Computerized tomography scan in pre-diagnostic pancreatic ductal adenocarcinoma: Stages of progression and potential benefits of early intervention: A retrospective study

Two‐stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra‐reader and inter‐reader reliability at full and reduced radiation dose on an external dataset

“…[34][35][36][37] In the course of regular clinical interpretation, the pancreas in these patients tends to be interpreted as morphologically normal. [34][35][36][37][38][39] Therefore, there is a critical need for automated pancreas segmentation and volumetry tools, which can compare the pancreas in patients at high risk for cancer to a normative database and augment physician expertise by alerting to subtle signs of early pancreatic cancer. However, further investigation and clinical translation of these possibilities has been constrained by the time-consuming process of manual segmentation and planimetry.…”

“…It has also been shown that imaging signs of small pancreatic cancer often go undetected on cross‐sectional imaging until symptoms appear. In fact, a pancreatic mass may not be present in patients even as close as 6 months before the clinical diagnosis of pancreatic cancer 34–37 . In the course of regular clinical interpretation, the pancreas in these patients tends to be interpreted as morphologically normal 34–39 .…”

“…In fact, a pancreatic mass may not be present in patients even as close as 6 months before the clinical diagnosis of pancreatic cancer 34–37 . In the course of regular clinical interpretation, the pancreas in these patients tends to be interpreted as morphologically normal 34–39 . Therefore, there is a critical need for automated pancreas segmentation and volumetry tools, which can compare the pancreas in patients at high risk for cancer to a normative database and augment physician expertise by alerting to subtle signs of early pancreatic cancer.…”

CT Abnormalities of the Pancreas Associated With the Subsequent Diagnosis of Clinical Stage I Pancreatic Ductal Adenocarcinoma More Than 1 Year Later: A Case-Control Study

“…As this study's main purpose was to investigate abnormal findings that may help detect PDAC earlier than stage I, the assessment only included examinations obtained at least one year before the diagnosis of clinical stage I PDAC. This may have resulted in the overall relatively low prevalence of focal abnormalities compared with previous studies that assessed findings predictive of PDAC on pre-diagnostic CT examinations, especially for focal mass (34%-89% in prior studies) and MPD change (21%-67% in prior studies) (13)(14)(15)(16)(17)(18). The earlier studies primarily evaluated CT examinations obtained less than one year before diagnosis (13,(16)(17)(18).…”

“…In addition, it is difficult to visualize earlier stage PDAC (i.e., stage T1a invasive carcinoma or high-grade PanIN) on imaging. Numerous studies have described early imaging findings that are predictive of subsequent PDAC [i.e., main pancreatic duct (MPD) cut-off or dilation, cyst, distal parenchymal atrophy, focal attenuation difference, and loss of fatty marbling] using pre-diagnostic examinations obtained months to years before the clinical or histopathologic diagnosis (13)(14)(15)(16)(17)(18)(19)(20)(21)(22). However, such studies are limited by small sample sizes, inconsistent tumor stage at diagnosis, and short time interval between pre-diagnostic and diagnostic examinations.…”