■根据2023Bethesda甲状腺细胞病理学报告系统(TBSRTC),深度卷积神经网络(DCNN)模型用于区分被诊断为不确定意义的非典型性(AUS)的甲状腺结节。这项研究的目的是研究ResNeSt在提高细针穿刺(FNA)活检的诊断准确性方面的效率。
■使用碎片图像来训练和测试DCNN模型。训练数据集是根据诊断为甲状腺乳头状癌(PTC)或良性结节的1,330个样本建立的。从173个被诊断为AUS的样本中建立了测试数据集。训练并测试ResNeSt以提供分化。关于AUS样品,使用Wilcoxon检验比较细胞核的特征。
■ResNeSt模型在碎片图像上的准确率为92.49%(160/173),从患者的角度来看,在区分AUS结节中的PTC和良性结节方面的准确率为84.78%(39/46)。ResNeSt模型的敏感性和特异性分别为95.79%和88.46%。ResNeSt与病理结果的κ值为0.847(P<0.001)。关于AUS结节的细胞核,恶性结节的面积和周长都大于良性结节,其中2,340.00(1,769.00,2,807.00)与1,941.00(1,567.50,2,455.75),P<0.001和190.46(167.64,208.46)与171.71(154.95,193.65),P分别<0.001。灰度(黑色为0,白色为255)恶性病变低于良性病变,这是37.52(31.41,46.67)与45.84(31.88,57.36),P<0.001,表明恶性病变的核染色比良性病变更深。
■总之,DCNN模型ResNeSt在鉴别诊断为AUS的甲状腺结节方面显示出巨大潜力.在这些结节中,与良性结节相比,恶性结节显示出更大,更深的细胞核染色。
UNASSIGNED: A deep convolutional neural network (DCNN) model was employed for the differentiation of thyroid nodules diagnosed as atypia of undetermined significance (AUS) according to the 2023 Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). The aim of this study was to investigate the efficiency of ResNeSt in improving the diagnostic accuracy of fine-needle aspiration (FNA) biopsy.
UNASSIGNED: Fragmented images were used to train and test DCNN models. A training dataset was built from 1,330 samples diagnosed as papillary thyroid carcinoma (PTC) or benign nodules, and a test dataset was built from 173 samples diagnosed as AUS. ResNeSt was trained and tested to provide a differentiation. With regard to AUS samples, the characteristics of the cell nuclei were compared using the Wilcoxon test.
UNASSIGNED: The ResNeSt model achieved an accuracy of 92.49% (160/173) on fragmented images and 84.78% (39/46) from a patient wise viewpoint in discrimination of PTC and benign nodules in AUS nodules. The sensitivity and specificity of ResNeSt model were 95.79% and 88.46%. The κ value between ResNeSt and the pathological results was 0.847 (P<0.001). With regard to the cell nuclei of AUS nodules, both area and perimeter of malignant nodules were larger than those of benign ones, which were 2,340.00 (1,769.00, 2,807.00) vs. 1,941.00 (1,567.50, 2,455.75), P<0.001 and 190.46 (167.64, 208.46) vs. 171.71 (154.95, 193.65), P<0.001, respectively. The grayscale (0 for black, 255 for white) of malignant lesions was lower than that of benign ones, which was 37.52 (31.41, 46.67) vs. 45.84 (31.88, 57.36), P <0.001, indicating nuclear staining of malignant lesions were deeper than benign ones.
UNASSIGNED: In summary, the DCNN model ResNeSt showed great potential in discriminating thyroid nodules diagnosed as AUS. Among those nodules, malignant nodules showed larger and more deeply stained nuclei than benign nodules.