scholarly journals Automated artificial intelligence quantification of aortic atherosclerotic calcifications by 18F-sodium fluoride PET/CT

Author(s):  
Arnold C. T. Ng ◽  
Alexander R. van Rosendael ◽  
Jeroen J. Bax
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
May Sadik ◽  
Jesús López-Urdaneta ◽  
Johannes Ulén ◽  
Olof Enqvist ◽  
Armin Krupic ◽  
...  

AbstractTo develop an artificial intelligence (AI)-based method for the detection of focal skeleton/bone marrow uptake (BMU) in patients with Hodgkin’s lymphoma (HL) undergoing staging with FDG-PET/CT. The results of the AI in a separate test group were compared to the interpretations of independent physicians. The skeleton and bone marrow were segmented using a convolutional neural network. The training of AI was based on 153 un-treated patients. Bone uptake significantly higher than the mean BMU was marked as abnormal, and an index, based on the total squared abnormal uptake, was computed to identify the focal uptake. Patients with an index above a predefined threshold were interpreted as having focal uptake. As the test group, 48 un-treated patients who had undergone a staging FDG-PET/CT between 2017–2018 with biopsy-proven HL were retrospectively included. Ten physicians classified the 48 cases regarding focal skeleton/BMU. The majority of the physicians agreed with the AI in 39/48 cases (81%) regarding focal skeleton/bone marrow involvement. Inter-observer agreement between the physicians was moderate, Kappa 0.51 (range 0.25–0.80). An AI-based method can be developed to highlight suspicious focal skeleton/BMU in HL patients staged with FDG-PET/CT. Inter-observer agreement regarding focal BMU is moderate among nuclear medicine physicians.


2013 ◽  
Vol 32 (1) ◽  
pp. 22-25 ◽  
Author(s):  
R. Quirce ◽  
I. Martínez-Rodríguez ◽  
M. De Arcocha Torres ◽  
J.F. Jiménez-Bonilla ◽  
I. Banzo ◽  
...  
Keyword(s):  

Diagnostics ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 17
Author(s):  
Kalevi Kairemo ◽  
S. Cheenu Kappadath ◽  
Timo Joensuu ◽  
Homer A. Macapinlac

Bone metastases are common in prostate cancer (PCa). Fluorocholine-18 (FCH) and sodium fluoride-18 (NaF) have been used to assess PCa associated skeletal disease in thousands of patients by demonstrating different mechanism of uptake-cell membrane (lipid) synthesis and bone mineralization. Here, this difference is characterized quantitatively in detail. Our study cohort consisted of 12 patients with advanced disease (> 5 lesions) (M) and of five PCa patients with no skeletal disease (N). They had routine PET/CT with FCH and NaF on consecutive days. Skeletal regions in CT were used to co-register the two PET/CT scans. Bone 3-D volume of interest (VOI) was defined on the CT of PET with a threshold of HU > 150, and sclerotic/dense bone as HU > 600, respectively. Additional VOIs were defined on PET uptake with the threshold values on both FCH (SUV > 3.5) and NaF (SUV > 10). The pathologic skeletal volumes for each technique (CT, HU > 600), NaF (SUV > 10) and FCH (SUV > 3.5) were developed and analyzed. The skeletal VOIs varied from 5.03 L to 7.31 L, whereas sclerotic bone VOIs were from 0.88 L to 2.99 L. Total choline kinase (cell membrane synthesis) activity for FCH (TCA) varied from 0.008 to 4.85 [kg] in M group and from 0.0006 to 0.085 [kg] in N group. Total accelerated osteoblastic (bone demineralization) activity for NaF (TBA varied from 0.25 to 13.6 [kg] in M group and varied from 0.000 to 1.09 [kg] in N group. The sclerotic bone volume represented only 1.86 ± 1.71% of the pathologic FCH volume and 4.07 ± 3.21% of the pathologic NaF volume in M group, and only 0.08 ± 0.09% and 0.18 ± 0.19% in N group, respectively. Our results suggest that CT alone cannot be used for the assessment of the extent of active metastatic skeletal disease in PCa. NaF and FCH give complementary information about the activity of the skeletal disease, improving diagnosis and disease staging.


PET Clinics ◽  
2022 ◽  
Vol 17 (1) ◽  
pp. 115-135
Author(s):  
Sriram S. Paravastu ◽  
Navid Hasani ◽  
Faraz Farhadi ◽  
Michael T. Collins ◽  
Lars Edenbrandt ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document