1
|
Deng W, Liu J, Wang X, Xie F, Wang S, Zhang X, Mao L, Li X, Hu Y, Jin Z, Xue H. Should All Pancreatic Cystic Lesions with Worrisome or High-Risk Features Be Resected? A Clinical and Radiological Machine Learning Model May Help to Answer. Acad Radiol 2024; 31:1889-1897. [PMID: 37977893 DOI: 10.1016/j.acra.2023.09.043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 09/22/2023] [Accepted: 09/26/2023] [Indexed: 11/19/2023]
Abstract
RATIONALE AND OBJECTIVES According to current guidelines, pancreatic cystic lesions (PCLs) with worrisome or high-risk features may have overtreatment. The purpose of this study was to build a clinical and radiological based machine-learning (ML) model to identify malignant PCLs for surgery among preoperative PCLs with worrisome or high-risk features. MATERIALS AND METHODS Clinical and radiological details of 317 pathologically confirmed PCLs with worrisome or high-risk features were retrospectively analyzed and applied to ML models including Support Vector Machine, Logistic Regression (LR), Decision Tree, Bernoulli NB, Gaussian NB, K Nearest Neighbors and Linear Discriminant Analysis. The diagnostic ability for malignancy of the optimal model with the highest diagnostic AUC in the cross-validation procedure was further evaluated in internal (n = 77) and external (n = 50) testing cohorts, and was compared to two published guidelines in internal mucinous cyst cohort. RESULTS Ten clinical and radiological feature-based LR model was the optimal model with the highest AUC (0.951) in the cross-validation procedure. In the internal testing cohort, LR model reached an AUC, accuracy, sensitivity, and specificity of 0.927, 0.909, 0.914, and 0.905; in the external testing cohort, LR model reached 0.948, 0.900, 0.963, and 0.826. When compared to the European guidelines and the ACG guidelines, LR model demonstrated significantly better accuracy and specificity in identifying malignancy, while maintaining the same high sensitivity. CONCLUSION Clinical- and radiological-based LR model can accurately identify malignant PCLs in patients with worrisome or high-risk features, possessing diagnostic performance better than the European guidelines as well as ACG guidelines.
Collapse
Affiliation(s)
- Wenyi Deng
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Jingyi Liu
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Xiheng Wang
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Fengtai District, Beijing, 100070, People's Republic of China (X.W.)
| | - Feiyang Xie
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Shitian Wang
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Xinyu Zhang
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Li Mao
- AI Lab, Deepwise Healthcare, Beijing 100080, People's Republic of China (L.M., X.L.)
| | - Xiuli Li
- AI Lab, Deepwise Healthcare, Beijing 100080, People's Republic of China (L.M., X.L.)
| | - Ya Hu
- Department of General Surgery, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing 100730, People's Republic of China (Y.H.)
| | - Zhengyu Jin
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.)
| | - Huadan Xue
- Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No 1, Wangfujing Street, Dongcheng District, Beijing 100730, People's Republic of China (W.D., J.L., F.X., S.W., X.Z., Z.J., H.X.).
| |
Collapse
|
2
|
Gardner TB, Park WG, Allen PJ. Diagnosis and Management of Pancreatic Cysts. Gastroenterology 2024:S0016-5085(24)00248-8. [PMID: 38442782 DOI: 10.1053/j.gastro.2024.02.041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/01/2024] [Accepted: 02/18/2024] [Indexed: 03/07/2024]
Abstract
As pancreatic cyst incidence rises, likely due to the ubiquitous increase in cross-sectional imaging, their management presents multiple challenges for both the practitioner and patient. It is critical that all pancreatic cysts are appropriately characterized, as treatment decisions depend on an accurate diagnosis. Diagnostic modalities such as cytology, biopsy, and cyst fluid biomarkers allow for definitive diagnosis of virtually all lesions. Some cysts, such as intraductal papillary mucinous neoplasms, mucinous cystic neoplasms, and cystic pancreatic endocrine neoplasms, have malignant potential and must be surveyed. Other cysts, such as serous cystadenomas and pancreatic fluid collections, do not have malignant potential. Surveillance strategies vary widely depending on cyst type and size and while multiple medical societies advocate surveillance, their published surveillance guidelines are heterogenous. Cysts with high-risk stigmata or worrisome features are usually resected, depending on the patient's surgical fitness. In patients unfit for resection, newer endoscopic ablative techniques are advocated. Controversial aspects regarding cyst management include whether surveillance can be stopped, how surveillance should be performed, and the extensive financial burden cyst management places on the health care system. Further study into the natural history of cystic lesions, including definitive determination of the rate of malignant transformation for each cyst type, is essential.
