Department of Information SystemsYarmouk University Irbid 21163 Jordan.
Statistics Online Computational ResourceDepartments of Health Behavior and Biological Sciences and Computational Medicine and BioinformaticsUniversity of Michigan Ann Arbor MI 48109 USA.
IEEE J Transl Eng Health Med. 2022 May 23;10:1800508. doi: 10.1109/JTEHM.2022.3176737. eCollection 2022.
Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have attracted researchers in medical imaging due to their capacity, performance, and potential to assist in accurate diagnosis, prognosis, and medical treatment technologies.
This paper presents a novel framework for segmenting 2D brain tumors in MR images using deep neural networks (DNN) and utilizing data augmentation strategies. The proposed approach (Znet) is based on the idea of skip-connection, encoder-decoder architectures, and data amplification to propagate the intrinsic affinities of a relatively smaller number of expert delineated tumors, e.g., hundreds of patients of the low-grade glioma (LGG), to many thousands of synthetic cases.
Our experimental results showed high values of the mean dice similarity coefficient (dice = 0.96 during model training and dice = 0.92 for the independent testing dataset). Other evaluation measures were also relatively high, e.g., pixel accuracy = 0.996, F1 score = 0.81, and Matthews Correlation Coefficient, MCC = 0.81. The results and visualization of the DNN-derived tumor masks in the testing dataset showcase the ZNet model's capability to localize and auto-segment brain tumors in MR images. This approach can further be generalized to 3D brain volumes, other pathologies, and a wide range of image modalities.
We can confirm the ability of deep learning methods and the proposed Znet framework to detect and segment tumors in MR images. Furthermore, pixel accuracy evaluation may not be a suitable evaluation measure for semantic segmentation in case of class imbalance in MR images segmentation. This is because the dominant class in ground truth images is the background. Therefore, a high value of pixel accuracy can be misleading in some computer vision applications. On the other hand, alternative evaluation metrics, such as dice and IoU (Intersection over Union), are more factual for semantic segmentation.
Artificial intelligence (AI) applications in medicine are advancing swiftly, however, there is a lack of deployed techniques in clinical practice. This research demonstrates a practical example of AI applications in medical imaging, which can be deployed as a tool for auto-segmentation of tumors in MR images.
使用磁共振成像（MR）图像检测和分割脑肿瘤是医学领域具有挑战性和价值的任务。早期诊断和定位脑肿瘤可以挽救生命，并为医生提供及时的选择，以制定有效的治疗计划。深度学习方法因其能力、性能和协助准确诊断、预后和医疗技术的潜力而吸引了医学影像学研究人员。
本文提出了一种使用深度神经网络（DNN）分割磁共振图像中 2D 脑肿瘤的新框架，并利用数据增强策略。所提出的方法（Znet）基于跳过连接、编码器-解码器架构和数据扩增的思想，将相对较少数量的专家勾画肿瘤的内在亲和力传播到成千上万的合成病例中，例如数百名低级别胶质瘤（LGG）患者。
我们的实验结果表明，平均骰子相似系数（dice 在模型训练期间为 0.96，在独立测试数据集上为 0.92）值较高。其他评估指标也相对较高，例如像素准确率为 0.996、F1 得分为 0.81、马修斯相关系数（MCC）为 0.81。测试数据集上 DNN 衍生的肿瘤掩模的结果和可视化展示了 ZNet 模型在磁共振图像中定位和自动分割脑肿瘤的能力。该方法可以进一步推广到 3D 脑体积、其他病变和广泛的图像模态。
我们可以确认深度学习方法和所提出的 Znet 框架在磁共振图像中检测和分割肿瘤的能力。此外，在磁共振图像分割中存在类别不平衡的情况下，像素准确率评估可能不是语义分割的合适评估指标。这是因为在地面真值图像中，占主导地位的类是背景。因此，在某些计算机视觉应用中，高像素准确率可能会产生误导。另一方面，替代评估指标，如骰子和交并比（IoU），对于语义分割更为实际。
人工智能（AI）在医学中的应用正在迅速发展，但在临床实践中缺乏已部署的技术。本研究展示了人工智能在医学成像中的实际应用示例，可作为磁共振图像中肿瘤自动分割的工具。
