Deep learning enables automated localization of the metastatic lymph node for thyroid cancer on 131I post-ablation whole-body planar scans
Deep learning enables automated localization of the metastatic lymph node for thyroid cancer on 131I post-ablation whole-body planar scans
复制标题
DOI：
10.1038/s41598-020-64455-w
复制
发表时间：
2020-05-08
影响因子：
4.6
通讯作者：
Ahn, Byeong-Cheol
中科院分区：
文献类型：
--
作者：
Kavitha, MuthuSubash;Lee, Chang-Hee;Ahn, Byeong-Cheol
在I-131消融后全身平面扫描（RxWBSs）上准确检测放射性碘性淋巴结（LN）转移对跟踪甲状腺乳头状癌（PTC）患者转移性淋巴结（mLNs）的进展具有重要意义。然而，严重的噪声伪影和与灰度值相似的相邻组织无法识别的mLN位置使得临床决策极具挑战性。本研究的目的是：(1)利用RxWBSs数据集开发一种多层全连接深度网络（MFDN），用于甲状腺残余组织中mln的自动识别；(2)利用消融后单光子发射计算机断层扫描评估其诊断性能。将聚焦于mLN和残余组织的图像补丁及其像素位置概率的变化作为输入输入网络。通过这种高效的自动方法，我们获得了很高的f1分，并超过了医生的评分(P
The accurate detection of radioactive iodine-avid lymph node (LN) metastasis on I-131 post-ablation whole-body planar scans (RxWBSs) is important in tracking the progression of the metastatic lymph nodes (mLNs) of patients with papillary thyroid cancer (PTC). However, severe noise artifacts and the indiscernible location of the mLN from adjacent tissues with similar gray-scale values make clinical decisions extremely challenging. This study aims (i) to develop a multilayer fully connected deep network (MFDN) for the automatic recognition of mLNs from thyroid remnant tissue by utilizing the dataset of RxWBSs and (ii) to evaluate its diagnostic performance using post-ablation single-photon emission computed tomography. Image patches focused on the mLN and remnant tissues along with their variations of probability of pixel positions were fed as inputs to the network. With this efficient automatic approach, we achieved a high F1-score and outperformed the physician score (P