卷积神经网络
Sørensen–骰子系数
人工智能
规范化(社会学)
模式识别(心理学)
掷骰子
试验装置
磁共振成像
分割
医学
深度学习
相似性(几何)
数据集
交叉验证
计算机科学
图像分割
统计
放射科
数学
图像(数学)
社会学
人类学
作者
Ying Liang,Karen Lee,Joseph Bovi,Joshua D. Palmer,Paul D. Brown,Vinai Gondi,Wolfgang A. Tomé,Tammie L.S. Benzinger,Minesh P. Mehta,X Allen Li
标识
DOI:10.1016/j.ijrobp.2022.06.081
摘要
Deep learning-based algorithms have been shown to be able to automatically detect and segment brain metastases (BMs) in magnetic resonance imaging, mostly based on single-institutional data sets. This work aimed to investigate the use of deep convolutional neural networks (DCNN) for BM detection and segmentation on a highly heterogeneous multi-institutional data set.A total of 407 patients from 98 institutions were randomly split into 326 patients from 78 institutions for training/validation and 81 patients from 20 institutions for unbiased testing. The data set contained T1-weighted gadolinium and T2-weighted fluid-attenuated inversion recovery magnetic resonance imaging acquired on diverse scanners using different pulse sequences and various acquisition parameters. Several variants of 3-dimensional U-Net based DCNN models were trained and tuned using 5-fold cross validation on the training set. Performances of different models were compared based on Dice similarity coefficient for segmentation and sensitivity and false positive rate (FPR) for detection. The best performing model was evaluated on the test set.A DCNN with an input size of 64 × 64 × 64 and an equal number of 128 kernels for all convolutional layers using instance normalization was identified as the best performing model (Dice similarity coefficient 0.73, sensitivity 0.86, and FPR 1.9) in the 5-fold cross validation experiments. The best performing model demonstrated consistent behavior on the test set (Dice similarity coefficient 0.73, sensitivity 0.91, and FPR 1.7) and successfully detected 7 BMs (out of 327) that were missed during manual delineation. For large BMs with diameters greater than 12 mm, the sensitivity and FPR improved to 0.98 and 0.3, respectively.The DCNN model developed can automatically detect and segment brain metastases with reasonable accuracy, high sensitivity, and low FPR on a multi-institutional data set with nonprespecified and highly variable magnetic resonance imaging sequences. For large BMs, the model achieved clinically relevant results. The model is robust and may be potentially used in real-world situations.
科研通智能强力驱动
Strongly Powered by AbleSci AI