Collapse
Affiliation(s)
- Timothy B Gardner
- Section of Gastroenterology and Hepatology, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire.
| | - Walter G Park
- Section of Gastroenterology and Hepatology, Stanford University Medical Center, Palo Alto, California
| | - Peter J Allen
- Division of Surgical Oncology, Duke University Medical Center, Durham, North Carolina
| |
Collapse
|
3
|
Rawlani P, Ghosh NK, Kumar A. Role of artificial intelligence in the characterization of indeterminate pancreatic head mass and its usefulness in preoperative diagnosis. Artif Intell Gastroenterol 2023; 4:48-63. [DOI: 10.35712/aig.v4.i3.48] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 09/11/2023] [Accepted: 10/08/2023] [Indexed: 12/07/2023] Open
Abstract
Artificial intelligence (AI) has been used in various fields of day-to-day life and its role in medicine is immense. Understanding of oncology has been improved with the introduction of AI which helps in diagnosis, treatment planning, management, prognosis, and follow-up. It also helps to identify high-risk groups who can be subjected to timely screening for early detection of malignant conditions. It is more important in pancreatic cancer as it is one of the major causes of cancer-related deaths worldwide and there are no specific early features (clinical and radiological) for diagnosis. With improvement in imaging modalities (computed tomography, magnetic resonance imaging, endoscopic ultrasound), most often clinicians were being challenged with lesions that were difficult to diagnose with human competence. AI has been used in various other branches of medicine to differentiate such indeterminate lesions including the thyroid gland, breast, lungs, liver, adrenal gland, kidney, etc. In the case of pancreatic cancer, the role of AI has been explored and is still ongoing. This review article will focus on how AI can be used to diagnose pancreatic cancer early or differentiate it from benign pancreatic lesions, therefore, management can be planned at an earlier stage.
Collapse
Affiliation(s)
- Palash Rawlani
- Department of Surgical Gastroenterology, Sanjay Gandhi Post Graduate Institute of Medical Sciences, Lucknow 226014, Uttar Pradesh, India
| | - Nalini Kanta Ghosh
- Department of Surgical Gastroenterology, Sanjay Gandhi Post Graduate Institute of Medical Sciences, Lucknow 226014, Uttar Pradesh, India
| | - Ashok Kumar
- Department of Surgical Gastroenterology, Sanjay Gandhi Post Graduate Institute of Medical Sciences, Lucknow 226014, Uttar Pradesh, India
| |
Collapse
|
4
|
Elmi N, McEvoy D, McInnes MDF, Alabousi M, Hecht EM, Luk L, Asghar S, Jajodia A, de Carvalho TL, Warnica WJ, Zha N, Ullah S, van der Pol CB. Percentage of Pancreatic Cysts on MRI With a Pancreatic Carcinoma: Systematic Review and Meta-Analysis. J Magn Reson Imaging 2023. [PMID: 38053468 DOI: 10.1002/jmri.29168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Revised: 11/20/2023] [Accepted: 11/20/2023] [Indexed: 12/07/2023] Open
Abstract
BACKGROUND Pancreatic cystic lesions (PCLs) are frequent on MRI and are thought to be associated with pancreatic adenocarcinoma (PDAC) necessitating long-term surveillance based on older studies suffering from selection bias. PURPOSE To establish the percentage of patients with PCLs on MRI with a present or future PDAC. STUDY TYPE Systematic review, meta-analysis. POPULATION Adults with PCLs on MRI and a present or future diagnosis of PDAC were eligible. MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, and Scopus were searched to April 2022 (PROSPERO:CRD42022320502). Studies limited to PCLs not requiring surveillance, <100 patients, or those with a history/genetic risk of PDAC were excluded. FIELD STRENGTH/SEQUENCE ≥1.5 T with ≥1 T2-weighted sequence. ASSESSMENT Two investigators extracted data, with discrepancies resolved by a third. QUADAS-2 assessed bias. PDAC was diagnosed using a composite reference standard. STATISTICAL TESTS A meta-analysis of proportions was performed at the patient-level with 95% confidence intervals (95% CI). RESULTS Eight studies with 1289 patients contributed to the percentage of patients with a present diagnosis of PDAC, and 10 studies with 3422 patients to the percentage with a future diagnosis. Of patients with PCLs on MRI, 14.8% (95% CI 2.4-34.9) had a PDAC at initial MRI, which decreased to 6.0% (2.2-11.3) for studies at low risk of bias. For patients without PDAC on initial MRI, 2.0% (1.1-3.2) developed PDAC during surveillance, similar for low risk of bias studies at 1.9% (0.7-3.6), with no clear trend of increased PDAC for longer surveillance durations. For patients without worrisome features or high-risk stigmata, 0.9% (0.1-2.2) developed PDAC during surveillance. Of 10, eight studies had a median surveillance ≥3 years (range 3-157 months). Sources of bias included retrospectively limiting PCLs to those with histopathology and inconsistent surveillance protocols. DATA CONCLUSION A low percentage of patients with PCLs on MRI develop PDAC while on surveillance. The first MRI revealing a PCL should be scrutinized for PDAC. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Nika Elmi
