Novel method of image analysis that combines Radon and Fourier image transformations for the purpose of differentiating between malignant and benign colonic biopsies

Chen Faibis, Edmond Sabo, Salam Mazareb, Geula Klorin

Research output: Contribution to journalArticlepeer-review

Abstract

Colorectal cancer is the third most common type of cancer. It develops slowly as a polyp that can turn into a cancerous tumor. This study aimed to develop a decision-making algorithm of microscopic images using texture analysis that is orientation free, to be used for automated classification of normal and neoplastic (malignant or premalignant) colonic biopsies. Forty-nine colonic adenocarcinomas, 41 adenomas and a control group of adjacent normal colonic mucosa were included in the texture analysis. Radon transform followed by the Fast Fourier transform were applied to the images. Subsequently, the gray level co-occurrence matrix (GLCM) transform was applied allowing the extraction of four textural variables (homogeneity, contrast, correlation, and entropy). For classification and prediction of the diagnosis, a statistical multivariate regression model and a neural network (NNET) model were used and compared. The statistical model provided a sensitivity of 71.3% and a specificity of 50% (Area under the ROC curve: 0.67) for classifying the neoplastic and the normal images, respectively. The NNET model was superior to the statistical model and produced a sensitivity of 97.9% and specificity of 88% (Area under the ROC curve: 0.92). To our knowledge, this is the first study that used a combination of Radon, FFT, and GLCM transformations in order to overcome the tissue orientation problem in texture analysis of microscopic images of colonic biopsies. The NNET classifier trained by the extracted textural features proved to be superior to the statistical classifier, thus predicting colonic neoplasia with high accuracy. Research Highlights: We propose a novel decision-making algorithm of orientation invariant image texture analysis, fast and easily implemented for automated differentiation between benign and neoplastic epithelial tumors of the colon. This method can reduce the turnaround time allowing to prioritize the biopsies during their examination and diagnosis by the pathologist.

Original languageEnglish
JournalMicroscopy Research and Technique
Early online date3 Mar 2024
DOIs
StateE-pub ahead of print - 3 Mar 2024
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2024 Wiley Periodicals LLC.

Keywords

  • colonic neoplasia
  • morphometry
  • neural network
  • radon

ASJC Scopus subject areas

  • Anatomy
  • Histology
  • Instrumentation
  • Medical Laboratory Technology

Fingerprint

Dive into the research topics of 'Novel method of image analysis that combines Radon and Fourier image transformations for the purpose of differentiating between malignant and benign colonic biopsies'. Together they form a unique fingerprint.

Cite this