Video Capsule Endoscopy Images Research Articles

Use of shape-from-shading to estimate three-dimensional architecture in the small intestinal lumen of celiac and control patients

BackgroundAs measured from videocapsule endoscopy images, the small intestinal mucosa of untreated celiac patients has significantly greater and more varied texture compared to normal patients. Three-dimensional modeling using shape-from-shading principles may further increase classification accuracy. MethodsA sequence of 200 consecutive videocapsule images acquired at a 2s–1 frame rate and 576×576 pixel dimension, were obtained at four locations in the small intestinal lumen of ten patients with biopsy-proven celiac disease and ten control patients. Each two-dimensional image was converted to a three-dimensional architectural approximation by considering the 256 grayscale level to be linearly representative of image depth. From the resulting three-dimensional architecture, distinct luminal protrusions, representative of the macro-architecture, were automatically identified by computer algorithm. The range and number of protrusions per image, and their width and height, were determined for celiacs versus controls and tabulated as mean±SD. ResultsThe mean number of villous protrusions per image was 402.2±15.0 in celiacs versus 420.8±24.0 in controls (p<0.001). The average protrusion width was 14.7 pixels in celiacs versus 13.9 pixels in controls (p=0.01). The mean protrusion height was 3.10±2.34 grayscale levels for celiacs versus 2.70±0.43 grayscale levels for controls (p<0.001). Thus celiac patients had significantly fewer protrusions on the luminal surface of the small intestine as compared with controls, and these protrusions had greater dimensions, suggesting they are indicative of a mosaic (cobblestone) macro-architectural pattern which is common in celiacs. ConclusionsShape-from-shading modeling is useful to explore luminal macro-architecture and to detect significant differences in luminal morphology in celiac versus normal patients, which can increase the usefulness of videocapsule studies.

Robust spectral analysis of videocapsule images acquired from celiac disease patients

BackgroundDominant frequency (DF) analysis of videocapsule endoscopy images is a new method to detect small intestinal periodicities that may result from mechanical rhythms such as peristalsis. Longer periodicity is related to greater image texture at areas of villous atrophy in celiac disease. However, extraneous features and spatiotemporal phase shift may mask DF rhythms.MethodThe robustness of Fourier and ensemble averaging spectral analysis to compute DF was tested. Videocapsule images from the distal duodenum of 11 celiac patients (frame rate 2/s and pixel resolution 576 × 576) were analyzed. For patients 1, 2, ... 11, respectively, a total of 10, 11, ..., 20 sequential images were extracted from a randomly selected time epoch. Each image sequence was artificially repeated to 200 frames, simulating periodicities of 0.2, 0.18, ..., 0.1Hz, respectively. Random white noise at four different levels, spatiotemporal phase shift, and frames with air bubbles were added. Power spectra were constructed pixel-wise over 200 frames, and an average spectrum was computed from the 576 × 576 individual spectra. The largest spectral peak in the average spectrum was the estimated DF. Error was defined as the absolute difference between actual DF and estimated DF.ResultsFor Fourier analysis, the mean absolute error between estimated and actual DF was 0.032 ± 0.052Hz. Error increased with greater degree of random noise imposed. In contrast, all ensemble average estimates precisely predicted the simulated DF.ConclusionsThe ensemble average DF estimate of videocapsule images with simulated periodicity is robust to noise and spatiotemporal phase shift as compared with Fourier analysis. Accurate estimation of DF eliminates the need to impose complex masking, extraction, and/or corrective preprocessing measures.

T1199 Distinguishing Patients With Celiac Disease by Quantitative Analysis of Videocapsule Endoscopy Images

T1199 Distinguishing Patients With Celiac Disease by Quantitative Analysis of Videocapsule Endoscopy Images

Distinguishing patients with celiac disease by quantitative analysis of videocapsule endoscopy images

