基于深度学习的淀粉样蛋白PET图像分类在视觉判定不确定病例中的临床可行性
本研究评估深度学习(DL)在视觉判定不确定的淀粉样蛋白PET病例中用于诊断和预后评估的临床可行性。回顾性纳入430例18F-florbetaben扫描(85例正常认知、233例轻度认知障碍、112例阿尔茨海默病),DL在280张二维PET图像上训练,在70例测试集和54例视觉不确定病例中验证。结果显示DL与定量测量一致性良好(83%,κ=0.59),DL判定的阴性病例随访中认知未见下降,DL有助于视觉不确定淀粉样蛋白扫描的临床诊断和预后评估。
要点
- 视觉判读不确定的54例中,DL判定37例阳性、40例经二轮视觉判读阳性、40例经定量判定阳性。
- DL与定量分类一致性良好(83%,κ=0.59),DL阳性与阴性病例复合SUVR差异有统计学意义(1.47 vs 1.29,P<0.001)。
- 随访期间DL阳性较阴性病例简易精神状态检查评分下降更明显(-4.21 vs -1.74,P=0.023),视觉判读未见此差异。
核心结论
- 在视觉判定不确定的扫描中,DL与定量测量的相关性优于视觉评估,DL判定的阴性病例认知结局未见下降。
- 作者认为DL有助于视觉不确定淀粉样蛋白扫描受试者的临床诊断和预后评估。
研究设计与样本
- 回顾性分析430例18F-florbetaben扫描,包括85例正常认知、233例轻度认知障碍和112例阿尔茨海默病。
- 采用视觉判读、定量测量和DL三种方法评估;DL用280张二维PET图像(80%)训练,其余70例(20%)随机分配为测试集,另设54例视觉不确定病例的临床验证集。
- 在视觉不确定病例中评估视觉判读、定量和DL之间的一致性,并按各方法判定的淀粉样蛋白状态比较临床结局。
主要发现
- 视觉判读阳性175例、不确定54例、阴性201例;复合SUVR截断值为1.32(AUC 0.99)。
- DL在测试集上的受试者水平性能为100%。
- 54例视觉不确定病例中,DL判定37例阳性(Eq(deep+))、二轮视觉评估判定40例阳性、定量判定40例阳性。
- DL与定量分类一致性良好(83%,κ=0.59);Eq(deep+)与Eq(deep-)的复合SUVR分别为1.47(0.13)和1.29(0.10),差异有统计学意义(P<0.001)。
- 随访(平均时长1.76年)期间,DL阳性与阴性病例的简易精神状态检查评分变化分别为-4.21(0.57)和-1.74(0.76),差异有统计学意义(P=0.023);视觉判读未见此差异。
关键数值与推荐
- 复合SUVR截断值为1.32(AUC 0.99)。
- DL与定量分类一致性83%,κ=0.59。
- Eq(deep+)复合SUVR 1.47(0.13) vs Eq(deep-) 1.29(0.10),P<0.001。
- 随访期简易精神状态检查评分变化:Eq(deep+) -4.21(0.57) vs Eq(deep-) -1.74(0.76),P=0.023。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: Although most deep learning (DL) studies have reported excellent classification accuracy, these studies usually target typical Alzheimer's disease (AD) and normal cognition (NC) for which conventional visual assessment performs well. A clinically relevant issue is the selection of high-risk subjects who need active surveillance among equivocal cases. We validated the clinical feasibility of DL compared with visual rating or quantitative measurement for assessing the diagnosis and prognosis of subjects with equivocal amyloid scans. METHODS: 18F-florbetaben scans of 430 cases (85 NC, 233 mild cognitive impairment, and 112 AD) were assessed through visual rating-based, quantification-based, and DL-based methods. DL was trained using 280 two-dimensional PET images (80%) and tested by randomly assigning the remaining (70 cases, 20%) cases and a clinical validation set of 54 equivocal cases. In the equivocal cases, we assessed the agreement among the visual rating, quantification, and DL and compared the clinical outcome according to each modality-based amyloid status. RESULTS: The visual reading was positive in 175 cases, equivocal in 54 cases, and negative in 201 cases. The composite SUVR cutoff value was 1.32 (AUC 0.99). The subject-level performance of DL using the test set was 100%. Among the 54 equivocal cases, 37 cases were classified as positive (Eq(deep+)) by DL, 40 cases were classified by a second-round visual assessment, and 40 cases were classified by quantification. The DL- and quantification-based classifications showed good agreement (83%, κ = 0.59). The composite SUVRs differed between Eq(deep+) (1.47 [0.13]) and Eq(deep-) (1.29 [0.10]; P < 0.001). DL, but not the visual rating, showed a significant difference in the Mini-Mental Status Examination score change during the follow-up between Eq(deep+) (- 4.21 [0.57]) and Eq(deep-) (- 1.74 [0.76]; P = 0.023) (mean duration, 1.76 years). CONCLUSIONS: In visually equivocal scans, DL was more related to quantification than to visual assessment, and the negative cases selected by DL showed no decline in cognitive outcome. DL is useful for clinical diagnosis and prognosis assessment in subjects with visually equivocal amyloid scans.
引用
- Son HJ, Oh JS, Oh M, et al. The clinical feasibility of deep learning-based classification of amyloid PET images in visually equivocal cases. Eur J Nucl Med Mol Imaging. 2019. PMID: 31811343. doi:10.1007/s00259-019-04595-y
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。