Appati Justice Kwame, Yirenkyi Isaac Adu
Department of Computer Science, University of Ghana, Accra, Ghana.
Heliyon. 2024 Sep 27;10(19):e38612. doi: 10.1016/j.heliyon.2024.e38612. eCollection 2024 Oct 15.
Accurate segmentation of kidney tumors in CT images is very important in the diagnosis of kidney cancer. Automatic semantic segmentation of the kidney tumor has shown promising results towards developing advance surgical planning techniques in the treatment of kidney tumor. However, the relatively small size of kidney tumor volume in comparison to the overall kidney volume, and its irregular distribution and shape makes it difficult to accurately segment the tumors. In addressing this issue, we proposed a coarse to fine segmentation which leverages on transfer learning using SE-ResNeXt model for the initial segmentation and ResNet and Feature Pyramid Network for the final segmentation. The processes are related and the output of the initial results was used for the final training. We trained and evaluated our method on the KITS19 dataset and achieved a dice score of 0.7388 and Jaccard score 0.7321 for the final segmentation demonstrating promising results when compared to other approaches.
在肾癌诊断中，CT图像中肾脏肿瘤的准确分割非常重要。肾脏肿瘤的自动语义分割在开发先进的肾脏肿瘤治疗手术规划技术方面已显示出有前景的结果。然而，与整个肾脏体积相比，肾脏肿瘤体积相对较小，且其分布和形状不规则，这使得准确分割肿瘤变得困难。为了解决这个问题，我们提出了一种从粗到细的分割方法，该方法利用迁移学习，使用SE-ResNeXt模型进行初始分割，使用ResNet和特征金字塔网络进行最终分割。这些过程是相关的，初始结果的输出用于最终训练。我们在KITS19数据集上对我们的方法进行了训练和评估，最终分割的骰子系数得分为0.7388，杰卡德系数得分为0.7321，与其他方法相比显示出有前景的结果。
