Histogram analysis of en face scattering coefficient map predicts malignancy in human ovarian tissue

Multiclass risk models for ovarian malignancy: an illustration of prediction uncertainty due to the choice of algorithm

BACKGROUND

Assessing malignancy risk is important to choose appropriate management of ovarian tumors. We compared six algorithms to estimate the probabilities that an ovarian tumor is benign, borderline malignant, stage I primary invasive, stage II-IV primary invasive, or secondary metastatic.

METHODS

This retrospective cohort study used 5909 patients recruited from 1999 to 2012 for model development, and 3199 patients recruited from 2012 to 2015 for model validation. Patients were recruited at oncology referral or general centers and underwent an ultrasound examination and surgery ≤ 120 days later. We developed models using standard multinomial logistic regression (MLR), Ridge MLR, random forest (RF), XGBoost, neural networks (NN), and support vector machines (SVM). We used nine clinical and ultrasound predictors but developed models with or without CA125.

RESULTS

Most tumors were benign (3980 in development and 1688 in validation data), secondary metastatic tumors were least common (246 and 172). The c-statistic (AUROC) to discriminate benign from any type of malignant tumor ranged from 0.89 to 0.92 for models with CA125, from 0.89 to 0.91 for models without. The multiclass c-statistic ranged from 0.41 (SVM) to 0.55 (XGBoost) for models with CA125, and from 0.42 (SVM) to 0.51 (standard MLR) for models without. Multiclass calibration was best for RF and XGBoost. Estimated probabilities for a benign tumor in the same patient often differed by more than 0.2 (20% points) depending on the model. Net Benefit for diagnosing malignancy was similar for algorithms at the commonly used 10% risk threshold, but was slightly higher for RF at higher thresholds. Comparing models, between 3% (XGBoost vs. NN, with CA125) and 30% (NN vs. SVM, without CA125) of patients fell on opposite sides of the 10% threshold.

CONCLUSION

Although several models had similarly good performance, individual probability estimates varied substantially.

Enhanced 3D visualization of human fallopian tube morphology using a miniature optical coherence tomography catheter

We demonstrate the use of our miniature optical coherence tomography catheter to acquire three-dimensional human fallopian tube images. Images of the fallopian tube's tissue morphology, vasculature, and tissue heterogeneity distribution are enhanced by adaptive thresholding, masking, and intensity inverting, making it easier to differentiate malignant tissue from normal tissue. The results show that normal fallopian tubes tend to have rich vasculature accompanied by a patterned tissue scattering background, features that do not appear in malignant cases. This finding suggests that miniature OCT catheters may have great potential for fast optical biopsy of the fallopian tube.

Depth-resolved attenuation mapping of the human ovary and fallopian tube using optical coherence tomography

Due to the lack of reliable early-diagnostic tools, most ovarian cancers are diagnosed at late stages. Although optical coherence tomography (OCT) has shown promise for identifying diseased ovaries and fallopian tubes at an earlier stage, previous studies either did not provide quantitative scattering mapping or simply used Beer's law to fit the scattering coefficients of each A-line. In this paper, we calculated the pixel-wise attenuation coefficients of ovaries and fallopian tubes in OCT images. Data from 73 freshly excised human ovaries and fallopian tubes from 36 patients have shown that statistical features are statistically different between cancerous ovaries, infundibula, and fimbriae and normal ones.

Optical coherence tomography for dynamic investigation of mammalian reproductive processes

The biological events associated with mammalian reproductive processes are highly dynamic and tightly regulated by molecular, genetic, and biomechanical factors. Implementation of live imaging in reproductive research is vital for the advancement of our understanding of normal reproductive physiology and for improving the management of reproductive disorders. Optical coherence tomography (OCT) is emerging as a promising tool for dynamic volumetric imaging of various reproductive processes in mice and other animal models. In this review, we summarize recent studies employing OCT-based approaches toward the investigation of reproductive processes in both, males and females. We describe how OCT can be applied to study structural features of the male reproductive system and sperm transport through the male reproductive tract. We review OCT applications for in vitro and dynamic in vivo imaging of the female reproductive system, staging and tracking of oocytes and embryos, and investigations of the oocyte/embryo transport through the oviduct. We describe how the functional OCT approach can be applied to the analysis of cilia dynamics within the male and female reproductive systems. We also discuss the areas of research, where OCT could find potential applications to progress our understanding of normal reproductive physiology and reproductive disorders.

