Radiomics-based prediction of nonalcoholic fatty liver disease following pancreatoduodenectomy.

Exocrine pancreatic insufficiency Machine learning Malnutrition Nonalcoholic fatty liver disease Pancreatectomy

Journal

Surgery today
ISSN: 1436-2813
Titre abrégé: Surg Today
Pays: Japan
ID NLM: 9204360

Informations de publication

Date de publication:
06 Apr 2024
Historique:
received: 18 12 2023
accepted: 09 01 2024
medline: 6 4 2024
pubmed: 6 4 2024
entrez: 6 4 2024
Statut: aheadofprint

Résumé

Predicting nonalcoholic fatty liver disease (NAFLD) following pancreaticoduodenectomy (PD) is challenging, which delays therapeutic intervention and makes its prevention difficult. We conducted this study to assess the potential application of preoperative computed tomography (CT) radiomics for predicting NAFLD. The subjects of this retrospective study were 186 patients with PD from a single institution. We extracted the predictors of NAFLD after PD statistically from conventional clinical and radiomic features of the estimated remnant pancreas and whole liver region on preoperative nonenhanced CT images. Based on these predictors, we developed a machine-learning predictive model, which integrated clinical and radiomic features. A comparative model used only clinical features as predictors. The incidence of NAFLD after PD was 43.5%. The variables of the clinicoradiomic model included one shape feature of the pancreas, two texture features of the liver, and sex; the variables of the clinical model were age, sex, and chemoradiotherapy. The accuracy%, precision%, recall%, F1 score, and area under the curve of the two models were 75.0, 72.7, 66.7, 69.6, and 0.80; and 69.6, 68.4, 54.2, 60.5, and 0.69, respectively. Preoperative CT-derived radiomic features from the pancreatic and liver regions are promising for the prediction of NAFLD post-PD. Using these features enhances the predictive model, enabling earlier intervention for high-risk patients.

Identifiants

pubmed: 38581555
doi: 10.1007/s00595-024-02822-0
pii: 10.1007/s00595-024-02822-0
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© 2024. The Author(s) under exclusive licence to Springer Nature Singapore Pte Ltd.

