Automating Periodontal bone loss measurement via dental landmark localisation.
Automating Periodontal bone loss measurement via dental landmark localisation.
复制标题
通过牙科地标定位自动化牙周骨质损失测量。
DOI：
10.1007/s11548-021-02431-z
复制
发表时间：
2021-07
影响因子：
3
通讯作者：
Stoyanov D
中科院分区：
文献类型：
--
作者：
Danks RP;Bano S;Orishko A;Tan HJ;Moreno Sancho F;D'Aiuto F;Stoyanov D
牙周炎是世界上第六大流行病，牙周骨丢失（PBL）检测对于早期识别和建立正确的诊断和预后至关重要。目前临床医生的影像学评估显示观察者之间存在很大差异。计算机辅助放射学评估可以客观地计算骨丢失，并有助于早期骨丢失检测。了解疾病进展的速度可以指导治疗的选择，并导致牙周治疗的早期开始。我们提出了一个端到端的系统，其中包括一个具有沙漏结构的深度神经网络，用于使用根尖周X光片预测单根，双根和三根牙齿的牙齿标志。然后，我们估计PBL和疾病的严重程度阶段使用预测的地标。我们还介绍了一种新的适应MixUp数据增强，提高了地标定位。我们评估了建议的系统使用交叉验证340 X光片从63例患者的情况下，包含463，115和56单，双和三根牙齿。地标定位实现了88.9%，73.9%和74.4%的正确关键点（PCK），分别和83.3%的所有根形态的组合PCK，优于下一个最好的架构1.7%。与临床医生对完整X线片的视觉评估相比，PBL的平均误差为10.69%，严重程度分级准确度为58%。这模拟了当前观察者间的变化，这意味着不同的数据可以提高准确性。该系统显示出有前途的能力，本地化的标志和估计牙周骨流失的根尖片。与其他文献一致认为，非CEJ（牙骨质-牙釉质交界处）标志最难定位。完善该系统的临床管道将允许其用于干预应用。在线版本包含补充材料，可通过10.1007/s11548-021-02431-z获得。
Periodontitis is the sixth most prevalent disease worldwide and periodontal bone loss (PBL) detection is crucial for its early recognition and establishment of the correct diagnosis and prognosis. Current radiographic assessment by clinicians exhibits substantial interobserver variation. Computer-assisted radiographic assessment can calculate bone loss objectively and aid in early bone loss detection. Understanding the rate of disease progression can guide the choice of treatment and lead to early initiation of periodontal therapy. We propose an end-to-end system that includes a deep neural network with hourglass architecture to predict dental landmarks in single, double and triple rooted teeth using periapical radiographs. We then estimate the PBL and disease severity stage using the predicted landmarks. We also introduce a novel adaptation of MixUp data augmentation that improves the landmark localisation. We evaluate the proposed system using cross-validation on 340 radiographs from 63 patient cases containing 463, 115 and 56 single, double and triple rooted teeth. The landmark localisation achieved Percentage Correct Keypoints (PCK) of 88.9%, 73.9% and 74.4%, respectively, and a combined PCK of 83.3% across all root morphologies, outperforming the next best architecture by 1.7%. When compared to clinicians’ visual evaluations of full radiographs, the average PBL error was 10.69%, with a severity stage accuracy of 58%. This simulates current interobserver variation, implying that diverse data could improve accuracy. The system showed a promising capability to localise landmarks and estimate periodontal bone loss on periapical radiographs. An agreement was found with other literature that non-CEJ (Cemento-Enamel Junction) landmarks are the hardest to localise. Honing the system’s clinical pipeline will allow for its use in intervention applications. The online version contains supplementary material available at 10.1007/s11548-021-02431-z.
登录
查看更多内容
影响因子：
6.7
作者：
KAIMENYI, JT;ASHLEY, FP
通讯作者：
ASHLEY, FP
DOI：
10.1016/j.oooo.2020.08.024
发表时间：
2021-06-04
影响因子：
2.9
作者：
Khan, Hassan Aqeel;Haider, Muhammad Ali;Khurram, Syed Ali
通讯作者：
Khurram, Syed Ali
影响因子：
6.7
作者：
AKESSON, L;HAKANSSON, J;ROHLIN, M
通讯作者：
ROHLIN, M
影响因子：
6.7
作者：
Marini, Lorenzo;Tonetti, Maurizio S.;Pilloni, Andrea
通讯作者：
Pilloni, Andrea
影响因子：
4.6
作者：
Krois, Joachim;Ekert, Thomas;Schwendicke, Falk
通讯作者：
Schwendicke, Falk