Tandel Gopal S, Balestrieri Antonella, Jujaray Tanay, Khanna Narender N, Saba Luca, Suri Jasjit S
Department of Computer Science and Engineering, VNIT, Nagpur, India.
Department of Radiology, A.O.U., Italy.
Comput Biol Med. 2020 Jul;122:103804. doi: 10.1016/j.compbiomed.2020.103804. Epub 2020 May 30.
Brain or central nervous system cancer is the tenth leading cause of death in men and women. Even though brain tumour is not considered as the primary cause of mortality worldwide, 40% of other types of cancer (such as lung or breast cancers) are transformed into brain tumours due to metastasis. Although the biopsy is considered as the gold standard for cancer diagnosis, it poses several challenges such as low sensitivity/specificity, risk during the biopsy procedure, and relatively long waiting times for the biopsy results. Due to an increase in the sheer volume of patients with brain tumours, there is a need for a non-invasive, automatic computer-aided diagnosis tool that can automatically diagnose and estimate the grade of a tumour accurately within a few seconds.
Five clinically relevant multiclass datasets (two-, three-, four-, five-, and six-class) were designed. A transfer-learning-based Artificial Intelligence paradigm using a Convolutional Neural Network (CCN) was proposed and led to higher performance in brain tumour grading/classification using magnetic resonance imaging (MRI) data. We benchmarked the transfer-learning-based CNN model against six different machine learning (ML) classification methods, namely Decision Tree, Linear Discrimination, Naive Bayes, Support Vector Machine, K-nearest neighbour, and Ensemble.
The CNN-based deep learning (DL) model outperforms the six types of ML models when considering five types of multiclass tumour datasets. These five types of data are two-, three-, four-, five, and six-class. The CNN-based AlexNet transfer learning system yielded mean accuracies derived from three kinds of cross-validation protocols (K2, K5, and K10) of 100, 95.97, 96.65, 87.14, and 93.74%, respectively. The mean areas under the curve of DL and ML were found to be 0.99 and 0.87, respectively, for p < 0.0001, and DL showed a 12.12% improvement over ML. Multiclass datasets were benchmarked against the TT protocol (where training and testing samples are the same). The optimal model was validated using a statistical method of a tumour separation index and verified on synthetic data consisting of eight classes.
The transfer-learning-based AI system is useful in multiclass brain tumour grading and shows better performance than ML systems.
脑癌或中枢神经系统癌是男性和女性死亡的第十大主要原因。尽管脑肿瘤在全球范围内不被视为主要死因，但40%的其他类型癌症（如肺癌或乳腺癌）会因转移而转化为脑肿瘤。尽管活检被认为是癌症诊断的金标准，但它存在一些挑战，如敏感性/特异性低、活检过程中的风险以及活检结果的等待时间相对较长。由于脑肿瘤患者数量的急剧增加，需要一种非侵入性的自动计算机辅助诊断工具，能够在几秒钟内自动准确诊断并估计肿瘤的分级。
设计了五个临床相关的多类数据集（两类、三类、四类、五类和六类）。提出了一种基于迁移学习的人工智能范式，使用卷积神经网络（CCN），在使用磁共振成像（MRI）数据进行脑肿瘤分级/分类方面取得了更高的性能。我们将基于迁移学习的CNN模型与六种不同的机器学习（ML）分类方法进行了基准测试，即决策树、线性判别、朴素贝叶斯、支持向量机、K近邻和集成学习。
在考虑五类多类肿瘤数据集时，基于CNN的深度学习（DL）模型优于六种类型的ML模型。这五类数据分别是两类、三类、四类、五类和六类。基于CNN的AlexNet迁移学习系统在三种交叉验证协议（K2、K5和K10）下得出的平均准确率分别为100%、95.97%、96.65%、87.14%和93.74%。对于p < 0.0001，DL和ML的曲线下平均面积分别为0.99和0.87，DL比ML提高了12.12%。多类数据集以TT协议（训练和测试样本相同）为基准。使用肿瘤分离指数的统计方法对最优模型进行了验证，并在由八类组成的合成数据上进行了验证。
基于迁移学习的人工智能系统在多类脑肿瘤分级中有用，并且表现出比ML系统更好的性能。