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - David McEvoy
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Matthew D F McInnes
- Department of Radiology and Epidemiology, University of Ottawa, Ottawa, Ontario, Canada
- Department of Medical Imaging, Ottawa Hospital Research Institute Clinical Epidemiology Program, The Ottawa Hospital-Civic Campus, Ottawa, Ontario, Canada
| | - Mostafa Alabousi
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Elizabeth M Hecht
- Department of Radiology, Weill Cornell Medicine, New York, New York, USA
| | - Lyndon Luk
- Department of Radiology, New York Presbyterian-Columbia University Medical Center, New York, New York, USA
| | - Sunna Asghar
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Ankush Jajodia
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Tiago Lins de Carvalho
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - William J Warnica
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Nanxi Zha
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Sadaf Ullah
- Library Services, Unity Health Toronto St. Michael's Hospital, East Li Ka Shing Knowledge Institute, Toronto, Ontario, Canada
| | - Christian B van der Pol
- Department of Medical Imaging, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada
- Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| |
Collapse
|
5
|
Machicado JD, Napoleon B, Akshintala V, Bazarbashi AN, Bilal M, Corral JE, Dugum M, Han S, Hussain FS, Johnson AM, Jovani M, Kolb JM, Leonor P, Lee PJ, Mulki R, Shah H, Singh H, Sánchez-Luna SA, Shah SL, Singla A, Vargas EJ, Tielleman T, Nikahd M, Fry M, Culp S, Krishna SG. Structured training program on confocal laser endomicroscopy for pancreatic cystic lesions: a multicenter prospective study among early-career endosonographers (with video). Gastrointest Endosc 2023; 98:953-964. [PMID: 37473969 PMCID: PMC10771632 DOI: 10.1016/j.gie.2023.07.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Revised: 06/08/2023] [Accepted: 07/17/2023] [Indexed: 07/22/2023]
Abstract
BACKGROUND AND AIMS Data on how to teach endosonographers needle-based confocal laser endomicroscopy (nCLE)-guided histologic diagnosis of pancreatic cystic lesions (PCLs) are limited. Hence, we developed and tested a structured educational program to train early-career endosonographers in nCLE-guided diagnosis of PCLs. METHODS Twenty-one early-career nCLE-naïve endosonographers watched a teaching module outlining nCLE criteria for diagnosing PCLs. Participants then reviewed 80 high-yield nCLE videos, recorded diagnoses, and received expert feedback (phase 1). Observers were then randomized to a refresher feedback session or self-learning at 4 weeks. Eight weeks after training, participants independently assessed the same 80 nCLE videos without feedback and provided histologic predictions (phase 2). Diagnostic performance of nCLE to differentiate mucinous versus nonmucinous PCLs and to diagnose specific subtypes were analyzed using histopathology as the criterion standard. Learning curves were determined using cumulative sum analysis. RESULTS Accuracy and diagnostic confidence for differentiating mucinous versus nonmucinous PCLs improved as endosonographers progressed through nCLE videos in phase 1 (P < .001). Similar trends were observed with the diagnosis of PCL subtypes. Most participants achieved competency interpreting nCLE, requiring a median of 38 assessments (range, 9-67). During phase 2, participants independently differentiated PCLs with high accuracy (89%), high confidence (83%), and substantial interobserver agreement (κ = .63). Accuracy for nCLE-guided PCL subtype diagnoses ranged from 82% to 96%. The learned nCLE skills did not deteriorate at 8 weeks and were not impacted by a refresher session. CONCLUSIONS We developed a practical, effective, and durable educational intervention to train early-career endosonographers in nCLE-guided diagnosis of PCLs.
