license: apache-2.0
tags:
- image-segmentation
- vision
- fundus
- optic disc
- optic cup
widget:
- src: >-
https://huggingface.co/pamixsun/swinv2_tiny_for_glaucoma_classification/resolve/main/example.jpg
example_title: fundus image
Model Card for Model ID
This model utilizes a Swin Transformer architecture and has undergone supervised fine-tuning on retinal fundus images from the REFUGE challenge dataset. It is specialized in automated analysis of retinal fundus photographs for glaucoma detection. By extracting hierarchical visual features from input fundus images in a cross-scale manner, the model is able to effectively categorize each image as either glaucoma or non-glaucoma. Extensive experiments demonstrate that this model architecture achieves state-of-the-art performance on the REFUGE benchmark for fundus image-based glaucoma classification. To obtain optimal predictions, it is recommended to provide this model with standardized retinal fundus photographs captured using typical fundus imaging protocols.
Model Details
Model Description
Uses
The pretrained model provides glaucoma classification functionality solely based on analysis of retinal fundus images. You may directly utilize the raw model without modification to categorize fundus images as either glaucoma or non-glaucoma. This model is specialized in extracting discriminative features from fundus images to identify glaucoma manifestations. However, to achieve optimal performance, it is highly recommended to fine-tune the model on a representative fundus image dataset prior to deployment in real-world applications.
Bias, Risks, and Limitations
The model has undergone specialized training and fine-tuning exclusively using retinal fundus images, with the objective to perform semantic segmentation of anatomical structures including the optic disc and optic cup. Therefore, in order to derive optimal segmentation performance, it is imperative to ensure that only fundus images are entered as inputs to this model.
How to Get Started with the Model
Use the code below to get started with the model.
import cv2
import torch
from transformers import AutoImageProcessor, SegformerForSemanticSegmentation
image = cv2.imread('./example.jpg')
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
processor = AutoImageProcessor.from_pretrained("pamixsun/segformer_for_optic_disc_cup_segmentation")
model = SegformerForSemanticSegmentation.from_pretrained("pamixsun/segformer_for_optic_disc_cup_segmentation")
inputs = processor(image, return_tensors="pt")
with torch.no_grad():
outputs = self.seg_model(**inputs)
logits = outputs.logits.cpu()
upsampled_logits = nn.functional.interpolate(
logits,
size=image.shape[:2],
mode="bilinear",
align_corners=False,
)
pred_disc_cup = upsampled_logits.argmax(dim=1)[0].numpy().astype(np.uint8)
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]