文献速递肿瘤 PET/CT神经核医学

基于数据中心人工智能的全自动全身18F-FDG PET/CT图像语义分割

Fully Automated, Semantic Segmentation of Whole-Body 18F-FDG PET/CT Images Based on Data-Centric Artificial Intelligence.
PubMed 文献 · J Nucl Med · 2022-06-30

研究开发了MOOSE软件,利用数据中心人工智能原则对全身PET/CT图像进行多器官自动分割。使用2台PET/CT系统的图像训练,非脑结构用50例CT(40训练/10测试),脑结构用34例18F-FDG PET/MRI脑图像(24训练/10测试)。结果显示92%的非脑组织DSC>0.90,仅29%的脑分区中位DSC>0.90,平均对称表面距离在2mm体素内。结论:该流程可自动分割120种独特组织。

要点

  • MOOSE软件可全自动分割全身18F-FDG PET/CT图像中的120种独特组织。
  • 非脑组织分割精度高:92%的组织DSC>0.90,但肾上腺(0.72)、胰腺(0.85)和膀胱(0.86)较低。
  • 脑分区基于PET图像的分割精度较低:仅29%的脑分区中位DSC>0.90,60%的区域中位DSC为0.80-0.89。

核心结论

  • 所提出的分割流程能够以高准确度自动分割全身18F-FDG PET/CT图像中的120种独特组织。

研究设计与样本

  • 研究使用2台PET/CT系统的图像数据训练MOOSE软件;非脑结构使用50例全身CT图像(30例健康对照,14男16女;20例肿瘤患者,14男6女),其中40例用于训练、10例用于测试。
  • 脑结构使用34例18F-FDG PET/MRI脑图像(10例健康对照,5男5女各成像两次;14例无病灶癫痫患者,7男7女),仅用18F-FDG PET图像训练,其中24例用于训练、10例用于测试。
  • 非脑组织包括13个腹部器官、20个骨段、皮下脂肪、内脏脂肪、腰大肌和骨骼肌;除皮下脂肪、内脏脂肪和骨骼肌采用阈值法半自动分割外,其余由专家小组手动分割,并采用多数投票算法生成参考标准分割。
  • 主要评价指标为Dice相似系数(DSC),次要指标为平均对称表面距离。

主要发现

  • 参考标签与MOOSE生成的器官分割之间重叠极好:92%的非脑组织DSC超过0.90,少数器官DSC较低,如肾上腺(0.72)、胰腺(0.85)和膀胱(0.86)。
  • 基于PET图像获得的脑分区中位DSC较低:仅29%的脑分区中位DSC超过0.90,而60%的区域分割中位DSC为0.80-0.89。
  • 平均对称表面距离分析表明,参考标准与自动分割组织表面(器官、骨骼和脑区)之间的平均距离在图像体素大小(2 mm)以内。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

We introduce multiple-organ objective segmentation (MOOSE) software that generates subject-specific, multiorgan segmentation using data-centric artificial intelligence principles to facilitate high-throughput systemic investigations of the human body via whole-body PET imaging. Methods: Image data from 2 PET/CT systems were used in training MOOSE. For noncerebral structures, 50 whole-body CT images were used, 30 of which were acquired from healthy controls (14 men and 16 women), and 20 datasets were acquired from oncology patients (14 men and 6 women). Noncerebral tissues consisted of 13 abdominal organs, 20 bone segments, subcutaneous fat, visceral fat, psoas muscle, and skeletal muscle. An expert panel manually segmented all noncerebral structures except for subcutaneous fat, visceral fat, and skeletal muscle, which were semiautomatically segmented using thresholding. A majority-voting algorithm was used to generate a reference-standard segmentation. From the 50 CT datasets, 40 were used for training and 10 for testing. For cerebral structures, 34 18F-FDG PET/MRI brain image volumes were used from 10 healthy controls (5 men and 5 women imaged twice) and 14 nonlesional epilepsy patients (7 men and 7 women). Only 18F-FDG PET images were considered for training: 24 and 10 of 34 volumes were used for training and testing, respectively. The Dice score coefficient (DSC) was used as the primary metric, and the average symmetric surface distance as a secondary metric, to evaluate the automated segmentation performance. Results: An excellent overlap between the reference labels and MOOSE-derived organ segmentations was observed: 92% of noncerebral tissues showed DSCs of more than 0.90, whereas a few organs exhibited lower DSCs (e.g., adrenal glands [0.72], pancreas [0.85], and bladder [0.86]). The median DSCs of brain subregions derived from PET images were lower. Only 29% of the brain segments had a median DSC of more than 0.90, whereas segmentation of 60% of regions yielded a median DSC of 0.80-0.89. The results of the average symmetric surface distance analysis demonstrated that the average distance between the reference standard and the automatically segmented tissue surfaces (organs, bones, and brain regions) lies within the size of image voxels (2 mm). Conclusion: The proposed segmentation pipeline allows automatic segmentation of 120 unique tissues from whole-body 18F-FDG PET/CT images with high accuracy.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Shiyam Sundar LK, Yu J, Muzik O, et al. Fully Automated, Semantic Segmentation of Whole-Body 18F-FDG PET/CT Images Based on Data-Centric Artificial Intelligence. J Nucl Med. 2022. PMID: 35772962. doi:10.2967/jnumed.122.264063

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。