Microscopic biopsy image reconstruction using inception block with denoising auto-encoder approach

Shiksha Singh, Rajesh Kumar

Research output: Contribution to journalArticlepeer-review

Abstract

The use of computer-aided image analysis for disease diagnosis and prognosis has dramatically increased during the past 10 years. The introduction of computer-assisted image analysis of images produced by equipment employed in medical science for the prognosis of various diseases has been made possible by the development of digital scanners and high-resolution imaging technologies. Additionally, much like any other digital image, the obtained medical images may become distorted by various distortions and sounds. The noise in histopathology images can be random or have an even frequency distribution; it can be introduced during data acquisition by imaging devices or as a result of signal processing algorithms; either way, the noise appears in the digital image in an uncorrelated way, inevitably lowering the visual quality of the images. In the present article, employed an integrative strategy for the image denoising of the histopathological images of Breast cancer through deep learning (DL) approach. Moreover, some noises remain intact while following the approach due to the direct conduction of the feature map and also the level noise. Henceforth, a denoising model using Denoising Autoencoder with an Inception network block (InDAENET) has been proposed to deal with the left-out feature maps and high noise signals related to the medical images. The proposed method has been prepared and verified on the publicly available dataset BreakHis. This approach has further been successfully compared with the conventional Denoising autoencoder (DAE) method. Henceforth, it paves the way for Histopathological Image Reconstruction using an Inception block with Denoising Autoencoder for Breast Cancer Detection.

Original languageEnglish
JournalInternational Journal of Information Technology (Singapore)
DOIs
StateAccepted/In press - 1 Jan 2024
Externally publishedYes

Keywords

  • Convolutional neural network
  • Denoising autoencoder
  • Histopathological image
  • Inception network
  • Medical image

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computer Networks and Communications
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Microscopic biopsy image reconstruction using inception block with denoising auto-encoder approach'. Together they form a unique fingerprint.

Cite this