1
|
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA. Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model. Ann Surg Oncol 2024:10.1245/s10434-024-16064-4. [PMID: 39179862 DOI: 10.1245/s10434-024-16064-4] [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: 05/10/2024] [Accepted: 08/04/2024] [Indexed: 08/26/2024]
Abstract
BACKGROUND PanNETs are a rare group of pancreatic tumors that display heterogeneous histopathological and clinical behavior. Nodal disease has been established as one of the strongest predictors of patient outcomes in PanNETs. Lack of accurate preoperative assessment of nodal disease is a major limitation in the management of these patients, in particular those with small (< 2 cm) low-grade tumors. The aim of the study was to evaluate the ability of radiomic features (RF) to preoperatively predict the presence of nodal disease in pancreatic neuroendocrine tumors (PanNETs). PATIENTS AND METHODS An institutional database was used to identify patients with nonfunctional PanNETs undergoing resection. Pancreas protocol computed tomography was obtained, manually segmented, and RF were extracted. These were analyzed using the minimum redundancy maximum relevance analysis for hierarchical feature selection. Youden index was used to identify the optimal cutoff for predicting nodal disease. A random forest prediction model was trained using RF and clinicopathological characteristics and validated internally. RESULTS Of the 320 patients included in the study, 92 (28.8%) had nodal disease based on histopathological assessment of the surgical specimen. A radiomic signature based on ten selected RF was developed. Clinicopathological characteristics predictive of nodal disease included tumor grade and size. Upon internal validation the combined radiomics and clinical feature model demonstrated adequate performance (AUC 0.80) in identifying nodal disease. The model accurately identified nodal disease in 85% of patients with small tumors (< 2 cm). CONCLUSIONS Non-invasive preoperative assessment of nodal disease using RF and clinicopathological characteristics is feasible.
Collapse
Affiliation(s)
- Taha M Ahmed
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Zhuotun Zhu
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Mohammad Yasrab
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Alejandra Blanco
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Satomi Kawamoto
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Jin He
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Elliot K Fishman
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Linda Chu
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Ammar A Javed
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
- Division of Hepatobiliary and Pancreatic Surgery, Department of Surgery, NYU Langone Grossman School of Medicine, New York, NY, USA.
| |
Collapse
|
2
|
Yan Q, Chen Y, Liu C, Shi H, Han M, Wu Z, Huang S, Zhang C, Hou B. Predicting histologic grades for pancreatic neuroendocrine tumors by radiologic image-based artificial intelligence: a systematic review and meta-analysis. Front Oncol 2024; 14:1332387. [PMID: 38725633 PMCID: PMC11080013 DOI: 10.3389/fonc.2024.1332387] [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: 11/02/2023] [Accepted: 04/02/2024] [Indexed: 05/12/2024] Open
Abstract
Background Accurate detection of the histological grade of pancreatic neuroendocrine tumors (PNETs) is important for patients' prognoses and treatment. Here, we investigated the performance of radiological image-based artificial intelligence (AI) models in predicting histological grades using meta-analysis. Method A systematic literature search was performed for studies published before September 2023. Study characteristics and diagnostic measures were extracted. Estimates were pooled using random-effects meta-analysis. Evaluation of risk of bias was performed by the QUADAS-2 tool. Results A total of 26 studies were included, 20 of which met the meta-analysis criteria. We found that the AI-based models had high area under the curve (AUC) values and showed moderate predictive value. The pooled distinguishing abilities between different grades of PNETs were 0.89 [0.84-0.90]. By performing subgroup analysis, we found that the radiomics feature-only models had a predictive value of 0.90 [0.87-0.92] with I2 = 89.91%, while the pooled AUC value of the combined group was 0.81 [0.77-0.84] with I2 = 41.54%. The validation group had a pooled AUC of 0.84 [0.81-0.87] without heterogenicity, whereas the validation-free group had high heterogenicity (I2 = 91.65%, P=0.000). The machine learning group had a pooled AUC of 0.83 [0.80-0.86] with I2 = 82.28%. Conclusion AI can be considered as a potential tool to detect histological PNETs grades. Sample diversity, lack of external validation, imaging modalities, inconsistent radiomics feature extraction across platforms, different modeling algorithms and software choices were sources of heterogeneity. Standardized imaging, transparent statistical methodologies for feature selection and model development are still needed in the future to achieve the transformation of radiomics results into clinical applications. Systematic Review Registration https://www.crd.york.ac.uk/prospero/, identifier CRD42022341852.
