A Transfer Learning Radiomics Nomogram to Predict the Postoperative Recurrence of Advanced Gastric Cancer.
1/5 보강
PICO 자동 추출 (휴리스틱, conf 2/4)
유사 논문P · Population 대상 환자/모집단
431 cases of AGC from three centers were included in this retrospective study.
I · Intervention 중재 / 시술
추출되지 않음
C · Comparison 대조 / 비교
추출되지 않음
O · Outcome 결과 / 결론
[CONCLUSION] TLS-WSI can be used to predict postoperative recurrence in AGC, whereas TLRM is more effective. TL can effectively improve the performance of clinical research models with a small sample size.
[BACKGROUND AND AIM] In this study, a transfer learning (TL) algorithm was used to predict postoperative recurrence of advanced gastric cancer (AGC) and to evaluate its value in a small-sample clinica
- p-value p < 0.05
APA
Huang L, Feng B, et al. (2025). A Transfer Learning Radiomics Nomogram to Predict the Postoperative Recurrence of Advanced Gastric Cancer.. Journal of gastroenterology and hepatology, 40(4), 844-854. https://doi.org/10.1111/jgh.16863
MLA
Huang L, et al.. "A Transfer Learning Radiomics Nomogram to Predict the Postoperative Recurrence of Advanced Gastric Cancer.." Journal of gastroenterology and hepatology, vol. 40, no. 4, 2025, pp. 844-854.
PMID
39730209
Abstract
[BACKGROUND AND AIM] In this study, a transfer learning (TL) algorithm was used to predict postoperative recurrence of advanced gastric cancer (AGC) and to evaluate its value in a small-sample clinical study.
[METHODS] A total of 431 cases of AGC from three centers were included in this retrospective study. First, TL signatures (TLSs) were constructed based on different source domains, including whole slide images (TLS-WSIs) and natural images (TLS-ImageNet). Clinical model and non-TLS based on CT images were constructed simultaneously. Second, TL radiomic model (TLRM) was constructed by combining optimal TLS and clinical factors. Finally, the performance of the models was evaluated by ROC analysis. The clinical utility of the models was assessed using integrated discriminant improvement (IDI) and decision curve analysis (DCA).
[RESULTS] TLS-WSI significantly outperformed TLS-ImageNet, non-TLS, and clinical models (p < 0.05). The AUC value of TLS-WSI in training cohort was 0.9459 (95CI%: 0.9054, 0.9863) and ranged from 0.8050 (95CI%: 0.7130, 0.8969) to 0.8984 (95CI%: 0.8420, 0.9547) in validation cohorts. TLS-WSI and the nodular or irregular outer layer of gastric wall were screened to construct TLRM. The AUC value of TLRM in training cohort was 0.9643 (95CI%: 0.9349, 0.9936) and ranged from 0.8561 (95CI%: 0.7571, 0.9552) to 0.9195 (95CI%: 0.8670, 0.9721) in validation cohorts. The IDI and DCA showed that the performance of TLRM outperformed the other models.
[CONCLUSION] TLS-WSI can be used to predict postoperative recurrence in AGC, whereas TLRM is more effective. TL can effectively improve the performance of clinical research models with a small sample size.
[METHODS] A total of 431 cases of AGC from three centers were included in this retrospective study. First, TL signatures (TLSs) were constructed based on different source domains, including whole slide images (TLS-WSIs) and natural images (TLS-ImageNet). Clinical model and non-TLS based on CT images were constructed simultaneously. Second, TL radiomic model (TLRM) was constructed by combining optimal TLS and clinical factors. Finally, the performance of the models was evaluated by ROC analysis. The clinical utility of the models was assessed using integrated discriminant improvement (IDI) and decision curve analysis (DCA).
[RESULTS] TLS-WSI significantly outperformed TLS-ImageNet, non-TLS, and clinical models (p < 0.05). The AUC value of TLS-WSI in training cohort was 0.9459 (95CI%: 0.9054, 0.9863) and ranged from 0.8050 (95CI%: 0.7130, 0.8969) to 0.8984 (95CI%: 0.8420, 0.9547) in validation cohorts. TLS-WSI and the nodular or irregular outer layer of gastric wall were screened to construct TLRM. The AUC value of TLRM in training cohort was 0.9643 (95CI%: 0.9349, 0.9936) and ranged from 0.8561 (95CI%: 0.7571, 0.9552) to 0.9195 (95CI%: 0.8670, 0.9721) in validation cohorts. The IDI and DCA showed that the performance of TLRM outperformed the other models.
[CONCLUSION] TLS-WSI can be used to predict postoperative recurrence in AGC, whereas TLRM is more effective. TL can effectively improve the performance of clinical research models with a small sample size.
MeSH Terms
Humans; Stomach Neoplasms; Nomograms; Retrospective Studies; Male; Female; Middle Aged; Neoplasm Recurrence, Local; Aged; Tomography, X-Ray Computed; Postoperative Period; Predictive Value of Tests; Algorithms; Radiomics
같은 제1저자의 인용 많은 논문 (5)
- Comparison of the efficacy of fruquintinib monotherapy versus fruquintinib combined with immune checkpoint inhibitors in the treatment of advanced colorectal cancer: a retrospective study.
- Hsa-miR-526b-5p Regulates the Sensitivity of Colorectal Cancer to 5-Fluorouracil by Targeting TP53 in Organoid Models.
- Multi-cohort and single-cell profiling of aging genes reveals prognostic and therapeutic targets in breast cancer.
- Chiral Bismuth Molybdate Nanoparticles Recruiting and Activating Group 3 Innate Lymphoid Cells to Suppress Gastric Cancer.
- Establishment of a multi-targeted magnetic combined enrichment system for circulating tumor cells in gastric cancer and analysis of their genomic profiles.