Chen Yingna, Li Feifan, Dai Zhuoheng, Liu Ying, Huang Shengsong, Cheng Qian
School of Information Engineering, College of Science & Technology Ningbo University, Ningbo, Zhejiang, China.
School of Physics Science and Engineering, Tongji University, Shanghai, China.
Front Oncol. 2025 Jul 9;15:1592815. doi: 10.3389/fonc.2025.1592815. eCollection 2025.
Photoacoustic spectral analysis has been demonstrated to be efficacious in the diagnosis of prostate cancer (PCa). With the incorporation of deep learning, its discrimination accuracy is progressively enhancing. Nevertheless, individual heterogeneity persists as a significant factor that impacts discrimination performance.
Extracting more reliable features from intricate biological tissue and augmenting discrimination accuracy of the prostate cancer.
Supervised contrastive learning is introduced to explore its performance in photoacoustic spectral feature extraction. Three distinct models, namely the CNN-based model, the supervised contrastive (SC) model, and the supervised contrastive loss adjust (SCL-adjust) model, have been compared, along with traditional feature extraction and machine learning-based methods.
The outcomes have indicated that the SCL-adjust model exhibits the optimal performance, its accuracy rate has increased by more than 10% compared with the traditional method. Besides, the features extracted from this model are more resilient, regardless of the presence of uniform or Gaussian noise and model transfer. Compared with CNN model, the transfer performance of the proposed model has improved by approximately 5%.
Supervised contrast learning is integrated into photoacoustic spectrum analysis and its effectiveness is verified. A comprehensive analysis is conducted on the performance improvement of the proposed SCL-adjust model in photoacoustic prostate cancer diagnosis, its resistance to noise, and its adaptability to the data heterogeneity of different systems.
光声光谱分析已被证明在前列腺癌（PCa）诊断中有效。随着深度学习的融入，其鉴别准确性在不断提高。然而，个体异质性仍然是影响鉴别性能的一个重要因素。
从复杂的生物组织中提取更可靠的特征，提高前列腺癌的鉴别准确性。
引入监督对比学习来探索其在光声光谱特征提取中的性能。比较了三种不同的模型，即基于卷积神经网络（CNN）的模型、监督对比（SC）模型和监督对比损失调整（SCL-adjust）模型，以及传统特征提取和基于机器学习的方法。
结果表明，SCL-adjust模型表现出最优性能，其准确率比传统方法提高了10%以上。此外，从该模型提取的特征更具弹性，无论存在均匀噪声还是高斯噪声以及模型迁移情况如何。与CNN模型相比，所提模型的迁移性能提高了约5%。
将监督对比学习集成到光声光谱分析中并验证了其有效性。对所提SCL-adjust模型在光声前列腺癌诊断中的性能提升、抗噪声能力及其对不同系统数据异质性的适应性进行了综合分析。
