In photoacoustic tomography (PAT), a tunable laser typically illuminates the tissue at multiple wavelengths, and the received photoacoustic waves are used to form functional images of relative total haemoglobin (rHbT) and blood oxygenation saturation (%sO₂). Due to measurement errors, the estimation of these parameters can be challenging, especially in clinical studies. In this study, we use a multi‐pixel method to smooth the measurements before calculating rHbT and %sO₂. We first perform phantom studies using blood tubes of calibrated %sO₂ to evaluate the accuracy of our %sO₂ estimation. We conclude by presenting diagnostic results from PAT of 33 patients with 51 ovarian masses imaged by our co‐registered PAT and ultrasound system. The ovarian masses were divided into malignant and benign/normal groups. Functional maps of rHbT and %sO₂ and their histograms as well as spectral features were calculated using the PAT data from all ovaries in these two groups. Support vector machine models were trained on different combinations of the significant features. The area under ROC (AUC) of 0.93 (0.95%CI: 0.90‐0.96) on the testing data set was achieved by combining mean %sO₂, a spectral feature, and the score of the study radiologist.

中文翻译：

---

血氧饱和度在多光谱光声断层扫描卵巢癌诊断中的作用

在光声断层扫描（PAT）中，可调谐激光通常以多个波长照射组织，接收到的光声波用于形成相对总血红蛋白（rHbT）和血氧饱和度（%sO ₂）的功能图像。由于测量误差，这些参数的估计可能具有挑战性，特别是在临床研究中。_{在本研究中，我们在计算 rHbT 和 %sO 2}之前使用多像素方法来平滑测量结果。_{我们首先使用经过校准的 %sO 2}血管进行模型研究，以评估我们 %sO ₂估计的准确性。最后，我们展示了 33 名患有 51 个卵巢肿块的患者的 PAT 诊断结果，这些患者是由我们共同注册的 PAT 和超声系统成像的。卵巢肿块分为恶性组和良性/正常组。使用这两组中所有卵巢的 PAT 数据计算rHbT 和 %sO ₂的功能图及其直方图以及光谱特征。支持向量机模型是根据重要特征的不同组合进行训练的。测试数据集上的 ROC (AUC) 面积为 0.93 (0.95%CI: 0.90-0.96)，这是通过结合平均 %sO ₂、光谱特征和研究放射科医生的评分来实现的。