Pedro Figueiredo

Automated Polyp Detection in Colon Capsule Endoscopy

Colorectal polyps are important precursors to colon cancer, a major health problem. Colon capsule endoscopy is a safe and minimally invasive examination procedure, in which the images of the intestine are obtained via digital cameras on board of a small capsule ingested by a patient. The video sequence is then analyzed for the presence of polyps. We propose an algorithm that relieves the labor of a human operator analyzing the frames in the video sequence. The algorithm acts as a binary classifier, which labels the frame as either containing polyps or not, based on the geometrical analysis and the texture content of the frame.We assume that the polyps are characterized as protrusions that are mostly round in shape. Thus, a best fit ball radius is used as a decision parameter of the classifier. We present a statistical performance evaluation of our approach on a data set containing over 18 900 frames from the endoscopic video sequences of five adult patients. The algorithm achieves 47% sensitivity per frame and 81% sensitivity per polyp at a specificity level of 90%. On average, with a video sequence length of 3747 frames, only 367 false positive frames need to be inspected by an operator.

Capsule endoscopy in inflammatory bowel disease type unclassified and indeterminate colitis serologically negative

Background: The value of capsule endoscopy in the setting of inflammatory bowel disease type unclassified (IBDU) and indeterminate colitis (IC) remains obscure. The aim was to evaluate the clinical impact of capsule endoscopy on IBDU/IC patients with negative serology. Methods: Eighteen patients with long‐standing IBDU (n = 14) and IC (n = 4) were enrolled to undergo a capsule endoscopy and then followed prospectively. Lesions considered diagnostic of Crohns disease (CD) were 4 or more erosions/ulcers and/or a stricture. The median follow‐up time after capsule endoscopy was 32 ± 11 months (23–54 months). Results: Total enteroscopy was possible in all patients. In 2 patients the examination was normal (Group 1). In 9 patients subtle findings were observed (Group 2): focal villi denudation (n = 1) and fewer than 4 erosions/ulcers (n = 8). In 7 patients, 4 or more erosions/ulcers were detected (Group 3), leading to a diagnosis of CD. However, their treatment was not reassessed on the basis of the capsule findings. Until now, a definitive diagnosis has been achieved in 2 additional patients: 1 from Group 1 (ulcerative colitis) and another patient from Group 2 (CD), who began infliximab infusions. Nine patients remained indeterminate at follow‐up. Conclusions: Although capsule endoscopy enabled the diagnosis of CD in 7 patients, in none of them was the clinical management changed. Moreover, a change in therapy due to a diagnosis of CD was made for only 1 patient, who presented nonspecific findings. Our results suggest that capsule findings are not helpful in the work‐up of these patients. Inflamm Bowel Dis 2010

Automatic Polyp Detection in Pillcam Colon 2 Capsule Images and Videos: Preliminary Feasibility Report

Background. The aim of this work is to present an automatic colorectal polyp detection scheme for capsule endoscopy. Methods. PillCam COLON2 capsule-based images and videos were used in our study. The database consists of full exam videos from five patients. The algorithm is based on the assumption that the polyps show up as a protrusion in the captured images and is expressed by means of a P-value, defined by geometrical features. Results. Seventeen PillCam COLON2 capsule videos are included, containing frames with polyps, flat lesions, diverticula, bubbles, and trash liquids. Polyps larger than 1 cm express a P-value higher than 2000, and 80% of the polyps show a P-value higher than 500. Diverticula, bubbles, trash liquids, and flat lesions were correctly interpreted by the algorithm as nonprotruding images. Conclusions. These preliminary results suggest that the proposed geometry-based polyp detection scheme works well, not only by allowing the detection of polyps but also by differentiating them from nonprotruding images found in the films.

Small-Bowel Capsule Endoscopy in Patients with Suspected Crohn's Disease—Diagnostic Value and Complications

Background. The aim of this work was to assess the value of capsule enteroscopy in the diagnosis of patients with suspected Crohns Disease (CD). Methods. This was a retrospective study in a single tertiary care centre involving patients undergoing capsule enteroscopy for suspected CD. Patients taking nonsteroidal anti inflammatory drugs during the thirty preceding days or with a follow-up period of less than six months were excluded. Results. Seventy eight patients were included. The endoscopic findings included mucosal breaks in 50%, ulcerated stenosis in 5%, and villous atrophy in 4%. The diagnosis of CD was established in 31 patients. The sensitivity, specificity, positive and negative predictive value of the endoscopic findings were 93%, 80%, 77%, and 94%, respectively. Capsule retention occurred in four patients (5%). The presence of ulcerated stenosis was significantly more frequent in patients with positive inflammatory markers. The diagnostic yield of capsule enteroscopy in patients with negative ileoscopy was 56%, with a diagnostic acuity of 93%. Conclusions. Small bowel capsule endoscopy is a safe and valid technique for assessing patients with suspected CD. Capsule retention is more frequent in patients with positive inflammatory markers. Patients with negative ileoscopy and suspected CD should be submitted to capsule enteroscopy.

URGENT CAPSULE ENDOSCOPY IS USEFUL IN SEVERE OBSCURE-OVERT GASTROINTESTINAL BLEEDING

Aim:  With capsule endoscopy (CE) it is possible to examine the entire small bowel. The present study assessed the diagnostic yield of CE in severe obscure‐overt gastrointestinal bleeding (OOGIB).

