An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma

Zapaishchykova, Anna; Dreizin, David; Li, Zhaoshuo; Wu, Jie; Faghihroohi, Shahrooz; Unberath, Mathias

doi:10.1007/978-3-030-87199-4_40

Cited by 11 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly (Singla et al, 2021) employ mediation analysis to identify the units and parameters of radiological reports that influence their classifier's outcomes; this method is applied on chest X-rays. In their work (Zapaishchykova et al, 2021) develop a Bayesian causal model to interpret the outputs and functionality of their Faster-RCNN based pelvic fracture classifier in CT images. Their Bayesian causal model matches lower confidence predictions with higher confidence ones and then updates the prediction set based on these matching.…”

Section: Fairness Safety and Explainabilitymentioning

confidence: 99%

A Review of Causality for Learning Algorithms in Medical Image Analysis

Vlontzos

Rueckert

Kainz

2022

Melba

View full text Add to dashboard Cite

Medical image analysis is a vibrant research area that offers doctors and medical practitioners invaluable insight and the ability to accurately diagnose and monitor disease. Machine learning provides an additional boost for this area. However, machine learning for medical image analysis is particularly vulnerable to natural biases like domain shifts that affect algorithmic performance and robustness. In this paper we analyze machine learning for medical image analysis within the framework of Technology Readiness Levels and review how causal analysis methods can fill a gap when creating robust and adaptable medical image analysis algorithms.<br>We review methods using causality in medical imaging AI/ML and find that causal analysis has the potential to mitigate critical problems for clinical translation but that uptake and clinical downstream research has been limited so far.

show abstract

Section: Fairness Safety and Explainabilitymentioning

confidence: 99%

A Review of Causality for Learning Algorithms in Medical Image Analysis

Vlontzos

Rueckert

Kainz

2022

Melba

View full text Add to dashboard Cite

show abstract

Section: Fairness Safety and Explainabilitymentioning

confidence: 99%

Untitled

2022

Melba

View full text Add to dashboard Cite

Medical image analysis is a vibrant research area that offers doctors and medical practitioners invaluable insight and the ability to accurately diagnose and monitor disease. Machine learning provides an additional boost for this area. However, machine learning for medical image analysis is particularly vulnerable to natural biases like domain shifts that affect algorithmic performance and robustness. In this paper we analyze machine learning for medical image analysis within the framework of Technology Readiness Levels and review how causal analysis methods can fill a gap when creating robust and adaptable medical image analysis algorithms. We review methods using causality in medical imaging AI/ML and find that causal analysis has the potential to mitigate critical problems for clinical translation but that uptake and clinical downstream research has been limited so far.

show abstract

“…1 In recent years, there has been a growing interest in studying the epidemiology of surgically treated pelvis and acetabulum fractures to better understand their incidence, demographic patterns, and associated risk factors. 2 The rising prevalence of these fractures is a matter of concern, as they often require complex surgical interventions and extensive rehabilitation. Additionally, they may have a significant negative effect on the quality of life of those who are impacted, which may result in long-term incapacity and financial strain on healthcare systems.…”

Section: Introductionmentioning

confidence: 99%

An epidemiological trend in surgical management of pelvis and acetabulum fractures at Indira Gandhi Institute of Medical Sciences level-1 trauma centre in Patna: a retrospective study

Kumar,

Shankar

et al. 2024

Int J Res Med Sci

View full text Add to dashboard Cite

Background: Pelvic and acetabular fractures, principally resulting from high-energy trauma like motor vehicle accidents, are challenging orthopedic injuries that can lead to significant morbidity and functional impairment. Understanding their epidemiology, treatment, and outcomes is crucial for improving patient care. Methods: This retrospective cohort study involving 34 patients who underwent surgery for pelvic and acetabular fractures from April 2021 to September 2023. Data on patient demographics, injury mechanisms, fracture types, surgical approaches, and post-operative outcomes were collected and analyzed. Results: The study group comprised predominantly males (67%) with mean age of 35 years. Road traffic accidents were the leading cause of injuries (95%). The most common fracture types were the posterior wall of the acetabulum (10%) and type II anteroposterior compression fractures (10%). Related injuries included long bone fractures (62.5%) and posterior hip dislocation (33.33%). Surgical treatment primarily involved open reduction and internal fixation with various approaches. Postoperative complications included sciatic nerve palsy (4.17%), venous thromboembolism (20.83%), and wound infections (12.5%), but both post-operative mortality and heterotopic ossification were absent. Conclusions: The study highlights the prevalence of pelvic and acetabular fractures due to road traffic accidents and the complexity of their surgical management. The associated injuries and postoperative complications underscore the need for specialized orthopedic care.

show abstract

An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma

Cited by 11 publications

References 21 publications

A Review of Causality for Learning Algorithms in Medical Image Analysis

A Review of Causality for Learning Algorithms in Medical Image Analysis

Untitled

An epidemiological trend in surgical management of pelvis and acetabulum fractures at Indira Gandhi Institute of Medical Sciences level-1 trauma centre in Patna: a retrospective study

Contact Info

Product

Resources

About