Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct;129(10):1444-1453.
doi: 10.1007/s11547-024-01878-9. Epub 2024 Aug 30.

Radiomics and 256-slice-dual-energy CT in the automated diagnosis of mild acute pancreatitis: the innovation of formal methods and high-resolution CT

Aldo Rocca #  1 , Maria Chiara Brunese #  2   3 , Antonella Santone  4 , Giulia Varriano  4 , Luca Viganò  5 , Corrado Caiazzo  4 , Gianfranco Vallone  4 , Luca Brunese  4 , Luigia Romano #  6 , Marco Di Serafino #  4   6 ; R O I Segmentation Collaborative Group
Collaborators, Affiliations

Radiomics and 256-slice-dual-energy CT in the automated diagnosis of mild acute pancreatitis: the innovation of formal methods and high-resolution CT

Aldo Rocca et al. Radiol Med. 2024 Oct.

Abstract

Introduction: Acute pancreatitis (AP) is a common disease, and several scores aim to assess its prognosis. Our study aims to automatically recognize mild AP from computed tomography (CT) images in patients with acute abdominal pain but uncertain diagnosis from clinical and serological data through Radiomic model based on formal methods (FMs).

Methods: We retrospectively reviewed the CT scans acquired with Dual Source 256-slice CT scanner (Somatom Definition Flash; Siemens Healthineers, Erlangen, Germany) of 80 patients admitted to the radiology unit of Antonio Cardarelli hospital (Naples) with acute abdominal pain. Patients were divided into 2 groups: 40 underwent showed a healthy pancreatic gland, and 40 affected by four different grades (CTSI 0, 1, 2, 3) of mild pancreatitis at CT without clear clinical presentation or biochemical findings. Segmentation was manually performed. Radiologists identified 6 patients with a high expression of diseases (CTSI 3) to formulate a formal property (Rule) to detect AP in the testing set automatically. Once the rule was formulated, and Model Checker classified 70 patients into "healthy" or "unhealthy".

Results: The model achieved: accuracy 81%, precision 78% and recall 81%. Combining FMs results with radiologists agreement, and applying the mode in clinical practice, the global accuracy would have been 100%.

Conclusions: Our model was reliable to automatically detect mild AP at primary diagnosis even in uncertain presentation and it will be tested prospectively in clinical practice.

Keywords: Artificial intelligence; Diagnosis; Formal methods; Mild acute pancreatitis; Pancreatitis; Radiomics.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Fig. 1
Fig. 1
a ROI of healthy pancreas patient; b ROI in a mild acute pancreatitis patient automatically detected
Fig. 2
Fig. 2
Schema of the methodology: starting from the medical images, there is the ROI segmentation step defining the pancreas region. After feature extraction and selection, the mathematical models are created and then verified through the formal Property written by radiologists and computer scientists. The Model Checker checks if the Property is satisfied or not, indicating the patient as healthy or affected by pancreatitis
Fig. 3
Fig. 3
a An example of a young patient not affected by mild acute pancreatitis misdiagnosed by some of the radiologists and correctly classified by FMs, b An example of a young patient affected by mild acute pancreatitis misdiagnosed by some of the radiologists and correctly classified by FMs
See this image and copyright information in PMC

References

    1. Xiao AY et al (2016) Global incidence and mortality of pancreatic diseases: a systematic review, meta-analysis, and meta-regression of population-based cohort studies. Lancet Gastroenterol Hepatol 1(1):45–55 - PubMed
    1. Thapa R et al (2022) Early prediction of severe acute pancreatitis using machine learning. Pancreatology 22(1):43–50 - PubMed
    1. Michalak N, Małecka-Wojciesko E (2023) Modifiable pancreatic ductal adenocarcinoma (PDAC) risk factors. J Clin Med. 10.3390/jcm12134318 - PMC - PubMed
    1. Crockett SD et al (2018) American gastroenterological association institute guideline on initial management of acute pancreatitis. Gastroenterology 154(4):1096–1101 - PubMed
    1. Banks PA et al (2013) Classification of acute pancreatitis–2012: revision of the Atlanta classification and definitions by international consensus. Gut 62(1):102–111 - PubMed