Al-Battal Abdullah F, Tang Van Ha, Tran Quang Duc, Truong Steven Q H, Phan Chien, Nguyen Truong Q, An Cheolhong
Electrical and Computer Engineering Department, UC San Diego, La Jolla, CA, USA; Electrical Engineering Department, King Fahd University of Petroleum and Minerals, Saudi Arabia.
Vinbrain JSC, Hanoi, Viet Nam.
Comput Biol Med. 2025 Mar;186:109602. doi: 10.1016/j.compbiomed.2024.109602. Epub 2024 Dec 31.
Automated segmentation and detection of tumors in CT scans of the liver and kidney have a significant potential in assisting clinicians with cancer diagnosis and treatment planning. However, current approaches, including state-of-the-art deep learning ones, still face many challenges. Many tumors are not detected by these approaches when tested on public datasets for tumor detection and segmentation such as the Kidney Tumor Segmentation Challenge (KiTS) and the Liver tumor segmentation challenge (LiTS). False negative rates by lesion as high as 50% are commonly observed, and this rate is even higher for smaller lesions as they exhibit a high degree of variability (heterogeneity) among themselves. Additionally, in numerous instances, these lesions share similarities (homogeneity) in intensity, size, and shape with other anatomical structures as well as blurriness and blending with surrounding tissue. To improve the detection and segmentation accuracy of lesions in CT scans of the liver and kidney, we propose a selective ensemble approach that uses the predictions of two models to select the best possible mask for lesions. Both models are based on the UNet architecture and use the ConvNext convolutional block in both the encoder and decoder. The first model is trained on lesion segmentation regardless of size, while the second is designed and fine-tuned to segment and detect small lesions. Once the segmentation mask is predicted from both models we extract intensity-based features from within the lesion, contrast them with features from surrounding tissue, and select the mask that maximizes features' separation between the two. We test our approach on three different datasets for lesion segmentation in the kidney and liver. Our proposed approach achieves an improved detection and segmentation performance and is able to increase the number of lesions detected in all three datasets when compared to current state-of-the-art models.
在肝脏和肾脏的CT扫描中自动分割和检测肿瘤，在协助临床医生进行癌症诊断和治疗规划方面具有巨大潜力。然而，目前的方法，包括最先进的深度学习方法，仍然面临许多挑战。在用于肿瘤检测和分割的公共数据集（如肾脏肿瘤分割挑战赛（KiTS）和肝脏肿瘤分割挑战赛（LiTS））上进行测试时，这些方法无法检测出许多肿瘤。通常观察到按病变计算的假阴性率高达50%，对于较小的病变，这一比率甚至更高，因为它们自身表现出高度的变异性（异质性）。此外，在许多情况下，这些病变在强度、大小和形状上与其他解剖结构相似（同质性），并且与周围组织存在模糊和融合。为了提高肝脏和肾脏CT扫描中病变的检测和分割准确性，我们提出了一种选择性集成方法，该方法使用两个模型的预测结果来选择最佳的病变掩码。这两个模型均基于UNet架构，并且在编码器和解码器中都使用了ConvNext卷积块。第一个模型在不考虑大小的情况下进行病变分割训练，而第二个模型则专门设计并微调以分割和检测小病变。一旦从两个模型中预测出分割掩码，我们就从病变内部提取基于强度的特征，将其与周围组织的特征进行对比，然后选择能使两者之间特征分离最大化的掩码。我们在三个不同的数据集上测试了我们的方法，用于肾脏和肝脏的病变分割。与当前的最先进模型相比，我们提出的方法实现了更好的检测和分割性能，并且能够增加在所有三个数据集中检测到的病变数量。
