Skip to main content
SpringerLink
Log in

Risk stratification of gallbladder masses by machine learning-based ultrasound radiomics models: a prospective and multi-institutional study

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

This study aimed to evaluate the diagnostic performance of machine learning (ML)–based ultrasound (US) radiomics models for risk stratification of gallbladder (GB) masses.

Methods

We prospectively examined 640 pathologically confirmed GB masses obtained from 640 patients between August 2019 and October 2022 at four institutions. Radiomics features were extracted from grayscale US images and germane features were selected. Subsequently, 11 ML algorithms were separately used with the selected features to construct optimum US radiomics models for risk stratification of the GB masses. Furthermore, we compared the diagnostic performance of these models with the conventional US and contrast-enhanced US (CEUS) models.

Results

The optimal XGBoost-based US radiomics model for discriminating neoplastic from non-neoplastic GB lesions showed higher diagnostic performance in terms of areas under the curves (AUCs) than the conventional US model (0.822–0.853 vs. 0.642–0.706, p < 0.05) and potentially decreased unnecessary cholecystectomy rate in a speculative comparison with performing cholecystectomy for lesions sized over 10 mm (2.7–13.8% vs. 53.6–64.9%, p < 0.05) in the validation and test sets. The AUCs of the XGBoost-based US radiomics model for discriminating carcinomas from benign GB lesions were higher than the conventional US model (0.904–0.979 vs. 0.706–0.766, p < 0.05). The XGBoost-US radiomics model performed better than the CEUS model in discriminating GB carcinomas (AUC: 0.995 vs. 0.902, p = 0.011).

Conclusions

The proposed ML-based US radiomics models possess the potential capacity for risk stratification of GB masses and may reduce the unnecessary cholecystectomy rate and use of CEUS.

Clinical relevance statement

The machine learning-based ultrasound radiomics models have potential for risk stratification of gallbladder masses and may potentially reduce unnecessary cholecystectomies.

Key Points

• The XGBoost-based US radiomics models are useful for the risk stratification of GB masses.

• The XGBoost-based US radiomics model is superior to the conventional US model for discriminating neoplastic from non-neoplastic GB lesions and may potentially decrease unnecessary cholecystectomy rate for lesions sized over 10 mm in comparison with the current consensus guideline.

• The XGBoost-based US radiomics model could overmatch CEUS model in discriminating GB carcinomas from benign GB lesions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CEA:

Carcinoembryonic antigen

CEUS:

Contrast-enhanced ultrasound

GB:

Gallbladder

ICC:

Intraclass correlation coefficient

ML:

Machine learning

ROI:

Region of interest

US:

Ultrasound

XGBoost:

Extreme gradient boosting

References

  1. McCain RS, Diamond A, Jones C, Coleman HG (2018) Current practices and future prospects for the management of gallbladder polyps: a topical review. World J Gastroenterol 24:2844–2852

    PubMed  PubMed Central  Google Scholar 

  2. Ganeshan D, Kambadakone A, Nikolaidis P et al (2021) Current update on gallbladder carcinoma. Abdom Radiol (NY) 46:2474–2489

    PubMed  Google Scholar 

  3. Mellnick VM, Menias CO, Sandrasegaran K et al (2015) Polypoid lesions of the gallbladder: disease spectrum with pathologic correlation. Radiographics 35:387–399

    PubMed  Google Scholar 

  4. Ramachandran A, Srivastava DN, Madhusudhan KS (2021) Gallbladder cancer revisited: the evolving role of a radiologist. Br J Radiol 94:20200726

    PubMed  Google Scholar 

  5. Randi G, Franceschi S, La Vecchia C (2006) Gallbladder cancer worldwide: geographical distribution and risk factors. Int J Cancer 118:1591–1602

    CAS  PubMed  Google Scholar 

  6. Jang JY, Kim SW, Lee SE et al (2009) Differential diagnostic and staging accuracies of high resolution ultrasonography, endoscopic ultrasonography, and multidetector computed tomography for gallbladder polypoid lesions and gallbladder cancer. Ann Surg 250:943–949

    PubMed  Google Scholar 

  7. Kai K, Aishima S, Miyazaki K (2014) Gallbladder cancer: clinical and pathological approach. World J Clin Cases 2:515–521

    PubMed  PubMed Central  Google Scholar 

  8. Babu BI, Dennison AR, Garcea G (2015) Management and diagnosis of gallbladder polyps: a systematic review. Langenbecks Arch Surg 400:455–462

