A Novel Model for Predicting Postoperative Liver Metastasis in R0 Resected Pancreatic Neuroendocrine Tumors: Integrating Computational Pathology and Deep Learning-radiomics

Overview

Journal J Transl Med

Publisher Biomed Central

Specialties Biomedical Engineering
General Medicine

Date 2024 Aug 14

PMID 39143624

Authors

Mengke Ma

Wenchao Gu

Yun Liang

Xueping Han

Meng Zhang

Midie Xu

Heli Gao

Wei Tang

Dan Huang

Affiliations

Soon will be listed here.

Abstract

Background: Postoperative liver metastasis significantly impacts the prognosis of pancreatic neuroendocrine tumor (panNET) patients after R0 resection. Combining computational pathology and deep learning radiomics can enhance the detection of postoperative liver metastasis in panNET patients.

Methods: Clinical data, pathology slides, and radiographic images were collected from 163 panNET patients post-R0 resection at Fudan University Shanghai Cancer Center (FUSCC) and FUSCC Pathology Consultation Center. Digital image analysis and deep learning identified liver metastasis-related features in Ki67-stained whole slide images (WSIs) and enhanced CT scans to create a nomogram. The model's performance was validated in both internal and external test cohorts.

Results: Multivariate logistic regression identified nerve infiltration as an independent risk factor for liver metastasis (p < 0.05). The Pathomics score, which was based on a hotspot and the heterogeneous distribution of Ki67 staining, showed improved predictive accuracy for liver metastasis (AUC = 0.799). The deep learning-radiomics (DLR) score achieved an AUC of 0.875. The integrated nomogram, which combines clinical, pathological, and imaging features, demonstrated outstanding performance, with an AUC of 0.985 in the training cohort and 0.961 in the validation cohort. High-risk group had a median recurrence-free survival of 28.5 months compared to 34.7 months for the low-risk group, showing significant correlation with prognosis (p < 0.05).

Conclusion: A new predictive model that integrates computational pathologic scores and deep learning-radiomics can better predict postoperative liver metastasis in panNET patients, aiding clinicians in developing personalized treatments.

References

Frilling A, Sotiropoulos G, Radtke A, Malago M, Bockisch A, Kuehl H . The impact of 68Ga-DOTATOC positron emission tomography/computed tomography on the multimodal management of patients with neuroendocrine tumors. Ann Surg. 2010; 252(5):850-6. DOI: 10.1097/SLA.0b013e3181fd37e8. View

Wang R, Dai W, Gong J, Huang M, Hu T, Li H . Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. J Hematol Oncol. 2022; 15(1):11. PMC: 8785554. DOI: 10.1186/s13045-022-01225-3. View

Genc C, Falconi M, Partelli S, Muffatti F, van Eeden S, Doglioni C . Recurrence of Pancreatic Neuroendocrine Tumors and Survival Predicted by Ki67. Ann Surg Oncol. 2018; 25(8):2467-2474. PMC: 6028862. DOI: 10.1245/s10434-018-6518-2. View

Pan M, Yang Y, Teng T, Lu F, Chen Y, Huang H . Development and validation of a simple-to-use nomogram to predict liver metastasis in patients with pancreatic neuroendocrine neoplasms: a large cohort study. BMC Gastroenterol. 2021; 21(1):101. PMC: 7934499. DOI: 10.1186/s12876-021-01685-w. View

Gu D, Hu Y, Ding H, Wei J, Chen K, Liu H . CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study. Eur Radiol. 2019; 29(12):6880-6890. DOI: 10.1007/s00330-019-06176-x. View

Zhou Y, Liu S, Liu C, Yang J, Lin Q, Zheng S . Single-cell RNA sequencing reveals spatiotemporal heterogeneity and malignant progression in pancreatic neuroendocrine tumor. Int J Biol Sci. 2021; 17(14):3760-3775. PMC: 8495381. DOI: 10.7150/ijbs.61717. View

Chu Q, Hill H, Douglass Jr H, Driscoll D, Smith J, Nava H . Predictive factors associated with long-term survival in patients with neuroendocrine tumors of the pancreas. Ann Surg Oncol. 2002; 9(9):855-62. DOI: 10.1007/BF02557521. View

Pulvirenti A, Javed A, Landoni L, Jamieson N, Chou J, Miotto M . Multi-institutional Development and External Validation of a Nomogram to Predict Recurrence After Curative Resection of Pancreatic Neuroendocrine Tumors. Ann Surg. 2019; 274(6):1051-1057. PMC: 8557638. DOI: 10.1097/SLA.0000000000003579. View

La Rosa S . Diagnostic, Prognostic, and Predictive Role of Ki67 Proliferative Index in Neuroendocrine and Endocrine Neoplasms: Past, Present, and Future. Endocr Pathol. 2023; 34(1):79-97. PMC: 10011307. DOI: 10.1007/s12022-023-09755-3. View

10.

