Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging

Abstract

Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis. Methods: This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting. Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively. Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors.

Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art

“…Their robustness, however, continues to fall behind expert performance [ 21 ]. Interestingly, single U-Net [ 83 ] based models [ 143 ] continue to perform well, corroborating the assertion that “a well-trained U-net is difficult to surpass” [ 144 ]. As a result, concerns such as properly analyzing 3D slice data and compressing the model as the number of network parameters rises, must be addressed in the future.…”

HSN: Hybrid Segmentation Network for Small Cell Lung Cancer Segmentation

“…We employed generalized Dice loss (GDL) function to address the class imbalance problem in CT images. Since many works have demonstrated Dice loss can achieve more robust results than Cross Entropy loss [19], [36], we focus on the difference in performance between Dice loss and generalized Dice loss. The Dice loss is defined as:…”

TMD-Unet: Triple-Unet with Multi-Scale Input Features and Dense Skip Connection for Medical Image Segmentation

“…To accomplish this goal, deep learning researchers have proposed an encoder–decoder structure such as fully convolution network (FCN) [ 5 ], Deeplab [ 6 ], Unet [ 7 ], etc. These network models are applicable for medical image segmentation applications such as liver and liver tumor [ 8 , 9 , 10 ], brain and brain tumor [ 11 , 12 , 13 ], lung and lung nodule [ 14 , 15 ], nuclei [ 16 , 17 ], polyp [ 18 , 19 ], skin lesion [ 20 , 21 , 22 ], etc. Many studies have proposed these models for many different types of medical imaging [ 23 , 24 , 25 , 26 , 27 ].…”