Oskouei Soroush, Valla Marit, Pedersen André, Smistad Erik, Dale Vibeke Grotnes, Høibø Maren, Wahl Sissel Gyrid Freim, Haugum Mats Dehli, Langø Thomas, Ramnefjell Maria Paula, Akslen Lars Andreas, Kiss Gabriel, Sorger Hanne
Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway.
Clinic of Medicine, Levanger Hospital, Nord-Trøndelag Health Trust, NO-7600 Levanger, Norway.
J Imaging. 2025 May 20;11(5):166. doi: 10.3390/jimaging11050166.
The increased workload in pathology laboratories today means automated tools such as artificial intelligence models can be useful, helping pathologists with their tasks. In this paper, we propose a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier, followed by a lightweight U-Net as a refinement model. Two datasets (Norwegian Lung Cancer Biobank and Haukeland University Lung Cancer cohort) were used to develop the model. The DRU-Net model achieved an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the Dice similarity coefficient from 0.88 to 0.91. Our findings show that selecting image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. A qualitative analysis by pathology experts showed that the DRU-Net model was generally successful in tumor detection. Results in the test set showed some areas of false-positive and false-negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes. In summary, the presented DRU-Net model demonstrated the best performance on the segmentation task, and the proposed augmentation technique proved to improve the results.
如今病理实验室工作量的增加意味着诸如人工智能模型之类的自动化工具会很有用,能够帮助病理学家完成任务。在本文中,我们提出了一种分割模型(DRU-Net),它可以描绘人类非小细胞肺癌,还提出了一种能改善分类结果的增强方法。所提出的模型是截断的预训练DenseNet201和ResNet101V2的融合组合,作为逐块分类器,随后是一个轻量级U-Net作为细化模型。使用了两个数据集(挪威肺癌生物样本库和豪克兰大学肺癌队列)来开发该模型。DRU-Net模型的平均骰子相似系数达到了0.91。所提出的空间增强方法(多镜头畸变)将骰子相似系数从0.88提高到了0.91。我们的研究结果表明,与其他采样方法相比,选择专门包含感兴趣区域的图像块会使逐块分类器得到更好的结果。病理专家的定性分析表明,DRU-Net模型在肿瘤检测方面总体上是成功的。测试集的结果显示,在外围存在一些假阳性和假阴性分割区域,特别是在有炎症和反应性变化的肿瘤中。总之,所展示的DRU-Net模型在分割任务中表现最佳,所提出的增强技术被证明可以改善结果。