PDF(Pubmed)
Abstract：
BACKGROUND: Bladder cancer (BC) segmentation on MRI images is the first step to determining the presence of muscular invasion. This study aimed to assess the tumor segmentation performance of three deep learning (DL) models on multi-parametric MRI (mp-MRI) images.
METHODS: We studied 53 patients with bladder cancer. Bladder tumors were segmented on each slice of T2-weighted (T2WI), diffusion-weighted imaging/apparent diffusion coefficient (DWI/ADC), and T1-weighted contrast-enhanced (T1WI) images acquired at a 3Tesla MRI scanner. We trained Unet, MAnet, and PSPnet using three loss functions: cross-entropy (CE), dice similarity coefficient loss (DSC), and focal loss (FL). We evaluated the model performances using DSC, Hausdorff distance (HD), and expected calibration error (ECE).
RESULTS: The MAnet algorithm with the CE+DSC loss function gave the highest DSC values on the ADC, T2WI, and T1WI images. PSPnet with CE+DSC obtained the smallest HDs on the ADC, T2WI, and T1WI images. The segmentation accuracy overall was better on the ADC and T1WI than on the T2WI. The ECEs were the smallest for PSPnet with FL on the ADC images, while they were the smallest for MAnet with CE+DSC on the T2WI and T1WI.
CONCLUSIONS: Compared to Unet, MAnet and PSPnet with a hybrid CE+DSC loss function displayed better performances in BC segmentation depending on the choice of the evaluation metric.
METHODS: We studied 53 patients with bladder cancer. Bladder tumors were segmented on each slice of T2-weighted (T2WI), diffusion-weighted imaging/apparent diffusion coefficient (DWI/ADC), and T1-weighted contrast-enhanced (T1WI) images acquired at a 3Tesla MRI scanner. We trained Unet, MAnet, and PSPnet using three loss functions: cross-entropy (CE), dice similarity coefficient loss (DSC), and focal loss (FL). We evaluated the model performances using DSC, Hausdorff distance (HD), and expected calibration error (ECE).
RESULTS: The MAnet algorithm with the CE+DSC loss function gave the highest DSC values on the ADC, T2WI, and T1WI images. PSPnet with CE+DSC obtained the smallest HDs on the ADC, T2WI, and T1WI images. The segmentation accuracy overall was better on the ADC and T1WI than on the T2WI. The ECEs were the smallest for PSPnet with FL on the ADC images, while they were the smallest for MAnet with CE+DSC on the T2WI and T1WI.
CONCLUSIONS: Compared to Unet, MAnet and PSPnet with a hybrid CE+DSC loss function displayed better performances in BC segmentation depending on the choice of the evaluation metric.
摘要：
背景：MRI图像上的膀胱癌（BC）分割是确定是否存在肌肉浸润的第一步。本研究旨在评估三种深度学习（DL）模型在多参数MRI（mp-MRI）图像上的肿瘤分割性能。
方法：我们研究了53例膀胱癌患者。膀胱肿瘤在T2加权（T2WI）的每个切片上进行分割，扩散加权成像/表观扩散系数（DWI/ADC），和在3TeslaMRI扫描仪上采集的T1加权对比增强（T1WI）图像。我们训练了Unet,MAnet,和PSPnet使用三个损失函数：交叉熵(CE)，骰子相似系数损失(DSC)，和病灶丢失（FL）。我们使用DSC评估了模型性能，Hausdorff距离(HD),和预期校准误差(ECE)。
结果：具有CE+DSC损失函数的MAnet算法在ADC上给出了最高的DSC值，T2WI,和T1WI图像。PSPnet与CE+DSC在ADC上获得了最小的HDs，T2WI,和T1WI图像。总体上，ADC和T1WI的分割精度优于T2WI。在ADC图像上，带FL的PSPnet的ECE最小，而在T2WI和T1WI上使用CE+DSC的MAnet是最小的。
结论：与Unet相比，根据评估指标的选择，具有混合CEDSC损失函数的MAnet和PSPnet在BC分割中显示出更好的性能。
方法：我们研究了53例膀胱癌患者。膀胱肿瘤在T2加权（T2WI）的每个切片上进行分割，扩散加权成像/表观扩散系数（DWI/ADC），和在3TeslaMRI扫描仪上采集的T1加权对比增强（T1WI）图像。我们训练了Unet,MAnet,和PSPnet使用三个损失函数：交叉熵(CE)，骰子相似系数损失(DSC)，和病灶丢失（FL）。我们使用DSC评估了模型性能，Hausdorff距离(HD),和预期校准误差(ECE)。
结果：具有CE+DSC损失函数的MAnet算法在ADC上给出了最高的DSC值，T2WI,和T1WI图像。PSPnet与CE+DSC在ADC上获得了最小的HDs，T2WI,和T1WI图像。总体上，ADC和T1WI的分割精度优于T2WI。在ADC图像上，带FL的PSPnet的ECE最小，而在T2WI和T1WI上使用CE+DSC的MAnet是最小的。
结论：与Unet相比，根据评估指标的选择，具有混合CEDSC损失函数的MAnet和PSPnet在BC分割中显示出更好的性能。
