Department of Surgery, Aga Khan University Hospital.
Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi.
J Pak Med Assoc. 2024 Apr;74(4 (Supple-4)):S5-S9. doi: 10.47391/JPMA.AKU-9S-02.
To segment dental implants on PA radiographs using a Deep Learning (DL) algorithm. To compare the performance of the algorithm relative to ground truth determined by the human annotator.
Three hundred PA radiographs were retrieved from the radiographic database and consequently annotated to label implants as well as teeth on the LabelMe annotation software. The dataset was augmented to increase the number of images in the training data and a total of 1294 images were used to train, validate and test the DL algorithm. An untrained U-net was downloaded and trained on the annotated dataset to allow detection of implants using polygons on PA radiographs.
A total of one hundred and thirty unseen images were run through the trained U-net to determine its ability to segment implants on PA radiographs. The performance metrics are as follows: accuracy of 93.8%, precision of 90%, recall of 83%, F-1 score of 86%, Intersection over Union of 86.4% and loss = 21%.
The trained DL algorithm segmented implants on PA radiographs with high performance similar to that of the humans who labelled the images forming the ground truth.
使用深度学习（DL）算法对 PA 射线照片上的牙种植体进行分割。将算法的性能与由人工注释器确定的真实情况进行比较。
从射线照相数据库中检索了 300 张 PA 射线照片，并在 LabelMe 注释软件中对其进行注释，以标记种植体和牙齿。扩充了数据集以增加训练数据中的图像数量，总共使用 1294 张图像来训练、验证和测试 DL 算法。下载并在注释数据集上训练了一个未训练的 U-Net，以允许使用 PA 射线照片上的多边形检测种植体。
总共运行了 130 张未见过的图像，以确定经过训练的 U-Net 对 PA 射线照片上的种植体进行分割的能力。性能指标如下：准确率为 93.8%，精度为 90%，召回率为 83%，F1 得分为 86%，交并比为 86.4%，损失=21%。
经过训练的 DL 算法对 PA 射线照片上的种植体进行分割的性能很高，与标记形成真实情况的图像的人类相似。
