# The use of deep learning enables high diagnostic accuracy in detecting syndesmotic instability on weight-bearing CT scanning

**Authors:** Alireza Borjali, Soheil Ashkani-Esfahani, Rohan Bhimani, Daniel Guss, Orhun K. Muratoglu, Christopher W. DiGiovanni, Kartik Mangudi Varadarajan, Bart Lubberts  
**arXiv:** [2207.03568](https://arxiv.org/abs/2207.03568)  
**Date:** 2022-07-07  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2207.03568v1/

## Key points

- Deep learning techniques have shown promising results in detecting syndesmotic instability on weight-bearing CT scans
- Syndesmosis instability can lead to significant morbidity and accelerated arthritic changes if left undiagnosed
- Traditional diagnostic methods for syndesmotic instability are reliable but time-consuming and experience-dependent
- The study aimed to improve accuracy, reduce analysis time, and minimize inter-observer bias by automating 3D volume assessment of syndesmosis anatomy using WBCT scans
- Deep learning has emerged as a powerful tool in medical imaging analysis with potential applications in detecting complex conditions like syndesmotic instability
- Specialized WBCT scans provide valuable information about ankle joint stability under weight-bearing conditions and are crucial for accurate diagnosis of syndesmosis instability
- By leveraging deep learning algorithms, the study aimed to automate the diagnosis process for syndesmotic instability and reduce reliance on manual interpretation
- The research findings have important implications for clinical practice, emphasizing the benefits of incorporating deep learning techniques into routine diagnostic procedures for identifying syndesmotic instability

## Summary

In a recent study by Borjali et al., the use of deep learning techniques has shown promising results in detecting syndesmotic instability on weight-bearing CT scans. Syndesmosis instability, if left undiagnosed, can lead to significant morbidity and accelerated arthritic changes in the ankle joint. While traditional diagnostic methods for syndesmotic instability are still widely used due to their reliability, they can be time-consuming and experience-dependent. The study aimed to improve accuracy, reduce analysis time, and minimize inter-observer bias by automating the 3D volume assessment of syndesmosis anatomy using WBCT scans. In recent years, deep learning has emerged as a powerful tool in medical imaging analysis, with potential applications in detecting complex conditions such as syndesmotic instability. This condition, if not identified early on, can result in significant complications and long-term consequences for patients. These specialized scans provide valuable information about the stability of the ankle joint under weight-bearing conditions and are crucial for accurate diagnosis of syndesmosis instability. By leveraging advanced technologies like deep learning algorithms, this study aimed to automate the diagnosis process for syndesmotic instability and reduce reliance on manual interpretation. The findings of this research have important implications for clinical practice, highlighting the potential benefits of incorporating deep learning techniques into routine diagnostic procedures for identifying syndesmotic instability.