Collapse
Affiliation(s)
- Jorge D Machicado
- Division of Gastroenterology and Hepatology, University of Michigan, Ann Arbor, Michigan, USA
| | - Bertrand Napoleon
- Gastroenterology Department, Hopital Privé Jean Mermoz, Ramsay Generale de Sante, Lyon, France
| | - Venkata Akshintala
- Division of Gastroenterology and Hepatology, Johns Hopkins Medicine, Baltimore, Maryland, USA
| | | | - Mohammad Bilal
- Division of Gastroenterology, Hepatology, and Nutrition, University of Minnesota, Minneapolis, Minnesota, USA
| | - Juan E Corral
- Division of Gastroenterology and Hepatology, Presbyterian Hospital, Albuquerque, New Mexico, USA
| | | | - Samuel Han
- Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| | | | - Alyson M Johnson
- Division of Gastroenterology, Duke University, Durham, North Carolina, USA
| | - Manol Jovani
- Division of Gastroenterology, Maimonides Medical Center, SUNY Downstate University, Brooklyn, New York, USA
| | - Jennifer M Kolb
- Division of Digestive Diseases, VA Greater Los Angeles Healthcare System, Los Angeles, California, USA
| | - Paul Leonor
- Division of Gastroenterology and Hepatology, Loma Linda University, Loma Linda, California, USA
| | - Peter J Lee
- Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| | - Ramzi Mulki
- Basil I. Hirschowitz Endoscopic Center of Excellence, Division of Gastroenterology & Hepatology, Department of Internal Medicine, The University of Alabama at Birmingham Heersink School of Medicine, Birmingham, Alabama, USA
| | - Hamza Shah
- Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| | - Harkirat Singh
- Division of Gastroenterology, Hepatology, and Nutrition, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, USA
| | - Sergio A Sánchez-Luna
- Basil I. Hirschowitz Endoscopic Center of Excellence, Division of Gastroenterology & Hepatology, Department of Internal Medicine, The University of Alabama at Birmingham Heersink School of Medicine, Birmingham, Alabama, USA
| | - Shawn L Shah
- Division of Digestive and Liver Diseases, Veterans Affairs North Texas Health Care System, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Anand Singla
- Division of Gastroenterology, University of Washington, Seattle, Washington, USA
| | - Eric J Vargas
- Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, Minnesota, USA
| | - Thomas Tielleman
- Division of Digestive and Liver Diseases, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Melica Nikahd
- Department of Biomedical Informatics, College of Medicine, The Ohio State University, Columbus, Ohio, USA
| | - Megan Fry
- Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| | - Stacey Culp
- Department of Biomedical Informatics, College of Medicine, The Ohio State University, Columbus, Ohio, USA
| | - Somashekar G Krishna
- Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA
| |
Collapse
|
6
|
Ryoo DY, Koehler B, Rath J, Shah ZK, Chen W, Esnakula AK, Hart PA, Krishna SG. A Comparison of Single Dimension and Volume Measurements in the Risk Stratification of Pancreatic Cystic Lesions. J Clin Med 2023; 12:5871. [PMID: 37762812 PMCID: PMC10531933 DOI: 10.3390/jcm12185871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Revised: 08/25/2023] [Accepted: 09/06/2023] [Indexed: 09/29/2023] Open
Abstract
The incidence of pancreatic cystic lesions (PCLs) has been rising due to improvements in imaging. Of these, intraductal papillary mucinous neoplasms (IPMNs) are the most common and are thought to contribute to almost 20% of pancreatic adenocarcinomas. All major society guidelines for the management of IPMNs use size defined by maximum diameter as the primary determinant of whether surveillance or surgical resection is recommended. However, there is no consensus on how these measurements should be obtained or whether a single imaging modality is superior. Furthermore, the largest diameter may fail to capture the complexity of PCLs, as most are not perfectly spherical. This article reviews current PCL measurement techniques in CT, MRI, and EUS and posits volume as a possible alternative to the largest diameter.
