Virtual colonoscopy vs optical colonoscopy

MM-GLCM-CNN: A multi-scale and multi-level based GLCM-CNN for polyp classification

Distinguishing malignant from benign lesions has significant clinical impacts on both early detection and optimal management of those early detections. Convolutional neural network (CNN) has shown great potential in medical imaging applications due to its powerful feature learning capability. However, it is very challenging to obtain pathological ground truth, addition to collected in vivo medical images, to construct objective training labels for feature learning, leading to the difficulty of performing lesion diagnosis. This is contrary to the requirement that CNN algorithms need a large number of datasets for the training. To explore the ability to learn features from small pathologically-proven datasets for differentiation of malignant from benign polyps, we propose a Multi-scale and Multi-level based Gray-level Co-occurrence Matrix CNN (MM-GLCM-CNN). Specifically, instead of inputting the lesions' medical images, the GLCM, which characterizes the lesion heterogeneity in terms of image texture characteristics, is fed into the MM-GLCN-CNN model for the training. This aims to improve feature extraction by introducing multi-scale and multi-level analysis into the construction of lesion texture characteristic descriptors (LTCDs). To learn and fuse multiple sets of LTCDs from small datasets for lesion diagnosis, we further propose an adaptive multi-input CNN learning framework. Furthermore, an Adaptive Weight Network is used to highlight important information and suppress redundant information after the fusion of the LTCDs. We evaluated the performance of MM-GLCM-CNN by the area under the receiver operating characteristic curve (AUC) merit on small private lesion datasets of colon polyps. The AUC score reaches 93.99% with a gain of 1.49% over current state-of-the-art lesion classification methods on the same dataset. This gain indicates the importance of incorporating lesion characteristic heterogeneity for the prediction of lesion malignancy using small pathologically-proven datasets.

Implications of Public Interest in Colonoscopy: Analysis of Google Trends Data From 12 European Countries

INTRODUCTION

Colorectal cancer (CRC) is one of the deadliest diseases in the European Union. Colonoscopy remains the gold standard of CRC screening. Analysis of colonoscopy-related Google Trends (GT; Google LLC, Mountain View, California, United States) data could provide useful information regarding interest in colonoscopy and potential barriers making patients unwilling to attend screening programs.

METHODS

Data were collected using GT for the main search term "colonoscopy" and the two most related queries. Colonoscopy volumes were extracted from the Eurostat database. Due to limited Eurostat data availability, analysis was performed from January 2004 to December 2015 for each of the 12 included countries.

RESULTS

Univariate linear regression analysis demonstrated statistically significant correlations between annual search volumes of "colonoscopy" and the annual number of colonoscopies performed in included countries (R2 = 0.923, P<.001). Trend analysis showed that the cumulative search volumes for "colonoscopy" gradually increased through the analyzed period. The spectrum of the most related queries encompassed "preparation for colonoscopy", "endoscopy", "after endoscopy", "colon", "colonoscopy diet", "virtual colonoscopy", "colonoscopy under anesthesia", "waiting times for colonoscopy" and "colonoscopy price". For eight out of nine queries, statistically significant correlations with procedure volumes were revealed.

CONCLUSIONS

GT could be a useful tool in assessing public interest in colonoscopy. Potential barriers that prevent people from attending CRC screening programs were identified. The study demonstrated that the internet has become an important field for CRC screening promotion. GT utility for colonoscopy and CRC screening providers was highlighted. This was the first analysis of GT data in colonoscopy focused on European countries.

Role of Advanced Diagnostic Aids in the Detection of Potentially Malignant Disorders and Oral Cancer at an Early Stage

One of the most prevalent malignancies diagnosed today is cancer of the mouth or oral cancer. Compared to systemic malignancies like lung cancer, colon cancer, etc., oral cancer tends to get less attention from the general public. However, these lesions may be lethal if not treated, even if diagnosed early. Early diagnosis improves the prognosis for successful therapy. Delayed diagnosis is hypothesized to be a pivotal contributor to the dismal oral cancer survival rate over five years. The current standard of care for diagnosis and detection is based on clinical evaluation, the histological study of biopsy material, and genetic methods. There have been several advancements in the diagnostic technologies available to detect oral cancer at the initial phase. This study aims to dissect the cutting-edge methods for detecting oral cancer in its earliest stages.

An Adaptive Learning Model for Multiscale Texture Features in Polyp Classification via Computed Tomographic Colonography

