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
|
Ohno E, Balduzzi A, Hijioka S, De Pastena M, Marchegiani G, Kato H, Takenaka M, Haba S, Salvia R. Association of high-risk stigmata and worrisome features with advanced neoplasia in intraductal papillary mucinous neoplasms (IPMN): A systematic review. Pancreatology 2024; 24:48-61. [PMID: 38161091 DOI: 10.1016/j.pan.2023.12.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 11/24/2023] [Accepted: 12/03/2023] [Indexed: 01/03/2024]
Abstract
BACKGROUND This systematic review aimed to assess the diagnostic accuracy of the International Consensus Fukuoka Guidelines (ICG2017) in identifying high-risk lesions of Intraductal Papillary Mucinous Neoplasms (IPMNs). METHODS The ICG2017 revision committee conducted a comprehensive literature review to establish evidence-based statements on IPMNs. The review focused on articles examining the diagnostic value of imaging features (e.g., cyst or main pancreatic duct diameter), clinical symptoms associated with IPMN, and serum biomarkers. Five clinical questions regarding high-risk stigmata (HRS) and worrisome features (WF) in the ICG2017 guidelines were addressed. RESULTS A total of 210 articles were reviewed. The findings revealed a significant association between the presence of mural nodules ≥5 mm in diameter or solid components with contrast enhancement and the diagnosis of high-grade dysplasia or invasive carcinoma. Contrast-enhanced diagnostic tools, such as CT, MRI, or EUS, demonstrated the highest prediction rate and were recommended. Positive cytology was identified as an HRS, while symptoms like acute pancreatitis and cyst diameter growth ≥2.5 mm per year were considered WFs. The use of nomograms and multiple diagnostic factors was recommended for optimal IPMN management. CONCLUSIONS This systematic review provides evidence supporting the improved diagnostic accuracy of ICG2017 in identifying high-risk lesions of IPMN. The multidisciplinary incorporation of HRS and WF based on imaging findings and clinical symptoms is crucial. These findings should inform the revision of ICG2017, enhancing the evaluation and management of IPMN patients. By implementing these recommendations, clinicians can make more informed decisions, leading to better diagnosis and treatment outcomes for high-risk IPMN cases.
Collapse
Affiliation(s)
- Eizaburo Ohno
- Fujita Health University, Department of Gastroenterology and Hepatology, Japan; Nagoya University Hospital, Department of Gastroenterology and Hepatology, Japan
| | - Alberto Balduzzi
- The Pancreas Institute Verona, Unit of General and Pancreatic Surgery Department of Surgery, Dentistry, Paediatrics and Gynaecology University of Verona, Italy
| | - Susumu Hijioka
- National Cancer Center Hospital, Department of Hepatobiliary and Pancreatic Oncology, Japan
| | - Matteo De Pastena
- The Pancreas Institute Verona, Unit of General and Pancreatic Surgery Department of Surgery, Dentistry, Paediatrics and Gynaecology University of Verona, Italy
| | - Giovanni Marchegiani
- Hepato-Pancreato-Biliary Surgery and Liver Transplantation Unit, Department of Surgical, Oncological and Gastroenterological Sciences (DISCOG), University of Padua, Padua, Italy
| | - Hironari Kato
- Okayama University Hospital, Department of Gastroenterology and Hepatology, Japan
| | - Mamoru Takenaka
- Kindai University, Department of Gastroenterology and Hepatology, Japan
| | - Shin Haba
- Aichi Cancer Center Hospital, Department of Gastroenterology, Japan
| | - Roberto Salvia
- The Pancreas Institute Verona, Unit of General and Pancreatic Surgery Department of Surgery, Dentistry, Paediatrics and Gynaecology University of Verona, Italy.
| |
Collapse
|
3
|
Pollini T, Marchegiani G, Facciorusso A, Balduzzi A, Biancotto M, Bassi C, Maker AV, Salvia R. It is not necessary to resect all mucinous cystic neoplasms of the pancreas: current guidelines do not reflect the actual risk of malignancy. HPB (Oxford) 2023:S1365-182X(23)00074-6. [PMID: 37003852 DOI: 10.1016/j.hpb.2023.03.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Revised: 02/06/2023] [Accepted: 03/03/2023] [Indexed: 04/03/2023]
Abstract
BACKGROUND Mucinous Cystic Neoplasms (MCN) of the pancreas are premalignant cysts for which current guidelines support pancreatic resection. The primary aim of this systematic review and meta-analysis is to define the pooled rate of malignancy for MCN. METHODS A systematic review of eligible studies published between 2000 and 2021 was performed on PubMed and Embase. Primary outcome was rate of malignancy. Data regarding high-risk features, including cyst size and mural nodules, were collected and analyzed. RESULTS A total of 40 studies and 3292 patients with resected MCN were included in the final analysis. The pooled rate of malignancy was 16.1% (95%CI 13.1-19.0). The rate of malignant MCN in studies published before 2012 was significantly higher than that of studies published after recent guidelines were published (21.0% vs 14.9%, p < 0.001). Malignant MCN were larger than benign (mean difference 25.9 mm 95%CI 14.50-37.43, p < 0.001) with a direct correlation between size and presence of malignant MCN (R2 = 0.28, p = 0.020). A SROC identified a threshold of 65 mm to be associated with the diagnosis of malignant MCN. Presence of mural nodules was associated with the diagnosis of a malignant MCN (OR = 4.34, 95%CI 3.00-6.29, p < 0.001). CONCLUSION Whereas guidelines recommend resection of all MCN, the rate of malignancy in resected MCN is 16%, implying that surveillance has a role in most cases, and that surgical selection criteria are warranted. Size and presence of mural nodules are significantly associated with an increased risk of malignant degeneration, small MCN and without mural nodules can be considered for surveillance.
Collapse
Affiliation(s)
- Tommaso Pollini
- Division of Surgical Oncology, Department of Surgery, University of California San Francisco, San Francisco, USA; The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy
| | - Giovanni Marchegiani
- The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy
| | - Antonio Facciorusso
- Gastroenterology Unit, Department of Surgical and Medical Sciences, University of Foggia, Foggia, Italy
| | - Alberto Balduzzi
- The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy
| | - Marco Biancotto
- The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy
| | - Claudio Bassi
- The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy
| | - Ajay V Maker
- Division of Surgical Oncology, Department of Surgery, University of California San Francisco, San Francisco, USA
| | - Roberto Salvia
- The Pancreas Institute, Department of General and Pancreatic Surgery, University of Verona, Verona, Italy.
| |
Collapse
|