The Angular Spectrum of the Scattering Coefficient Map Reveals Subsurface Colorectal Cancer

Deep learning classification of ex vivo human colon tissues using spectroscopic optical coherence tomography

Screening for colorectal cancer (CRC) with colonoscopy has improved patient outcomes; however, it remains the third leading cause of cancer-related mortality, novel strategies to improve screening are needed. Here, we propose an optical biopsy technique based on spectroscopic optical coherence tomography (OCT). Depth resolved OCT images are analyzed as a function of wavelength to measure optical tissue properties and used as input to machine learning algorithms. Previously, we used this approach to analyze mouse colon polyps. Here, we extend the approach to examine human biopsied colonic epithelial tissue samples ex vivo. Optical properties are used as input to a novel deep learning architecture, producing accuracy of up to 97.9% in discriminating tissue type. SOCT parameters are used to create false colored en face OCT images and deep learning classifications are used to enable visual classification by tissue type. This study advances SOCT toward clinical utility for analysis of colonic epithelium.

Deep learning classification of ex vivo human colon tissues using spectroscopic OCT

Screening programs for colorectal cancer (CRC) have had a profound impact on the morbidity and mortality of this disease by detecting and removing early cancers and precancerous adenomas with colonoscopy. However, CRC continues to be the third leading cause of cancer-related mortality in both men and woman, partly because of limitations in colonoscopy-based screening. Thus, novel strategies to improve the efficiency and effectiveness of screening colonoscopy are urgently needed. Here, we propose to address this need using an optical biopsy technique based on spectroscopic optical coherence tomography (OCT). The depth resolved images obtained with OCT are analyzed as a function of wavelength to measure optical tissue properties. The optical properties can be used as input to machine learning algorithms as a means to classify adenomatous tissue in the colon. In this study, biopsied tissue samples from the colonic epithelium are analyzed ex vivo using spectroscopic OCT and tissue classifications are generated using a novel deep learning architecture, informed by machine learning methods including LSTM and KNN. The overall classification accuracy obtained was 88.9%, 76.0% and 97.9% in discriminating tissue type for these methods. Further, we apply an approach using false coloring of en face OCT images based on SOCT parameters and deep learning predictions to enable visual identification of tissue type. This study advances the spectroscopic OCT towards clinical utility for analyzing colonic epithelium for signs of adenoma.

Spectroscopic optical coherence tomography for classification of colorectal cancer in a mouse model

Noninvasive diagnosis of the malignant potential of colon polyps can improve prevention of colorectal cancer without the need for time-consuming and expensive biopsies. This study examines the use of spectroscopic optical coherence tomography (OCT) to classify tissue from genetically engineered mouse models of early-stage adenoma (APC) and advanced adenocarcinoma (AKP) in which tumors are induced in the distal colon. The optical tissue properties of scattering power and scattering attenuation coefficient are evaluated by analyzing the imaging data collected from tissues. Classifications are generated using 2D linear discriminant analysis with high levels of discrimination obtained. The overall classification accuracy obtained was 91.5%, with 100% sensitivity and 96.7% specificity in separating tumors from benign tissue, and 77.8% sensitivity and 99.4% specificity in separating adenocarcinoma from nonmalignant tissue. Thus, this study demonstrates the clinical potential of using spectroscopic OCT for rapid detection of colon adenoma and colorectal cancer.

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.

Adaptive Boosting (AdaBoost)-based multiwavelength spatial frequency domain imaging and characterization for ex vivo human colorectal tissue assessment

The current gold standard diagnostic test for colorectal cancer remains histological inspections of endoluminal neoplasia in biopsy specimens. However, biopsy site selection requires visual inspection of the bowel, typically with a white-light endoscope. Therefore, this technique is poorly suited to detect small or innocuous-appearing lesions. We hypothesize that an alternative modality-multiwavelength spatial frequency domain imaging (SFDI)-would be able to differentiate various colorectal neoplasia from normal tissue. In this ex vivo study of human colorectal tissues, we report the optical absorption and scattering signatures of normal, adenomatous polyp and cancer specimens. An abnormal vs. normal adaptive boosting (AdaBoost) classifier is trained to dichotomize tissue based on SFDI imaging characteristics, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.95 is achieved. We conclude that AdaBoost-based multiwavelength SFDI can differentiate abnormal from normal colorectal tissues, potentially improving endoluminal screening of the distal gastrointestinal tract in the future.

