arXiv:2511.06769eess.IVcs.CV2025-11被引 1

面向资源有限场景的结肠镜数据集,助力真实世界下智能诊断研究

RRTS Dataset: A Benchmark Colonoscopy Dataset from Resource-Limited Settings for Computer-Aided Diagnosis Research

  • 采集真实临床环境下的结肠镜图像,包含运动模糊、反光等复杂干扰
  • 含1288张带病灶图像与1657张无病灶图像,标注由临床专家审核确保质量
  • 提供分类与分割基准结果,适合研究真实医疗影像挑战的开发者参考

结直肠癌预防依赖于结肠镜检查中对息肉的早期发现。现有公开数据集如CVC-ClinicDB和Kvasir-SEG虽具价值,但受限于样本量小、图像筛选严格或缺乏真实世界伪影。为填补这一空白,我们构建了BUET息肉数据集(BPD),基于奥林巴斯170和宾得i-Scan系列内窥镜,在常规临床条件下采集。数据集包含1,288张带息肉图像(来自164名患者)及对应专家标注的二值掩码,另有1,657张无息肉图像(来自31名患者)。图像涵盖运动模糊、镜面反光、粪便残留、出血和低光照等多种现实挑战。标注经临床专家人工复核以确保质量。为展示基线性能,我们提供基于VGG16、ResNet50、InceptionV3的分类结果,以及采用VGG16、ResNet34、InceptionV4作为主干的UNet变体在分割任务上的表现。实验结果表明,二分类最高准确率达90.8%(VGG16),分割最大Dice分数为0.64(InceptionV4-UNet)。性能低于精心筛选的数据集,反映出真实图像中伪影和质量差异带来的实际困难。

原文摘要 · Abstract (English)

Background and Objective: Colorectal cancer prevention relies on early detection of polyps during colonoscopy. Existing public datasets, such as CVC-ClinicDB and Kvasir-SEG, provide valuable benchmarks but are limited by small sample sizes, curated image selection, or lack of real-world artifacts. There remains a need for datasets that capture the complexity of clinical practice, particularly in resource-constrained settings. Methods: We introduce a dataset, BUET Polyp Dataset (BPD), of colonoscopy images collected using Olympus 170 and Pentax i-Scan series endoscopes under routine clinical conditions. The dataset contains images with corresponding expert-annotated binary masks, reflecting diverse challenges such as motion blur, specular highlights, stool artifacts, blood, and low-light frames. Annotations were manually reviewed by clinical experts to ensure quality. To demonstrate baseline performance, we provide benchmark results for classification using VGG16, ResNet50, and InceptionV3, and for segmentation using UNet variants with VGG16, ResNet34, and InceptionV4 backbones. Results: The dataset comprises 1,288 images with polyps from 164 patients with corresponding ground-truth masks and 1,657 polyp-free images from 31 patients. Benchmarking experiments achieved up to 90.8% accuracy for binary classification (VGG16) and a maximum Dice score of 0.64 with InceptionV4-UNet for segmentation. Performance was lower compared to curated datasets, reflecting the real-world difficulty of images with artifacts and variable quality.

医学影像结肠镜数据集计算机辅助诊断

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。