Automated Detection of Liver Histopathological Findings Based on Biopsy Image Processing

Abstract

Hepatic steatosis is the accumulation of fat in the hepatic cells and the liver. Triglycerides and other kinds of molecules are included in the lipids. When there is some defect in the process, hepatic steatosis arise, during which the free fatty acids are taken by the liver and exuded as lipoproteins. Alcohol is the main cause of steatosis when excessive amounts are consumed for a long period of time. In many cases, steatosis can lead to inflammation that is mentioned as steatohepatitis or non-alcoholic steatohepatitis (NASH), which can later lead to fibrosis and finally cirrhosis. For automated detection and quantification of hepatic steatosis, a novel two-stage methodology is developed in this study. Initially, the image is processed in order to become more suitable for the detection of fat regions and steatosis quantification. In the second stage, initial candidate image regions are detected, and then they are either validated or discarded based on a series of criteria. The methodology is based on liver biopsy image analysis, and has been tested using 40 liver biopsy images obtained from patients who suffer from hepatitis C. The obtained results indicate that the proposed methodology can accurately assess liver steatosis.

A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

“…Fuzzy logic can also be employed in other stages like the segmentation and classification as will be described in the following sections. In [53], edge sharpening is also used after converting the original image to gray scale. A gray level threshold T3 can be used to segment different image areas and the pixels having gray level equal to T3 (or "T3 ± a small margin" for higher flexibility) can be assumed to be the border of a spot.…”

“…A gray level threshold T3 can be used to segment different image areas and the pixels having gray level equal to T3 (or "T3 ± a small margin" for higher flexibility) can be assumed to be the border of a spot. The conversion of an image to gray scale can be performed either by simply averaging the basic color components or by a weighted averaging like I_grayscale = 0.2989R + 0.5870G + 0.1140B [53]. Using Octave to demonstrate this simple T3 thresholding, we get the Figure 4a where the red dots show the recognized spot boundaries.…”

“…The conversion of an image to gray scale and then to black and white (binary mask) is performed for several purposes. In [53], the gray version of the image displaying liver tissue is subject to equalization and then a gray level threshold (similar to T3 in the previous paragraph) is used to convert the image to binary (black and white) representation. The white color corresponds to fat regions while the rest of the liver area is painted in black.…”

“…Image resizing is applied for different reasons in various approaches. The size of the biopsy image in [53] is magnified to zoom in the details. Bicubic interpolation and the weighted average of the pixels in the nearest 4-by-4 neighborhood is employed for the estimation of a new pixel value.…”

“…The MRI images used in this approach were retrieved from Cannizzaro Hospital (Catania, Italy). Fat in the liver can be recognized as described in [53] where images are captured from a microscope during biopsy. The use of fuzzy logic in medical image processing applications is reviewed in [54].…”