Rao Roopa S, Shivanna Divya Biligere, Lakshminarayana Surendra, Mahadevpur Kirti Shankar, Alhazmi Yaser Ali, Bakri Mohammed Mousa H, Alharbi Hazar S, Alzahrani Khalid J, Alsharif Khalaf F, Banjer Hamsa Jameel, Alnfiai Mrim M, Reda Rodolfo, Patil Shankargouda, Testarelli Luca
Department of Oral Pathology and Microbiology, Faculty of Dental Sciences, Ramaiah University of Applied Sciences, Bengaluru 560054, India.
Department of Computer Science and Engineering, Faculty of Engineering and Technology, Ramaiah University of Applied Sciences, Bengaluru 560054, India.
J Pers Med. 2022 Jul 27;12(8):1220. doi: 10.3390/jpm12081220.
(1) Background: Odontogenic keratocysts (OKCs) are enigmatic developmental cysts that deserve special attention due to their heterogeneous appearance in histopathological characteristics and high recurrence rate. Despite several nomenclatures for classification, clinicians still confront challenges in its diagnosis and predicting its recurrence. This paper proposes an ensemble deep-learning-based prognostic and prediction algorithm, for the recurrence of sporadic odontogenic keratocysts, on hematoxylin and eosin stained pathological images of incisional biopsies before treatment. (2) Materials and Methods: In this study, we applied a deep-learning algorithm to an ensemble approach integrated with DenseNet-121, Inception-V3, and Inception-Resnet-V3 classifiers. Around 1660 hematoxylin and eosin stained pathologically annotated digital images of OKC-diagnosed (60) patients were supplied to train and predict recurrent OKCs. (3) Results: The presence of SEH ( = 0.004), an incomplete epithelial lining, ( = 0.023), and a corrugated surface ( = 0.049) were the most significant histological parameters distinguishing recurrent and non-recurrent OKCs. Amongst the classifiers, DenseNet-121 showed 93% accuracy in predicting recurrent OKCs. Furthermore, integrating and training the traditional ensemble model showed an accuracy of 95% and an AUC of 0.9872, with an execution time of 192.9 s. In comparison, our proposed model showed 97% accuracy with an execution time of 154.6 s. (4) Conclusions: Considering the outcome of our novel ensemble model, based on accuracy and execution time, the presented design could be embedded into a computer-aided design system for automation of risk stratification of odontogenic keratocysts.
(1) 背景：牙源性角化囊肿（OKCs）是一种神秘的发育性囊肿，因其组织病理学特征的异质性外观和高复发率而值得特别关注。尽管有几种分类命名法，但临床医生在其诊断和预测复发方面仍面临挑战。本文提出了一种基于深度学习的集成预后和预测算法，用于在治疗前对切开活检苏木精和伊红染色的病理图像上散发性牙源性角化囊肿的复发情况进行预测。(2) 材料与方法：在本研究中，我们将深度学习算法应用于一种集成方法，该方法集成了DenseNet - 121、Inception - V3和Inception - Resnet - V3分类器。提供了大约1660张经病理标注的牙源性角化囊肿诊断患者的苏木精和伊红染色数字图像，用于训练和预测复发性牙源性角化囊肿。(3) 结果：SEH的存在（P = 0.004）、上皮衬里不完整（P = 0.023）和表面呈波纹状（P = 0.049）是区分复发性和非复发性牙源性角化囊肿的最显著组织学参数。在分类器中，DenseNet - 121在预测复发性牙源性角化囊肿方面显示出93%的准确率。此外，整合并训练传统集成模型显示准确率为95%，AUC为0.9872，执行时间为192.9秒。相比之下，我们提出的模型准确率为97%，执行时间为154.6秒。(4) 结论：考虑到我们基于准确率和执行时间的新型集成模型的结果，所提出的设计可以嵌入到计算机辅助设计系统中，用于牙源性角化囊肿风险分层的自动化。
