CineMA / README.md

Update README.md

b1251ee verified 11 days ago

25.6 kB

	---
	license: mit
	language:
	- en
	datasets:
	- mathpluscode/ACDC
	tags:
	- medical
	- cardiac
	- MRI
	- foundation model
	- MAE
	---

	# CineMA - A Foundation Model for Cine Cardiac Magnetic Resonance Images 🎥🫀

	CineMA is a foundation model for Cine cardiac magnetic resonance (CMR) imaging based on
	Masked-Autoencoder. CineMA has been pre-trained on UK Biobank data and fine-tuned on multiple clinically
	relevant tasks such as ventricle and myocaridum segmentation, ejection fraction (EF) regression, cardiovascular disease
	(CVD) detection and classification, and mid-valve plane and apical landmark localization. The model has been evaluated
	on multiple datasets, including [ACDC](https://www.creatis.insa-lyon.fr/Challenge/acdc/),
	[M&Ms](https://www.ub.edu/mnms/), [M&Ms2](https://www.ub.edu/mnms-2/),
	[Kaggle](https://www.kaggle.com/c/second-annual-data-science-bowl/data),
	[Rescan](https://www.ahajournals.org/doi/full/10.1161/CIRCIMAGING.119.009214), and
	[Landmark](https://pubs.rsna.org/doi/10.1148/ryai.2021200197), etc.

	➡️ Manuscript: https://arxiv.org/abs/2506.00679.

	➡️ Code: [mathpluscode/CineMA](https://github.com/mathpluscode/CineMA)

	## Fine-tuned CineMA Models

	The filenames of fine-tuned model weights follow the convention of
	`finetuned/<task>/<data>_<view>/<data>_<view>_<seed>.safetensors` where number 0, 1, and 2 correspond to the different
	training seeds.

	Check the "Inference Example" column to see example inference scripts using these trained models.

