Open-source blip-histopathology-finetuned model - Automatically generate descriptive text for pathological slide images

Blip Histopathology Finetuned

Developed by ragunath-ravi

This model is a fine-tuned version of the BLIP base model specifically for pathological slide images, used to automatically generate descriptive text for pathological slides.

Image-to-Text

Transformers

EnglishOpen Source License:Apache-2.0 #Pathological image description #Medical vision-language #Fine-tuned BLIP

Downloads 25

Release Time : 5/4/2025

Model Overview

Based on Salesforce's BLIP image captioning base model, this model has been fine-tuned on pathological slide image datasets, specializing in generating textual descriptions for medical pathology images.

Model Features

Specialized for pathological images

Fine-tuned specifically for pathological slide images, capable of understanding medical image features

Efficient training

Utilizes gradient accumulation strategy for effective training with limited resources

Low loss value

Achieves an average training loss of only 0.0098, demonstrating excellent performance

Model Capabilities

Pathological image analysis

Medical image caption generation

Vision-language understanding

Use Cases

Medical diagnosis assistance

Automatic pathology report generation

Automatically generates preliminary diagnostic descriptions based on pathological slide images

Improves pathologists' work efficiency and reduces human errors

Medical education

Provides automatic explanations of pathological images for medical students

Assists medical teaching and enhances learning efficiency

🚀 BLIP model fine-tuned on histopathology images

This model is a fine-tuned version of Salesforce/blip-image-captioning-base on histopathology images, aiming to provide accurate automatic captioning for histopathology images.

🚀 Quick Start

This model is a fine - tuned version of Salesforce/blip-image-captioning-base on a histopathology image dataset with the average loss of 0.0098.

✨ Features

Fine - tuned on histopathology images for automatic captioning.
Can be further fine - tuned on other datasets using the provided checkpoint.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoProcessor, BlipForConditionalGeneration
from PIL import Image

# Load model and processor
model = BlipForConditionalGeneration.from_pretrained("ragunath-ravi/blip-histopathology-finetuned")
processor = AutoProcessor.from_pretrained("ragunath-ravi/blip-histopathology-finetuned")

# Load image
image = Image.open("path_to_histopathology_image.jpg").convert('RGB')

# Process image
inputs = processor(images=image, return_tensors="pt")
pixel_values = inputs.pixel_values

# Generate caption
generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)

Advanced Usage

The last checkpoint is included in this repository under the 'last_checkpoint' directory. You can use this checkpoint to continue fine - tuning on another dataset.

📚 Documentation

Model description

The model was fine - tuned on the histopathology-image-caption-dataset for automatic captioning of histopathology images.

Training procedure

The model was trained for 10 epochs with a batch size of 4 and a learning rate of 5e - 5. Images were processed using the BLIP processor and gradient accumulation steps of 2 were used.

Training details

Property	Details
Dataset	Histopathology Image Caption Dataset (Kaggle)
Base model	Salesforce/blip-image-captioning-base
Training epochs	10
Batch size	4
Learning rate	5e-5
Gradient accumulation steps	2
Device	CUDA (if available)

📄 License

This model is licensed under the Apache 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご