EUVIMEDEUVIMED entdecken
Multizentrische Studie

Multitask deep learning for prediction of microvascular invasion and recurrence‐free survival in hepatocellular carcinoma based on MRI images

Fang Wang iD, Gan Zhan, Qing-Qing Chen, Hou-Yun Xu, Dan Cao, Yuan-Yuan Zhang, Yin-Hao Li, Chu-Jie Zhang, Yao Jin, Wen-Bin Ji, Jian-Bing Ma, Yun-Jun Yang und 7 weitere

Liver International · 2024-06 · 44 (6) · 1351-1362

DOI: 10.1111/liv.15870 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Liver International, online erschienen am 04.03.2024. Verfasst von Fang Wang und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Liver Neoplasms, Deep Learning, Magnetic Resonance Imaging. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Zhejiang Province, Program Co-sponsored by Province and Ministry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Aims Accurate preoperative prediction of microvascular invasion (MVI) and recurrence‐free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans.

Methods

Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets ( n = 212, 111, 110).

Results

The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter‐rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C‐index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA‐TACE improved RFS only in patients predicted to have high MVI risk and low survival scores ( p < .001).

Conclusions

Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularLiver NeoplasmsDeep LearningMagnetic Resonance ImagingNeoplasm InvasivenessHumansRetrospective StudiesFemaleMaleMiddle AgedAgedMicrovesselsDisease-Free SurvivalNeoplasm Recurrence, Local

Stichwörter der Autor:innen

deep learninghepatocellular carcinomamagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
  • College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Japan.
  • Department of Radiology, The Fourth Affiliated Hospital, Zhejiang University School of Medicine, Yiwu, China.
  • School of Medicine, Shaoxing University, Shaoxing, China.
  • Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China.
  • Department of Radiology, Ningbo Medical Center Li Huili Hospital, Ningbo, China.

ORCID-Profile: Fang Wang

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Program of Zhejiang Province
  • Program Co-sponsored by Province and Ministry
  • Fundamental Research Funds for the Central Universities
  • Public Welfare Applied Research Project of Huzhou

Zitieren

APA

Wang, F., Zhan, G., Chen, Q. Q., Xu, H. Y., Cao, D., Zhang, Y. Y., Li, Y. H., Zhang, C. J., Jin, Y., Ji, W. B., Ma, J. B., Yang, Y. J., Zhou, W., Peng, Z. Y., Liang, X., Deng, L. P., Lin, L. F., Chen, Y. W., & Hu, H. J. (2024). Multitask deep learning for prediction of microvascular invasion and recurrence‐free survival in hepatocellular carcinoma based on MRI images. Liver International, 44(6), 1351-1362. https://doi.org/10.1111/liv.15870

Vancouver

Wang F, Zhan G, Chen QQ, Xu HY, Cao D, Zhang YY, et al. Multitask deep learning for prediction of microvascular invasion and recurrence‐free survival in hepatocellular carcinoma based on MRI images. Liver International. 2024;44(6):1351-1362. doi:10.1111/liv.15870

BibTeX
@article{Wang2024,
  author = {Wang, Fang and Zhan, Gan and Chen, Qing-Qing and Xu, Hou-Yun and Cao, Dan and Zhang, Yuan-Yuan and Li, Yin-Hao and Zhang, Chu-Jie and Jin, Yao and Ji, Wen-Bin and Ma, Jian-Bing and Yang, Yun-Jun and Zhou, Wei and Peng, Zhi-Yi and Liang, Xiao and Deng, Li-Ping and Lin, Lan-Fen and Chen, Yen-Wei and Hu, Hong-Jie},
  title = {Multitask deep learning for prediction of microvascular invasion and recurrence‐free survival in hepatocellular carcinoma based on MRI images},
  journal = {Liver International},
  year = {2024},
  volume = {44},
  number = {6},
  pages = {1351--1362},
  doi = {10.1111/liv.15870}
}
Kostenlos starten →