Computer-assisted bleeding detection in wireless capsule endoscopy images

Wireless capsule endoscopy (WCE) has revolutionised the diagnosis and treatment of gastrointestinal tract, especially the small intestine where traditional endoscopies cannot reach. However, this new technology leads to the inspection of a large number of images, which is a time-consuming process and also too hard by naked eyes for doctors. In this paper, we propose a new computerised method for bleeding detection in WCE images. We use the second component of CIE Lab colour space together with appropriate segmentation and enhancement techniques, involving an adaptive anisotropic diffusion (alike Perona–Malik diffusion). As a result of this procedure, it is possible to devise four functions to discriminate between bleeding and normal regions in WCE images. These four bleeding detectors rely on the eigenvalues of the Hessian and on the Laplacian of the modified enhanced image. Multiscale image analysis approach is also involved in the definition of these detectors for handling the maximum and minimum sizes at which the bleeding regions are expected to be found. Experimental results on several medical data-sets show that the new algorithm achieves a very good rate of success and promising performance for bleeding detection.

Severe acute liver failure as the initial manifestation of haematological malignancy.

Acute liver failure is rarely secondary to lymphoma or leukaemia and it is extremely uncommon as the initial presentation of malignancy. We report a case of a young adult patient with severe acute liver failure referred for liver transplant, in which a Burkitt acute lymphoblastic leukaemia was diagnosed by bone marrow examination. A complete recovery and long remission were obtained with chemotherapy.

Virtual chromoendoscopy can be a useful software tool in capsule endoscopy

BACKGROUND capsule endoscopy (CE) has revolutionized the study of small bowel. One major drawback of this technique is that we cannot interfere with image acquisition process. Therefore, the development of new software tools that could modify the images and increase both detection and diagnosis of small-bowel lesions would be very useful. The Flexible Spectral Imaging Color Enhancement (FICE) that allows for virtual chromoendoscopy is one of these software tools. AIMS to evaluate the reproducibility and diagnostic accuracy of the FICE system in CE. METHODS this prospective study involved 20 patients. First, four physicians interpreted 150 static FICE images and the overall agreement between them was determined using the Fleiss Kappa Test. Second, two experienced gastroenterologists, blinded to each other results, analyzed the complete 20 video streams. One interpreted conventional capsule videos and the other, the CE-FICE videos at setting 2. All findings were reported, regardless of their clinical value. Non-concordant findings between both interpretations were analyzed by a consensus panel of four gastroenterologists who reached a final result (positive or negative finding). RESULTS in the first arm of the study the overall concordance between the four gastroenterologists was substantial (0.650). In the second arm, the conventional mode identified 75 findings and the CE-FICE mode 95. The CE-FICE mode did not miss any lesions identified by the conventional mode and allowed the identification of a higher number of angiodysplasias (35 vs 32), and erosions (41 vs. 24). CONCLUSIONS there is reproducibility for the interpretation of CE-FICE images between different observers experienced in conventional CE. The use of virtual chromoendoscopy in CE seems to increase its diagnostic accuracy by highlighting small bowel erosions and angiodysplasias that weren´t identified by the conventional mode.

Mucosal region detection and 3D reconstruction in wireless capsule endoscopy videos using active contours

Wireless capsule endoscopy (WCE) provides an inner view of the human digestive system. The inner tubular like structure of the intestinal tract consists of two major regions: lumen - intermediate region where the capsule moves, mucosa - membrane lining the lumen cavities. We study the use of the Split Bregman version of the extended active contour model of Chan and Vese for segmenting mucosal regions in WCE videos. Utilizing this segmentation we obtain a 3D reconstruction of the mucosal tissues using a near source perspective shape-from-shading (SfS) technique. Numerical results indicate that the active contour based segmentation provides better segmentations compared to previous methods and in turn gives better 3D reconstructions of mucosal regions.

Capsule endoscopy assisted by traditional upper endoscopy

BACKGROUND AND AIMS Capsule endoscopy (CE) can be prevented by difficulties in swallowing the device and/or its gastric retention. In such cases, endoscopic delivery of the capsule to duodenum is very useful. We describe the indications and outcomes of cases in which traditional endoscopic techniques allowed placement of the capsule in duodenum. PATIENTS AND METHODS This is a retrospective, descriptive case series. All patients in the above conditions were identified and indications for CE, endoscopic-placement technique, complications and completeness of small bowel imaging were registered. RESULTS Endoscopic-assisted delivery of the capsule was necessary in 13 patients (2.1% of all CE; 7 males; mean age--47.9 +/- 24.9 years, range 13 to 79 years). Indications for endoscopic delivery included: inability to swallow the capsule (7), gastric retention in previous exams (3), abnormal upper gastrointestinal anatomy (3). In eight patients, the capsule was introduced in GI tract with: foreign body retrieval net alone (3), retrieval net and a translucent cap (2), prototype delivery device (2) or a polypectomy snare (1). Five patients ingested the capsule that was then placed in duodenum with a polypectomy snare (3) or a retrieval net (2). No major complications occurred. Complete small bowel examination was possible in 10 patients (77%). CONCLUSIONS Endoscopic placement of capsule endoscope in the duodenum is rarely needed. However it may be safely performed by different techniques avoiding some limitations of CE. The best methods for endoscopic delivery of the capsule in the duodenum seem to be retrieval net with a translucent cap when the patient is unable to swallow the device or a retrieval net only to capture the capsule in the stomach when the patients swallows it easily.