The feasibility of deep learning-based synthetic contrast-enhanced CT from nonenhanced CT in emergency department patients with acute abdominal pain

Abstract

Our objective was to investigate the feasibility of deep learning-based synthetic contrast-enhanced CT (DL-SCE-CT) from nonenhanced CT (NECT) in patients who visited the emergency department (ED) with acute abdominal pain (AAP). We trained an algorithm generating DL-SCE-CT using NECT with paired precontrast/postcontrast images. For clinical application, 353 patients from three institutions who visited the ED with AAP were included. Six reviewers (experienced radiologists, ER1-3; training radiologists, TR1-3) made diagnostic and disposition decisions using NECT alone and then with NECT and DL-SCE-CT together. The radiologists’ confidence in decisions was graded using a 5-point scale. The diagnostic accuracy using DL-SCE-CT improved in three radiologists (50%, P = 0.023, 0.012, < 0.001, especially in 2/3 of TRs). The confidence of diagnosis and disposition improved significantly in five radiologists (83.3%, P < 0.001). Particularly, in subgroups with underlying malignancy and miscellaneous medical conditions (MMCs) and in CT-negative cases, more radiologists reported increased confidence in diagnosis (83.3% [5/6], 100.0% [6/6], and 83.3% [5/6], respectively) and disposition (66.7% [4/6], 83.3% [5/6] and 100% [6/6], respectively). In conclusion, DL-SCE-CT enhances the accuracy and confidence of diagnosis and disposition regarding patients with AAP in the ED, especially for less experienced radiologists, in CT-negative cases, and in certain disease subgroups with underlying malignancy and MMCs.

Artificial intelligence in interventional radiology: state of the art

“…Creating synthetic contrast-enhanced CT images has been proposed in diagnostic radiology [ 30 , 31 ] to reduce usage of iodinated contrast agents. Pinnock et al proposed a first study on synthetic contrast-enhanced CT in IR, which poses challenges such as organ displacement and needle insertion [ 32 ].…”

Synthetic Post-Contrast Imaging through Artificial Intelligence: Clinical Applications of Virtual and Augmented Contrast Media

“…CT scans for abdominal pain are very common in the emergency room setting and very useful for diagnosis and decision making [82,83]. Since contrast injection is not required for all patients with abdominal pain, Kim et al, sought to increase non-contrast CT (NCCT) diagnostic performance by generating contrast-enhanced CT (CECT) through a DL algorithm in more than 500 patients (divided into training, test, and external validation sets) [84]. The consultant and in-training radiologists involved in the research reported increased confidence in diagnosing, especially oncologic conditions such as biliary disease or inflammatory conditions (appendicitis, pancreatitis, diverticulitis) [84].…”

“…Since contrast injection is not required for all patients with abdominal pain, Kim et al, sought to increase non-contrast CT (NCCT) diagnostic performance by generating contrast-enhanced CT (CECT) through a DL algorithm in more than 500 patients (divided into training, test, and external validation sets) [84]. The consultant and in-training radiologists involved in the research reported increased confidence in diagnosing, especially oncologic conditions such as biliary disease or inflammatory conditions (appendicitis, pancreatitis, diverticulitis) [84]. However, the main drawback of the study was the increased confidence in both correct and incorrect diagnoses, raising some concerns about the utility of this approach.…”

Time conditioning for arbitrary contrast phase generation in interventional computed tomography

“…Recently there has been a growing interest in generating synthetic contrast-enhanced (sCE) CT images to avoid the use of RCAs entirely (Choi et al 2021 , Kim et al 2021 ). Liu et al developed a two-stage GAN (generating first coarse and then fine detail) (Liu et al 2020 ) while Chandrashekar et al and Xie et al opted to use CycleGAN, a GAN architecture designed for style transfer in unpaired data (Chandrashekar et al 2020 , Xie et al 2021 ).…”