Références

Kato H, Isaji S, Azumi Y, Kishiwada M, Hamada T, Mizuno S, et al. Development of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH) after pancreaticoduodenectomy: proposal of a postoperative NAFLD scoring system. J Hepato-Bil Pancreat Sci. 2010;17:296–304. https://doi.org/10.1007/s00534-009-0187-2 .
doi: 10.1007/s00534-009-0187-2
Sato R, Kishiwada M, Kuriyama N, Azumi Y, Mizuno S, Usui M, et al. Paradoxical impact of the remnant pancreatic volume and infectious complications on the development of nonalcoholic fatty liver disease after pancreaticoduodenectomy. J Hepato-Bil Pancreat Sci. 2014;21:562–72. https://doi.org/10.1002/jhbp.115 .
doi: 10.1002/jhbp.115
Miura H, Ijichi M, Ando Y, Hayama K, IIhara K, Yamada H, et al. A rapidly progressive and fatal case of nonalcoholic steatohepatitis following pancreaticoduodenectomy. Clin J Gastroenterol. 2013;6:470–5. https://doi.org/10.1007/s12328-013-0421-y .
doi: 10.1007/s12328-013-0421-y pubmed: 26182139
Murata Y, Mizuno S, Kato H, Kishiwada M, Ohsawa I, Hamada T, et al. Nonalcoholic steatohepatitis (NASH) after pancreaticoduodenectomy: association of pancreatic exocrine deficiency and infection. Clin J Gastroenterol. 2011;4:242–8. https://doi.org/10.1007/s12328-011-0226-9 .
doi: 10.1007/s12328-011-0226-9 pubmed: 26189528
Nakagawa N, Murakami Y, Uemura K, Sudo T, Hashimoto Y, Kondo N, et al. Nonalcoholic fatty liver disease after pancreatoduodenectomy is closely associated with postoperative pancreatic exocrine insufficiency. J Surg Oncol. 2014;110:720–6. https://doi.org/10.1002/jso.23693 .
doi: 10.1002/jso.23693 pubmed: 24965234
Matsumoto J, Traverso LW. Exocrine function following the Whipple operation as assessed by stool elastase. J Gastrointest Surg. 2006;10:1225–9. https://doi.org/10.1016/j.gassur.2006.08.001 .
doi: 10.1016/j.gassur.2006.08.001 pubmed: 17114009
Satoi S, Sho M, Yanagimoto H, Yamamoto T, Akahori T, Kinoshita S, et al. Do pancrelipase delayed-release capsules have a protective role against nonalcoholic fatty liver disease after pancreatoduodenectomy in patients with pancreatic cancer? A randomized controlled trial. J Hepatobiliary Pancreat Sci. 2016;23:167–73. https://doi.org/10.1002/jhbp.318 .
doi: 10.1002/jhbp.318 pubmed: 26748629
Yasukawa K, Shimizu A, Yokoyama T, Kubota K, Notake T, Seki H, et al. Preventive effect of high-dose digestive enzyme management on development of nonalcoholic fatty liver disease after pancreaticoduodenectomy: a randomized controlled clinical trial. J Am Coll Surg. 2020;231:658–69. https://doi.org/10.1016/j.jamcollsurg.2020.08.761 .
doi: 10.1016/j.jamcollsurg.2020.08.761 pubmed: 32927075
Hoshino I, Yokota H. Radiogenomics of gastroenterological cancer: the dawn of personalized medicine with artificial intelligence-based image analysis. Ann Gastroenterol Surg. 2021;5:427–35. https://doi.org/10.1002/ags3.12437 .
doi: 10.1002/ags3.12437 pubmed: 34337291 pmcid: 8316732
van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. Radiomics in medical imaging “how-to” guide and critical reflection. Insights Imaging. 2020;11:91. https://doi.org/10.1186/s13244-020-00887-2 .
doi: 10.1186/s13244-020-00887-2 pubmed: 32785796 pmcid: 7423816
Mayerhoefer ME, Materka A, Langs G, Häggström I, Szczypiński P, Gibbs P, et al. Introduction to radiomics. J Nucl Med. 2020;61:488–95. https://doi.org/10.2967/jnumed.118.222893 .
doi: 10.2967/jnumed.118.222893 pubmed: 32060219 pmcid: 9374044
Wu L, Lou X, Kong N, Xu M, Gao C. Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? Syst Rev Eur Radiol. 2023;33:2105–17. https://doi.org/10.1007/s00330-022-09174-8 .
doi: 10.1007/s00330-022-09174-8
Mukherjee S, Patra A, Khasawneh H, Korfiatis P, Rajamohan N, Suman G, et al. Radiomics-based machine learning models can detect pancreatic cancer on prediagnostic CTs at a substantial lead time prior to clinical diagnosis. Gastroenterology. 2022;163:1435-1446.e3. https://doi.org/10.1053/j.gastro.2022.06.066 .
doi: 10.1053/j.gastro.2022.06.066 pubmed: 35788343
van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77:e104–7. https://doi.org/10.1158/0008-5472.CAN-17-0339 .
doi: 10.1158/0008-5472.CAN-17-0339 pubmed: 29092951 pmcid: 5672828
Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825–30.