Real-time colorectal cancer diagnosis using PR-OCT with deep learning

Prior reports have shown optical coherence tomography (OCT) can differentiate normal colonic mucosa from neoplasia, potentially offering an alternative technique to endoscopic biopsy - the current gold-standard colorectal cancer screening and surveillance modality. To help clinical translation limited by processing the large volume of generated data, we designed a deep learning-based pattern recognition (PR) OCT system that automates image processing and provides accurate diagnosis potentially in real-time. Method: OCT is an emerging imaging technique to obtain 3-dimensional (3D) "optical biopsies" of biological samples with high resolution. We designed a convolutional neural network to capture the structure patterns in human colon OCT images. The network is trained and tested using around 26,000 OCT images acquired from 20 tumor areas, 16 benign areas, and 6 other abnormal areas. Results: The trained network successfully detected patterns that identify normal and neoplastic colorectal tissue. Experimental diagnoses predicted by the PR-OCT system were compared to the known histologic findings and quantitatively evaluated. A sensitivity of 100% and specificity of 99.7% can be reached. Further, the area under the receiver operating characteristic (ROC) curves (AUC) of 0.998 is achieved. Conclusions: Our results demonstrate that PR-OCT can be used to give an accurate real-time computer-aided diagnosis of colonic neoplastic mucosa. Future development of this system as an "optical biopsy" tool to assist doctors in real-time for early mucosal neoplasms screening and treatment evaluation following initial oncologic therapy is planned.

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

Ovarian cancer is a heterogeneous disease at the molecular and histologic level. Optical coherence tomography (OCT) is able to map ovarian tissue optical properties and heterogeneity, which has been proposed as a feature to aid in diagnosis of ovarian cancer. In this manuscript, depth-resolved en face scattering maps of malignant ovaries, benign ovaries, and benign fallopian tubes obtained from 20 patients are provided to visualize the heterogeneity of ovarian tissues. Six features are extracted from histograms of scattering maps. All features are able to statistically distinguish benign from malignant ovaries. Two prediction models were constructed based on these features: a logistic regression model (LR) and a support vector machine (SVM). The optimal set of features is mean scattering coefficient and scattering map entropy. The LR achieved a sensitivity and specificity of 97.0% and 97.8%, and SVM demonstrated a sensitivity and specificity of 99.6% and 96.4%. Our initial results demonstrate the feasibility of using OCT as an "optical biopsy tool" for detecting the microscopic scattering changes associated with neoplasia in human ovarian tissue.

Co-registered photoacoustic and ultrasound imaging of human colorectal cancer

<p>Colorectal cancer is the second most common malignancy diagnosed globally. Critical gaps exist in diagnostic and surveillance imaging modalities for colorectal neoplasia. Although prior studies have demonstrated the capability of photoacoustic imaging techniques to differentiate normal from neoplastic tissue in the gastrointestinal tract, evaluation of deep tissue with a fast speed and a large field of view remains limited. To investigate the ability of photoacoustic technology to image deeper tissue, we conducted a pilot study using a real-time co-registered photoacoustic tomography (PAT) and ultrasound (US) system. A total of 23 <italic>ex vivo</italic> human colorectal tissue samples were imaged immediately after surgical resection. Co-registered photoacoustic images of malignancies showed significantly increased PAT signal compared to normal regions of the same sample. The quantitative relative total hemoglobin (rHbT) concentration computed from four optical wavelengths, the spectral features, such as the mean spectral slope, and 0.5-MHz intercept extracted from PAT and US spectral data, and image features, such as the first- and second-order statistics along with the standard deviation of the mean radon transform of PAT images, have shown statistical significance between untreated colorectal tumors and the normal tissue. Using either a logistic regression model or a support vector machine, the best set of parameters of rHbT and PAT intercept has achieved area-under-the-curve (AUC) values of 0.97 and 0.95 for both training and testing data sets, respectively, for prediction of histologically confirmed invasive carcinoma.</p>.

Co-registered photoacoustic and ultrasound imaging of human colorectal cancer

<p>Colorectal cancer is the second most common malignancy diagnosed globally. Critical gaps exist in diagnostic and surveillance imaging modalities for colorectal neoplasia. Although prior studies have demonstrated the capability of photoacoustic imaging techniques to differentiate normal from neoplastic tissue in the gastrointestinal tract, evaluation of deep tissue with a fast speed and a large field of view remains limited. To investigate the ability of photoacoustic technology to image deeper tissue, we conducted a pilot study using a real-time co-registered photoacoustic tomography (PAT) and ultrasound (US) system. A total of 23 <italic>ex vivo</italic> human colorectal tissue samples were imaged immediately after surgical resection. Co-registered photoacoustic images of malignancies showed significantly increased PAT signal compared to normal regions of the same sample. The quantitative relative total hemoglobin (rHbT) concentration computed from four optical wavelengths, the spectral features, such as the mean spectral slope, and 0.5-MHz intercept extracted from PAT and US spectral data, and image features, such as the first- and second-order statistics along with the standard deviation of the mean radon transform of PAT images, have shown statistical significance between untreated colorectal tumors and the normal tissue. Using either a logistic regression model or a support vector machine, the best set of parameters of rHbT and PAT intercept has achieved area-under-the-curve (AUC) values of 0.97 and 0.95 for both training and testing data sets, respectively, for prediction of histologically confirmed invasive carcinoma.</p>.