Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis

Yanzhe Xu,Teresa Wu,Jennifer R Charlton,Fei Gao,Kevin M Bennett

doi:10.1038/s41598-019-57223-y

Abstract

Imaging biomarkers are being rapidly developed for early diagnosis and staging of disease. The development of these biomarkers requires advances in both image acquisition and analysis. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap between the blobs. The Difference of Gaussian (DoG) detector has been used to overcome these challenges in blob detection. However, the DoG detector is susceptible to over-detection and must be refined for robust, reproducible detection in a wide range of medical images. In this research, we propose a joint constraint blob detector from U-Net, a deep learning model, and Hessian analysis, to overcome these problems and identify true blobs from noisy medical images. We evaluate this approach, UH-DoG, using a public 2D fluorescent dataset for cell nucleus detection and a 3D kidney magnetic resonance imaging dataset for glomerulus detection. We then compare this approach to methods in the literature. While comparable to the other four comparing methods on recall, the UH-DoG outperforms them on both precision and F-score.

Highlights

In image analysis, detection is used to identify objects such as organs and tumors, and segmentation is used to isolate the objects from an image
Since Laplacian of Gaussian (LoG) and Difference of Gaussian (DoG) suffer from over-detection, a Variational Bayesian Gaussian Mixture Model (VBGMM) was implemented as a final step
LoG and DoG were the first two detectors applied to magnetic resonance (MR) images of the kidney to identify glomeruli

Summary

Introduction

Detection is used to identify objects such as organs and tumors, and segmentation is used to isolate the objects from an image. Mathematical morphology is preferred when the blobs are relatively large in size and small in number Weaknesses of this approach include the tendency to under-segment and diminished performance in the presence of noise. Zhang et al developed the Hessian-based Laplacian of Gaussian (HLoG) detector[1] and the Hessian-based Difference of Gaussian (HDoG) detector[28] to automatically detect glomeruli in CFE-MR images They employed the LoG or DoG to smooth the images, followed by Hessian analysis of each voxel for pre-segmentation. To validate the performance of UH-DoG, four methods were chosen from the literature: HLoG1, gLoG21, LoG22, and Radial-Symmetry[17] We tested these on dataset of 2D fluorescent images (n = 200) where the locations of blobs were known. The differences between UH-DoG and HDoG were negligible but the average computation time of UH-DoG was 35% shorter than that of HDoG

Objectives

Methods

Results

Discussion

Conclusion