Fahmida Haque, Jorge A Carrasquillo, Evrim B Turkbey, Esther Mena, Liza Lindenberg, Philip C Eclarinal, Naris Nilubol, Peter L Choyke, Charalampos S Floudas, Frank I Lin, Baris Turkbey, Stephanie A Harmon
{"title":"An automated pheochromocytoma and paraganglioma lesion segmentation AI-model at whole-body <sup>68</sup>Ga- DOTATATE PET/CT.","authors":"Fahmida Haque, Jorge A Carrasquillo, Evrim B Turkbey, Esther Mena, Liza Lindenberg, Philip C Eclarinal, Naris Nilubol, Peter L Choyke, Charalampos S Floudas, Frank I Lin, Baris Turkbey, Stephanie A Harmon","doi":"10.1186/s13550-024-01168-5","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Somatostatin receptor (SSR) targeting radiotracer <sup>68</sup>Ga-DOTATATE is used for Positron Emission Tomography (PET)/Computed Tomography (CT) imaging to assess patients with Pheochromocytoma and paraganglioma (PPGL), rare types of Neuroendocrine tumor (NET) which can metastasize thereby becoming difficult to quantify. The goal of this study is to develop an artificial intelligence (AI) model for automated lesion segmentation on whole-body 3D DOTATATE-PET/CT and to automate the tumor burden calculation. 132 <sup>68</sup>Ga-DOTATATE PET/CT scans from 38 patients with metastatic and inoperable PPGL, were split into 70, and 62 scans, from 20, and 18 patients for training, and test sets, respectively. The training set was further divided into patient-stratified 5 folds for cross-validation. 3D-full resolution nnUNet configuration was trained with 5-fold cross-validation. The model's detection performance was evaluated at both scan and lesion levels for the PPGL test set and two other clinical cohorts with NET (n = 9) and olfactory neuroblastoma (ONB, n = 5). Additionally, quantitative statistical analysis of PET parameters including SUVmax, total lesion uptake (TLU), and total tumor volume (TTV), was conducted.</p><p><strong>Results: </strong>The nnUNet AI model achieved an average 5-fold validation dice similarity coefficient of 0.84 at the scan level. The model achieved dice similarity coefficients (DSC) of 0.88, 0.6, and 0.67 at the scan level, the sensitivity of 86%, 61.13%, and 61.64%, and a positive predictive value of 89%, 74%, and 86.54% at the lesion level for the PPGL test, NET and ONB cohorts, respectively. For PPGL cohorts, smaller lesions with low uptake were missed by the AI model (p < 0.001). Anatomical region-based failure analysis showed most of the false negative and false positive lesions within the liver for all the cohorts, mainly due to the high physiologic liver background activity and image noise on <sup>68</sup>Ga- DOTATATE PET scans.</p><p><strong>Conclusions: </strong>The developed deep learning-based AI model showed reliable performance for automated segmentation of metastatic PPGL lesions on whole-body <sup>68</sup>Ga-DOTATATE-PET/CT images, which may be beneficial for tumor burden estimation for objective evaluation during therapy follow-up. https://www.</p><p><strong>Clinicaltrials: </strong>gov/study/NCT03206060 , https://www.</p><p><strong>Clinicaltrials: </strong>gov/study/NCT04086485 , https://www.</p><p><strong>Clinicaltrials: </strong>gov/study/NCT05012098 .</p>","PeriodicalId":11611,"journal":{"name":"EJNMMI Research","volume":"14 1","pages":"103"},"PeriodicalIF":3.1000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11538206/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EJNMMI Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13550-024-01168-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Somatostatin receptor (SSR) targeting radiotracer 68Ga-DOTATATE is used for Positron Emission Tomography (PET)/Computed Tomography (CT) imaging to assess patients with Pheochromocytoma and paraganglioma (PPGL), rare types of Neuroendocrine tumor (NET) which can metastasize thereby becoming difficult to quantify. The goal of this study is to develop an artificial intelligence (AI) model for automated lesion segmentation on whole-body 3D DOTATATE-PET/CT and to automate the tumor burden calculation. 132 68Ga-DOTATATE PET/CT scans from 38 patients with metastatic and inoperable PPGL, were split into 70, and 62 scans, from 20, and 18 patients for training, and test sets, respectively. The training set was further divided into patient-stratified 5 folds for cross-validation. 3D-full resolution nnUNet configuration was trained with 5-fold cross-validation. The model's detection performance was evaluated at both scan and lesion levels for the PPGL test set and two other clinical cohorts with NET (n = 9) and olfactory neuroblastoma (ONB, n = 5). Additionally, quantitative statistical analysis of PET parameters including SUVmax, total lesion uptake (TLU), and total tumor volume (TTV), was conducted.
Results: The nnUNet AI model achieved an average 5-fold validation dice similarity coefficient of 0.84 at the scan level. The model achieved dice similarity coefficients (DSC) of 0.88, 0.6, and 0.67 at the scan level, the sensitivity of 86%, 61.13%, and 61.64%, and a positive predictive value of 89%, 74%, and 86.54% at the lesion level for the PPGL test, NET and ONB cohorts, respectively. For PPGL cohorts, smaller lesions with low uptake were missed by the AI model (p < 0.001). Anatomical region-based failure analysis showed most of the false negative and false positive lesions within the liver for all the cohorts, mainly due to the high physiologic liver background activity and image noise on 68Ga- DOTATATE PET scans.
Conclusions: The developed deep learning-based AI model showed reliable performance for automated segmentation of metastatic PPGL lesions on whole-body 68Ga-DOTATATE-PET/CT images, which may be beneficial for tumor burden estimation for objective evaluation during therapy follow-up. https://www.
EJNMMI ResearchRADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING&nb-
CiteScore
5.90
自引率
3.10%
发文量
72
审稿时长
13 weeks
期刊介绍：
EJNMMI Research publishes new basic, translational and clinical research in the field of nuclear medicine and molecular imaging. Regular features include original research articles, rapid communication of preliminary data on innovative research, interesting case reports, editorials, and letters to the editor. Educational articles on basic sciences, fundamental aspects and controversy related to pre-clinical and clinical research or ethical aspects of research are also welcome. Timely reviews provide updates on current applications, issues in imaging research and translational aspects of nuclear medicine and molecular imaging technologies.
The main emphasis is placed on the development of targeted imaging with radiopharmaceuticals within the broader context of molecular probes to enhance understanding and characterisation of the complex biological processes underlying disease and to develop, test and guide new treatment modalities, including radionuclide therapy.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
