
| * **Peak Fold:** **Fold 2** achieved **99.81% accuracy, 0.9987 F1, 100% recall, 99.26% specificity** (`best_student_cv.pt`). | |
| 2. **Official Held-Out Test Set (624 Images) Benchmark:** | |
| * **BioHCL-SSSM:** **96.47% Accuracy, 97.22% F1, 99.37% ROC-AUC** with only **14.01M parameters and 8.56 GFLOPs**. | |
| * Outperforms standard Vision Transformers (**ViT-Base:** 86.57M params, 92.47% Acc) with **83.8% fewer parameters**. | |
| * Matches/exceeds Hierarchical Shifted-Window Transformers (**Swin-T:** 27.52M params, 95.99% Acc) with **49.1% fewer parameters**. | |
| --- | |
| ## π Quick Execution on New GPU (i9 + RTX 3080 Ti or Colab) | |
| To execute the remaining 4 core ablation runs: | |
| ```bash | |
| # 1. Clone this repository | |
| git clone https://huggingface.co/unknownBrain/BioHCL-SSSM-Complete-Workspace | |
| cd BioHCL-SSSM-Complete-Workspace | |
| # 2. Install dependencies | |
| pip install torch torchvision timm albumentations huggingface_hub scikit-learn pandas pillow | |
| # 3. Run the automated ablation suite | |
| python run_colab_remaining_ablations.py | |
| ``` | |
| --- | |
| ## π License & Citation | |
| Licensed under the **MIT License**. | |
| Guangzhou Women and Childrenβs Medical Center Chest X-Ray Cohort (Kermany et al., *Cell* 2018). | |