Rockall A, Reznek R . Imaging of neuroendocrine tumours (CT/MR/US). Best Pract Res Clin Endocrinol Metab. 2007; 21(1):43-68. DOI: 10.1016/j.beem.2007.01.003. View

11.

Homps M, Soyer P, Coriat R, Dermine S, Pellat A, Fuks D . A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors. Eur J Endocrinol. 2023; 189(4):476-484. DOI: 10.1093/ejendo/lvad130. View

12.

Ito T, Igarashi H, Nakamura K, Sasano H, Okusaka T, Takano K . Epidemiological trends of pancreatic and gastrointestinal neuroendocrine tumors in Japan: a nationwide survey analysis. J Gastroenterol. 2014; 50(1):58-64. DOI: 10.1007/s00535-014-0934-2. View

13.

Li J, Huang L, Liao C, Liu G, Tian Y, Chen S . Two machine learning-based nomogram to predict risk and prognostic factors for liver metastasis from pancreatic neuroendocrine tumors: a multicenter study. BMC Cancer. 2023; 23(1):529. PMC: 10257274. DOI: 10.1186/s12885-023-10893-4. View

14.

Lopez-Aguiar A, Ethun C, Postlewait L, Zhelnin K, Krasinskas A, El-Rayes B . Redefining the Ki-67 Index Stratification for Low-Grade Pancreatic Neuroendocrine Tumors: Improving Its Prognostic Value for Recurrence of Disease. Ann Surg Oncol. 2017; 25(1):290-298. DOI: 10.1245/s10434-017-6140-8. View

15.

Canellas R, Burk K, Parakh A, Sahani D . Prediction of Pancreatic Neuroendocrine Tumor Grade Based on CT Features and Texture Analysis. AJR Am J Roentgenol. 2017; 210(2):341-346. DOI: 10.2214/AJR.17.18417. View

16.

Sonbol M, Mazza G, Mi L, Oliver T, Starr J, Gudmundsdottir H . Survival and Incidence Patterns of Pancreatic Neuroendocrine Tumors Over the Last 2 Decades: A SEER Database Analysis. Oncologist. 2022; 27(7):573-578. PMC: 9255979. DOI: 10.1093/oncolo/oyac049. View

17.

Frilling A, Modlin I, Kidd M, Russell C, Breitenstein S, Salem R . Recommendations for management of patients with neuroendocrine liver metastases. Lancet Oncol. 2014; 15(1):e8-21. DOI: 10.1016/S1470-2045(13)70362-0. View

18.

Huang B, Lin X, Shen J, Chen X, Chen J, Li Z . Accurate and Feasible Deep Learning Based Semi-Automatic Segmentation in CT for Radiomics Analysis in Pancreatic Neuroendocrine Neoplasms. IEEE J Biomed Health Inform. 2021; 25(9):3498-3506. DOI: 10.1109/JBHI.2021.3070708. View

19.

An P, Zhang J, Li M, Duan P, He Z, Wang Z . Clinical Data-CT Radiomics-Based Model for Predicting Prognosis of Patients with Gastrointestinal Pancreatic Neuroendocrine Neoplasms (GP-NENs). Comput Math Methods Med. 2022; 2022:4186305. PMC: 9410919. DOI: 10.1155/2022/4186305. View

20.

Luchini C, Pantanowitz L, Adsay V, Asa S, Antonini P, Girolami I . Ki-67 assessment of pancreatic neuroendocrine neoplasms: Systematic review and meta-analysis of manual vs. digital pathology scoring. Mod Pathol. 2022; 35(6):712-720. PMC: 9174054. DOI: 10.1038/s41379-022-01055-1. View