    PubMed  Google Scholar 

  9. Bhatt NR, Gillis A, Smoothey CO, Awan FN, Ridgway PF (2016) Evidence based management of polyps of the gall bladder: a systematic review of the risk factors of malignancy. Surgeon 14:278–286

    PubMed  Google Scholar 

  10. Park HY, Oh SH, Lee KH, Lee JK, Lee KT (2015) Is cholecystectomy a reasonable treatment option for simple gallbladder polyps larger than 10 mm? World J Gastroenterol 21:4248–4254

    PubMed  PubMed Central  Google Scholar 

  11. Coburn NG, Cleary SP, Tan JC, Law CH (2008) Surgery for gallbladder cancer: a population-based analysis. J Am Coll Surg 207:371–382

    PubMed  Google Scholar 

  12. Yu MH, Kim YJ, Park HS, Jung SI (2020) Benign gallbladder diseases: imaging techniques and tips for differentiating with malignant gallbladder diseases. World J Gastroenterol 26:2967–2986

    CAS  PubMed  PubMed Central  Google Scholar 

  13. Elmasry M, Lindop D, Dunne DF et al (2016) The risk of malignancy in ultrasound detected gallbladder polyps: a systematic review. Int J Surg 33:28–35

    PubMed  Google Scholar 

  14. Kim JH, Lee JY, Baek JH et al (2015) High-resolution sonography for distinguishing neoplastic gallbladder polyps and staging gallbladder cancer. AJR Am J Roentgenol 204:W150-159

    PubMed  Google Scholar 

  15. Kim JS, Lee JK, Kim Y, Lee SM (2016) US characteristics for the prediction of neoplasm in gallbladder polyps 10 mm or larger. Eur Radiol 26:1134–1140

    PubMed  Google Scholar 

  16. Lee JS, Kim JH, Kim YJ et al (2017) Diagnostic accuracy of transabdominal high-resolution US for staging gallbladder cancer and differential diagnosis of neoplastic polyps compared with EUS. Eur Radiol 27:3097–3103

    PubMed  Google Scholar 

  17. Choi TW, Kim JH, Park SJ et al (2018) Risk stratification of gallbladder polyps larger than 10 mm using high-resolution ultrasonography and texture analysis. Eur Radiol 28:196–205

    PubMed  Google Scholar 

  18. Cheng Y, Wang M, Ma B, Ma X (2018) Potential role of contrast-enhanced ultrasound for the differentiation of malignant and benign gallbladder lesions in east Asia: a meta-analysis and systematic review. Medicine (Baltimore) 97:e11808

    PubMed  Google Scholar 

  19. Negrão de Figueiredo G, Mueller-Peltzer K, Armbruster M, Rübenthaler J, Clevert DA (2019) Contrast-enhanced ultrasound (CEUS) for the evaluation of gallbladder diseases in comparison to cross-sectional imaging modalities and histopathological results. Clin Hemorheol Microcirc 71:141–149

    PubMed  Google Scholar 

  20. Liang X, Jing X (2020) Meta-analysis of contrast-enhanced ultrasound and contrast-enhanced harmonic endoscopic ultrasound for the diagnosis of gallbladder malignancy. BMC Med Inform Decis Mak 20:235

    PubMed  PubMed Central  Google Scholar 

  21. Xie XH, Xu HX, Xie XY et al (2010) Differential diagnosis between benign and malignant gallbladder diseases with real-time contrast-enhanced ultrasound. Eur Radiol 20:239–248

    PubMed  Google Scholar 

  22. Liu LN, Xu HX, Lu MD et al (2012) Contrast-enhanced ultrasound in the diagnosis of gallbladder diseases: a multi-center experience. PLoS One 7:e48371

    CAS  PubMed  PubMed Central  Google Scholar 

  23. Yuan Z, Liu X, Li Q et al (2021) Is contrast-enhanced ultrasound superior to computed tomography for differential diagnosis of gallbladder polyps? a cross-sectional study. Front Oncol 11:657223

    CAS  PubMed  PubMed Central  Google Scholar 

  24. Liu Z, Zhang XY, Shi YJ et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res 23:7253–7262

    CAS  PubMed  Google Scholar 

  25. Huang YQ, Liang CH, He L (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164

    PubMed  Google Scholar 

  26. Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762

    PubMed  Google Scholar 

  27. Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446

    PubMed  PubMed Central  Google Scholar 

  28. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577

    PubMed  Google Scholar 

  29. Jeong Y, Kim JH, Chae HD et al (2020) Deep learning-based decision support system for the diagnosis of neoplastic gallbladder polyps on ultrasonography: preliminary results. Sci Rep 10:7700

