Brain Tumor Segmentation Using U-Net

Jyothsna, Paturi; Spandhana, Mamidi Sai Sri Venkata; Jayasri, Rayi; Sandeep, Nirujogi Venkata Sai; Kalam, Swathi; Kumari, Neha; Rao, N. Thirupathi; Bhattacharyya, Debnath

doi:10.1007/978-981-19-6880-8_16

Cited by 1 publication

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Loss function is crucial in the CNN training process, which is primarily used to measure the error of the predicted value that is used to update or optimize the weight of back propagation. Sudre et al [32] suggested that when category imbalance occurs, the following loss functions can be used in network training: weight cross entropy (WCE), generalized dice loss (GDL) and sensitivity-specificity (SS), as shown in Equations ( 7)- (9).…”

Section: Weight Loss Functionmentioning

confidence: 99%

“…and [3,3,9,3], respectively. The data for two-stage Unet is from [28] and the data for TransConver is from [29].…”

Section: Number Of Convnext Blocksmentioning

confidence: 99%

“…To address this problem, the U-Net, a U-shaped network structure proposed in 2015, has been used to achieve ideal results in the segmentation of different targets in medical images [7]. This breakthrough has enabled CNNs to achieve good performance in multimodal brain tumour segmentation [8][9][10][11]. However, these methods are based on 2D image segmentation in which the 3D MRI images are divided into individual 2D slices.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

WD‐UNeXt: Weight loss function and dropout U‐Net with ConvNeXt for automatic segmentation of few shot brain gliomas

Yin

Gao

Gong

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Accurate segmentation of brain gliomas (BG) is a crucial and challenging task for effective treatment planning in BG therapy. This study presents the weight loss function and dropout U‐Net with ConvNeXt block (WD‐UNeXt), which precisely segments BG from few shot MRI. The ConvNeXt block, which comprises the main body of the network, is a structure that can extract more detailed features from images. The weight loss function addresses the issue of category imbalance, thereby enhancing the network's ability to achieve more precise segmentation. The training set of BraTS2019 was used to train the network and apply it to test data. Dice similarity coefficient (DSC), sensitivity (Sen), specificity (Spec) and Hausdorff distance (HD) were used to assess the performance of the method. The experimental results demonstrate that the DSC of whole tumour, tumour core and enhancing tumour reached 0.934, 0.911 and 0.851, respectively. Sen of the sub‐regions achieved 0.922, 0.911 and 0.867. Spec and HD reached 1.000, 1.000, 1.000 and 3.224, 2.990, 2.844, respectively. Compared with the performance of state‐of‐the‐art methods, the DSC and HD of WD‐UNeXt were improved to varying degrees. Therefore, this method has considerable potential for the segmentation of BG.

show abstract

Section: Weight Loss Functionmentioning

confidence: 99%

“…and [3,3,9,3], respectively. The data for two-stage Unet is from [28] and the data for TransConver is from [29].…”

Section: Number Of Convnext Blocksmentioning

confidence: 99%