Computer-aided detection of early Barrett’s cancer

Summary: 

People suffering from gastric reflux over a longer period of time will develop a so-called Barrett’s Esophagus (BE). As a defense mechanmism, the nbody starts replacing the esophageal tissue with acid resistant tissue which may lead to cancer.
If the developing cancer is detected at an early stage, it can be removed by a small surgical procedure. In this project, we study the detection of early cancer in an automated way by advanced video analysis of the endoscopic inspection video.


Project Description: 
People suffering from gastric reflux over a longer period of time will develop a so-called Barrett’s Esophagus (BE). This is a condition, in which the lower part of the esophagus is covered with a different type of tissue. Normal esophageal tissue cannot resist gastric acid, which typically escapes from the stomach in people suffering from reflux. As a defense mechanism the body starts replacing the esophageal tissue with a tissue type similar to that of the small intestine, which is acid-resistant. However, this process, called metaplasia, greatly increases the chance of developing cancer. Patients with a BE are regularly screened and if the developing cancer is detected at an early stage, it can be removed by a small surgical procedure. When the cancer is detected at a later stage of the disease, the only treatment is surgical removal of the entire esophagus and the survival chances of the patient are drastically decreased (nearly 100% five-year-survival for early detection vs. 10-15% five-year-survival for late detection). Hence, it is of crucial importance to the patient that these cancers are detected at an early stage. However, these early cancerous lesions have shown to be very hard to identify by endoscopic inspection and are therefore regularly missed. For this reason, a Computer-Aided Detection (CAD) system to aid the gastroenterologist in identifying these early cancerous lesions in BE is highly desirable.
The project objective is to develop such a CAD system, which inspects the esophageal tissue during endoscopic screening. In our studies, we have analyzed the spectral characteristics of early cancerous tissue and exploited this knowledge to develop tuned wavelet-based filters that are able to capture the distinctive texture patterns associated with early cancer. Over the past couple of years, for reliable detection, we have explored different machine learning methods, such as Support Vector Machines (SVM), Decision Forests and Neural Networks to support automated detection. Furthermore, we have experimented with different features that are often used in computer vision algorithms, such as Local Binary Patterns (LBP), Gray-Level Co-occurrence Matrices (GLCM) and Histogram of Oriented Gradients (HOG). Our latest results show that trained computer algorithms are able to detect early cancer in BE, with an accuracy close to that of internationally recognized experts. In a recent study, we have also explored the possibilities of quantitative analysis of an Optical Coherence Tomography (OCT) images in order to acquire in-vivo histology of the esophageal tissue. This allows for an even more accurate detection of these early cancerous lesions and enables large-scale screening of BE patients. Our latest results show that CAD algorithms have the ability to outperform medical experts in grading OCT images of Barrett’s tissue and we think that such algorithms can be of great value to clinical practice.
The quality and originality of this research work has resulted in an international challenge in which various research groups test and evaluate their detection algorithms, using the same image dataset. This international challenge has been announced and presented at the MICCAI 2015 in Munich by ir. Fons van der Sommen, the key researcher in this project. More information can be found at http://grand-challenge.org/site/endovissub-barrett/background/ . This project is a cooperation by Catharina Hospital Eindhoven, Amsterdam Medical Center and Eindhoven University of Technpology. Key researchers are Fons van der Sommen, Sveta Zinger and Peter H.N. de With
Application Area: 
Healthcare
Video/Imaging Discipline: 
Content Analysis
Partners: