A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients.

BACKGROUND: At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive. OBJECTIVE: This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients. METHODS: A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method. RESULTS: Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models. CONCLUSIONS: This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

Optical coherence tomography for multicellular tumor spheroid category recognition and drug screening classification via multi-spatial-superficial-parameter and machine learning.

Optical coherence tomography (OCT) is an ideal imaging technique for noninvasive and longitudinal monitoring of multicellular tumor spheroids (MCTS). However, the internal structure features within MCTS from OCT images are still not fully utilized. In this study, we developed cross-statistical, cross-screening, and composite-hyperparameter feature processing methods in conjunction with 12 machine learning models to assess changes within the MCTS internal structure. Our results indicated that the effective features combined with supervised learning models successfully classify OVCAR-8 MCTS culturing with 5,000 and 50,000 cell numbers, MCTS with pancreatic tumor cells (Panc02-H7) culturing with the ratio of 0%, 33%, 50%, and 67% of fibroblasts, and OVCAR-4 MCTS treated by 2-methoxyestradiol, AZD1208, and R-ketorolac with concentrations of 1, 10, and 25 µM. This approach holds promise for obtaining multi-dimensional physiological and functional evaluations for using OCT and MCTS in anticancer studies.

Dimension-based quantification of aging-associated cerebral microvasculature determined by optical coherence tomography and two-photon microscopy.

Cerebral microvascular health is a key biomarker for the study of natural aging and associated neurological diseases. Our aim is to quantify aging-associated change of microvasculature at diverse dimensions in mice brain. We used optical coherence tomography (OCT) and two-photon microscopy (TPM) to obtain nonaged and aged C57BL/6J mice cerebral microvascular images in vivo. Our results indicated that artery & vein, arteriole & venule, and capillary from nonaged and aged mice showed significant differences in density, diameter, complexity, perimeter, and tortuosity. OCT angiography and TPM provided the comprehensive quantification for arteriole and venule via compensating the limitation of each modality alone. We further demonstrated that arteriole and venule at specific dimensions exhibited negative correlations in most quantification analyses between nonaged and aged mice, which indicated that TPM and OCT were able to offer complementary vascular information to study the change of cerebral blood vessels in aging.

Optical Coherence Tomography of Tumor Spheroids Identifies Candidates for Drug Repurposing in Ovarian Cancer.

OBJECTIVE: Multicellular tumor spheroids (MCTs) are indispensable models for evaluating drug efficacy for precision cancer therapeutic strategies as well as for repurposing FDA-approved drugs for ovarian cancer. However, current imaging techniques cannot provide effective monitoring of pathological responses due to shallow penetration and experimentally operative destruction. We plan to utilize a noninvasive optical imaging tool to achieve in vivo longitudinal monitoring of the growth of MCTs and therapeutic responses to repurpose three FDA-approved drugs for ovarian cancer therapy. METHODS: A swept-source optical coherence tomography (SS-OCT) system was used to monitor the volume growth of MCTs over 11 days. Three inhibitors of 2-Methoxyestradiol (2-ME), AZD1208, and R-Ketorolac (R-keto) with concentrations of 1, 10, and 25 µM were employed to treat ovarian MCTs on day 5. Three-dimensional (3D), intrinsic optical attenuation contrast, and degree of uniformity were applied to analyze the therapeutic effect of these inhibitors on ovarian MCTs. RESULTS: We found that 2-ME, AZD1208, and R-keto with concentration of 10 and 25 µM significantly inhibited the volume growth of ovarian MCTs. There was no effect to necrotic tissues from all concentrations of 2-ME, AZD1208, and R-keto inhibitors from our OCT results. 2-ME and AZD1208 inhibited the growth of high uniformity tissues within MCTs and higher concentrations provided more significant inhibitory effects. CONCLUSION: Our results indicated that OCT was capable and reliable to monitor the therapeutic effect of inhibitors to ovarian MCTs and it can be used for the rapid characterization of novel therapeutics for ovarian cancers in the future.