    CAS  PubMed  PubMed Central  Google Scholar 

  30. Yuan HX, Yu QH, Zhang YQ et al (2020) Ultrasound radiomics effective for preoperative identification of true and pseudo gallbladder polyps based on spatial and morphological features. Front Oncol 10:1719

    PubMed  PubMed Central  Google Scholar 

  31. Zhao CK, Ren TT, Yin YF et al (2021) A comparative analysis of two machine learning-based diagnostic patterns with thyroid imaging reporting and data system for thyroid nodules: diagnostic performance and unnecessary biopsy rate. Thyroid 31:470–481

    CAS  PubMed  Google Scholar 

  32. Yushkevich PA, Piven J, Hazlett HC et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128

    PubMed  Google Scholar 

  33. Varma S, Simon R (2006) Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7:91

    PubMed  PubMed Central  Google Scholar 

  34. Foley KG, Lahaye MJ, Thoeni RF (2022) Management and follow-up of gallbladder polyps: updated joint guidelines between the ESGAR, EAES, EFISDS and ESGE. Eur Radiol 32:3358–3368

    PubMed  Google Scholar 

  35. Wiles R, Thoeni R, Barbu S et al (2017) Management and follow-up of gallbladder polyps: joint guidelines between the European Society of Gastrointestinal and Abdominal Radiology (ESGAR), European Association for Endoscopic Surgery and other Inter-ventional Techniques (EAES), International Society of Digestive Surgery - European Federation (EFISDS) and European Society of Gastrointestinal Endoscopy (ESGE). Eur Radiol 27:3856–3866

    PubMed  PubMed Central  Google Scholar 

  36. Isherwood J, Oakland K, Khanna A (2019) A systematic review of the ae- tiology and management of post cholecystectomy syndrome. Surgeon 17:33–42

    PubMed  Google Scholar 

  37. Womack NA, Crider RL (1947) The persistence of symptoms following cholecystectomy. Ann Surg 126:31–55

    CAS  PubMed  PubMed Central  Google Scholar 

  38. Tarnasky PR (2016) Post-cholecystectomy syndrome and sphincter of Oddi dysfunction: past, present and future. Expert Rev Gastroenterol Hepatol 10:1359–1372

    CAS  PubMed  Google Scholar 

  39. Misra S, Chaturvedi A, Misra NC, Sharma ID (2003) Carcinoma of the gallbladder. Lancet Oncol 4:167–176

    PubMed  Google Scholar 

  40. Tian YH, Ji X, Liu B et al (2015) Surgical treatment of incidental gallbladder cancer discovered during or following laparoscopic cholecystectomy. World J Surg 39:746–752

    PubMed  Google Scholar 

  41. Zhou W, Yang Y, Yu C et al (2021) Ensembled deep learning model outperforms human experts in diagnosing biliary atresia from sonographic gallbladder images. Nat Commun 12:1259

    CAS  PubMed  PubMed Central  Google Scholar 

  42. Ji GW, Zhang YD, Zhang H et al (2019) Biliary tract cancer at CT: a radiomics-based model to predict lymph node metastasis and survival outcomes. Radiology 290:90–98

    PubMed  Google Scholar 

  43. Xiang F, Liang X, Yang L, Liu X, Yan S (2022) Contrast-enhanced CT radiomics for prediction of recurrence-free survival in gallbladder carcinoma after surgical resection. Eur Radiol 32:7087–7097

    PubMed  Google Scholar 

  44. Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining-KDD 2016, San Francisco, CA, USA, pp 785–794

  45. Cha BH, Hwang JH, Lee SH et al (2011) Pre-operative factors that can predict neoplastic polypoid lesions of the gallbladder. World J Gastroenterol 17:2216–2222

    PubMed  PubMed Central  Google Scholar 

  46. French DG, Allen PD, Ellsmere JC (2013) The diagnostic accuracy of transabdominal ultrasonography needs to be considered when managing gallbladder polyps. Surg Endosc 27:4021–4025

    PubMed  Google Scholar 

  47. Zhang HP, Bai M, Gu JY, He YQ, Qiao XH, Du LF (2018) Value of contrast-enhanced ultrasound in the differential diagnosis of gallbladder lesion. World J Gastroenterol 24:744–751

