Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation

Tingting Yang, Liang Xiao, Yizhe Zhang

TL;DR

The proposed Test-time Self-guided Bounding-box Propagation (TSBP) method, leveraging Earth Mover's Distance (EMD) to enhance object detection in histology images significantly improves detection outcomes when working in conjunction with state-of-the-art deep learning-based detection networks.

Abstract

A global threshold (e.g., 0.5) is often applied to determine which bounding boxes should be included in the final results for an object detection task. A higher threshold reduces false positives but may result in missing a significant portion of true positives. A lower threshold can increase detection recall but may also result in more false positives. Because of this, using a preset global threshold (e.g., 0.5) applied to all the bounding box candidates may lead to suboptimal solutions. In this paper, we propose a Test-time Self-guided Bounding-box Propagation (TSBP) method, leveraging Earth Mover's Distance (EMD) to enhance object detection in histology images. TSBP utilizes bounding boxes with high confidence to influence those with low confidence, leveraging visual similarities between them. This propagation mechanism enables bounding boxes to be selected in a controllable, explainable, and robust manner, which surpasses the effectiveness of using simple thresholds and uncertainty calibration methods. Importantly, TSBP does not necessitate additional labeled samples for model training or parameter estimation, unlike calibration methods. We conduct experiments on gland detection and cell detection tasks in histology images. The results show that our proposed TSBP significantly improves detection outcomes when working in conjunction with state-of-the-art deep learning-based detection networks. Compared to other methods such as uncertainty calibration, TSBP yields more robust and accurate object detection predictions while using no additional labeled samples. The code is available at https://github.com/jwhgdeu/TSBP.

TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation

TL;DR

The proposed Test-time Self-guided Bounding-box Propagation (TSBP) method, leveraging Earth Mover's Distance (EMD) to enhance object detection in histology images significantly improves detection outcomes when working in conjunction with state-of-the-art deep learning-based detection networks.

Abstract

A global threshold (e.g., 0.5) is often applied to determine which bounding boxes should be included in the final results for an object detection task. A higher threshold reduces false positives but may result in missing a significant portion of true positives. A lower threshold can increase detection recall but may also result in more false positives. Because of this, using a preset global threshold (e.g., 0.5) applied to all the bounding box candidates may lead to suboptimal solutions. In this paper, we propose a Test-time Self-guided Bounding-box Propagation (TSBP) method, leveraging Earth Mover's Distance (EMD) to enhance object detection in histology images. TSBP utilizes bounding boxes with high confidence to influence those with low confidence, leveraging visual similarities between them. This propagation mechanism enables bounding boxes to be selected in a controllable, explainable, and robust manner, which surpasses the effectiveness of using simple thresholds and uncertainty calibration methods. Importantly, TSBP does not necessitate additional labeled samples for model training or parameter estimation, unlike calibration methods. We conduct experiments on gland detection and cell detection tasks in histology images. The results show that our proposed TSBP significantly improves detection outcomes when working in conjunction with state-of-the-art deep learning-based detection networks. Compared to other methods such as uncertainty calibration, TSBP yields more robust and accurate object detection predictions while using no additional labeled samples. The code is available at https://github.com/jwhgdeu/TSBP.
Paper Structure (10 sections, 2 equations, 3 figures, 4 tables)

This paper contains 10 sections, 2 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Initialization
  5. Multi-Round EMD Matching and Bounding-Box Propagation
  6. Experiments
  7. Datasets
  8. Main Results
  9. Ablation and Additional Studies
  10. Conclusion

Figures (3)

  • Figure 1: Shown are examples of detected bounding boxes (b-boxes) with varying confidence scores in two test images. The yellow arrows highlight how higher-confident b-boxes influence lower confident b-boxes in TSBP based on visual similarities.
  • Figure 2: Overview of Test-time Self-guided Bounding-box Propagation (TSBP).
  • Figure 3: Top: Gland detection. Bottom: Cell nucleus detection. The red arrows indicate additional true positives compared to the baseline results. The orange arrows indicate additional false positives compared to the baseline results. The blue arrow indicates missed detections compared to the baseline results.