# A Neural Template Matching Method to Detect Knee Joint Areas

arXiv: https://arxiv.org/abs/2209.11791 · HTML: https://mlsanity.com/paper/2209.11791/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 Sep 2022.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1609.02469/) (2016)
- [Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks](https://mlsanity.com/paper/1703.09856/) (2017)
- [A novel method for automatic localization of joint area on knee plain radiographs](https://mlsanity.com/paper/1701.08991/) (2017)
- [Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity](https://mlsanity.com/paper/1908.08840/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Parts Based Registration Loss for Detecting Knee Joint Areas](https://mlsanity.com/paper/2307.00083/) (2023)

## Abstract (arXiv)

In this paper, new methods are considered to detect knee joint areas in bilateral PA fixed flexion knee X-ray images. The methods are of template matching type where the distance criterion is based on the negative normalized cross-correlation. The manual annotations are made on only one side of a single bilateral image when the templates are selected. The best matching patch search is formulated as an unconstrained continuous domain minimization problem. For the minimization problem different optimization methods are considered. The main method of the paper is a trainable optimizer where the method is taught to take zoomed and possibly rotated patches from its input images which look like the template. In the experiments, we compare the minimum values found by different optimization methods. We also look at some test images to examine the correspondence between the minimum value and how well the knee area is localized. It seems that making annotations only to a single image enables to detect knee joint areas quite precisely.