Collapse
Affiliation(s)
- Da Yeon Ryoo
- Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (D.Y.R.); (B.K.)
| | - Bryn Koehler
- Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (D.Y.R.); (B.K.)
| | - Jennifer Rath
- Department of Radiology, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (J.R.); (Z.K.S.)
| | - Zarine K. Shah
- Department of Radiology, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (J.R.); (Z.K.S.)
| | - Wei Chen
- Department of Pathology, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (W.C.); (A.K.E.)
| | - Ashwini K. Esnakula
- Department of Pathology, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (W.C.); (A.K.E.)
| | - Phil A. Hart
- Division of Gastroenterology, Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA;
| | - Somashekar G. Krishna
- Division of Gastroenterology, Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA;
| |
Collapse
|
7
|
Lv B, Wang K, Wei N, Yu F, Tao T, Shi Y. Diagnostic value of deep learning-assisted endoscopic ultrasound for pancreatic tumors: a systematic review and meta-analysis. Front Oncol 2023; 13:1191008. [PMID: 37576885 PMCID: PMC10414790 DOI: 10.3389/fonc.2023.1191008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 07/13/2023] [Indexed: 08/15/2023] Open
Abstract
Background and aims Endoscopic ultrasonography (EUS) is commonly utilized in the diagnosis of pancreatic tumors, although as this modality relies primarily on the practitioner's visual judgment, it is prone to result in a missed diagnosis or misdiagnosis due to inexperience, fatigue, or distraction. Deep learning (DL) techniques, which can be used to automatically extract detailed imaging features from images, have been increasingly beneficial in the field of medical image-based assisted diagnosis. The present systematic review included a meta-analysis aimed at evaluating the accuracy of DL-assisted EUS for the diagnosis of pancreatic tumors diagnosis. Methods We performed a comprehensive search for all studies relevant to EUS and DL in the following four databases, from their inception through February 2023: PubMed, Embase, Web of Science, and the Cochrane Library. Target studies were strictly screened based on specific inclusion and exclusion criteria, after which we performed a meta-analysis using Stata 16.0 to assess the diagnostic ability of DL and compare it with that of EUS practitioners. Any sources of heterogeneity were explored using subgroup and meta-regression analyses. Results A total of 10 studies, involving 3,529 patients and 34,773 training images, were included in the present meta-analysis. The pooled sensitivity was 93% (95% confidence interval [CI], 87-96%), the pooled specificity was 95% (95% CI, 89-98%), and the area under the summary receiver operating characteristic curve (AUC) was 0.98 (95% CI, 0.96-0.99). Conclusion DL-assisted EUS has a high accuracy and clinical applicability for diagnosing pancreatic tumors. Systematic review registration https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023391853, identifier CRD42023391853.
Collapse
Affiliation(s)
- Bing Lv
- School of Computer Science and Technology, Shandong University of Technology, Zibo, Shandong, China
| | - Kunhong Wang
- Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China
| | - Ning Wei
- Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China
| | - Feng Yu
- Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China
| | - Tao Tao
- Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China
| | - Yanting Shi
- Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China
| |
Collapse
|
8
|
Megibow AJ. Pancreatic Cysts: Radiology. Gastrointest Endosc Clin N Am 2023; 33:519-531. [PMID: 37245933 DOI: 10.1016/j.giec.2023.03.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/30/2023]
Abstract
This article reviews the types of pancreatic cysts encountered in Radiologic practice. It summarizes the malignancy risk of each of the following: serous cystadenoma, mucinous cystic tumor, intraductal papillary mucinous neoplasm main duct and side branch, and some miscellaneous cysts such as neuroendocrine tumor and solid pseudopapillary epithelial neoplasm. Specific reporting recommendations are given. The choice between radiology follow-up versus endoscopic analysis is discussed.
Collapse
Affiliation(s)
- Alec J Megibow
- Department of Radiology, NYU-Langone Health, 550 1st Avenue, Room HCC 232, New York, NY 10016, USA.
