Downloads · 30 days
0
jayantsom/unet-resnet34-rsna23-abd-ct-seg-ep10-lr1e4-v1
unet-resnet34-rsna23-abd-ct-seg-ep10-lr1e4-v1 is a image segmentation model from jayantsom. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is a U-Net architecture with a ResNet-34 encoder backbone, fine-tuned specifically for the pixel-level segmentation of intraabdominal hemorrhages and active contrast extravasation. It was developed to serve…
Downloads · 30 days
0
Access
Public
Updated Apr 29, 2026
Repo size
97.9 MB
Likes
0
Public
Click a slice to open those files.
.pth97.9 MB · 100%
From the Hugging Face model README
This model is a U-Net architecture with a ResNet-34 encoder backbone, fine-tuned specifically for the pixel-level segmentation of intraabdominal hemorrhages and active contrast extravasation. It was developed to serve as "Layer 3" in the Trauma Lifesaver medical AI pipeline, estimating the precise volume (in mL) of blood to facilitate AAST grading and EAST guideline recommendations.
segmentation_models_pytorchThe model takes a 2.5D RGB array (3 stacked axial CT slices at soft-tissue windows: Center 50, Width 400) and outputs a binary pixel mask indicating the presence of active hemorrhage. It is intended for:
Use the code below to download the model and perform inference using PyTorch and segmentation_models_pytorch.
import torch
import segmentation_models_pytorch as smp
from huggingface_hub import hf_hub_download
# 1. Download the weights from Hugging Face
model_path = hf_hub_download(
repo_id="jayantsom/unet-resnet34-rsna23-abd-ct-seg-ep10-lr1e4-v1",
filename="model.pth"
)
# 2. Initialize the architecture
model = smp.Unet(
encoder_name="resnet34",
encoder_weights=None, # We load our trained weights below
in_channels=3,
classes=1,
activation=None
)
# 3. Load the weights
model.load_state_dict(torch.load(model_path, map_location="cpu"))
model.eval()
print("Hemorrhage segmenter ready for inference!")
The model was fine-tuned on a 1,000-sample streaming subset of the RSNA 2023 Abdominal Trauma Detection dataset.
z was stacked with its adjacent slices z-1 and z+1 to form a 3-channel RGB image, providing spatial depth context to the 2D U-Net.1e-4)torch.amp.autocast) using Colab GPU.Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
1e-4.1.0916.BibTeX:
@misc{rsna2023trauma,
author = {RSNA},
title = {RSNA 2023 Abdominal Trauma Detection},
year = {2023},
publisher = {Kaggle},
url = {https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection}
}
APA:
Radiological Society of North America (RSNA). (2023). RSNA 2023 abdominal trauma detection. Kaggle. https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection
U-Net: A Convolutional Neural Network (CNN) architecture designed for fast and precise biomedical image segmentation.
ResNet34: A 34-layer Residual Network used here as the encoder backbone for the U-Net, pre-trained on ImageNet to provide strong feature extraction.
Dice Loss: A spatial overlap-based loss function highly effective for medical image segmentation, especially when the target (hemorrhage) occupies a very small percentage of the total image pixels.
NIfTI: Neuroimaging Informatics Technology Initiative. A popular file format for storing 3D medical imaging data (e.g., CT volumes).
HU (Hounsfield Units): A quantitative scale for describing radiodensity in medical CT. Soft tissue windowing (center: 50, width: 400) is used here.
This segmentation model is released for educational and research purposes. I encourage the community to:
I am open to collaboration, questions, and feedback. Feel free to reach out via Hugging Face or email below.
Jayant Som
Jayant Som
(Reach out via Hugging Face profile or [email protected])