Abdolali Fatemeh, Kapur Jeevesh, Jaremko Jacob L, Noga Michelle, Hareendranathan Abhilash R, Punithakumar Kumaradevan
Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Canada; MEDO.ai, Dual Headquarters at Singapore and Edmonton, Canada.
MEDO.ai, Dual Headquarters at Singapore and Edmonton, Canada.
Comput Biol Med. 2020 Jul;122:103871. doi: 10.1016/j.compbiomed.2020.103871. Epub 2020 Jun 22.
Thyroid cancer is the most common endocrine cancer and its incidence has continuously increased worldwide. In this paper, we focus on the challenging problem of nodule detection from ultrasound scans. In current clinical practice, this task is performed manually, which is tedious, subjective and highly depends on the clinical experience of radiologists. We propose a novel deep neural network architecture with carefully designed loss function regularization, and network hyperparameters to perform nodule detection without complex post-processing refinement steps. The local training and validation datasets consist of 2461 and 820 ultrasound frames acquired from 60 and 20 patients with a high degree of variability, respectively. The core of the proposed method is a deep learning framework based on multi-task model Mask R-CNN. We have developed a loss function with regularization that prioritizes detection over segmentation. Validation was conducted for 821 ultrasound frames from 20 patients. The proposed model can detect various types of thyroid nodules. The experimental results indicate that our proposed method is effective in thyroid nodule detection. Comparisons with the results by Faster R-CNN and conventional Mask R-CNN demonstrate that the proposed model outperforms the prior state-of-the-art detection methods.
甲状腺癌是最常见的内分泌癌，其发病率在全球范围内持续上升。在本文中，我们聚焦于超声扫描中结节检测这一具有挑战性的问题。在当前临床实践中，这项任务是人工完成的，既繁琐又主观，且高度依赖放射科医生的临床经验。我们提出了一种新颖的深度神经网络架构，精心设计了损失函数正则化和网络超参数，无需复杂的后处理细化步骤即可进行结节检测。局部训练和验证数据集分别由从60名和20名患者获取的2461帧和820帧超声图像组成，具有高度的变异性。所提方法的核心是基于多任务模型Mask R-CNN的深度学习框架。我们开发了一种带有正则化的损失函数，将检测置于分割之上进行优先考虑。对来自20名患者的821帧超声图像进行了验证。所提模型能够检测各种类型的甲状腺结节。实验结果表明，我们提出的方法在甲状腺结节检测中是有效的。与Faster R-CNN和传统Mask R-CNN的结果比较表明，所提模型优于先前的最先进检测方法。
