TY - JOUR
T1 - Determining age and sex-specific distribution of pancreatic whole-gland CT attenuation using artificial intelligence aided image segmentation
T2 - Associations with body composition and pancreatic cancer risk
AU - Janssens, Laurens P.
AU - Weston, Alexander D.
AU - Singh, Dhruv
AU - Spears, Grant
AU - Harmsen, William S.
AU - Takahashi, Naoki
AU - Philbrick, Kenneth A.
AU - Erickson, Bradley J.
AU - Abu Dayyeh, Barham K.
AU - Chari, Suresh T.
AU - Chandrasekhara, Vinay
AU - Gleeson, Ferga C.
AU - Levy, Michael J.
AU - Pearson, Randall K.
AU - Petersen, Bret T.
AU - Vege, Santhi Swaroop
AU - Majumder, Shounak
N1 - Funding Information:
In summary, in this study we report for the first time, mean pancreas HU values on non-contrast CT in a cohort of adults without underlying pancreatic disease across a spectrum of age and sex. Using whole organ segmentation, we demonstrate association of low mean pancreatic HU with intra-abdominal visceral adiposity and our findings support previously reported associations between increased intrapancreatic fat and increasing age, BMI, and diabetes mellitus. We have also demonstrated that pancreatic mean HU is significantly lower in the pre-diagnostic phase of PDAC compared to cancer-free controls matched for age, sex, and glycemic status, indicating that this may be a radiologic risk factor or an imaging feature that predates the onset of overt PDAC. This early finding will need to be validated in larger independent cohorts.This study was supported by Award Number P50 CA102701 (Mayo Clinic SPORE in Pancreatic Cancer). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Cancer Institute or the National Institutes of Health.
Funding Information:
This study was supported by Award Number P50 CA102701 ( Mayo Clinic SPORE in Pancreatic Cancer ). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Cancer Institute or the National Institutes of Health.
Publisher Copyright:
© 2021
PY - 2021/12
Y1 - 2021/12
N2 - Background & aims: Increased intrapancreatic fat is associated with pancreatic diseases; however, there are no established objective diagnostic criteria for fatty pancreas. On non-contrast computed tomography (CT), adipose tissue shows negative Hounsfield Unit (HU) attenuations (−150 to −30 HU). Using whole organ segmentation on non-contrast CT, we aimed to describe whole gland pancreatic attenuation and establish 5th and 10th percentile thresholds across a spectrum of age and sex. Subsequently, we aimed to evaluate the association between low pancreatic HU and risk of pancreatic ductal adenocarcinoma (PDAC). Methods: The whole pancreas was segmented in 19,456 images from 469 non-contrast CT scans. A convolutional neural network was trained to assist pancreas segmentation. Mean pancreatic HU, volume, and body composition metrics were calculated. The lower 5th and 10th percentile for mean pancreatic HU were identified, examining the association with age and sex. Pre-diagnostic CT scans from patients who later developed PDAC were compared to cancer-free controls. Results: Less than 5th percentile mean pancreatic HU was significantly associated with increase in BMI (OR 1.07; 1.03–1.11), visceral fat (OR 1.37; 1.15–1.64), total abdominal fat (OR 1.12; 1.03–1.22), and diabetes mellitus type 1 (OR 6.76; 1.68–27.28). Compared to controls, pre-diagnostic scans in PDAC cases had lower mean whole gland pancreatic HU (−0.2 vs 7.8, p = 0.026). Conclusion: In this study, we report age and sex-specific distribution of pancreatic whole-gland CT attenuation. Compared to controls, mean whole gland pancreatic HU is significantly lower in the pre-diagnostic phase of PDAC.
AB - Background & aims: Increased intrapancreatic fat is associated with pancreatic diseases; however, there are no established objective diagnostic criteria for fatty pancreas. On non-contrast computed tomography (CT), adipose tissue shows negative Hounsfield Unit (HU) attenuations (−150 to −30 HU). Using whole organ segmentation on non-contrast CT, we aimed to describe whole gland pancreatic attenuation and establish 5th and 10th percentile thresholds across a spectrum of age and sex. Subsequently, we aimed to evaluate the association between low pancreatic HU and risk of pancreatic ductal adenocarcinoma (PDAC). Methods: The whole pancreas was segmented in 19,456 images from 469 non-contrast CT scans. A convolutional neural network was trained to assist pancreas segmentation. Mean pancreatic HU, volume, and body composition metrics were calculated. The lower 5th and 10th percentile for mean pancreatic HU were identified, examining the association with age and sex. Pre-diagnostic CT scans from patients who later developed PDAC were compared to cancer-free controls. Results: Less than 5th percentile mean pancreatic HU was significantly associated with increase in BMI (OR 1.07; 1.03–1.11), visceral fat (OR 1.37; 1.15–1.64), total abdominal fat (OR 1.12; 1.03–1.22), and diabetes mellitus type 1 (OR 6.76; 1.68–27.28). Compared to controls, pre-diagnostic scans in PDAC cases had lower mean whole gland pancreatic HU (−0.2 vs 7.8, p = 0.026). Conclusion: In this study, we report age and sex-specific distribution of pancreatic whole-gland CT attenuation. Compared to controls, mean whole gland pancreatic HU is significantly lower in the pre-diagnostic phase of PDAC.
KW - Artificial intelligence
KW - Convolutional neural network
KW - Deep learning
KW - Pancreatic ductal carcinomas
KW - Pancreatic steatosis
UR - http://www.scopus.com/inward/record.url?scp=85114706478&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114706478&partnerID=8YFLogxK
U2 - 10.1016/j.pan.2021.08.004
DO - 10.1016/j.pan.2021.08.004
M3 - Article
C2 - 34507900
AN - SCOPUS:85114706478
SN - 1424-3903
VL - 21
SP - 1524
EP - 1530
JO - Pancreatology
JF - Pancreatology
IS - 8
ER -