| |
Collapse
|
9
|
Comparative Performance of Endoscopic Ultrasound-Based Techniques in Patients With Pancreatic Cystic Lesions: A Network Meta-Analysis. Am J Gastroenterol 2023; 118:243-255. [PMID: 36563321 DOI: 10.14309/ajg.0000000000002088] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/09/2022] [Accepted: 11/02/2022] [Indexed: 12/25/2022]
Abstract
INTRODUCTION Evidence on the comparative diagnostic performance of endoscopic ultrasound (EUS)-based techniques for pancreatic cystic lesions (PCLs) is limited. This network meta-analysis comprehensively compared EUS-based techniques for PCL diagnosis. METHODS A comprehensive literature search was performed for all comparative studies assessing the accuracy of 2 or more modalities for PCL diagnosis. The primary outcome was the diagnostic efficacy for mucinous PCLs. Secondary outcomes were the diagnostic efficacy for malignant PCLs, diagnostic success rate, and adverse event rate. A network meta-analysis was conducted using the ANOVA model to assess the diagnostic accuracy of each index. RESULTS Forty studies comprising 3,641 patients were identified. The network ranking of the superiority index for EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) and EUS-guided through-the-needle biopsy (EUS-TTNB) were significantly higher than other techniques for differentiating mucinous PCLs; besides, EUS-TTNB was also the optimal technique in identifying malignant PCLs. The evidence was inadequate for EUS-nCLE diagnosing malignant PCLs and contrast-enhanced harmonic EUS diagnosing both mucinous and malignant PCLs. Glucose showed a high sensitivity but low specificity, and molecular analysis (KRAS, GNAS, and KRAS + GNAS mutations) showed a high specificity but low sensitivity for diagnosing mucinous PCLs. Satisfactory results were not obtained during the evaluation of the efficiency of pancreatic cyst fluid (PCF) biomarkers in detecting malignant PCLs. DISCUSSION For centers with relevant expertise and facilities, EUS-TTNB and EUS-nCLE were better choices for the diagnosis of PCLs. Further studies are urgently required for further improving PCF biomarkers and validating the diagnostic performance of the index techniques.
Collapse
|
10
|
Alwahbi O, Ghumman Z, van der Pol CB, Patlas M, Gopee-Ramanan P. Pancreatic Cystic Lesions: Review of the Current State of Diagnosis and Surveillance. Can Assoc Radiol J 2022:8465371221130524. [PMID: 36220377 DOI: 10.1177/08465371221130524] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Pancreatic cystic lesions (PCLs) are both common and often incidental. These encompass a range of pathologies with varying degrees of concern for malignancy. Although establishing a diagnosis is helpful for determining malignant potential, many PCLs are either too small to characterize or demonstrate nonspecific morphologic features. The most salient modalities involved in diagnosis and surveillance are magnetic resonance imaging, multidetector computerized tomography, and endoscopic ultrasound. Fine needle aspiration has a role in conjunction with molecular markers as a diagnostic tool, particularly for identifying malignant lesions. Although several major consensus guidelines exist internationally, there remains uncertainty in establishing the strength of the association between all PCLs and pancreatic adenocarcinoma, and in showing a benefit from extended periods of imaging surveillance. No consensus exists between the major guidelines, particularly regarding surveillance duration, frequency, or endpoints. This review paper discusses PCL subtypes, diagnosis, and compares the major consensus guidelines with considerations for local adaptability along with questions regarding current and future priorities for research.
Collapse
Affiliation(s)
- Omar Alwahbi
- Department of Radiology, 62703McMaster University Health Sciences Centre (HSC - 3N26), Hamilton, ON, Canada
| | - Zonia Ghumman
- Department of Radiology, 62703McMaster University Health Sciences Centre (HSC - 3N26), Hamilton, ON, Canada.,Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, ON, Canada
| | - Christian B van der Pol
- Department of Radiology, 62703McMaster University Health Sciences Centre (HSC - 3N26), Hamilton, ON, Canada.,Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, ON, Canada
| | - Michael Patlas
- Department of Radiology, 62703McMaster University Health Sciences Centre (HSC - 3N26), Hamilton, ON, Canada.,Hamilton General Hospital, Hamilton Health Sciences, Hamilton, ON, Canada
| | - Prasaanthan Gopee-Ramanan
- Department of Radiology, 62703McMaster University Health Sciences Centre (HSC - 3N26), Hamilton, ON, Canada.,Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, ON, Canada
| |
Collapse
|
11
|