	\| Training Task \| Training Data \| Input View \| Input Timeframes \| Model Weights and Configurations \| Inference Example \|
	\| ----------------------------------------------- \| ------------- \| ---------- \| ---------------- \| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- \| ------------------------------------------------------------------------------------------------------------------------ \|
	\| Ventricle and myocardium segmentation \| ACDC \| SAX \| 1 \| [finetuned/segmentation/acdc_sax/acdc_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/acdc_sax/acdc_sax_0.safetensors)<br>[finetuned/segmentation/acdc_sax/acdc_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/acdc_sax/acdc_sax_1.safetensors)<br>[finetuned/segmentation/acdc_sax/acdc_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/acdc_sax/acdc_sax_2.safetensors)<br>[finetuned/segmentation/acdc_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/acdc_sax/config.yaml) \| [segmentation_sax.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/segmentation_sax.py) \|
	\| Ventricle and myocardium segmentation \| M&Ms \| SAX \| 1 \| [finetuned/segmentation/mnms_sax/mnms_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms_sax/mnms_sax_0.safetensors)<br>[finetuned/segmentation/mnms_sax/mnms_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms_sax/mnms_sax_1.safetensors)<br>[finetuned/segmentation/mnms_sax/mnms_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms_sax/mnms_sax_2.safetensors)<br>[finetuned/segmentation/mnms_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms_sax/config.yaml) \| [segmentation_sax.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/segmentation_sax.py) \|
	\| Ventricle and myocardium segmentation \| M&Ms2 \| SAX \| 1 \| [finetuned/segmentation/mnms2_sax/mnms2_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_sax/mnms2_sax_0.safetensors)<br>[finetuned/segmentation/mnms2_sax/mnms2_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_sax/mnms2_sax_1.safetensors)<br>[finetuned/segmentation/mnms2_sax/mnms2_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_sax/mnms2_sax_2.safetensors)<br>[finetuned/segmentation/mnms2_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_sax/config.yaml) \| [segmentation_sax.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/segmentation_sax.py) \|
	\| Ventricle and myocardium segmentation \| M&Ms2 \| LAX 4C \| 1 \| [finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_0.safetensors)<br>[finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_1.safetensors)<br>[finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_lax_4c/mnms2_lax_4c_2.safetensors)<br>[finetuned/segmentation/mnms2_lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/segmentation/mnms2_lax_4c/config.yaml) \| [segmentation_lax_4c.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/segmentation_lax_4c.py) \|
	\| CVD classification \| ACDC \| SAX \| 2 (ED and ES) \| [finetuned/classification_cvd/acdc_sax/acdc_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/acdc_sax/acdc_sax_0.safetensors)<br>[finetuned/classification_cvd/acdc_sax/acdc_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/acdc_sax/acdc_sax_1.safetensors)<br>[finetuned/classification_cvd/acdc_sax/acdc_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/acdc_sax/acdc_sax_2.safetensors)<br>[finetuned/classification_cvd/acdc_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/acdc_sax/config.yaml) \| [classification_cvd.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_cvd.py) \|
	\| CVD classification \| M&Ms \| SAX \| 2 (ED and ES) \| [finetuned/classification_cvd/mnms_sax/mnms_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms_sax/mnms_sax_0.safetensors)<br>[finetuned/classification_cvd/mnms_sax/mnms_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms_sax/mnms_sax_1.safetensors)<br>[finetuned/classification_cvd/mnms_sax/mnms_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms_sax/mnms_sax_2.safetensors)<br>[finetuned/classification_cvd/mnms_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms_sax/config.yaml) \| [classification_cvd.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_cvd.py) \|
	\| CVD classification \| M&Ms2 \| SAX \| 2 (ED and ES) \| [finetuned/classification_cvd/mnms2_sax/mnms2_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_sax/mnms2_sax_0.safetensors)<br>[finetuned/classification_cvd/mnms2_sax/mnms2_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_sax/mnms2_sax_1.safetensors)<br>[finetuned/classification_cvd/mnms2_sax/mnms2_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_sax/mnms2_sax_2.safetensors)<br>[finetuned/classification_cvd/mnms2_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_sax/config.yaml) \| [classification_cvd.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_cvd.py) \|
	\| CVD classification \| M&Ms2 \| LAX 4C \| 2 (ED and ES) \| [finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_0.safetensors)<br>[finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_1.safetensors)<br>[finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_lax_4c/mnms2_lax_4c_2.safetensors)<br>[finetuned/classification_cvd/mnms2_lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_cvd/mnms2_lax_4c/config.yaml) \| [classification_cvd.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_cvd.py) \|
	\| Patient sex classification \| M&Ms \| SAX \| 2 (ED and ES) \| [finetuned/classification_sex/mnms_sax/mnms_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_sex/mnms_sax/mnms_sax_0.safetensors)<br>[finetuned/classification_sex/mnms_sax/mnms_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_sex/mnms_sax/mnms_sax_1.safetensors)<br>[finetuned/classification_sex/mnms_sax/mnms_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_sex/mnms_sax/mnms_sax_2.safetensors)<br>[finetuned/classification_sex/mnms_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_sex/mnms_sax/config.yaml) \| [classification_sex.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_sex.py) \|
	\| CMR machine vendor classification \| M&Ms2 \| SAX \| 2 (ED and ES) \| [finetuned/classification_vendor/mnms2_sax/mnms2_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_sax/mnms2_sax_0.safetensors)<br>[finetuned/classification_vendor/mnms2_sax/mnms2_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_sax/mnms2_sax_1.safetensors)<br>[finetuned/classification_vendor/mnms2_sax/mnms2_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_sax/mnms2_sax_2.safetensors)<br>[finetuned/classification_vendor/mnms2_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_sax/config.yaml) \| [classification_vendor.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_vendor.py) \|
	\| CMR machine vendor classification \| M&Ms2 \| LAX 4C \| 2 (ED and ES) \| [finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_0.safetensors)<br>[finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_1.safetensors)<br>[finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_lax_4c/mnms2_lax_4c_2.safetensors)<br>[finetuned/classification_vendor/mnms2_lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/classification_vendor/mnms2_lax_4c/config.yaml) \| [classification_vendor.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/classification_vendor.py) \|
