Lisson Catharina Silvia, Lisson Christoph Gerhard, Mezger Marc Fabian, Wolf Daniel, Schmidt Stefan Andreas, Thaiss Wolfgang M, Tausch Eugen, Beer Ambros J, Stilgenbauer Stephan, Beer Meinrad, Goetz Michael
Department of Diagnostic and Interventional Radiology, University Hospital of Ulm, Albert-Einstein-Allee 23, 89081 Ulm, Germany.
Center for Personalized Medicine (ZPM), University Hospital of Ulm, Albert-Einstein-Allee 23, 89081 Ulm, Germany.
Cancers (Basel). 2022 Apr 15;14(8):2008. doi: 10.3390/cancers14082008.
Mantle cell lymphoma (MCL) is a rare lymphoid malignancy with a poor prognosis characterised by frequent relapse and short durations of treatment response. Most patients present with aggressive disease, but there exist indolent subtypes without the need for immediate intervention. The very heterogeneous behaviour of MCL is genetically characterised by the translocation t(11;14)(q13;q32), leading to Cyclin D1 overexpression with distinct clinical and biological characteristics and outcomes. There is still an unfulfilled need for precise MCL prognostication in real-time. Machine learning and deep learning neural networks are rapidly advancing technologies with promising results in numerous fields of application. This study develops and compares the performance of deep learning (DL) algorithms and radiomics-based machine learning (ML) models to predict MCL relapse on baseline CT scans. Five classification algorithms were used, including three deep learning models (3D SEResNet50, 3D DenseNet, and an optimised 3D CNN) and two machine learning models based on K-nearest Neighbor (KNN) and Random Forest (RF). The best performing method, our optimised 3D CNN, predicted MCL relapse with a 70% accuracy, better than the 3D SEResNet50 (62%) and the 3D DenseNet (59%). The second-best performing method was the KNN-based machine learning model (64%) after principal component analysis for improved accuracy. Our optimised CNN developed by ourselves correctly predicted MCL relapse in 70% of the patients on baseline CT imaging. Once prospectively tested in clinical trials with a larger sample size, our proposed 3D deep learning model could facilitate clinical management by precision imaging in MCL.
套细胞淋巴瘤（MCL）是一种罕见的淋巴恶性肿瘤，预后较差，其特征是频繁复发且治疗反应持续时间短。大多数患者表现为侵袭性疾病，但也存在无需立即干预的惰性亚型。MCL的异质性行为在基因上的特征是t(11;14)(q13;q32)易位，导致细胞周期蛋白D1过度表达，具有独特的临床、生物学特征和预后。目前仍需要实时精确的MCL预后评估。机器学习和深度学习神经网络是快速发展的技术，在众多应用领域都取得了有前景的成果。本研究开发并比较了深度学习（DL）算法和基于放射组学的机器学习（ML）模型在基线CT扫描上预测MCL复发的性能。使用了五种分类算法，包括三种深度学习模型（3D SEResNet50、3D DenseNet和优化的3D CNN）以及两种基于K近邻（KNN）和随机森林（RF）的机器学习模型。表现最佳的方法，即我们优化的3D CNN，预测MCL复发的准确率为70%，优于3D SEResNet50（62%）和3D DenseNet（59%）。表现第二好的方法是基于KNN的机器学习模型（64%），经过主成分分析以提高准确率。我们自行开发的优化CNN在基线CT成像上正确预测了70%患者的MCL复发。一旦在更大样本量的临床试验中进行前瞻性测试，我们提出的3D深度学习模型可通过MCL的精确成像促进临床管理。