Alwahbi O, Larocque N, Kulkarni A, Gopee-Ramanan PP, Ghumman Z, Sarkar R, Kagoma Y, Alabousi A, Tsai S, Wat J, McInnes M, van der Pol CB. Pancreatic Cystic Lesions on MRI: What Is The Likelihood of a Present or Future Diagnosis of Pancreatic Carcinoma? J Magn Reson Imaging 2022; 57:1567-1575. [PMID: 36151888 DOI: 10.1002/jmri.28438] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Revised: 09/07/2022] [Accepted: 09/07/2022] [Indexed: 11/09/2022] Open
Abstract
BACKGROUND Pancreatic cystic lesions (PCLs) are followed for years due to older and likely biased works demonstrating a strong association with pancreatic carcinoma; more recent data are needed clarifying this relationship. PURPOSE To determine the association between PCLs on MRI and a synchronous or future diagnosis of pancreatic carcinoma. STUDY TYPE Single-center retrospective cohort. POPULATION A total of 192 patients (111 female, 58%) with median age 66 years (range 26-87 years) with PCLs on abdominal MRI from 2011 to 2016. FIELD STRENGTH/SEQUENCES 1.5 T and 3 T, including T2 WI, T1 WI, diffusion weighted imaging and contrast-enhanced T1 WI. ASSESSMENT Each PCL was reviewed independently by 2 of 10 fellowship-trained abdominal radiologists. Fukuoka guideline worrisome features and high-risk stigmata were evaluated. Follow-up imaging and clinical notes were reviewed within a system that captures pancreatic carcinoma for the region, for a median follow-up of 67 months (interquartile range: 43-88 months). STATISTICAL TESTS Pancreatic carcinoma prevalence and incidence rate for future carcinoma with 95% confidence intervals (95% CI). Fisher exact test, logistic regression with odds ratios (OR) and the Wilcoxon rank-sum test were used to assess PCL morphologic features with the Kolmogorov-Smirnov test used to assess for normality. P < 0.05 defined statistical significance. RESULTS The prevalence of pancreatic carcinoma on initial MRI showing a PCL was 2.4% (95% CI: 0.9%, 5.2%). Thickened/enhancing cyst wall was associated with pancreatic carcinoma, OR 52 (95% CI: 4.5, 1203). Of 189 patients with a PCL but without pancreatic carcinoma at the time of initial MRI, one developed high-grade dysplasia and none developed invasive carcinoma for an incidence rate of 0.97 (95% CI: 0.02, 5.43) and 0 (95% CI: 0, 3.59) cases per 1000 person-years, respectively. DATA CONCLUSION A low percentage of patients with a PCL on MRI had a pancreatic carcinoma at the time of initial evaluation and none developed carcinoma over a median 67 months of follow-up. EVIDENCE LEVEL 3 TECHNICAL EFFICACY: 5.
Collapse
Affiliation(s)
- Omar Alwahbi
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada
| | - Natasha Larocque
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Hamilton General Hospital, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Ameya Kulkarni
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Prasaanthan Prasa Gopee-Ramanan
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Zonia Ghumman
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Rahul Sarkar
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Yoan Kagoma
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Abdullah Alabousi
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, St. Joseph's Healthcare Hamilton, Hamilton, Ontario, Canada
| | - Scott Tsai
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Josephine Wat
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| | - Matthew McInnes
- Department of Radiology and Epidemiology, University of Ottawa, Canada.,Ottawa Hospital Research Institute Clinical Epidemiology Program, Ontario, Canada
| | - Christian B van der Pol
- Department of Radiology, Hamilton Health Sciences, McMaster University, Hamilton, Ontario, Canada.,Department of Diagnostic Imaging, Juravinski Hospital and Cancer Centre, Hamilton Health Sciences, Hamilton, Ontario, Canada
| |
Collapse
|
12
|
Pancreatic Incidentaloma. J Clin Med 2022; 11:jcm11164648. [PMID: 36012893 PMCID: PMC9409921 DOI: 10.3390/jcm11164648] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Revised: 08/03/2022] [Accepted: 08/08/2022] [Indexed: 11/16/2022] Open
Abstract
Pancreatic incidentalomas (PIs) represent a clinical entity increasingly recognized due to advances in and easier access to imaging techniques. By definition, PIs should be detected during abdominal imaging performed for indications other than a pancreatic disease. They range from small cysts to invasive cancer. The incidental diagnosis of pancreatic cancer can contribute to early diagnosis and treatment. On the other hand, inadequate management of PIs may result in overtreatment and unneeded morbidity. Therefore, there is a strong need to evaluate the nature and clinical features of individual PIs. In this review, we summarize the major characteristics related to PIs and present suggestions for their management.
