Poursina Olia, Khayyat Azadeh, Maleki Sara, Amin Ali
Department of Pathology and Laboratory Medicine, Brown University, Providence, Rhode Island, USA.
Department of Pathology and Laboratory Medicine, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
Acta Cytol. 2025;69(2):161-170. doi: 10.1159/000543344. Epub 2025 Jan 2.
Thyroid cytopathology, particularly in cases of atypia of undetermined significance/follicular lesions of undetermined significance (AUS/FLUS), suffers from suboptimal sensitivity and specificity challenges. Recent advancements in digital pathology and artificial intelligence (AI) hold promise for enhancing diagnostic accuracy. This systematic review included studies that focused on diagnostic accuracy in AUS/FLUS cases using AI, whole slide imaging (WSI), or both.
Of the 176 studies from 2000 to 2023, 13 met the inclusion criteria. The datasets range from 145 to 964 WSIs, with an overall number of 494 AUS cases ranging from eight to 254. Five studies used convolutional neural networks (CNNs), and two used artificial neural networks (ANNs). The preparation methods included Romanowsky-stained smears either alone or combined with Papanicolaou-stained or H&E and liquid-based cytology (ThinPrep). The scanner models that were used for scanning the slides varied, including Leica/Aperio, Alyuda Neurointelligence Cupertino, and PANNORAMIC™ Desk Scanner. Classifiers used include Feedforward Neural Networks (FFNNs), Two-Layer Feedforward Neural Networks (2L-FFNNs), Classifier Machine Learning Algorithm (MLA), Visual Geometry Group 11 (VGG11), Gradient Boosting Trees (GBT), Extra Trees Classifier (ETC), YOLOv4, EfficientNetV2-L, Back-Propagation Multi-Layer Perceptron (BP MLP), and MobileNetV2.
The available studies have shown promising results in differentiating between thyroid lesions, including AUS/FLUS. AI can be especially effective in removing sources of errors such as subjective assessment, variation in staining, and algorithms. CNN has been successful in processing WSI data and identifying diagnostic features with minimal human supervision. ANNs excelled in integrating structured clinical data with image-derived features, particularly when paired with WSI, enhancing diagnostic accuracy for indeterminate thyroid lesions.
A combined approach using both CNN and ANN can take advantage of their strengths. While AI and WSI integration shows promise in improving diagnostic accuracy and reducing uncertainty in indeterminate thyroid cytology, challenges such as the lack of standardization need to be addressed.
甲状腺细胞病理学，尤其是意义未明的非典型性病变/意义未明的滤泡性病变（AUS/FLUS），面临着敏感性和特异性欠佳的挑战。数字病理学和人工智能（AI）的最新进展有望提高诊断准确性。本系统评价纳入了聚焦于使用AI、全切片成像（WSI）或两者结合来诊断AUS/FLUS病例准确性的研究。
在2000年至2023年的176项研究中，13项符合纳入标准。数据集包含145至964张全切片图像，AUS病例总数为494例，范围从8例到254例。5项研究使用了卷积神经网络（CNN），2项使用了人工神经网络（ANN）。制备方法包括单独的罗曼诺夫斯基染色涂片，或与巴氏染色、苏木精-伊红染色及液基细胞学（ThinPrep）相结合。用于扫描玻片的扫描仪型号各异，包括徕卡/阿珀里奥、阿卢达神经智能库比蒂诺和全景桌面扫描仪。使用的分类器包括前馈神经网络（FFNN）、两层前馈神经网络（2L-FFNN）、分类器机器学习算法（MLA）、视觉几何组11（VGG11）、梯度提升树（GBT）、极端随机树分类器（ETC）、YOLOv4、高效神经网络V2-L、反向传播多层感知器（BP MLP）和MobileNetV2。
现有研究在鉴别甲状腺病变（包括AUS/FLUS）方面显示出了有前景的结果。AI在消除诸如主观评估、染色差异和算法等误差来源方面可能特别有效。CNN已成功处理全切片图像数据并在极少人工监督的情况下识别诊断特征。ANN在将结构化临床数据与图像衍生特征整合方面表现出色，特别是与全切片图像结合使用时，提高了对不确定甲状腺病变的诊断准确性。
结合使用CNN和ANN的方法可以发挥它们的优势。虽然AI与全切片成像的整合在提高诊断准确性和减少不确定甲状腺细胞学的不确定性方面显示出前景，但仍需解决诸如缺乏标准化等挑战。
