EUVIMEDΑνακαλύψτε το EUVIMED
Systematische ÜbersichtMetaanalyseOpen access

The Application Status of Radiomics-Based Machine Learning in Intrahepatic Cholangiocarcinoma: Systematic Review and Meta-Analysis

Anwendung von radiombasiertem Machine Learning beim intrahepatischen Cholangiokarzinom: systematische Übersichtsarbeit und Metaanalyse

Lan Xu iD, Zian Chen iD, Dan Zhu iD, Yingjun Wang iD

Journal of Medical Internet Research · 2025-05-05 · 27 · e69906

DOI: 10.2196/69906 ↗

Auf einen Blick

58 Studien mit 12.903 Patient:innen untersuchten radiombasiertes Machine Learning beim intrahepatischen Cholangiokarzinom. Für die Diagnose wurden mit Radiomics bessere Kennwerte berichtet als mit klinischen Merkmalen allein.

Fragestellung

Wie gut ist radiombasiertes Machine Learning beim intrahepatischen Cholangiokarzinom für Diagnose und weitere klinische Aufgaben geeignet?

Methode

Systematische Übersichtsarbeit und Metaanalyse; Suche in PubMed, Web of Science, Cochrane Library und Embase; Qualitätsbewertung mit Radiomics Quality Score; Subgruppen nach Datensätzen, Bildgebung und Modelltyp.

Ergebnisse

58 Studien mit 12.903 Patient:innen. Für den ICC-Nachweis in der Validierung: klinische Merkmale C-index 0,762 (95 %-KI 0,728–0,796), Sensitivität 0,72 (0,66–0,77), Spezifität 0,72 (0,66–0,78); Radiomics C-index 0,853 (0,824–0,882), Sensitivität 0,80 (0,73–0,85), Spezifität 0,88 (0,83–0,92).

Einschränkungen

Studien zu PNI und TLSs waren selten; begrenzte Daten zu Deep Learning; Heterogenität und Interpretierbarkeit durch Segmentierung und Bildparameter.

Schlussfolgerung der Autor:innen

Radiombasiertes Machine Learning zeigt eine ausgezeichnete Genauigkeit für die klinische Diagnose des ICC. Weitere Forschung ist nötig, um spezifische Aufgaben und methodische Einschränkungen besser zu adressieren.

Kernaussagen

  • Radiomics zeigte bei der ICC-Diagnose bessere Kennwerte als klinische Merkmale allein.
  • Auch Prognose und einige Zusatzaufgaben wurden mit Radiomics untersucht.
  • PNI, TLSs und Deep Learning waren in den Daten nur begrenzt vertreten.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Journal of Medical Internet Research, published online on 2025-05-05. Written by Lan Xu and 3 co-authors. Institution: Department of First Clinical Medical College, Zhejiang Chinese Medical University, Hangzhou, China. Major MEDLINE topics: Cholangiocarcinoma, Machine Learning, Bile Duct Neoplasms. Cited 12 times so far (Crossref); 35 references. The full text is freely available in PubMed Central.

Auf einen BlickΠερίληψηSubjectsΒιβλιογραφικά στοιχείαCiteRelated studies

Abstract (original language)

Background

Over the past few years, radiomics for the detection of intrahepatic cholangiocarcinoma (ICC) has been extensively studied. However, systematic evidence is lacking in the use of radiomics in this domain, which hinders its further development.

Objective

To address this gap, our study delved into the status quo and application value of radiomics in ICC and aimed to offer evidence-based support to promote its systematic application in this field.

Methods

PubMed, Web of Science, Cochrane Library, and Embase were comprehensively retrieved to determine relevant original studies. The study quality was appraised through the Radiomics Quality Score. In addition, subgroup analyses were undertaken according to datasets (training and validation sets), imaging sources, and model types.

Results

Fifty-eight studies encompassing 12,903 patients were eligible, with an average Radiomics Quality Score of 9.21. Radiomics-based machine learning (ML) was mainly used to diagnose ICC (n=30), microvascular invasion (n=8), gene mutations (n=5), perineural invasion (PNI; n=2), lymph node (LN) positivity (n=2), and tertiary lymphoid structures (TLSs; n=2), and predict overall survival (n=6) and recurrence (n=9). The C-index, sensitivity (SEN), and specificity (SPC) of the ML model developed using clinical features (CFs) for ICC detection were 0.762 (95% CI 0.728-0.796), 0.72 (95% CI 0.66-0.77), and 0.72 (95% CI 0.66-0.78), respectively, in the validation dataset. In contrast, the C-index, SEN, and SPC of the radiomics-based ML model for detecting ICC were 0.853 (95% CI 0.824-0.882), 0.80 (95% CI 0.73-0.85), and 0.88 (95% CI 0.83-0.92), respectively. The C-index, SEN, and SPC of ML constructed using both radiomics and CFs for diagnosing ICC were 0.912 (95% CI 0.889-0.935), 0.77 (95% CI 0.72-0.81), and 0.90 (95% CI 0.86-0.92). The deep learning–based model that integrated both radiomics and CFs yielded a notably higher C-index of 0.924 (0.863-0.984) in the task of detecting ICC. Additional analyses showed that radiomics demonstrated promising accuracy in predicting overall survival and recurrence, as well as in diagnosing microvascular invasion, gene mutations, PNI, LN positivity, and TLSs.

Conclusions

Radiomics-based ML demonstrates excellent accuracy in the clinical diagnosis of ICC. However, studies involving specific tasks, such as diagnosing PNI and TLSs, are still scarce. The limited research on deep learning has hindered both further analysis and the development of subgroup analyses across various models. Furthermore, challenges such as data heterogeneity and interpretability caused by segmentation and imaging parameter variations require further optimization and refinement. Future research should delve into the application of radiomics to enhance its clinical use. Its integration into clinical practice holds great promise for improving decision-making, boosting diagnostic and treatment accuracy, minimizing unnecessary tests, and optimizing health care resource usage.

Subjects

MeSH terms (MEDLINE)

CholangiocarcinomaMachine LearningBile Duct NeoplasmsHumansRadiomics

Author keywords

bile duct cancerintrahepatic cholangiocarcinomamachine learningmeta-analysisradiomicsystematic review

Authors and institutions

  • Department of First Clinical Medical College, Zhejiang Chinese Medical University, Hangzhou, China.
  • Dispensary TCM, Quzhou Municipal Hospital of Traditional Chinese Medicine, Quzhou, China.
  • Department of Dermatology, Quzhou Municipal Hospital of Traditional Chinese Medicine, Quzhou, China.

ORCID profiles: Lan Xu, Zian Chen, Dan Zhu, Yingjun Wang

Cite

APA

Xu, L., Chen, Z., Zhu, D., & Wang, Y. (2025). The Application Status of Radiomics-Based Machine Learning in Intrahepatic Cholangiocarcinoma: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 27, e69906. https://doi.org/10.2196/69906

Vancouver

Xu L, Chen Z, Zhu D, Wang Y. The Application Status of Radiomics-Based Machine Learning in Intrahepatic Cholangiocarcinoma: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2025;27:e69906. doi:10.2196/69906

BibTeX
@article{Xu2025,
  author = {Xu, Lan and Chen, Zian and Zhu, Dan and Wang, Yingjun},
  title = {The Application Status of Radiomics-Based Machine Learning in Intrahepatic Cholangiocarcinoma: Systematic Review and Meta-Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e69906},
  doi = {10.2196/69906}
}
Start for free →