Abstract：
OBJECTIVE: To develop and validate a modified deep learning (DL) model based on nnU-net for classifying and segmenting five-class jaw lesions using cone-beam computed tomography (CBCT).
METHODS: A total of 368 CBCT scans (37 168 slices) were used to train a multi-class segmentation model. The data underwent manual annotation by two oral and maxillofacial surgeons (OMSs) to serve as ground truth. Sensitivity, specificity, precision, F1-score, and accuracy were used to evaluate the classification ability of the model and doctors, with or without artificial intelligence assistance. The dice similarity coefficient (DSC), average symmetric surface distance (ASSD) and segmentation time were used to evaluate the segmentation effect of the model.
RESULTS: The model achieved the dual task of classifying and segmenting jaw lesions in CBCT. For classification, the sensitivity, specificity, precision, and accuracy of the model were 0.871, 0.974, 0.874 and 0.891, respectively, surpassing oral and maxillofacial radiologists (OMFRs) and OMSs, approaching the specialist. With the model\'s assistance, the classification performance of OMFRs and OMSs improved, particularly for odontogenic keratocyst (OKC) and ameloblastoma (AM), with F1-score improvements ranging from 6.2% to 12.7%. For segmentation, the DSC was 87.2% and the ASSD was 1.359 mm. The model\'s average segmentation time was 40 ± 9.9 s, contrasting with 25 ± 7.2 min for OMSs.
CONCLUSIONS: The proposed DL model accurately and efficiently classified and segmented five classes of jaw lesions using CBCT. In addition, it could assist doctors in improving classification accuracy and segmentation efficiency, particularly in distinguishing confusing lesions (e.g., AM and OKC).
METHODS: A total of 368 CBCT scans (37 168 slices) were used to train a multi-class segmentation model. The data underwent manual annotation by two oral and maxillofacial surgeons (OMSs) to serve as ground truth. Sensitivity, specificity, precision, F1-score, and accuracy were used to evaluate the classification ability of the model and doctors, with or without artificial intelligence assistance. The dice similarity coefficient (DSC), average symmetric surface distance (ASSD) and segmentation time were used to evaluate the segmentation effect of the model.
RESULTS: The model achieved the dual task of classifying and segmenting jaw lesions in CBCT. For classification, the sensitivity, specificity, precision, and accuracy of the model were 0.871, 0.974, 0.874 and 0.891, respectively, surpassing oral and maxillofacial radiologists (OMFRs) and OMSs, approaching the specialist. With the model\'s assistance, the classification performance of OMFRs and OMSs improved, particularly for odontogenic keratocyst (OKC) and ameloblastoma (AM), with F1-score improvements ranging from 6.2% to 12.7%. For segmentation, the DSC was 87.2% and the ASSD was 1.359 mm. The model\'s average segmentation time was 40 ± 9.9 s, contrasting with 25 ± 7.2 min for OMSs.
CONCLUSIONS: The proposed DL model accurately and efficiently classified and segmented five classes of jaw lesions using CBCT. In addition, it could assist doctors in improving classification accuracy and segmentation efficiency, particularly in distinguishing confusing lesions (e.g., AM and OKC).
摘要：
目的：开发并验证基于nnU-net的改进的深度学习（DL）模型，用于使用锥形束计算机断层扫描（CBCT）对五类颌骨病变进行分类和分割。
方法：总共使用368次CBCT扫描（37168个切片）来训练多类分割模型。数据经过两名口腔颌面外科医生（OMS）的手动注释，以作为地面实况。灵敏度,特异性，精度,F1分数，和准确性用于评估模型和医生的分类能力，有或没有人工智能援助。骰子相似系数(DSC)，平均对称表面距离(ASSD)和分割时间用于评价模型的分割效果。
结果：该模型实现了CBCT中颌骨病变分类和分割的双重任务。对于分类，灵敏度,特异性，精度,模型的准确度分别为0.871、0.974、0.874和0.891，超越口腔颌面放射科医师（OMFR）和OMS，接近专家。在模型的帮助下，OMFR和OMS的分类性能得到了提高，特别是牙源性角化囊肿（OKC）和成釉细胞瘤（AM），F1分数改善从6.2%到12.7%不等。对于分割，DSC为87.2%,ASSD为1.359mm。模型的平均分割时间为40±9.9s，与OMS的25±7.2分钟形成对比。
结论：所提出的DL模型使用CBCT准确有效地对五类颌骨病变进行分类和分割。此外,它可以帮助医生提高分类精度和分割效率，特别是在区分令人困惑的病变时(例如，AM和OKC）。
方法：总共使用368次CBCT扫描（37168个切片）来训练多类分割模型。数据经过两名口腔颌面外科医生（OMS）的手动注释，以作为地面实况。灵敏度,特异性，精度,F1分数，和准确性用于评估模型和医生的分类能力，有或没有人工智能援助。骰子相似系数(DSC)，平均对称表面距离(ASSD)和分割时间用于评价模型的分割效果。
结果：该模型实现了CBCT中颌骨病变分类和分割的双重任务。对于分类，灵敏度,特异性，精度,模型的准确度分别为0.871、0.974、0.874和0.891，超越口腔颌面放射科医师（OMFR）和OMS，接近专家。在模型的帮助下，OMFR和OMS的分类性能得到了提高，特别是牙源性角化囊肿（OKC）和成釉细胞瘤（AM），F1分数改善从6.2%到12.7%不等。对于分割，DSC为87.2%,ASSD为1.359mm。模型的平均分割时间为40±9.9s，与OMS的25±7.2分钟形成对比。
结论：所提出的DL模型使用CBCT准确有效地对五类颌骨病变进行分类和分割。此外,它可以帮助医生提高分类精度和分割效率，特别是在区分令人困惑的病变时(例如，AM和OKC）。