McGhee-Jez AE, Chervoneva I, Yi M, Ahuja A, Nahar R, Shah S, et al. Nonalcoholic fatty liver disease after pancreaticoduodenectomy for a cancer diagnosis. J Pancreat Cancer. 2021;7:23–30. https://doi.org/10.1089/pancan.2020.0006 .
doi: 10.1089/pancan.2020.0006 pubmed: 34095739 pmcid: 8175252
Tanaka N, Horiuchi A, Yokoyama T, Kaneko G, Horigome N, Yamaura T, et al. Clinical characteristics of de novo nonalcoholic fatty liver disease following pancreaticoduodenectomy. J Gastroenterol. 2011;46:758–68. https://doi.org/10.1007/s00535-011-0370-5 .
doi: 10.1007/s00535-011-0370-5 pubmed: 21267748
Takemura N, Saiura A, Koga R, Yamamoto J, Yamaguchi T. Risk factors for and management of postpancreatectomy hepatic steatosis. Scand J Surg. 2017;106:224–9. https://doi.org/10.1177/1457496916669630 .
doi: 10.1177/1457496916669630 pubmed: 27651297
Maehira H, Iida H, Maekawa T, Yasukawa D, Mori H, Takebayashi K, et al. Estimated functional remnant pancreatic volume predicts nonalcoholic fatty liver disease after pancreaticoduodenectomy: use of computed tomography attenuation value of the pancreas. HPB (Oxford). 2021;23:802–11. https://doi.org/10.1016/j.hpb.2020.09.019 .
doi: 10.1016/j.hpb.2020.09.019 pubmed: 33046368
Ohgi K, Okamura Y, Yamamoto Y, Ashida R, Ito T, Sugiura T, et al. Perioperative computed tomography assessments of the pancreas predict nonalcoholic fatty liver disease after pancreaticoduodenectomy. Medicine. 2016;95: e2535. https://doi.org/10.1097/MD.0000000000002535 .
doi: 10.1097/MD.0000000000002535 pubmed: 26871772 pmcid: 4753867
Kato H, Kamei K, Suto H, Misawa T, Unno M, Nitta H, et al. Incidence and risk factors of nonalcoholic fatty liver disease after total pancreatectomy: a first multicenter prospective study in Japan. J Hepato-Bil Pancreat Sci. 2022;29:428–38. https://doi.org/10.1002/jhbp.1093 .
doi: 10.1002/jhbp.1093
Jeon D, Park BH, Lee HC, Park Y, Lee W, Lee JH, et al. The impact of pylorus preservation on the development of nonalcoholic fatty liver disease after pancreaticoduodenectomy: a historical cohort study. J Hepato-Bil Pancreat Sci. 2022;29:863–73. https://doi.org/10.1002/jhbp.1150 .
doi: 10.1002/jhbp.1150
Luu C, Thapa R, Rose T, Woo K, Jeong D, Thomas K, et al. Identification of nonalcoholic fatty liver disease following pancreatectomy for noninvasive intraductal papillary mucinous neoplasm. Int J Surg. 2018;58:46–9. https://doi.org/10.1016/j.ijsu.2018.09.002 .
doi: 10.1016/j.ijsu.2018.09.002 pubmed: 30218781 pmcid: 7771269
Robin X, Turck N, Hainard A, et al. Proc an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics. 2011;12:1–8.
doi: 10.1186/1471-2105-12-77
Traverso A, Wee L, Dekker A, Gillies R. Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys. 2018;102:1143–58. https://doi.org/10.1016/j.ijrobp.2018.05.053 .
doi: 10.1016/j.ijrobp.2018.05.053 pubmed: 30170872 pmcid: 6690209
Kim YJ, Lee HJ, Kim KG, Lee SH. The effect of CT scan parameters on the measurement of CT radiomic features: a lung nodule phantom study. Comput Math Methods Med. 2019;2019:8790694. https://doi.org/10.1155/2019/8790694 .
doi: 10.1155/2019/8790694 pubmed: 30881480 pmcid: 6381551
Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48:441–6. https://doi.org/10.1016/j.ejca.2011.11.036 .
doi: 10.1016/j.ejca.2011.11.036 pubmed: 22257792 pmcid: 4533986

Auteurs

Takehiro Fujii (T)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan. t-fujii@med.mie-u.ac.jp.

Yusuke Iizawa (Y)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Takumi Kobayashi (T)

School of Medicine, Faculty of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Aoi Hayasaki (A)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Takahiro Ito (T)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Yasuhiro Murata (Y)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Akihiro Tanemura (A)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Yasutaka Ichikawa (Y)

Department of Radiology, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Naohisa Kuriyama (N)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Masashi Kishiwada (M)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Hajime Sakuma (H)

Department of Radiology, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Shugo Mizuno (S)

Department of Hepatobiliary Pancreatic and Transplant Surgery, Graduate School of Medicine, Mie University, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.

Classifications MeSH