	\| Direct EF regression \| ACDC \| SAX \| 2 (ED and ES) \| [finetuned/regression_ef/acdc_sax/acdc_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/acdc_sax/acdc_sax_0.safetensors)<br>[finetuned/regression_ef/acdc_sax/acdc_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/acdc_sax/acdc_sax_1.safetensors)<br>[finetuned/regression_ef/acdc_sax/acdc_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/acdc_sax/acdc_sax_2.safetensors)<br>[finetuned/regression_ef/acdc_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/acdc_sax/config.yaml) \| [regression_ef.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_ef.py) \|
	\| Direct EF regression \| M&Ms \| SAX \| 2 (ED and ES) \| [finetuned/regression_ef/mnms_sax/mnms_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms_sax/mnms_sax_0.safetensors)<br>[finetuned/regression_ef/mnms_sax/mnms_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms_sax/mnms_sax_1.safetensors)<br>[finetuned/regression_ef/mnms_sax/mnms_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms_sax/mnms_sax_2.safetensors)<br>[finetuned/regression_ef/mnms_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms_sax/config.yaml) \| [regression_ef.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_ef.py) \|
	\| Direct EF regression \| M&Ms2 \| SAX \| 2 (ED and ES) \| [finetuned/regression_ef/mnms2_sax/mnms2_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_sax/mnms2_sax_0.safetensors)<br>[finetuned/regression_ef/mnms2_sax/mnms2_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_sax/mnms2_sax_1.safetensors)<br>[finetuned/regression_ef/mnms2_sax/mnms2_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_sax/mnms2_sax_2.safetensors)<br>[finetuned/regression_ef/mnms2_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_sax/config.yaml) \| [regression_ef.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_ef.py) \|
	\| Direct EF regression \| M&Ms2 \| LAX 4C \| 2 (ED and ES) \| [finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_0.safetensors)<br>[finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_1.safetensors)<br>[finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_lax_4c/mnms2_lax_4c_2.safetensors)<br>[finetuned/regression_ef/mnms2_lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_ef/mnms2_lax_4c/config.yaml) \| [regression_ef.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_ef.py) \|
	\| Patient BMI regression \| ACDC \| SAX \| 2 (ED and ES) \| [finetuned/regression_bmi/acdc_sax/acdc_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_bmi/acdc_sax/acdc_sax_0.safetensors)<br>[finetuned/regression_bmi/acdc_sax/acdc_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_bmi/acdc_sax/acdc_sax_1.safetensors)<br>[finetuned/regression_bmi/acdc_sax/acdc_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_bmi/acdc_sax/acdc_sax_2.safetensors)<br>[finetuned/regression_bmi/acdc_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_bmi/acdc_sax/config.yaml) \| [regression_bmi.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_bmi.py) \|
	\| Patient age regression \| M&Ms \| SAX \| 2 (ED and ES) \| [finetuned/regression_age/mnms_sax/mnms_sax_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_age/mnms_sax/mnms_sax_0.safetensors)<br>[finetuned/regression_age/mnms_sax/mnms_sax_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_age/mnms_sax/mnms_sax_1.safetensors)<br>[finetuned/regression_age/mnms_sax/mnms_sax_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_age/mnms_sax/mnms_sax_2.safetensors)<br>[finetuned/regression_age/mnms_sax/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/regression_age/mnms_sax/config.yaml) \| [regression_age.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/regression_age.py) \|
	\| Landmark localization by heatmap regression \| Landmark \| LAX 2C \| 1 \| [finetuned/landmark_heatmap/lax_2c/lax_2c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_2c/lax_2c_0.safetensors)<br>[finetuned/landmark_heatmap/lax_2c/lax_2c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_2c/lax_2c_1.safetensors)<br>[finetuned/landmark_heatmap/lax_2c/lax_2c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_2c/lax_2c_2.safetensors)<br>[finetuned/landmark_heatmap/lax_2c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_2c/config.yaml) \| [landmark_heatmap.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/landmark_heatmap.py) \|
	\| Landmark localization by heatmap regression \| Landmark \| LAX 4C \| 1 \| [finetuned/landmark_heatmap/lax_4c/lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_4c/lax_4c_0.safetensors)<br>[finetuned/landmark_heatmap/lax_4c/lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_4c/lax_4c_1.safetensors)<br>[finetuned/landmark_heatmap/lax_4c/lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_4c/lax_4c_2.safetensors)<br>[finetuned/landmark_heatmap/lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_heatmap/lax_4c/config.yaml) \| [landmark_heatmap.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/landmark_heatmap.py) \|
	\| Landmark localization by coordinates regression \| Landmark \| LAX 2C \| 1 \| [finetuned/landmark_coordinate/lax_2c/lax_2c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_2c/lax_2c_0.safetensors)<br>[finetuned/landmark_coordinate/lax_2c/lax_2c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_2c/lax_2c_1.safetensors)<br>[finetuned/landmark_coordinate/lax_2c/lax_2c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_2c/lax_2c_2.safetensors)<br>[finetuned/landmark_coordinate/lax_2c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_2c/config.yaml) \| [landmark_coordinate.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/landmark_coordinate.py) \|
	\| Landmark localization by coordinates regression \| Landmark \| LAX 4C \| 1 \| [finetuned/landmark_coordinate/lax_4c/lax_4c_0.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_4c/lax_4c_0.safetensors)<br>[finetuned/landmark_coordinate/lax_4c/lax_4c_1.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_4c/lax_4c_1.safetensors)<br>[finetuned/landmark_coordinate/lax_4c/lax_4c_2.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_4c/lax_4c_2.safetensors)<br>[finetuned/landmark_coordinate/lax_4c/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/finetuned/landmark_coordinate/lax_4c/config.yaml) \| [landmark_coordinate.py](https://github.com/mathpluscode/CineMA/blob/main/examples/inference/landmark_coordinate.py) \|

	## Pre-trained CineMA Model

	The pre-trained CineMA model backbone is available at
	[pretrained/cinema.safetensors](https://huggingface.co/mathpluscode/CineMA/blob/main/pretrained/cinema.safetensors) with
	configuration [pretrained/config.yaml](https://huggingface.co/mathpluscode/CineMA/blob/main/pretrained/config.yaml).

	Following scripts demonstrated how to fine-tune this backbone using
	[a preprocessed version of ACDC dataset](https://huggingface.co/datasets/mathpluscode/ACDC):

	- [Ventricle and myocardium segmentation](https://github.com/mathpluscode/CineMA/blob/main/examples/train/segmentation.py)
	- [Cardiovascular disease classification](https://github.com/mathpluscode/CineMA/blob/main/examples/train/classification.py)
	- [Ejection fraction regression](https://github.com/mathpluscode/CineMA/blob/main/examples/train/regression.py)

	## Citation

	## Contact

	For questions or collaborations, please contact Yunguan Fu ([email protected]).