基于超声的膀胱癌检测AI模型数据集

数据集获取（Figshare）

• 源站标题：AI Model for Ultrasound-Based Bladder Cancer Detection
• DOI：10.6084/m9.figshare.28505048.v1
• 发布日期：2025-02-27
• 文件数：1 个
• 文件总体积：38.38 MB
• 源站页面：https://figshare.com/articles/dataset/AI_Model_for_Ultrasound-Based_Bladder_Cancer_Detection/28505048

命令行下载

curl -L -o "bladdercancer.zip" "https://ndownloader.figshare.com/files/52653629"

文件清单

• bladdercancer.zip（38.38 MB）

文件总体积 38.38 MB（源站 API 实测）。

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

数据说明

This study aims to construct and validate an AI model based on ultrasound images to evaluate its accuracy in bladder cancer detection, provide an auxiliary tool for clinical diagnosis, and reduce the rates of misdiagnosis and missed diagnosis. Ultrasound image data from patients with bladder cancer at the Heilongjiang Provincial Hospital were collected. Deep learning algorithms were employed to extract and analyze features from the images, and an AI model based on Mask R-CNN was developed. After model training, its performance was assessed using an independent validation set. The results showed that the AI model demonstrated high diagnostic performance, with an overall accuracy of 95.1% in the validation group and 90.4% in the test group. Compared with traditional ultrasound diagnosis, the AI model can provide preliminary assessments of the size, location, and invasion degree of the lesions, offering valuable references for clinical decision-making. The study concludes that the ultrasound-based AI model has significant potential for application in bladder cancer detection, significantly improving diagnostic accuracy and efficiency. Future research will focus on further optimizing the model’'s performance and validating it with larger-scale clinical data to promote its application in real-world medical settings.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.28505048.v1（source: https://figshare.com/articles/dataset/AI_Model_for_Ultrasound-Based_Bladder_Cancer_Detection/28505048）。