Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment

07/07/2020
by   Aadarsh Jha, et al.
0

Automatic instance segmentation of glomeruli within kidney Whole Slide Imaging (WSI) is essential for clinical research in renal pathology. In computer vision, the end-to-end instance segmentation methods (e.g., Mask-RCNN) have shown their advantages relative to detect-then-segment approaches by performing complementary detection and segmentation tasks simultaneously. As a result, the end-to-end Mask-RCNN approach has been the de facto standard method in recent glomerular segmentation studies, where downsampling and patch-based techniques are used to properly evaluate the high resolution images from WSI (e.g., >10,000x10,000 pixels on 40x). However, in high resolution WSI, a single glomerulus itself can be more than 1,000x1,000 pixels in original resolution which yields significant information loss when the corresponding features maps are downsampled via the Mask-RCNN pipeline. In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework. Beyond such a comparison, we also comprehensively evaluate the performance of our detect-then-segment pipeline through: 1) two of the most prevalent segmentation backbones (U-Net and DeepLab_v3); 2) six different image resolutions (from 512x512 to 28x28); and 3) two different color spaces (RGB and LAB). Our detect-then-segment pipeline, with the DeepLab_v3 segmentation framework operating on previously detected glomeruli of 512x512 resolution, achieved a 0.953 dice similarity coefficient (DSC), compared with a 0.902 DSC from the end-to-end Mask-RCNN pipeline. Further, we found that neither RGB nor LAB color spaces yield better performance when compared against each other in the context of a detect-then-segment framework. Detect-then-segment pipeline achieved better segmentation performance compared with End-to-end method.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 8

page 9

research
06/30/2021

SOLO: A Simple Framework for Instance Segmentation

Compared to many other dense prediction tasks, e.g., semantic segmentati...
research
04/06/2022

End-to-End Instance Edge Detection

Edge detection has long been an important problem in the field of comput...
research
04/12/2021

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Tremendous efforts have been made on instance segmentation but the mask ...
research
05/27/2020

Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

We present a new version of YOLO with better performance and extended wi...
research
02/13/2021

Fast, Accurate Barcode Detection in Ultra High-Resolution Images

Object detection in Ultra High-Resolution (UHR) images has long been a c...
research
03/31/2021

Using depth information and colour space variations for improving outdoor robustness for instance segmentation of cabbage

Image-based yield detection in agriculture could raiseharvest efficiency...
research
10/09/2019

Fast Panoptic Segmentation Network

In this work, we present an end-to-end network for fast panoptic segment...

Please sign up or login with your details

Forgot password? Click here to reset