Abstract：
OBJECTIVE: We aim to develop a YOLOX-based convolutional neural network model for the precise detection of multiple oral lesions, including OLP, OLK, and OSCC, in patient photos.
METHODS: We collected 1419 photos for model development and evaluation, conducting both a comparative analysis to gauge the model\'s capabilities and a multicenter evaluation to assess its diagnostic aid, where 24 participants from 14 centers across the nation were invited. We further integrated this model into a mobile application for rapid and accurate diagnostics.
RESULTS: In the comparative analysis, our model overperformed the senior group (comprising three most experienced experts with more than 10 years of experience) in macro-average recall (85 % vs 77.5 %), precision (87.02 % vs 80.29 %), and specificity (95 % vs 92.5 %). In the multicenter model-assisted diagnosis evaluation, the dental, general, and community hospital groups showed significant improvement when aided by the model, reaching a level comparable to the senior group, with all macro-average metrics closely aligning or even surpassing with those of the latter (recall of 78.67 %, 74.72 %, 83.54 % vs 77.5 %, precision of 80.56 %, 76.42 %, 85.15 % vs 80.29 %, specificity of 92.89 %, 91.57 %, 94.51 % vs 92.5 %).
CONCLUSIONS: Our model exhibited a high proficiency in detection of oral lesions, surpassing the performance of highly experienced specialists. The model can also help specialists and general dentists from dental and community hospitals in diagnosing oral lesions, reaching the level of highly experienced specialists. Moreover, our model\'s integration into a mobile application facilitated swift and precise diagnostic procedures.
METHODS: We collected 1419 photos for model development and evaluation, conducting both a comparative analysis to gauge the model\'s capabilities and a multicenter evaluation to assess its diagnostic aid, where 24 participants from 14 centers across the nation were invited. We further integrated this model into a mobile application for rapid and accurate diagnostics.
RESULTS: In the comparative analysis, our model overperformed the senior group (comprising three most experienced experts with more than 10 years of experience) in macro-average recall (85 % vs 77.5 %), precision (87.02 % vs 80.29 %), and specificity (95 % vs 92.5 %). In the multicenter model-assisted diagnosis evaluation, the dental, general, and community hospital groups showed significant improvement when aided by the model, reaching a level comparable to the senior group, with all macro-average metrics closely aligning or even surpassing with those of the latter (recall of 78.67 %, 74.72 %, 83.54 % vs 77.5 %, precision of 80.56 %, 76.42 %, 85.15 % vs 80.29 %, specificity of 92.89 %, 91.57 %, 94.51 % vs 92.5 %).
CONCLUSIONS: Our model exhibited a high proficiency in detection of oral lesions, surpassing the performance of highly experienced specialists. The model can also help specialists and general dentists from dental and community hospitals in diagnosing oral lesions, reaching the level of highly experienced specialists. Moreover, our model\'s integration into a mobile application facilitated swift and precise diagnostic procedures.
摘要：
目的：我们旨在开发一种基于YOLOX的卷积神经网络模型，用于精确检测多个口腔病变，包括OLP,OLK,OSCC,病人的照片。
方法：我们收集了1419张照片用于模型开发和评估，进行比较分析以衡量模型的能力，并进行多中心评估以评估其诊断辅助，邀请了来自全国14个中心的24名参与者。我们进一步将此模型集成到移动应用程序中，以进行快速准确的诊断。
结果：在比较分析中，我们的模型在宏观平均召回方面表现优于高级组（包括三位经验最丰富的专家，经验超过10年）（85％vs77.5％），精度（87.02%对80.29%），和特异性（95％vs92.5％）。在多中心模型辅助诊断评估中，牙齿,一般,社区医院小组在模型的帮助下表现出显著的改善，达到与高级组相当的水平，所有宏观平均指标都与后者密切相关甚至超过后者(召回率78.67%，74.72%,83.54%vs77.5%，精度为80.56%，76.42%,85.15%vs80.29%，特异性92.89%，91.57%,94.51%vs92.5%）。
结论：我们的模型在检测口腔病变方面表现出很高的熟练程度，超越经验丰富的专家的表现。该模型还可以帮助牙科和社区医院的专家和普通牙医诊断口腔病变，达到经验丰富的专家的水平。此外，我们的模型集成到移动应用程序中，促进了快速和精确的诊断程序。
方法：我们收集了1419张照片用于模型开发和评估，进行比较分析以衡量模型的能力，并进行多中心评估以评估其诊断辅助，邀请了来自全国14个中心的24名参与者。我们进一步将此模型集成到移动应用程序中，以进行快速准确的诊断。
结果：在比较分析中，我们的模型在宏观平均召回方面表现优于高级组（包括三位经验最丰富的专家，经验超过10年）（85％vs77.5％），精度（87.02%对80.29%），和特异性（95％vs92.5％）。在多中心模型辅助诊断评估中，牙齿,一般,社区医院小组在模型的帮助下表现出显著的改善，达到与高级组相当的水平，所有宏观平均指标都与后者密切相关甚至超过后者(召回率78.67%，74.72%,83.54%vs77.5%，精度为80.56%，76.42%,85.15%vs80.29%，特异性92.89%，91.57%,94.51%vs92.5%）。
结论：我们的模型在检测口腔病变方面表现出很高的熟练程度，超越经验丰富的专家的表现。该模型还可以帮助牙科和社区医院的专家和普通牙医诊断口腔病变，达到经验丰富的专家的水平。此外，我们的模型集成到移动应用程序中，促进了快速和精确的诊断程序。