Collapse
Affiliation(s)
- Qian Yan
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- School of Medicine, South China University of Technology, Guangzhou, China
| | - Yubin Chen
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- School of Medicine, South China University of Technology, Guangzhou, China
| | - Chunsheng Liu
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Hexian Shi
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Mingqian Han
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Zelong Wu
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Shanzhou Huang
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- School of Medicine, South China University of Technology, Guangzhou, China
| | - Chuanzhao Zhang
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- School of Medicine, South China University of Technology, Guangzhou, China
| | - Baohua Hou
- Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of General Surgery, Heyuan People’s Hospital, Heyuan, China
| |
Collapse
|
3
|
Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC. A primer on artificial intelligence in pancreatic imaging. Diagn Interv Imaging 2023; 104:435-447. [PMID: 36967355 DOI: 10.1016/j.diii.2023.03.002] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2023] [Accepted: 03/06/2023] [Indexed: 06/18/2023]
Abstract
Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication. This article reviews the current status of artificial intelligence in pancreatic imaging and critically appraises the quality of existing evidence using the radiomics quality score.
Collapse
Affiliation(s)
- Taha M Ahmed
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Satomi Kawamoto
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Ralph H Hruban
- Sol Goldman Pancreatic Research Center, Department of Pathology, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Elliot K Fishman
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Philippe Soyer
- Université Paris Cité, Faculté de Médecine, Department of Radiology, Hôpital Cochin-APHP, 75014, 75006, Paris, France, 7501475006
| | - Linda C Chu
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA.
| |
Collapse
|
4
|
Javed AA, Pulvirenti A, Zheng J, Michelakos T, Sekigami Y, Razi S, McIntyre CA, Thompson E, Klimstra DS, Deshpande V, Singhi AD, Weiss MJ, Wolfgang CL, Cameron JL, Wei AC, Zureikat AH, Ferrone CR, He J. A novel tool to predict nodal metastasis in small pancreatic neuroendocrine tumors: A multicenter study. Surgery 2022; 172:1800-1806. [PMID: 36192215 DOI: 10.1016/j.surg.2022.08.022] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2022] [Revised: 07/25/2022] [Accepted: 08/19/2022] [Indexed: 01/06/2023]
Abstract
BACKGROUND Nonfunctional pancreatic neuroendocrine tumors display a wide range of biological behavior, and nodal disease is associated with metastatic disease and poorer survival. The aim of this study was to develop a tool to predict nodal disease in patients with small (≤2 cm) nonfunctional pancreatic neuroendocrine tumors. METHODS A multicenter retrospective study was performed on patients undergoing resection for small nonfunctional pancreatic neuroendocrine tumors. Patients with genetic syndromes, metastatic disease at diagnosis, neoadjuvant therapy, or positive resection margin were excluded. Factors associated with nodal disease were identified to develop a predictive model. Internal validation was performed using bootstrap with 1,000 resamples. RESULTS Nodal disease was observed in 39 (11.1%) of the 353 patients included. Presence of nodal disease was significantly associated with lower 5-year disease-free survival (71.6% vs 96.2%, P < .001). Two predictors were strongly associated with nodal disease: G2 grade (odds ratio: 3.51, 95% confidence interval: 1.71-7.22, P = .001) and tumor size (per mm increase, odds ratio: 1.14, 95% confidence interval: 1.03-1.25, P = .009). Adequate discrimination was observed with an area under the curve of 0.71 (95% confidence interval: 0.63-0.80). Based on risk distribution, 3 risk groups of nodal disease were identified; low (<5%), intermediate (≥5% to <20%), and high (≥20%) risk. The observed mean risk of nodal disease was 3.7% in the low-risk patients, 9.6% in the intermediate-risk patients, and 30.4% in the high-risk patients (P < .001). The 10-year disease-free survival in the low, intermediate, and high-risk groups was 100%, 88.8%, and 50.1%, respectively. CONCLUSION Our model using tumor grade and size can predict nodal disease in small nonfunctional pancreatic neuroendocrine tumors. Integration of this tool into clinical practice could help guide management of these patients.
