El-Khatib Mohamed, Popescu Dan, Teodor Oana, Ichim Loretta
National University of Science and Technology POLITEHNICA Bucharest, Bucharest, Romania.
"Ștefan S. Nicolau" Institute of Virology, Bucharest, Romania.
Heliyon. 2024 Sep 3;10(17):e37386. doi: 10.1016/j.heliyon.2024.e37386. eCollection 2024 Sep 15.
Ovarian tumors, especially malignant ones, represent a global concern, with increased prevalence in recent years. More accurate medical support systems are urgently needed to support medical staff in obtaining an efficient ovarian tumors diagnosis since detection in early stages could lead to immediately applying appropriate treatment, and implicitly improving the survival rate. The current paper aims to demonstrate that more accurate systems could be designed by combining different convolutional neural networks using different custom combination approaches and by selecting the appropriate networks to be involved in the ensemble model to achieve the best performance metrics. It is essential to understand if combining all experimented networks or only the best-performing ones could always lead to the most effective results or not. The current paper is structured in three main phases. The first step is to propose the individual networks involved in the experiments. Five DeepLab-V3+ networks with different encoders (ResNet-18, ResNet-50, MobileNet-V2, InceptionResNet-V2, and Xception) were used. In the second step, the paper proposes a custom algorithm to combine multiple individual semantic segmentation networks, while the last step describes the iterative selection approach for selecting all individual networks to be combined so that the most accurate ensemble is obtained. The system performing semantic segmentation for different types of ovarian tumors, covering both benign and malignant ones, achieved 91.18 % Intersection over union (IoU), thus overperforming all individual networks. The proposed method could be extended so that more powerful deep learning models could be used.
卵巢肿瘤，尤其是恶性肿瘤，是一个全球性问题，近年来其发病率呈上升趋势。迫切需要更精确的医疗支持系统，以协助医护人员进行高效的卵巢肿瘤诊断，因为早期检测能够立即采取适当治疗，从而提高生存率。本文旨在证明，通过使用不同的自定义组合方法来组合不同的卷积神经网络，并选择合适的网络参与集成模型，可以设计出更精确的系统，以实现最佳性能指标。了解组合所有实验网络还是仅组合性能最佳的网络是否总能产生最有效的结果至关重要。本文分为三个主要阶段。第一步是提出参与实验的各个网络。使用了五个带有不同编码器的DeepLab-V3+网络（ResNet-18、ResNet-50、MobileNet-V2、InceptionResNet-V2和Xception）。第二步，本文提出一种自定义算法，用于组合多个单独的语义分割网络，而最后一步描述了用于选择所有要组合的单独网络的迭代选择方法，以便获得最精确的集成。该系统对不同类型的卵巢肿瘤（包括良性和恶性肿瘤）进行语义分割，平均交并比（IoU）达到91.18%，从而超越了所有单独的网络。所提出的方法可以扩展，以便能够使用更强大的深度学习模型。
