Deep learning-based combined noise reduction and contrast enhancement for post-neoadjuvant pancreatic cancer CT: does improved image quality translate to better resectability assessment?

Clinical Snapshot

Key Findings

• P Value: Not significant (exact values not provided)

• Effect Size: No significant difference in accuracy between DLR (62.3%-65.8%) and conventional IR

• Primary Outcome: Diagnostic accuracy for R0 resectability prediction

• Nnt Or Sensitivity: AUC 0.485-0.520 for both methods (poor discriminatory ability)

• Confidence Interval: Not reported

Clinical Application

Requires advanced CT reconstruction software and trained radiologists familiar with post-neoadjuvant imaging changes Relevant to major Australian pancreatic surgery centres. TGA approval would be needed for ClariACE system. Limited impact given no improvement in diagnostic accuracy despite higher costs Patients with pancreatic cancer post-neoadjuvant therapy being considered for surgical resection

Abstract

PURPOSE: To evaluate whether deep learning-based combined noise reduction and contrast enhancement reconstruction (DLR) improves image quality and resectability prediction accuracy compared to conventional iterative reconstruction (IR) in post-neoadjuvant pancreatic cancer CT assessment. METHODS: This retrospective study included 114 patients with pancreatic cancer following neoadjuvant therapy. Contrast-enhanced CT images were reconstructed using conventional IR and vendor-neutral ClariACE. Three abdominal radiologists independently assessed image quality (based on 8 parameters: tumor conspicuity, tumor margin, image noise, sharpness of the main pancreatic duct, arterial depiction, venous depiction, plasticity and overall image quality) and determined tumor resectability with confidence levels. Quantitative analysis included aortic and portal venous attenuation measurements and pancreas-to-tumor contrast-to-noise ratio (CNR). Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUC) with DeLong's test. Sensitivity, specificity, accuracy, and reader confidence were compared using McNemar's test. RESULTS: DLR demonstrated significantly superior vessel enhancement (p < 0.001) and improved CNR (p < 0.001) versus conventional IR. Two readers consistently rated DLR images higher across all qualitative categories (p < 0.001) except plasticity, while the third reader favored DLR in five of eight parameters (p < 0.001 to 0.020). However, all readers noted increased artificial appearance in DLR images (p < 0.001). Despite image quality improvements, no significant differences were observed in resectability assessment accuracy (62.3%-65.8%), AUC values (0.485-0.520), or high-confidence diagnosis rates between reconstruction methods. CONCLUSION: Although deep learning-based combined noise reduction and contrast enhancement reconstruction significantly improved quantitative and subjective image quality metrics, it did not enhance diagnostic accuracy for predicting R0 resectability in post-neoadjuvant pancreatic cancer patients.

References

1. 1.Hong, S. J., Jeon, S. K., Yoo, J., Zhu, L., Yoon, J. H., Kang, H. J., Park, J., & Lee, J. M. (2026). Deep learning-based combined noise reduction and contrast enhancement for post-neoadjuvant pancreatic cancer CT: does improved image quality translate to better resectability assessment? Abdominal Radiology. https://doi.org/10.1016/j.ejrad.2021.109825