Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection

01/15/2019
by   Timo Kohlberger, et al.
6

Digital pathology enables remote access or consults and powerful image analysis algorithms. However, the slide digitization process can create artifacts such as out-of-focus (OOF). OOF is often only detected upon careful review, potentially causing rescanning and workflow delays. Although scan-time operator screening for whole-slide OOF is feasible, manual screening for OOF affecting only parts of a slide is impractical. We developed a convolutional neural network (ConvFocus) to exhaustively localize and quantify the severity of OOF regions on digitized slides. ConvFocus was developed using our refined semi-synthetic OOF data generation process, and evaluated using real whole-slide images spanning 3 different tissue types and 3 different stain types that were digitized by two different scanners. ConvFocus's predictions were compared with pathologist-annotated focus quality grades across 514 distinct regions representing 37,700 35x35μm image patches, and 21 digitized "z-stack" whole-slide images that contain known OOF patterns. When compared to pathologist-graded focus quality, ConvFocus achieved Spearman rank coefficients of 0.81 and 0.94 on two scanners, and reproduced the expected OOF patterns from z-stack scanning. We also evaluated the impact of OOF on the accuracy of a state-of-the-art metastatic breast cancer detector and saw a consistent decrease in performance with increasing OOF. Comprehensive whole-slide OOF categorization could enable rescans prior to pathologist review, potentially reducing the impact of digitization focus issues on the clinical workflow. We show that the algorithm trained on our semi-synthetic OOF data generalizes well to real OOF regions across tissue types, stains, and scanners. Finally, quantitative OOF maps can flag regions that might otherwise be misclassified by image analysis algorithms, preventing OOF-induced errors.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 13

page 15

page 16

page 17

page 19

page 21

page 28

page 29

09/25/2012

Segmentation of Breast Regions in Mammogram Based on Density: A Review

The focus of this paper is to review approaches for segmentation of brea...
10/21/2018

Hierarchical ResNeXt Models for Breast Cancer Histology Image Classification

Microscopic histology image analysis is a cornerstone in early detection...
04/15/2013

Multispectral Spatial Characterization: Application to Mitosis Detection in Breast Cancer Histopathology

Accurate detection of mitosis plays a critical role in breast cancer his...
02/03/2018

Ensembling Neural Networks for Digital Pathology Images Classification and Segmentation

In the last years, neural networks have proven to be a powerful framewor...
10/27/2019

Deep Learning Models for Digital Pathology

Histopathology images; microscopy images of stained tissue biopsies cont...
08/04/2016

Identifying Metastases in Sentinel Lymph Nodes with Deep Convolutional Neural Networks

Metastatic presence in lymph nodes is one of the most important prognost...
11/01/2019

Validation of a deep learning mammography model in a population with low screening rates

A key promise of AI applications in healthcare is in increasing access t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.