Background Although videocapsule endoscopy images are helpful in the evaluation of celiac disease, their interpretation is subjective. Quantitative disease markers could assist in determining the extent of villous atrophy and response to treatment. Method Capsule endoscopy images were acquired from celiac patients with small bowel pathology ( N = 11) and from control patients ( N = 10). Image resolution was 576 × 576 pixels in dimension, 256 grayscale levels, and had a 2 s −1 frame rate. Pixel brightness and image texture were measured over 10 × 10 pixel subimages and then averaged for 56 × 56 subimages per frame. Measurements were obtained at five locations from proximal to distal small intestine in each patient. At each location, measurements were calculated using 200 consecutive image frames (100 s). Mean frame-to-frame pixel brightness, image texture, and periodicity in brightness, an estimate of wall motion or intestinal motility, were computed and used for classification with a nonlinear discriminant function. Results From pooled data, celiac images had greater texture than did images from control patients ( p < 0.001) and exhibited more frame-to-frame brightness variation as well ( p = 0.032). The dominant period of brightness was longer in celiacs ( p = 0.001), possibly indicating decreased motility. Using the markers for three-dimensional nonlinear classification of celiacs versus controls, sensitivity was 92.7% and specificity was 93.5%. The relationship between dominant period and small intestinal transit time was approximately linear for both celiacs and controls ( r 2 = 0.42 and r 2 =0 .55, respectively). Conclusions Videocapsule images can be quantified to detect villous atrophy throughout the small intestine, and to distinguish individuals with celiac disease from individuals lacking mucosal atrophy.

Detection of small bowel tumors by videocapsule endoscopy in patients with acromegaly

The prevalence of colon polyposis andmalignancies is increased in acromegalic patients as compared to the general population. An epidemiological study suggests a high prevalence also of small bowel (SB) tumors that nowadays may be detected by videocapsule endoscopy (VCE). The aim of the study was to assess the prevalence of SB neoplasms using VCE in acromegalic patients in comparison to control subjects and to correlate it with cancer risk factors and acromegaly-related parameters. Eighteen acromegalic patients (6 males and 12 females, age+/-SD: 54+/-10 yr), 5 cured after surgery (followed by radiotherapy in 3 cases) and 13 on pharmacological treatment were enrolled, and 36 sex- and age-matched non-acromegalic subjects served as a control group. Cancer risk factors, duration of acromegaly, GH and IGF-I levels, IGF binding protein 3 and IGF-II concentrations, metabolic parameters, tumor markers, colonic lesions by total colonoscopy, and SB lesions by VCE were investigated. VCE images suggestive of SB lesions were detected in 5/36 controls [14%, 4 described as gastrointestinal stromal nodular tumors (GIST), and 1 as polyp] and in 5/18 acromegalic patients [28%, 2 GIST and 3 polyps]. In acromegaly, the calculated relative risk for all SB lesions was 1.69 [95%confidence interval (CI): 0.78-3.65], while the relative risk for SB polyps was 2.50 (95% CI: 1.23-5.07). The effective duration of active disease was longer in patients with positive than in those with negative VCE (112+/-89 vs 49+/-40 months, p=0.06). In conclusion, these preliminary results suggest that acromegalic patients might have a high risk of SB polyp development. VCE might be a useful adjunctive diagnostic tool in acromegaly.

NEW OBJECTIVE EVALUATION METHOD FOR FUNCTIONAL BOWEL DISORDER USING VIDEO CAPSULE ENDOSCOPY

The aim of the present study was to use video capsule endoscopy (VCE) to objectively evaluate bowel movements in patients with irritable bowel syndrome (IBS) compared with healthy volunteers. Subjects were nine healthy volunteers (group A) and five IBS patients (group B) whose VCE reached the cecum within the examination time. As the darkest component in an image of VCE is the lumen, we regarded real movements of the intestine observed in the images as the changes of luminal movement, and analyzed them. We trimmed the luminal edge, counted pixels in the lumen and the low brightness area (LBA), of all VCE images and compared them between the groups. There was no difference in the frequency observed in the LBA corresponding to the luminal area between the groups. As for the average volume of the LBA found in an image, it was 1702 pixels in healthy persons versus 305 in IBS patients (P = 0.21) and in healthy persons it tends to be larger. We drew a graph of LBA by time-course. A periodic change in the volume of LBA was found in eight of nine (88.9%) healthy persons over time, but in only two of five (40.0%) IBS patients (P = 0.62). Using endoscopy, a difference in the bowel movement between groups A and B could be evaluated objectively. The present study presents the possibility of a new technique to evaluate functional bowel disorders objectively using an endoscopic procedure.

