Chen Weimin, Han Yong, Awais Ashraf Muhammad, Liu Junhan, Zhang Mu, Su Feng, Huang Zhiguo, Wong Kelvin K L
School of Information and Electronics, Hunan City University, Yiyang, Hunan 413000, China.
School of Design, Quanzhou University of Information Engineering, Quanzhou, Fujian 362000, China.
J Bone Oncol. 2024 Nov 16;49:100649. doi: 10.1016/j.jbo.2024.100649. eCollection 2024 Dec.
Magnetic resonance imaging (MRI) plays a vital role in diagnosing spinal diseases, including different types of spinal tumors. However, conventional segmentation techniques are often labor-intensive and susceptible to variability. This study aims to propose a full-automatic segmentation method for spine MRI images, utilizing a convolutional-deconvolution neural network and patch-based deep learning. The objective is to improve segmentation efficiency, meeting clinical needs for accurate diagnoses and treatment planning.
The methodology involved the utilization of a convolutional neural network to automatically extract deep learning features from spine data. This allowed for the effective representation of anatomical structures. The network was trained to learn discriminative features necessary for accurate segmentation of the spine MRI data. Furthermore, a patch extraction (PE) based deep neural network was developed using a convolutional neural network to restore the feature maps to their original image size. To improve training efficiency, a combination of pre-training and an enhanced stochastic gradient descent method was utilized.
The experimental results highlight the effectiveness of the proposed method for spine image segmentation using Gadolinium-enhanced T1 MRI. This approach not only delivers high accuracy but also offers real-time performance. The innovative model attained impressive metrics, achieving 90.6% precision, 91.1% recall, 93.2% accuracy, 91.3% F1-score, 83.8% Intersection over Union (IoU), and 91.1% Dice Coefficient (DC). These results indicate that the proposed method can accurately segment spine tumors CT images, addressing the limitations of traditional segmentation algorithms.
In conclusion, this study introduces a fully automated segmentation method for spine MRI images utilizing a convolutional neural network, enhanced by the application of the PE-module. By utilizing a patch extraction based neural network (PENN) deep learning techniques, the proposed method effectively addresses the deficiencies of traditional algorithms and achieves accurate and real-time spine MRI image segmentation.
磁共振成像（MRI）在诊断脊柱疾病（包括不同类型的脊柱肿瘤）中起着至关重要的作用。然而，传统的分割技术通常劳动强度大且易受变异性影响。本研究旨在提出一种用于脊柱MRI图像的全自动分割方法，利用卷积-反卷积神经网络和基于图像块的深度学习。目的是提高分割效率，满足临床准确诊断和治疗规划的需求。
该方法涉及利用卷积神经网络从脊柱数据中自动提取深度学习特征。这使得解剖结构能够得到有效表示。对该网络进行训练，以学习准确分割脊柱MRI数据所需的判别特征。此外，使用卷积神经网络开发了一种基于图像块提取（PE）的深度神经网络，将特征图恢复到其原始图像大小。为提高训练效率，采用了预训练和增强随机梯度下降方法相结合的方式。
实验结果突出了所提出的使用钆增强T1 MRI进行脊柱图像分割方法的有效性。这种方法不仅提供了高精度，还具有实时性能。该创新模型获得了令人印象深刻的指标，精度达到90.6%，召回率达到91.1%，准确率达到93.2%，F1分数达到91.3%，交并比（IoU）达到83.8%，骰子系数（DC）达到91.1%。这些结果表明，所提出的方法能够准确分割脊柱肿瘤CT图像，解决了传统分割算法的局限性。
总之，本研究介绍了一种利用卷积神经网络并通过应用PE模块增强的脊柱MRI图像全自动分割方法。通过利用基于图像块提取的神经网络（PENN）深度学习技术，所提出的方法有效解决了传统算法的不足，实现了准确且实时的脊柱MRI图像分割。
