Blind deblurring for microscopic pathology images using deep learning networks

11/24/2020
by   Cheng Jiang, et al.
17

Artificial Intelligence (AI)-powered pathology is a revolutionary step in the world of digital pathology and shows great promise to increase both diagnosis accuracy and efficiency. However, defocus and motion blur can obscure tissue or cell characteristics hence compromising AI algorithms'accuracy and robustness in analyzing the images. In this paper, we demonstrate a deep-learning-based approach that can alleviate the defocus and motion blur of a microscopic image and output a sharper and cleaner image with retrieved fine details without prior knowledge of the blur type, blur extent and pathological stain. In this approach, a deep learning classifier is first trained to identify the image blur type. Then, two encoder-decoder networks are trained and used alone or in combination to deblur the input image. It is an end-to-end approach and introduces no corrugated artifacts as traditional blind deconvolution methods do. We test our approach on different types of pathology specimens and demonstrate great performance on image blur correction and the subsequent improvement on the diagnosis outcome of AI algorithms.

READ FULL TEXT

page 3

page 5

page 6

page 8

page 9

page 10

research
07/23/2019

Blind Deblurring using Deep Learning: A Survey

We inspect all the deep learning based solutions and provide holistic un...
research
08/05/2023

Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks

In recent years, the removal of motion blur in photographs has seen impr...
research
02/25/2016

CNN for License Plate Motion Deblurring

In this work we explore the previously proposed approach of direct blind...
research
04/01/2021

Learning Deep Latent Subspaces for Image Denoising

Heterogeneity exists in most camera images. This heterogeneity manifests...
research
09/29/2006

Conditional Expressions for Blind Deconvolution: Multi-point form

We present conditional expression (CE) for finding blurs convolved in gi...
research
09/30/2006

Conditional Expressions for Blind Deconvolution: Derivative form

We developed novel conditional expressions (CEs) for Lane and Bates' bli...
research
01/18/2023

Blur Invariants for Image Recognition

Blur is an image degradation that is difficult to remove. Invariants wit...

Please sign up or login with your details

Forgot password? Click here to reset