For pediatric lymphoma, quantitative FDG PET/CT imaging features such as metabolic tumor volume (MTV) are important for prognosis and risk stratification strategies. However, feature extraction is difficult and time-consuming in cases of high disease burden. The purpose of this study was to fully automate the measurement of PET imaging features in PET/CT images of pediatric lymphoma. 18F-FDG PET/CT baseline images of 100 pediatric Hodgkin lymphoma patients were retrospectively analyzed. Two nuclear medicine physicians identified and segmented FDG avid disease using PET thresholding methods. Both PET and CT images were used as inputs to a three-dimensional patch-based, multi-resolution pathway convolutional neural network architecture, DeepMedic. The model was trained to replicate physician segmentations using an ensemble of three networks trained with 5-fold cross-validation. The maximum SUV (SUVmax), MTV, total lesion glycolysis (TLG), surface-area-to-volume ratio (SA/MTV), and a measure of disease spread (Dmaxpatient) were extracted from the model output. Pearson’s correlation coefficient and relative percent differences were calculated between automated and physician-extracted features. Median Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78–0.91). Automated SUVmax values matched exactly the physician determined values in 81/100 cases, with Pearson’s correlation coefficient (R) of 0.95. Automated MTV was strongly correlated with physician MTV (R = 0.88), though it was slightly underestimated with a median (IQR) relative difference of − 4.3% (− 10.0–5.7%). Agreement of TLG was excellent (R = 0.94), with median (IQR) relative difference of − 0.4% (− 5.2–7.0%). Median relative percent differences were 6.8% (R = 0.91; IQR 1.6–4.3%) for SA/MTV, and 4.5% (R = 0.51; IQR − 7.5–40.9%) for Dmaxpatient, which was the most difficult feature to quantify automatically. An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.

中文翻译：

---

儿科霍奇金淋巴瘤患者FDG PET / CT图像上基线PET成像指标的自动定量

对于小儿淋巴瘤，定量的FDG PET / CT影像学特征（例如代谢肿瘤体积（MTV））对于预后和风险分层策略很重要。然而，在疾病负担高的情况下，特征提取是困难且耗时的。这项研究的目的是使小儿淋巴瘤的PET / CT图像中的PET成像特征的测量完全自动化。回顾性分析了100例小儿霍奇金淋巴瘤患者的18F-FDG PET / CT基线图像。两名核医学医师使用PET阈值分析方法鉴定并细分了FDG狂热疾病。PET和CT图像都用作基于三维补丁的多分辨率路径卷积神经网络体系结构DeepMedic的输入。使用经过5倍交叉验证训练的三个网络的集合，对模型进行了训练以复制医师细分。从模型输出中提取了最大SUV（SUVmax），MTV，总病变糖酵解（TLG），表面积/体积比（SA / MTV）和疾病传播量度（Dmax Patient）。计算了自动特征和医生提取的特征之间的皮尔逊相关系数和相对百分比差异。自动轮廓线和医师轮廓线之间的患者轮廓线中值骰子相似系数为0.86（IQR 0.78–0.91）。自动化的SUVmax值在81/100个病例中与医师确定的值完全匹配，而Pearson的相关系数（R）为0.95。自动化MTV与医师MTV密切相关（R = 0.88），尽管它被低估了，中位数（IQR）相对差异为-4.3％（-10.0-5.7％）。TLG的一致性极好（R = 0.94），中位数（IQR）相对差异为− 0.4％（− 5.2–7.0％）。SA / MTV的中位数相对百分比差异为6.8％（R = 0.91; IQR 1.6–4.3％），Dmax Patient的中位数相对百分比差异为4.5％（R = 0.51; IQR − 7.5–40.9％），这是最难自动量化的特征。一种使用多分辨率途径3D CNN集成的自动化方法能够量化基线FDG PET / CT图像上淋巴瘤的PET成像特征，与参考医师的PET分割非常吻合。MTV和TLG等具有较高PET定量通量的自动化方法在更易于访问的临床和研究应用中显示出了希望。中位数（IQR）相对差异为− 0.4％（− 5.2–7.0％）。SA / MTV的中位数相对百分比差异为6.8％（R = 0.91; IQR 1.6–4.3％），Dmax Patient的中位数相对百分比差异为4.5％（R = 0.51; IQR − 7.5–40.9％），这是最难自动量化的特征。一种使用多分辨率途径3D CNN集成的自动化方法能够量化基线FDG PET / CT图像上淋巴瘤的PET成像特征，与参考医师的PET分割非常吻合。MTV和TLG等具有较高PET定量通量的自动化方法在更易于访问的临床和研究应用中显示出了希望。中位数（IQR）相对差异为− 0.4％（− 5.2–7.0％）。SA / MTV的中位数相对百分比差异为6.8％（R = 0.91; IQR 1.6–4.3％），Dmax Patient的中位数相对百分比差异为4.5％（R = 0.51; IQR − 7.5–40.9％），这是最难自动量化的特征。一种使用多分辨率途径3D CNN集成的自动化方法能够量化基线FDG PET / CT图像上淋巴瘤的PET成像特征，与参考医师的PET分割非常吻合。MTV和TLG等具有较高PET定量通量的自动化方法在更易于访问的临床和研究应用中显示出了希望。这是最难自动量化的功能。一种使用多分辨率途径3D CNN集成的自动化方法能够量化基线FDG PET / CT图像上淋巴瘤的PET成像特征，与参考医师的PET分割非常吻合。MTV和TLG等具有较高PET定量通量的自动化方法在更易于访问的临床和研究应用中显示出了希望。这是最难自动量化的功能。一种使用多分辨率途径3D CNN集成的自动化方法能够量化基线FDG PET / CT图像上淋巴瘤的PET成像特征，与参考医师的PET分割非常吻合。MTV和TLG等具有较高PET定量通量的自动化方法在更易于访问的临床和研究应用中显示出了希望。