Please see the Editorial Comment by Neeraj Lalwani discussing this article. Background: Pancreatic ductal adenocarcinoma (PDAC) is highly lethal, partly due to challenges in early diagnosis. Howeve...
Deep learning (DL) image quality improvement has been studied for application to 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT). It is unclear, however, whether DL can increase the quality of images obtained with semiconductor-based PET/CT scanners. This study aimed to compare the quality of semiconductor-based PET/CT scanner images obtained by DL-based technology and conventional OSEM image with Gaussian postfilter. For DL-based data processing implementation, we used Advanced Intelligent Clear-IQ Engine (AiCE, Canon Medical Systems, Tochigi, Japan) and for OSEM images, Gaussian postfilter of 3 mm FWHM is used. Thirty patients who underwent semiconductor-based PET/CT scanner imaging between May 6, 2021, and May 19, 2021, were enrolled. We compared AiCE images and OSEM images and scored them for delineation, image noise, and overall image quality. We also measured standardized uptake values (SUVs) in tumors and healthy tissues and compared them between AiCE and OSEM. AiCE images scored significantly higher than OSEM images for delineation, image noise, and overall image quality. The Fleiss kappa value for the interobserver agreement was 0.57. Among the 21 SUV measurements in healthy organs, 11 (52.4%) measurements were significantly different between AiCE and OSEM images. More pathological lesions were detected in AiCE images as compared with OSEM images, with AiCE images showing higher SUVs for pathological lesions than OSEM images. AiCE can improve the quality of images acquired with semiconductor-based PET/CT scanners, including the noise level, contrast, and tumor detection capability.
1 January 2018 in Magnetic Resonance in Medical Sciences
Despite the presence of various guidelines, diagnosing malignant intraductal papillary mucinous neoplasm (IPMN) continues to pose challenges. Furthermore, although endoscopic ultrasonography (EUS) offers high-resolution images, it has not yet recognized as the primary tool for malignancy diagnosis. The study objective was to develop a simplified and user-friendly scoring system to improve the diagnostic accuracy of malignant IPMNs. Additionally, the utility of EUS and its effect on diagnostic accuracy were assessed. We retrospectively collected the clinical data on 160 cases of resected IPMN at Tokyo Medical and Dental University Hospital from January 2008 to December 2022. We examined clinical features, computed tomography (CT) and magnetic resonance imaging (MRI) findings, and EUS results if available. We then calculated the odds ratio of malignancy for these factors and developed an IPMN malignancy prediction (IMAP) scoring system. There were 89 (55.6%) cases of benign IPMNs and 71 (44.4%) of malignant IPMNs. Eight clinical and imaging findings, including age, diabetes mellitus status, jaundice, CA19-9 level, enhancing mural nodules ≥5mm, thickened wall, and main duct dilatation, were significantly associated with malignancy. The IMAP score was calculated by assigning 0 to 2 points to these factors based on the odds ratio. The area under the receiver operating characteristic curve for the IMAP score was 0.78 [95% confidence interval (CI): 0.71–0.85] based on CT/MRI alone and improved to 0.81 (95% CI: 0.74–0.87) when EUS was added. When the total exceeds 5 points, the positive predictive value becomes 100% (95% CI: 95.9–100). In conclusion, the IMAP scoring system has demonstrated promise as a clinically useful tool, offering both simplicity and sufficient accuracy. It holds potential as an important decision criterion for determining the treatment approach for IPMN. Additionally, EUS contributes to enhancing the diagnostic accuracy of the IMAP scoring system, thereby enabling more precise decision-making.