Purpose/Objectives
Fractures of the vertebral bodies of the dorsal column are an increasingly frequent pathology, especially in the elderly; however, these are often unreported by radiologists. This is mainly due to the fact that the spine is an “hidden area” in the routine thoracic study. In addition, radiologists are not always aware of spinal fractures associated morbidity.
This study aims to evaluate the performance of an artificial intelligence (AI) algorithm assessing spinal alterations in the detection of fractures of the dorsal spine.
Methods and Materials
348 patients who underwent chest CT scans were retrospectively evaluated by the AI ​​algorithm (Siemens AI RAD Companion) that assigned a score (MSK range) ranging from 1 to 4; score 1 is considered normal and score 2 to 4 abnormal. Subsequently, the 348 scans were reviewed by 2 experienced radiologists which evaluated the clinical relevance of the spinal alterations in each study and whether these alterations were previously reported by the reporting radiologist.
Results
The AI ​​algorithm detected abnormal spinal findings in 130 patients (37.4% of cases). Of those, only 18 (13.8%) were considered to have clinically relevant findings by the reviewing radiologist. Among these 18 cases, 15 were previously reported by the radiologist reporting the study (83.3%), while in 3 patients the spinal alteration was not reported (16,67%). Sensitivity and specificity of the AI algorithm were estimated at 47,37% and 63,87%, respectively.
Conclusion
This study demonstrates that this AI tool can be useful as an auxiliary diagnostic method for dorsal column fractures.

**Purpose/Objectives**
Fractures of the vertebral bodies of the dorsal column are an increasingly frequent pathology, especially in the elderly; however, these are often unreported by radiologists. This is mainly due to the fact that the spine is an “hidden area” in the routine thoracic study. In addition, radiologists are not always aware of spinal fractures associated morbidity.
This study aims to evaluate the performance of an artificial intelligence (AI) algorithm assessing spinal alterations in the detection of fractures of the dorsal spine.
**Methods and Materials**
348 patients who underwent chest CT scans were retrospectively evaluated by the AI ​​algorithm (Siemens AI RAD Companion) that assigned a score (MSK range) ranging from 1 to 4; score 1 is considered normal and score 2 to 4 abnormal. Subsequently, the 348 scans were reviewed by 2 experienced radiologists which evaluated the clinical relevance of the spinal alterations in each study and whether these alterations were previously reported by the reporting radiologist.
**Results**
The AI ​​algorithm detected abnormal spinal findings in 130 patients (37.4% of cases). Of those, only 18 (13.8%) were considered to have clinically relevant findings by the reviewing radiologist. Among these 18 cases, 15 were previously reported by the radiologist reporting the study (83.3%), while in 3 patients the spinal alteration was not reported (16,67%). Sensitivity and specificity of the AI algorithm were estimated at 47,37% and 63,87%, respectively.
**Conclusion**
This study demonstrates that this AI tool can be useful as an auxiliary diagnostic method for dorsal column fractures.

Evaluation of AI applications in thoracic imaging: Performance in the detection of vertebral body alterations

The Winter Course 2021 covers a variety of topics from basics in interstitial lung disease, infections including Covid-19, malignancies, lung cancer screening, and artificial intelligence. The combination of topics is aimed to serve as a good introduction to radiologists embarking on a career in thoracic imaging as well as a solid refresher for experienced thoracic radiologists.

[ESTI Winter Course 2021 Evaluation Form](https://www.surveymonkey.com/r/PP9WFTJ?sid=%5Bsid_value%5D&uid=%5Buid_value%5D&tkn=%5Btkn_value%5D&cgrid=%5Bcgrid_value)

ESTI Winter Course 2021

A Computed Tomography-based Radiomics Model for Patient Prognostic Stratification in Non-Small Cell Lung Cancer

Break Video

CT-Guided Microcoil placement for VATS Resection of Pulmonary Nodules

Development of a risk prediction model for pneumothorax in percutaneous CT guided lung biopsy

Evaluation of an AI program in thoracic imaging: Performance in detection of thoracic aorta ectasia

A Single Centre Institutional Study on 2295 patients for COVID-19 Detection from Radiographs Using a Deep Learning Model - Our Experience and Insights

Can inclusion of the combination of chemical shift ratio and signal intensity increase the number of patient’s classified as definitively benign on thymic MRI beyond use of chemical shift ratio alone? Experience from a UK thoracic tertiary referral centre

Relative contribution of emphysema and airway disease to disease severity in COPD patients GOLD stages I to IV using quantitative computed tomography

Lung Thermal Ablation: Comparison between an Augmented Reality Computed Tomography (CT) 3D Navigation System (SIRIO) and Standard CT-Guided Technique

Differentiating COVID-19 pneumonia from atypical bacterial, fungal and non-COVID-19 viral pneumonia on Chest-CT: Is it possible?

Reliability of Ultra-Short Echo Time MRI sequence in the assessment of Interstitial Lung Disease related to Systemic Sclerosis

Assessing longitudinal changes in lung gas transfer in dyspnoeic post-COVID-19 patients using hyperpolarized Xenon-129 Magnetic Resonance Imaging

Session Introduction