Deployment of a real-time prostate cancer confirmation system with Raman spectroscopy: fine-tuning versus test-time adaptation of 1D CNNs.
1/5 보강
PICO 자동 추출 (휴리스틱, conf 2/4)
유사 논문P · Population 대상 환자/모집단
202 patients), along with pre-trained bacterial models, followed by efficient fine-tuning and test-time adaptation (TTA) to adapt to unseen domains.
I · Intervention 중재 / 시술
추출되지 않음
C · Comparison 대조 / 비교
추출되지 않음
O · Outcome 결과 / 결론
TTA improved predictions when labels were unavailable. [CONCLUSIONS] Pre-trained 1D-CNNs combined with efficient fine-tuning or TTA enable accurate PCa detection in small-cohort settings using real-time RS.
[SIGNIFICANCE] Prostate cancer (PCa) confirmation during needle-based procedures is limited by the lack of intraoperative diagnostic tools.
APA
Grajales D, Le WT, et al. (2025). Deployment of a real-time prostate cancer confirmation system with Raman spectroscopy: fine-tuning versus test-time adaptation of 1D CNNs.. Biophotonics discovery, 2(3), 032706. https://doi.org/10.1117/1.BIOS.2.3.032706
MLA
Grajales D, et al.. "Deployment of a real-time prostate cancer confirmation system with Raman spectroscopy: fine-tuning versus test-time adaptation of 1D CNNs.." Biophotonics discovery, vol. 2, no. 3, 2025, pp. 032706.
PMID
42028257
Abstract
[SIGNIFICANCE] Prostate cancer (PCa) confirmation during needle-based procedures is limited by the lack of intraoperative diagnostic tools. Raman spectroscopy (RS), combined with classification models, offers a promising solution for real-time tissue characterization, potentially improving sampling accuracy and therapy guidance. However, such models require tissue- and organ-specific data, making deployment in studies challenging due to limited data availability.
[AIM] The aim is to develop a one-dimensional convolutional neural network (1D-CNN) for real-time PCa detection using RS on prospectively collected data, leveraging multi-organ pre-training and evaluating two domain adaptation strategies.
[APPROACH] A ResNet-based 1D-CNN was trained for binary cancer/normal tissue classification. We implemented a pre-training strategy using retrospective RS data from brain, breast, and prostate (202 patients), along with pre-trained bacterial models, followed by efficient fine-tuning and test-time adaptation (TTA) to adapt to unseen domains.
[RESULTS] Prospective RS data were acquired using a robotic system from 10 PCa patients (two to five biopsies each). The fine-tuned model achieved 0.76 area under the receiver operating characteristic curve, 0.79 accuracy, 0.83 sensitivity, and 0.72 specificity, outperforming support vector machines. TTA improved predictions when labels were unavailable.
[CONCLUSIONS] Pre-trained 1D-CNNs combined with efficient fine-tuning or TTA enable accurate PCa detection in small-cohort settings using real-time RS.
[AIM] The aim is to develop a one-dimensional convolutional neural network (1D-CNN) for real-time PCa detection using RS on prospectively collected data, leveraging multi-organ pre-training and evaluating two domain adaptation strategies.
[APPROACH] A ResNet-based 1D-CNN was trained for binary cancer/normal tissue classification. We implemented a pre-training strategy using retrospective RS data from brain, breast, and prostate (202 patients), along with pre-trained bacterial models, followed by efficient fine-tuning and test-time adaptation (TTA) to adapt to unseen domains.
[RESULTS] Prospective RS data were acquired using a robotic system from 10 PCa patients (two to five biopsies each). The fine-tuned model achieved 0.76 area under the receiver operating characteristic curve, 0.79 accuracy, 0.83 sensitivity, and 0.72 specificity, outperforming support vector machines. TTA improved predictions when labels were unavailable.
[CONCLUSIONS] Pre-trained 1D-CNNs combined with efficient fine-tuning or TTA enable accurate PCa detection in small-cohort settings using real-time RS.