Biomedical Research Institute, Pusan National University Yangsan Hospital, Yangsan 50612, Korea.
Captos Co., Ltd., Yangsan 50652, Korea.
Medicina (Kaunas). 2022 Mar 7;58(3):397. doi: 10.3390/medicina58030397.
: Capsule endoscopy (CE) for bowel cleanliness evaluation primarily depends on subjective methods. To objectively evaluate bowel cleanliness, we focused on artificial intelligence (AI)-based assessments. We aimed to generate a large segmentation dataset from CE images and verify its quality using a convolutional neural network (CNN)-based algorithm. : Images were extracted and divided into 10 stages according to the clean regions in a CE video. Each image was classified into three classes (clean, dark, and floats/bubbles) or two classes (clean and non-clean). Using this semantic segmentation dataset, a CNN training was performed with 169 videos, and a clean region (visualization scale (VS)) formula was developed. Then, measuring mean intersection over union (mIoU), Dice index, and clean mucosal predictions were performed. The VS performance was tested using 10 videos. : A total of 10,033 frames of the semantic segmentation dataset were constructed from 179 patients. The 3-class and 2-class semantic segmentation's testing performance was 0.7716 mIoU (range: 0.7031-0.8071), 0.8627 Dice index (range: 0.7846-0.8891), and 0.8927 mIoU (range: 0.8562-0.9330), 0.9457 Dice index (range: 0.9225-0.9654), respectively. In addition, the 3-class and 2-class clean mucosal prediction accuracy was 94.4% and 95.7%, respectively. The VS prediction performance for both 3-class and 2-class segmentation was almost identical to the ground truth. : We established a semantic segmentation dataset spanning 10 stages uniformly from 179 patients. The prediction accuracy for clean mucosa was significantly high (above 94%). Our VS equation can approximately measure the region of clean mucosa. These results confirmed our dataset to be ideal for an accurate and quantitative assessment of AI-based bowel cleanliness.
胶囊内镜（CE）用于评估肠道清洁度主要依赖于主观方法。为了客观地评估肠道清洁度，我们专注于基于人工智能（AI）的评估。我们的目标是从 CE 图像中生成一个大型分割数据集，并使用基于卷积神经网络（CNN）的算法验证其质量。
从 CE 视频中清洁区域的角度，提取并将图像分为 10 个阶段。每个图像被分为三类（清洁、黑暗和漂浮物/气泡）或两类（清洁和非清洁）。使用这个语义分割数据集，我们对 169 个视频进行了 CNN 训练，并开发了一个清洁区域（可视化比例（VS））公式。然后，进行了平均交并比（mIoU）、Dice 指数和清洁黏膜预测的测量。使用 10 个视频测试了 VS 的性能。
总共从 179 名患者构建了 10033 帧的语义分割数据集。3 类和 2 类语义分割的测试性能分别为 0.7716 mIoU（范围：0.7031-0.8071）、0.8627 Dice 指数（范围：0.7846-0.8891）和 0.8927 mIoU（范围：0.8562-0.9330）、0.9457 Dice 指数（范围：0.9225-0.9654）。此外，3 类和 2 类清洁黏膜预测准确率分别为 94.4%和 95.7%。3 类和 2 类分割的 VS 预测性能几乎与真实值相同。
我们从 179 名患者中建立了一个均匀跨越 10 个阶段的语义分割数据集。清洁黏膜的预测准确率非常高（超过 94%）。我们的 VS 方程可以近似测量清洁黏膜的区域。这些结果证实了我们的数据集非常适合基于 AI 的肠道清洁度的准确和定量评估。