Human colorectal cancer tissue assessment using optical coherence tomography catheter and deep learning

Optical coherence tomography (OCT) can differentiate normal colonic mucosa from neoplasia, potentially offering a new mechanism of endoscopic tissue assessment and biopsy targeting, with a high optical resolution and an imaging depth of ~1 mm. Recent advances in convolutional neural networks (CNN) have enabled application in ophthalmology, cardiology, and gastroenterology malignancy detection with high sensitivity and specificity. Here, we describe a miniaturized OCT catheter and a residual neural network (ResNet)-based deep learning model manufactured and trained to perform automatic image processing and real-time diagnosis of the OCT images. The OCT catheter has an outer diameter of 3.8 mm, a lateral resolution of ~7 μm, and an axial resolution of ~6 μm. A customized ResNet is utilized to classify OCT catheter colorectal images. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.975 is achieved to distinguish between normal and cancerous colorectal tissue images.

Classification of Salivary Gland Tumors Based on Quantitative Optical Coherence Tomography

BACKGROUND AND OBJECTIVES

Visual inspection is the primary diagnostic method for oral diseases, and its accuracy of diagnosis mainly depends on surgeons' experience. Histological examination is still the golden standard, but it is invasive and time-consuming. In order to address these issues, as a noninvasive imaging technique, optical coherence tomography (OCT) can differentiate oral tissue with advantages of real-time, in situ, and high resolution. The aim of this study is to explore optimal quantitative parameters in OCT images to distinguish different salivary gland tumors.

STUDY DESIGN/MATERIALS AND METHODS

OCT images of four salivary gland tumors were obtained from 14 patients, including mucoepidermoid carcinoma (MC), adenoid cystic carcinoma (ACC), basal cell adenoma (BCA), and pleomorphic adenoma (PA). Two parameters of optical attenuation coefficient (OAC) and standard deviation (SD) along the depth of OCT signal were combined to create a computational model of classification, and sensitivity/specificity of classification was calculated statistically to evaluate their results.

RESULTS

A total of 5,919 two-dimensional (2D) OCT images were used for quantitative analysis. The classification sensitivities of 89.6%, 95.0%, 89.5%, 97.8%, and specificities of 97.6%, 99.0%, 98.0%, 98.2%, respectively, were obtained for MC, ACC, BCA, and PA, with the thresholds of 3.6 mm^-1 based on OAC and 0.22/0.18 based on SD.

CONCLUSION

It was demonstrated that OAC and SD could be considered as important parameters in quantitative analysis of OCT images for salivary gland tissue characterization and intraoperative diagnosis. It is of great potential value in promoting the application of this method based on OCT in clinical practice. Lasers Surg. © 2020 Wiley Periodicals LLC.

Diagnosing colorectal abnormalities using scattering coefficient maps acquired from optical coherence tomography

Optical coherence tomography (OCT) has shown potential in differentiating normal colonic mucosa from neoplasia. In this study of 33 fresh human colon specimens, we report the first use of texture features and computer vision-based imaging features acquired from en face scattering coefficient maps to characterize colorectal tissue. En face scattering coefficient maps were generated automatically using a new fast integral imaging algorithm. From these maps, a gray-level cooccurrence matrix algorithm was used to extract texture features, and a scale-invariant feature transform algorithm was used to derive novel computer vision-based features. In total, 25 features were obtained, and the importance of each feature in diagnosis was evaluated using a random forest model. Two classifiers were assessed on two different classification tasks. A support vector machine model was found to be optimal for distinguishing normal from abnormal tissue, with 94.7% sensitivity and 94.0% specificity, while a random forest model performed optimally in further differentiating abnormal tissues (i.e., cancerous tissue and adenomatous polyp) with 86.9% sensitivity and 85.0% specificity. These results demonstrated the potential of using OCT to aid the diagnosis of human colorectal disease.

Optical Resolution Photoacoustic Microscopy of Ovary and Fallopian Tube

Ovarian cancer is the leading cause of death among gynecological cancers, but is poorly amenable to preoperative diagnosis. In this study, we investigate the feasibility of "optical biopsy," using high-optical-resolution photoacoustic microscopy (OR-PAM) to quantify the microvasculature of ovarian and fallopian tube tissue. The technique is demonstrated using excised human ovary and fallopian tube specimens imaged immediately after surgery. Quantitative parameters are derived using Amira software. The parameters include three-dimensional vascular segment count, total volume and length, which are associated with tumor angiogenesis. Qualitative results of OR-PAM demonstrate that malignant ovarian tissue has larger and more tortuous blood vessels as well as smaller vessels of different sizes, while benign and normal ovarian tissue has smaller vessels of uniform size. Quantitative analysis shows that malignant ovaries have greater tumor vessel volume, length and number of segments, as compared with benign and normal ovaries. The vascular pattern of benign fallopian tube is different than that of benign ovarian tissue. Our initial results demonstrate the potential of OR-PAM as an imaging tool for fast assessment of ovarian tissue and fallopian tube and could avoid unnecessary surgery if the risk of the examined ovary is extremely low.