Upload folder using huggingface_hub

README.md

@@ -0,0 +1,136 @@
+---
+license: agpl-3.0
+library_name: ultralytics
+tags:
+  - object-detection
+  - medical-imaging
+  - colonoscopy
+  - polyp-detection
+  - endoscopy
+pipeline_tag: object-detection
+---
+
+# TRUE-Colon — YOLOv8-M (REAL-Colon, seed 123)
+
+YOLOv8-M trained on the **REAL-Colon** dataset of 60 complete, unedited colonoscopy
+procedures, released alongside the TRUE-Colon evaluation protocol
+(MICCAI 2026 EndoLINA workshop).
+
+This is one of three seeds. Reporting a single seed of this model in isolation would
+overstate its precision; the paper aggregates all three.
+
+## Model Details
+
+- **Developed by:** Chair of Explainable Machine Learning, Otto-Friedrich-University Bamberg
+- **Model type:** Single-class object detector (`lesion`)
+- **License:** AGPL-3.0, inherited from Ultralytics. This is **not** the MIT license of the
+  `true_colon` evaluation package. Using these weights in a product carries the AGPL's
+  source-availability obligations.
+- **Framework:** Ultralytics
+
+### Model Sources
+
+- **Paper:** https://arxiv.org/abs/2608.13711
+- **Repository:** https://github.com/sdoerrich97/true-colon
+- **Protocol package:** https://pypi.org/project/true-colon/
+
+### Architecture and training
+
+| | |
+|---|---|
+| Backbone | YOLOv8 |
+| Input | 640 x 640 |
+| Classes | 1 (`lesion`) |
+| Training data | REAL-Colon, patient-level split, 86.47% lesion-free training frames |
+| Seed | 123 |
+| Batch size | 208 |
+| Optimizer | SGD, lr0 0.01, momentum 0.9, weight decay 5e-4 (resolved from `optimizer=auto`) |
+| Schedule | 100 epochs, early stopping patience 10, 3-epoch warm-up |
+| Initialization | COCO-pretrained, as shipped by Ultralytics |
+| Ultralytics version | 8.3.232 |
+
+This is the configuration this checkpoint was trained with. The paper states the recipe in
+one sentence and otherwise defers to the frameworks' defaults, so the values it does not
+state — the optimizer, learning rate, momentum, weight decay and warm-up — come from the
+training run itself.
+
+> **On the optimizer.** The run recorded `optimizer: auto`, which is the framework
+> default the paper keeps. Ultralytics resolves that at runtime: SGD when the iteration
+> budget exceeds 10,000, AdamW otherwise. This run reaches 820,500 iterations, so
+> it trained with **SGD**, at `lr0=0.01` and `momentum=0.9` — `auto` sets both, so the
+> run's own `momentum` entry does not apply.
+
+## Uses
+
+### Direct use
+
+Research on polyp detection and on evaluation methodology for video-based computer-aided
+detection. The intended use is reproducing and extending the TRUE-Colon benchmark.
+
+### Out-of-scope use
+
+**This is not a medical device and must not be used for clinical decision-making.** The
+paper's own conclusion is that performance under realistic full-procedure conditions
+remains insufficient for reliable clinical deployment. It has not been validated
+prospectively, cleared by any regulator, or tested against the population, scope hardware
+or bowel-preparation quality of any particular site.
+
+## Bias, risks and limitations
+
+- Trained on 60 procedures from 4 institutions; endoscope hardware, imaging mode and
+  patient population all shift performance.
+- Detection is dominated by medium and large lesions; average precision on small lesions
+  is near zero.
+- Two histological subtypes (SSL, TSA) appear only in the test split, and sessile serrated
+  lesions have the highest miss rates.
+- Frame-level, with no temporal model: each frame is scored independently.
+
+## How to get started
+
+```python
+from ultralytics import YOLO  # or RTDETR for the RT-DETR variant
+from huggingface_hub import hf_hub_download
+
+weights = hf_hub_download("sdoerrich97/true_colon_yolov8m_realcolon_s123", "model.pt")
+model = YOLO(weights)
+results = model.predict("frame.jpg", conf=0.06)
+```
+
+Then evaluate under the protocol:
+
+```python
+import true_colon as tc
+
+evaluator = tc.create_evaluator(dataset="realcolon", id_source="pred_string")
+result = evaluator.evaluate_paths("gt.json", "predictions.json")
+```
+
+## Evaluation
+
+Evaluate with the TRUE-Colon protocol rather than COCO mAP alone: the point of the
+benchmark is that localization accuracy alone does not predict deployment behaviour. The
+paper reports this architecture at a matched false-alert operating point of
+**tau* = 0.06** on REAL-Colon, targeting a frame-level false-positive rate of 4-5%.
+
+For the full result tables, see the paper. Per-seed numbers are not reproduced on this
+card, because a single seed's values are not the quantity the paper reports.
+
+## Citation
+
+```bibtex
+@inproceedings{doerrich2026truecolon,
+  title         = {TRUE-Colon: Exposing a Consistent Transfer Asymmetry in Real-Time Polyp Detection},
+  author        = {Doerrich, Sebastian and Schwab, Andreas Franz and Di Salvo, Francesco
+                   and Rai, Shyam Nandan and Nguyen, Hanh Huyen My and Ledig, Christian},
+  booktitle     = {MICCAI Workshop on Endoscopic Lesion Identification and Analysis (EndoLINA)},
+  year          = {2026},
+  eprint        = {2608.13711},
+  archivePrefix = {arXiv},
+  primaryClass  = {eess.IV},
+  doi           = {10.48550/arXiv.2608.13711}
+}
+```
+
+## Contact
+
+sebastian.doerrich@uni-bamberg.de

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "YOLOv8"
+  ],
+  "model_type": "yolov8",
+  "library_name": "ultralytics",
+  "input_size": 640,
+  "num_classes": 1,
+  "class_names": [
+    "lesion"
+  ],
+  "training_dataset": "REAL-Colon",
+  "training_seed": 123,
+  "matched_threshold_realcolon": 0.06,
+  "license": "agpl-3.0",
+  "source_sha256": "a6c7f7065d1bf2d48cef84ca215b6bd13717bf13b4471c04babcb1cf641a0917"
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c7f7065d1bf2d48cef84ca215b6bd13717bf13b4471c04babcb1cf641a0917
+size 103832394