    CAS  PubMed  PubMed Central  Google Scholar 

  48. Chen LD, Huang Y, Xie XH et al (2017) Diagnostic nomogram for gallbladder wall thickening mimicking malignancy: using contrast-enhanced ultrasonography or multi-detector computed tomography? Abdom Radiol (NY) 42:2436–2446

    PubMed  Google Scholar 

  49. Sun LP, Guo LH, Xu HX et al (2015) Value of contrast-enhanced ultrasound in the differential diagnosis between gallbladder adenoma and gallbladder adenoma canceration. Int J Clin Exp Med 8:1115–1121

    PubMed  PubMed Central  Google Scholar 

  50. Ganeshan D, Kambadakone A, Nikolaidis P, Subbiah V, Subbiah IM, Devine C (2021) Current update on gallbladder carcinoma. Abdom Radiol (NY) 46:2474–2489

    PubMed  Google Scholar 

  51. Wang YF, Feng FL, Zhao XH et al (2014) Combined detection tumor markers for diagnosis and prognosis of gallbladder cancer. World J Gastroenterol 20:4085–4092

    PubMed  PubMed Central  Google Scholar 

  52. Shukla VK, Gurubachan, Sharma D, Dixit VK, Usha (2006) Diagnostic value of serum CA242, CA 19-9, CA 15-3 and CA 125 in patients with carcinoma of the gallbladder. Trop Gastroenterol 27:160-165

Download references

Funding

This work was supported in part by the National Natural Science Foundation of China (Grant 82202174), the Science and Technology Commission of Shanghai Municipality (Grants 18441905500, and 19DZ2251100), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), Shanghai Science and Technology Innovation Action Plan (21Y11911200), and Fundamental Research Funds for the Central Universities (ZD-11-202151), Scientific Research and Development Fund of Zhongshan Hospital of Fudan University (Grant 2022ZSQD07).

Author information

Author notes

  1. Li-Fan Wang and Qiao Wang contributed equally to this work.

Authors and Affiliations

  1. Department of Ultrasound, Institute of Ultrasound in Medicine and Engineering, Zhongshan Hospital, Fudan University, Shanghai, China

    Li-Fan Wang, Bo-Yang Zhou, Hao-Hao Yin, Xiao-Long Li, Yi-Kang Sun, Dan Lu, Cong-Yu Tang, Hai-Xia Yuan, Chong-Ke Zhao & Hui-Xiong Xu

  2. Department of Medical Ultrasound, Center of Minimally Invasive Treatment for Tumor, Shanghai Tenth People’s Hospital, Ultrasound Education and Research Institute, School of Medicine, Tongji University, Shanghai, China

    Qiao Wang, Li-Ping Sun, Hui Shi & Ya-Qin Zhang

  3. Shanghai Engineering Research Center of Ultrasound Diagnosis and Treatment, Shanghai, China

    Qiao Wang, Li-Ping Sun, Hui Shi & Ya-Qin Zhang

  4. Department of Medical Ultrasound, First Hospital of Ningbo University, Ningbo, Zhejiang, China

    Feng Mao

  5. Department of Ultrasonography, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China

    Shi-Hao Xu

  6. Bayer Healthcare, Radiology, Shanghai, China

    Ting-Fan Wu

  7. Department of Ultrasound, Zhongshan Hospital of Fudan University (Qingpu Branch), Shanghai, China

    Hai-Xia Yuan

Authors
  1. Li-Fan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qiao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Feng Mao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shi-Hao Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Li-Ping Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ting-Fan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Bo-Yang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Hao-Hao Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Hui Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Ya-Qin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Xiao-Long Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Yi-Kang Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Dan Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Cong-Yu Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Hai-Xia Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Chong-Ke Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Hui-Xiong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Hai-Xia Yuan, Chong-Ke Zhao or Hui-Xiong Xu.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Hui-Xiong Xu.

Conflict of interest

These authors declare that they have no conflict of interest.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from patients in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• prospective

• diagnostic or prognostic study

• performed at four institutions

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 257 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, LF., Wang, Q., Mao, F. et al. Risk stratification of gallbladder masses by machine learning-based ultrasound radiomics models: a prospective and multi-institutional study. Eur Radiol 33, 8899–8911 (2023). https://doi.org/10.1007/s00330-023-09891-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09891-8

Keywords

Search

Navigation