Wireless Video-Capsule Endoscopy Is a More Sensitive Investigative Method Than Gastro-Intestinal Endoscopy and Biopsies for the Diagnosis of Acute GI-Gvhd.

Acute gastro-intestinal graft-versus-host disease (GI-GVHD) is a major complication following allogeneic stem cell transplantation (allo-SCT) and results in high morbidity and mortality. Diagnosis of GI-GVHD is problematic due a lack of specific symptoms and confounding variables in allo-SCT patients. Although diarrhea is the most common (but non-specific) presenting symptom in acute GI-GVHD, diagnosis is especially difficult when the diarrheal disorder is atypical (i.e. when there is no or limited skin involvement). In a previous study, we reported the positive impact of wireless video-capsule endoscopy (VCE) in the diagnosis of post-transplant diarrhea. Here, we report our experience over the last 5 years with an overall diagnostic approach (including VCE) to the management of allo-SCT patients with suspected acute GI-GVHD. In addition to wireless VCE, patients with atypical post-transplant diarrhea underwent bacterial and viral investigations and upper and/or lower GI-tract endoscopy (plus biopsies, as appropriate). VCE images were scored according to standard endoscopic classification. The final diagnosis took account of the results of the investigation as a whole and the response to therapy. Between August 2002 and October 2007, 240 patients underwent allo-SCT. Thirty patients underwent 37 extensive investigations, with VCE being performed in the following situations: febrile and/or hemorrhagic diarrhea (n=17), isolated diarrhea (n=15), persistent diarrhea or relapse despite appropriate adjustment of immunosuppressive (IS) treatment (n=5). Median time between allo-SCT and VCE was 50 days (range: 19–197). The final diagnosis was acute GVHD (n=19), viral infection (n=6, with 5 CMVs and 1 HHV6s) and a combination of both in 3 cases. The result of our approach was negative in 9 cases (with a normal GI tract by VCE in 8 of them) who were ultimately diagnosed as having functional diarrhea and recovered without any specific treatment.We observed 5 (14%) VCE failures, either due to an absence of intestinal passage (n=3) or major GI hemorrhage (n=2). In the other cases, VCE results were concordant with the final diagnosis. It was noteworthy that VCE was superior to biopsies in some cases. Thus, while VCE demonstrated typical GI-GVHD lesions in 8 patients with histological proven GI-GVHD, VCE showed a normal GI tract (n=4) or GI-GVHD features in 8 other cases where the biopsies were uncertain (n=7) or non-contributive (n=1). The response to appropriate treatment was favorable in 20 cases but was unfavorable and required further therapeutic adjustment in 8 cases (7 GVHDs, 1 CMV). Five patients died of GVHD (n=3), HHV6 infection (n=1) or both (n=1). This study confirms that VCE is a more sensitive investigative method than GI-endoscopy and biopsies. This approach enhanced our ability to modulate IS treatments in patients suffering from atypical post-transplant diarrhea. With its apparently high predictive value, routine use of VCE could be of great interest, particularly with a view to avoiding unnecessary digestive biopsies.

Successful videocapsule endoscopy in patients with an abdominal cardiac pacemaker

Pacemaker location in the abdominal wall is considered a contraindication to videocapsule endoscopy (VCE). The aim of this study was to review our experience on the use of VCE in patients with a pacemaker located in the abdominal wall. VCE was carried out with monitoring of cardiac rhythm. This was a retrospective review of VCE case studies performed at two tertiary care university medical centers (pediatric and adult). The main outcome measures were adverse events and quality of VCE images. No adverse events were experienced in any of the five patients with implanted cardiac pacemakers, including the two with abdominal pacemaker. No interference with the VCE recording was observed during the studies, although the capsule was observed to be briefly inactivated by the pacemaker in one case. The present study, though small, suggests that VCE is safe in adult and pediatric patients who are fitted with cardiac pacemakers, even when implanted in the abdominal wall. The VCE exam can be carried out successfully under close supervision. Dysfunction of the capsule appears to be more likely than problems with cardiac pacing.