Collapse
|
13
|
Pușcașu CI, Rimbaş M, Mateescu RB, Larghi A, Cauni V. Advances in the Diagnosis of Pancreatic Cystic Lesions. Diagnostics (Basel) 2022; 12:diagnostics12081779. [PMID: 35892490 PMCID: PMC9394320 DOI: 10.3390/diagnostics12081779] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2022] [Revised: 07/18/2022] [Accepted: 07/18/2022] [Indexed: 11/16/2022] Open
Abstract
Pancreatic cystic lesions (PCLs) are a heterogenous group of lesions ranging from benign to malignant. There has been an increase in PCLs prevalence in recent years, mostly due to advances in imaging techniques, increased awareness of their existence and population aging. Reliable discrimination between neoplastic and non-neoplastic cystic lesions is paramount to ensuring adequate treatment and follow-up. Although conventional diagnostic techniques such as ultrasound (US), magnetic resonance imaging (MRI) and computer tomography (CT) can easily identify these lesions, assessing the risk of malignancy is limited. Endoscopic ultrasound (EUS) is superior to cross-sectional imaging in identifying potentially malignant lesions due to its high resolution and better imaging characteristics, and the advantage of allowing for cyst fluid sampling via fine-needle aspiration (FNA). More complex testing, such as cytological and histopathological analysis and biochemical and molecular testing of the aspirated fluid, can ensure an accurate diagnosis.
Collapse
Affiliation(s)
- Claudia Irina Pușcașu
- Gastroenterology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania; (C.I.P.); (R.B.M.)
| | - Mihai Rimbaş
- Gastroenterology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania; (C.I.P.); (R.B.M.)
- Department of Internal Medicine, Carol Davila University of Medicine, 050474 Bucharest, Romania
- Correspondence: ; Tel.: +40-723-232-052
| | - Radu Bogdan Mateescu
- Gastroenterology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania; (C.I.P.); (R.B.M.)
- Department of Internal Medicine, Carol Davila University of Medicine, 050474 Bucharest, Romania
| | - Alberto Larghi
- Digestive Endoscopy Unit, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy;
| | - Victor Cauni
- Urology Department, Colentina Clinical Hospital, 020125 Bucharest, Romania;
| |
Collapse
|
14
|
Rangwani S, Ardeshna DR, Rodgers B, Melnychuk J, Turner R, Culp S, Chao WL, Krishna SG. Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions. Biomimetics (Basel) 2022; 7:biomimetics7020079. [PMID: 35735595 PMCID: PMC9221027 DOI: 10.3390/biomimetics7020079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Revised: 06/07/2022] [Accepted: 06/07/2022] [Indexed: 12/10/2022] Open
Abstract
The rate of incidentally detected pancreatic cystic lesions (PCLs) has increased over the past decade and was recently reported at 8%. These lesions pose a unique challenge, as each subtype of PCL carries a different risk of malignant transformation, ranging from 0% (pancreatic pseudocyst) to 34–68% (main duct intraductal papillary mucinous neoplasm). It is imperative to correctly risk-stratify the malignant potential of these lesions in order to provide the correct care course for the patient, ranging from monitoring to surgical intervention. Even with the multiplicity of guidelines (i.e., the American Gastroenterology Association guidelines and Fukuoka/International Consensus guidelines) and multitude of diagnostic information, risk stratification of PCLs falls short. Studies have reported that 25–64% of patients undergoing PCL resection have pancreatic cysts with no malignant potential, and up to 78% of mucin-producing cysts resected harbor no malignant potential on pathological evaluation. Clinicians are now incorporating artificial intelligence technology to aid in the management of these difficult lesions. This review article focuses on advancements in artificial intelligence within digital pathomics, radiomics, and genomics as they apply to the diagnosis and risk stratification of PCLs.
Collapse
Affiliation(s)
- Shiva Rangwani
- Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (S.R.); (D.R.A.)
| | - Devarshi R. Ardeshna
- Department of Internal Medicine, Ohio State University Wexner Medical Center, Columbus, OH 43210, USA; (S.R.); (D.R.A.)
| | - Brandon Rodgers
- College of Medicine, The Ohio State University, Columbus, OH 43210, USA; (B.R.); (J.M.); (R.T.)
| | - Jared Melnychuk
- College of Medicine, The Ohio State University, Columbus, OH 43210, USA; (B.R.); (J.M.); (R.T.)
| | - Ronald Turner
- College of Medicine, The Ohio State University, Columbus, OH 43210, USA; (B.R.); (J.M.); (R.T.)
| | - Stacey Culp
- Department of Biomedical Informatics, The Ohio State University College of Medicine, Columbus, OH 43210, USA;
| | - Wei-Lun Chao
- Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210, USA;
| | - Somashekar G. Krishna
- Department of Gastroenterology, Hepatology, and Nutrition, The Ohio State University Wexner Medical Center, Columbus, OH 43210, USA
- Correspondence: ; Tel.: +614-293-6255
| |
Collapse
|