Collapse
Affiliation(s)
- Ammar A Javed
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD. http://www.twitter.com/ammar_asrar
| | | | - Jian Zheng
- Department of Surgery, University of Pittsburgh School of Medicine, PA
| | | | - Yurie Sekigami
- Department of Surgery, Massachusetts General Hospital, Boston, MA
| | - Samrah Razi
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD
| | - Caitlin A McIntyre
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Elizabeth Thompson
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD
| | - David S Klimstra
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Vikram Deshpande
- Department of Surgery, Massachusetts General Hospital, Boston, MA
| | - Aatur D Singhi
- Department of Surgery, University of Pittsburgh School of Medicine, PA
| | | | | | - John L Cameron
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD
| | - Alice C Wei
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Amer H Zureikat
- Department of Surgery, University of Pittsburgh School of Medicine, PA
| | | | - Jin He
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD.
| |
Collapse
|
5
|
Staal FCR, Aalbersberg EA, van der Velden D, Wilthagen EA, Tesselaar MET, Beets-Tan RGH, Maas M. GEP-NET radiomics: a systematic review and radiomics quality score assessment. Eur Radiol 2022; 32:7278-7294. [PMID: 35882634 DOI: 10.1007/s00330-022-08996-w] [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: 02/21/2022] [Revised: 05/25/2022] [Accepted: 06/26/2022] [Indexed: 11/04/2022]
Abstract
OBJECTIVE The number of radiomics studies in gastroenteropancreatic neuroendocrine tumours (GEP-NETs) is rapidly increasing. This systematic review aims to provide an overview of the available evidence of radiomics for clinical outcome measures in GEP-NETs, to understand which applications hold the most promise and which areas lack evidence. METHODS PubMed, Embase, and Wiley/Cochrane Library databases were searched and a forward and backward reference check of the identified studies was executed. Inclusion criteria were (1) patients with GEP-NETs and (2) radiomics analysis on CT, MRI or PET. Two reviewers independently agreed on eligibility and assessed methodological quality with the radiomics quality score (RQS) and extracted outcome data. RESULTS In total, 1364 unique studies were identified and 45 were included for analysis. Most studies focused on GEP-NET grade and differential diagnosis of GEP-NETs from other neoplasms, while only a minority analysed treatment response or long-term outcomes. Several studies were able to predict tumour grade or to differentiate GEP-NETs from other lesions with a good performance (AUCs 0.74-0.96 and AUCs 0.80-0.99, respectively). Only one study developed a model to predict recurrence in pancreas NETs (AUC 0.77). The included studies reached a mean RQS of 18%. CONCLUSION Although radiomics for GEP-NETs is still a relatively new area, some promising models have been developed. Future research should focus on developing robust models for clinically relevant aims such as prediction of response or long-term outcome in GEP-NET, since evidence for these aims is still scarce. KEY POINTS • The majority of radiomics studies in gastroenteropancreatic neuroendocrine tumours is of low quality. • Most evidence for radiomics is available for the identification of tumour grade or differentiation of gastroenteropancreatic neuroendocrine tumours from other neoplasms. • Radiomics for the prediction of response or long-term outcome in gastroenteropancreatic neuroendocrine tumours warrants further research.
Collapse
Affiliation(s)
- Femke C R Staal
- Department of Radiology, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.,GROW School for Oncology and Reproduction, Maastricht University Medical Centre, Universiteitssingel 40, 6229 ER, Maastricht, The Netherlands.,The Netherlands Cancer Institute/University Medical Center Utrecht Center for Neuroendocrine Tumors, ENETS Center of Excellence, Amsterdam/Utrecht, The Netherlands
| | - Else A Aalbersberg
- The Netherlands Cancer Institute/University Medical Center Utrecht Center for Neuroendocrine Tumors, ENETS Center of Excellence, Amsterdam/Utrecht, The Netherlands.,Department of Nuclear Medicine, The Netherlands Cancer Institute Amsterdam, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Daphne van der Velden
- Department of Radiology, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Erica A Wilthagen
- Scientific Information Service, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Margot E T Tesselaar
- The Netherlands Cancer Institute/University Medical Center Utrecht Center for Neuroendocrine Tumors, ENETS Center of Excellence, Amsterdam/Utrecht, The Netherlands.,Department of Medical Oncology, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands
| | - Regina G H Beets-Tan
- Department of Radiology, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.,GROW School for Oncology and Reproduction, Maastricht University Medical Centre, Universiteitssingel 40, 6229 ER, Maastricht, The Netherlands.,Faculty of Health Sciences, University of Southern Denmark, J. B. Winsløws Vej 19, 3, 5000, Odense, Denmark
| | - Monique Maas
- Department of Radiology, The Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.
| |
Collapse
|
6
|
van der Velden D, Staal F, Aalbersberg E, Castagnoli F, Wilthagen E, Beets-Tan R. Prognostic value of CT characteristics in GEP-NET: a systematic review. Crit Rev Oncol Hematol 2022; 175:103713. [DOI: 10.1016/j.critrevonc.2022.103713] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2022] [Revised: 05/04/2022] [Accepted: 05/16/2022] [Indexed: 11/16/2022] Open
|