Ali Redha, Li Hailong, Zhang Huixian, Pan Wen, Reeder Scott B, Harris David, Masch William, Aslam Anum, Shanbhogue Krishna, Bernieh Anas, Ranganathan Sarangarajan, Parikh Nehal, Dillman Jonathan R, He Lili
Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
Eur Radiol. 2025 Jan 9. doi: 10.1007/s00330-024-11312-3.
Chronic liver disease (CLD) is a substantial cause of morbidity and mortality worldwide. Liver stiffness, as measured by MR elastography (MRE), is well-accepted as a surrogate marker of liver fibrosis.
To develop and validate deep learning (DL) models for predicting MRE-derived liver stiffness using routine clinical non-contrast abdominal T1-weighted (T1w) and T2-weighted (T2w) data from multiple institutions/system manufacturers in pediatric and adult patients.
We identified pediatric and adult patients with known or suspected CLD from four institutions, who underwent clinical MRI with MRE from 2011 to 2022. We used T1w and T2w data to train DL models for liver stiffness classification. Patients were categorized into two groups for binary classification using liver stiffness thresholds (≥ 2.5 kPa, ≥ 3.0 kPa, ≥ 3.5 kPa, ≥ 4 kPa, or ≥ 5 kPa), reflecting various degrees of liver stiffening.
We identified 4695 MRI examinations from 4295 patients (mean ± SD age, 47.6 ± 18.7 years; 428 (10.0%) pediatric; 2159 males [50.2%]). With a primary liver stiffness threshold of 3.0 kPa, our model correctly classified patients into no/minimal (< 3.0 kPa) vs moderate/severe (≥ 3.0 kPa) liver stiffness with AUROCs of 0.83 (95% CI: 0.82, 0.84) in our internal multi-site cross-validation (CV) experiment, 0.82 (95% CI: 0.80, 0.84) in our temporal hold-out validation experiment, and 0.79 (95% CI: 0.75, 0.81) in our external leave-one-site-out CV experiment. The developed model is publicly available ( https://github.com/almahdir1/Multi-channel-DeepLiverNet2.0.git ).
Our DL models exhibited reasonable diagnostic performance for categorical classification of liver stiffness on a large diverse dataset using T1w and T2w MRI data.
Question Can DL models accurately predict liver stiffness using routine clinical biparametric MRI in pediatric and adult patients with CLD? Findings DeepLiverNet2.0 used biparametric MRI data to classify liver stiffness, achieving AUROCs of 0.83, 0.82, and 0.79 for multi-site CV, hold-out validation, and external CV. Clinical relevance Our DeepLiverNet2.0 AI model can categorically classify the severity of liver stiffening using anatomic biparametric MR images in children and young adults. Model refinements and incorporation of clinical features may decrease the need for MRE.
慢性肝病（CLD）是全球发病和死亡的重要原因。通过磁共振弹性成像（MRE）测量的肝脏硬度，已被广泛认可为肝纤维化的替代标志物。
利用来自多个机构/系统制造商的儿科和成年患者的常规临床非增强腹部T1加权（T1w）和T2加权（T2w）数据，开发并验证用于预测MRE衍生肝脏硬度的深度学习（DL）模型。
我们从四个机构中识别出已知或疑似患有CLD的儿科和成年患者，他们在2011年至2022年期间接受了带有MRE的临床MRI检查。我们使用T1w和T2w数据训练用于肝脏硬度分类的DL模型。使用肝脏硬度阈值（≥2.5kPa、≥3.0kPa、≥3.5kPa、≥4kPa或≥5kPa）将患者分为两组进行二元分类，这些阈值反映了不同程度的肝脏硬化。
我们识别出4295名患者的4695次MRI检查（平均±标准差年龄，47.6±18.7岁；428名（10.0%）儿科患者；2159名男性[50.2%]）。在主要肝脏硬度阈值为3.0kPa的情况下，我们的模型在内部多站点交叉验证（CV）实验中，将患者正确分类为无/轻度（<3.0kPa）与中度/重度（≥3.0kPa）肝脏硬度，曲线下面积（AUROC）为0.83（95%置信区间：0.82，0.84）；在时间留出验证实验中为0.82（95%置信区间：0.80，0.84）；在外部留一站点出交叉验证实验中为0.79（95%置信区间：0.75，0.81）。开发的模型可公开获取（https://github.com/almahdir1/Multi-channel-DeepLiverNet2.0.git）。
我们的DL模型在使用T1w和T2w MRI数据的大型多样数据集上，对肝脏硬度的分类诊断表现出合理的性能。
问题DL模型能否使用常规临床双参数MRI准确预测儿科和成年CLD患者的肝脏硬度？发现DeepLiverNet2.0使用双参数MRI数据对肝脏硬度进行分类，在多站点CV、留出验证和外部CV中分别实现了0.83、0.82和0.79的AUROC。临床意义我们的DeepLiverNet2.0人工智能模型可以使用解剖学双参数MR图像对儿童和年轻人肝脏硬化的严重程度进行分类。模型的改进和临床特征的纳入可能会减少对MRE的需求。
