Pang Lifang, Zhang Zheng, Liu Guobing, Hu Pengcheng, Chen Shuguang, Gu Yushen, Huang Yukun, Zhang Jia, Shi Yuhang, Cao Tuoyu, Zhang Yiqiu, Shi Hongcheng
Department of Nuclear Medicine, Zhongshan Hospital, Fudan University, No. 180, Fenglin Road, Shanghai, 200032, People's Republic of China.
Shanghai Institute of Medical Imaging, Shanghai, 200032, China.
Mol Imaging Biol. 2024 Oct;26(5):802-811. doi: 10.1007/s11307-024-01943-9. Epub 2024 Aug 14.
Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance.
The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers.
Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45 min vs 61 ± 12 min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI).
The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.
开发一种用于PET/CT和PET/MRI的通用病变识别算法，对其进行验证，并探索影响性能的因素。
使用2022年自动PET挑战赛的1014例PET/CT数据集，基于二维和三维分数残差（F-Res）模型训练病变检测模型。为了将其扩展到PET/MRI，利用41组全身MR和相应的CT数据，开发了一个将MR图像转换为合成CT（sCT）的网络。使用38例患者的PET/CT和PET/MRI数据验证通用病变识别算法。使用信噪比（SNR）和对比噪声比（CNR）评估图像质量。从所得病变掩码中计算总病变糖酵解（TLG）、代谢肿瘤体积（MTV）和病变数量。经验丰富的医生对模型输出进行审查和校正，确定真实情况。通过检测准确率、精确率、召回率和骰子系数评估病变检测深度学习模型在不同PET图像上的性能。将检测准确率得分（DAS）小于1的数据用于异常值分析。
与PET/CT相比，PET/MRI扫描的延迟时间明显更长（135±45分钟对61±12分钟），SNR更低（6.17±1.11对9.27±2.77）。然而，CNR值相似（7.37±5.40对5.86±6.69）。PET/MRI检测到更多病变（平均差异为-3.184）。PET/CT和PET/MRI之间的TLG和MTV无显著差异（TLG：119.18±203.15对123.57±151.58，p = 0.41；MTV：36.58±57.00对39.16±48.34，p = 0.33）。共有12例PET/CT和14例PET/MRI数据集纳入异常值分析。异常值分析显示，PET/CT在肠道、输尿管和肌肉中存在异常，而PET/MRI在肠道、睾丸和低示踪剂摄取区域存在异常，输尿管（PET/CT）和肠道/睾丸（PET/MRI）出现假阳性。
深度学习病变检测模型在PET/CT和PET/MRI上均表现良好。SNR、CNR和重建参数对识别准确率的影响最小，但注射后延迟时间有显著影响。
