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.

No abstract

Ultrasound (US)-guided near-infrared diffuse optical tomography (DOT) has demonstrated great potential as an adjunct breast cancer diagnosis tool to US imaging alone, especially in reducing unnecessary benign biopsies. However, DOT data processing and image reconstruction speeds remain slow compared to the real-time speed of US. Real-time or near real-time diagnosis with DOT is an important step toward the clinical translation of US-guided DOT. Here, to address this important need, we present a two-stage diagnostic strategy that is both computationally efficient and accurate. In the first stage, benign lesions are identified in near real-time by use of a random forest classifier acting on the DOT measurements and the radiologists' US diagnostic scores. Any lesions that cannot be reliably classified by the random forest classifier will be passed on to the second stage which begins with image reconstruction. Functional information from the reconstructed hemoglobin concentrations is employed by a Support Vector Machine (SVM) classifier for diagnosis at the end of the second stage. This two-step classification approach which combines both perturbation data and functional features, results in improved classification, as denoted by the receiver operating characteristic (ROC) curve. Using this two-step approach, the area under the ROC curve (AUC) is 0.937 ± 0.009, with a sensitivity of 91.4% and specificity of 85.7%. In comparison, using functional features and US score yields an AUC of 0.892 ± 0.027, with a sensitivity of 90.2% and specificity of 74.5%. Most notably, the specificity is increased by more than 10% due to the implementation of the random forest classifier.