Background: Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.
Purpose: MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.
Methods: A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.
Results: The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.
Conclusions: Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10546304 | PMC |
| http://dx.doi.org/10.3389/fonc.2023.1181270 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Radiomics for differentiating pancreatic Mucinous Cystic Neoplasm from Serous Cystic Neoplasm: Systematic Review and Meta-Analysis.
Acad Radiol
December 2024
Division of Pancreatic Surgery, Department of General Surgery, Qilu Hospital, Shandong University, Jinan, Shandong Province, China (L.Z., B.D., Z.F., H.Z.). Electronic address:
Background: As pancreatic cystic neoplasms (PCN) differ in current standard of care, and these treatments can affect quality of life to varying degrees, a definitive preoperative diagnosis must be reliable. Current diagnostic approaches, specifically traditional cross-sectional imaging techniques, face certain limitations. But radiomics has been shown to have high diagnostic accuracy across a range of diseases.
View Article and Find Full Text PDFNext-generation sequencing improves diagnostic accuracy of imaging and carcinoembryonic antigen alone for pancreatic cystic neoplasms.
Pancreatology
December 2024
Abdominal Center, Department of Gastrointestinal Surgery, Helsinki University Hospital and Helsinki University, Finland.
Background: New tools are needed to determine the pancreatic cysts that require surgical resection. This study aimed to evaluate whether next-generation sequencing (NGS) is useful for identifying mucinous, malignant, or pre-malignant cysts leading to surgery.
Methods: Laboratory, cytological, and histological data from 97 patients with worrisome features on imaging or an unclear pancreatic cystic lesion (PCL) who were indicated for further investigation and who underwent endoscopic ultrasound (EUS) and fine-needle aspiration (FNA) between 2018 and 2022 were analyzed.
[Pancreatic cystic neoplasms].
Chirurgie (Heidelb)
November 2024
Klink für Allgemein- und Viszeralchirurgie, Universitätsklinikum der Friedrich-Alexander-Universität Erlangen, Krankenhausstraße 12, 91054, Erlangen, Deutschland.
Pancreatic cystic lesions represent a challenging heterogeneous entity with a potential risk of malignant transformation. The diagnostics include in particular medical history taking with collection of relevant clinical information and high-resolution imaging, preferably using magnetic resonance imaging (MRI) with MR cholangiopancreatography (MRCP) and/or endoscopic ultrasonography. A differentiation between different cystic entities and identification of risk factors are crucial for making appropriate treatment decisions.
View Article and Find Full Text PDFThe differential diagnosis of pancreatic cystic neoplasms with conventional ultrasound and contrast-enhanced ultrasound.
Quant Imaging Med Surg
July 2024
Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, China.
Background: Advances in imaging have improved the detection rate of pancreatic cystic neoplasms (PCNs), but clinical management varies depending on the pathological type of PCNs, and thus accurate differential diagnosis is of considerable clinical significance. We conducted this study to identify the clinical and sonographic features of PCNs with significance for differential diagnosis and to compare the diagnostic accuracy of conventional ultrasound and conventional ultrasound combined with contrast-enhanced ultrasound (CEUS) for PCNs.
Methods: From January 1, 2011, to December 31, 2022, a total of 100 patients with PCNs who underwent CEUS examination and were confirmed to have PCNs by postoperative pathology in West China Hospital of Sichuan University were included in this study.
DenseNet model incorporating hybrid attention mechanisms and clinical features for pancreatic cystic tumor classification.
J Appl Clin Med Phys
July 2024
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Purpose: The aim of this study is to develop a deep learning model capable of discriminating between pancreatic plasma cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN) by leveraging patient-specific clinical features and imaging outcomes. The intent is to offer valuable diagnostic support to clinicians in their clinical decision-making processes.
Methods: The construction of the deep learning model involved utilizing a dataset comprising abdominal magnetic resonance T2-weighted images obtained from patients diagnosed with pancreatic cystic tumors at Changhai Hospital.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!