Computer‐aided grading system for endoscopic severity in patients with ulcerative colitis

Abstract

The degree of mucosal redness can be quantified as an index of hemoglobin (IHB) that changes with photographic conditions. The first aim of the present study was to stress the exclusion of γ correction as a critical procedure for reliable measurements of IHB. The second aim was to characterize Matts grade by pictorial parameters in the gray scale picture of IHB and to establish a computer‐aided grading system of endoscopic severity in ulcerative colitis. A total of 130 digital endoscopic pictures of 55 patients with ulcerative colitis (30 Matts 1, 70 Matts 2, 20 Matts 3 and 10 Matts 4) were used. The pictures without γ correction were processed for the mean IHB, SD of IHB, kurtosis of IHB and contrast feature. A computer‐aided grading system was constructed on the basis of Bayes decision theory. Significant increase in the mean IHB was seen when comparing Matts 1 to Matts 2. The SD of IHB or contrast feature significantly increased from Matts 2 to Matts 3 or from Matts 3 to Matts 4. Kurtosis of IHB was significantly larger in Matts 3 than in Matts 1 or Matts 4. Sensitivity and specificity when discriminating Matts 1 from Matts 2, Matts 2 from Matts 3 and Matts 3 from Matts 4 by the grading system were found to be 84 and 96%, 94 and 70%, and 100 and 85%, respectively. The computer‐aided grading system may permit quantitative evaluation of effects of treatments in ulcerative colitis with minimal interobserver variation.

Morphometry for Microvessels in Early Gastric Cancer by Narrow Band Imaging‐equipped Magnifying Endoscopy

“…CAD is a general term used for a variety of artificial intelligence techniques applied to interpretation of gray‐scale medical images, including mammogram or chest X‐ray radiogram for cancer screening 19 . We have previously reported a reliable image‐processing method to extract the morphological features for spatial arrangements of mucosal color 6 and the degree of mucosal surface roughness 7 . These quantitative methods are potential tools to improve reliability in image interpretation by minimizing interobserver variation.…”

“…Although it is quite easy for human observers to recognize and describe the features of the microvascular structure or spatial arrangements in empirical terms, it has been extremely refractory to get a precise definition and analysis by computers. Image processing method has been a useful means to quantify any element composing an endoscopic picture, including mucosal pattern (spatial arrangements of mucosal color) 6 or the degree of mucosal surface roughness 7 …”

Computer-Aided Estimation for the Risk of Development of Gastric Cancer by Image Processing

“…We have previously established CAD for grading endoscopic severity in patients with ulcerative colitis [8] or CAD for detecting flat type early esophageal cancer [13]. In the present study, it has been demonstrated that CAD methods can be utilized as a means for an effective screening of gastric cancer by identifying the high risk population needing follow-up endoscopy.…”

“…The color of any object in the digitized picture can be quantified by the intensity of red (R), green (G) and blue (B) reflectance. As hemoglobin is the predominant chromophore in the gastrointestinal mucosa, a colorant endoscopic picture is equivalent to a grey scale picture with index of hemoglobin (IHB=32log2[R/G] ) assigned to each pixel ( Figure 2) [8]. The grey scale picture with blackout or halation excluded was processed for 4 basic statistical parameters (mean IHB, SD of IHB, skewness of IHB, kurtosis of IHB) and 11 textural features that are related with spatial arrangements of the grey scale intensities (Table 1) [10].…”

“…CAD methods are important for: (a) improving the sensitivity of cancer detection, (b) reducing interobserver variation in image interpretation, (c) improving efficiency of screening by identifying suspect lesions [7]. We have developed a quantitative method to characterize endoscopic features in a processed endoscopic picture [8]. The aims of this study were to characterize background gastric mucosa at higher risk for gastric cancer and to establish a CAD system for determining the risk of development of gastric cancer in a population with positive H. pylori.…”