Objective: As an effective lesion heterogeneity depiction, texture information extracted from computed tomography has become increasingly important in polyp classification. However, variation and redundancy among multiple texture descriptors render a challenging task of integrating them into a general characterization. Considering these two problems, this work proposes an adaptive learning model to integrate multi-scale texture features. Methods: To mitigate feature variation, the whole feature set is geometrically split into several independent subsets that are ranked by a learning evaluation measure after preliminary classifications. To reduce feature redundancy, a bottom-up hierarchical learning framework is proposed to ensure monotonic increase of classification performance while integrating these ranked sets selectively. Two types of classifiers, traditional (random forest + support vector machine)- and convolutional neural network (CNN)-based, are employed to perform the polyp classification under the proposed framework with extended Haralick measures and gray-level co-occurrence matrix (GLCM) as inputs, respectively. Experimental results are based on a retrospective dataset of 63 polyp masses (defined as greater than 3 cm in largest diameter), including 32 adenocarcinomas and 31 benign adenomas, from adult patients undergoing first-time computed tomography colonography and who had corresponding histopathology of the detected masses. Results: We evaluate the performance of the proposed models by the area under the curve (AUC) of the receiver operating characteristic curve. The proposed models show encouraging performances of an AUC score of 0.925 with the traditional classification method and an AUC score of 0.902 with CNN. The proposed adaptive learning framework significantly outperforms nine well-established classification methods, including six traditional methods and three deep learning ones with a large margin. Conclusions: The proposed adaptive learning model can combat the challenges of feature variation through a multiscale grouping of feature inputs, and the feature redundancy through a hierarchal sorting of these feature groups. The improved classification performance against comparative models demonstrated the feasibility and utility of this adaptive learning procedure for feature integration.

Experiences of Patients Undergoing Bowel Preparation and Colonoscopy: A Qualitative Longitudinal Study

Introduction

Colonoscopy remains the reference standard for diagnosing and monitoring colorectal cancer and for diagnosis and surveillance of inflammatory bowel disease. However, there is a limited knowledge of the patients’ needs when undergoing colonoscopy and the challenges within in order to reduce the number of cancelled colonoscopies. The purpose of the study was to explore the experiences of undergoing bowel preparation and colonoscopy.

Methods

The study was designed as a qualitative longitudinal interview study with an inductive research approach. Patients were considered for inclusion consecutively and selected based on the following criteria of variation: way of referral for colonoscopy (outpatient or screening), age and gender. The interviews were analyzed using qualitative content analysis, and results reported according to COREQ guidelines.

Results

Based on the findings, three categories emerged: To weigh up participation, A greater challenge than expected, and Not so challenging after all. Throughout these categories, the experience of uncertainty was reported.

Discussion

The process of undergoing bowel preparation and colonoscopy was influenced by uncertainty due to insufficient information. There is a need to strengthen the patient-centered care by adjusting the information to patient’s needs to better support them in decision-making for participation, to better prepare them for the bowel preparation and to better prepare them for the procedure. In addition, it is vital that patients are provided with results of the colonoscopy that correspond to the timeframe specified in written information.

Multi-scale characterizations of colon polyps via computed tomographic colonography

Texture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

Texture Feature Extraction and Analysis for Polyp Differentiation via Computed Tomography Colonography

Image textures in computed tomography colonography (CTC) have great potential for differentiating non-neoplastic from neoplastic polyps and thus can advance the current CTC detection-only paradigm to a new level with diagnostic capability. However, image textures are frequently compromised, particularly in low-dose CT imaging. Furthermore, texture feature extraction may vary, depending on the polyp spatial orientation variation, resulting in variable results. To address these issues, this study proposes an adaptive approach to extract and analyze the texture features for polyp differentiation. Firstly, derivative (e.g. gradient and curvature) operations are performed on the CT intensity image to amplify the textures with adequate noise control. Then Haralick co-occurrence matrix (CM) is used to calculate texture measures along each of the 13 directions (defined by the first and second order image voxel neighbors) through the polyp volume in the intensity, gradient and curvature images. Instead of taking the mean and range of each CM measure over the 13 directions as the so-called Haralick texture features, Karhunen-Loeve transform is performed to map the 13 directions into an orthogonal coordinate system so that the resulted texture features are less dependent on the polyp orientation variation. These simple ideas for amplifying textures and stabilizing spatial variation demonstrated a significant impact for the differentiating task by experiments using 384 polyp datasets, of which 52 are non-neoplastic polyps and the rest are neoplastic polyps. By the merit of area under the curve of receiver operating characteristic, the innovative ideas achieved differentiation capability of 0.8016, indicating the CTC diagnostic feasibility.

PillCam colon capsule endoscopy versus conventional colonoscopy for the detection of severity and extent of ulcerative colitis

OBJECTIVE

To evaluate PillCam colon capsule endoscopy (PCCE) in detecting the severity and extent of active ulcerative colitis (UC), in comparison with conventional endoscopy.

METHODS

From July 2009 to June 2012, patients with confirmed UC were enrolled in this prospective single-center study. After they had undergone the PCCE, they received a conventional colonoscopy. The extent of mucosal damage and inflammatory lesions during both procedures was recorded for comparison. In addition, the regimen of bowel preparation, completion rate, colonic cleansing, compliance or adverse events were analyzed.

RESULTS

A total of 26 patients was consecutively included, among whom one was withdrawn. The remaining 25 (nine females and 16 males with a mean age of 44.2 years) completed the study. There was significant correlation in the severity (κ = 0.751, P < 0.001) and extent (κ = 0.522, P < 0.001) of UC between the PCCE and conventional colonoscopy. In addition, the excellent to good rate of colonic cleanliness in PCCE was 80%. There were no remarkable adverse events during the study.

CONCLUSION

PCCE provides an outstanding performance in the detection of the severity and extent of active UC.