Feasibility and clinical value of deep learning reconstruction in accelerated MRI of shoulder

Journal Title: Chinese Journal of Clinical Research - Year 2024, Vol 37, Issue 8

Abstract

Objective To investigate the feasibility and clinical value of the deep learning reconstruction (DLR) algorithm in enhancing image quality and reducing scan time in shoulder MRI. Methods Fifty patients suspected of having shoulder joint lesions in the Fourth Affiliated Hospital of Nanjing Medical University from June to October 2023 were prospectively included. Routine sequence scanning images with 1.5T MRI were grouped as Fsecon, while scanning images with parallel acquisition acceleration factor 2 were grouped as Fsefast. The scanning sequences included fat-suppression proton density-weighted imaging (PDWI-FS) and T1 weighted imaging (T1WI). The Fsefast group was then transferred to Subtle MRTM dlr to obtain images in the Fsedlr group. The signal-to-noise ratio (SNR) of supraspinatus muscle, long head tendon of biceps brachii, glenoid labrum cartilage, and humerus marrow, as well as the contrast-to-noise ratio (CNR) of supraspinatus muscle/glenoid labrum cartilage, were measured and compared among the three groups. Two radiologists blindly evaluated the image clarity and artifacts of the Fsedlr group and the Fsecon group using the Likert 4-point scale, and compared the diagnostic efficacy of pathological abnormal structures between the two groups. Results Compared with the Fsecon group, the scan time of the Fsedlr group was shortened by 44%, and the image clarity and artifact scores were higher, with statistically significant differences (P<0.05). The intraclass correlation coefficients(ICC)for subjective scores within the two radiologists' groups were 0.797 to 0.919. Among the objective evaluation indicators, the SNR and CNR of the Fsedlr group were significantly higher than those of the Fsecon group and the Fsefast group, with statistically significant differences (P<0.05). In the evaluation of the pathological abnormal structures of the Fsecon group and the Fsedlr group by two radiologists, the diagnostic results of the two groups were consistent (Kappa value: 0.675-1.000), and also showed excellent consistency in the evaluation of the same radiologist (Kappa value: 0.771-1.000), among which the Kappa values of humerus bone marrow, joint bursa and long head tendon of biceps brachii were higher than 0.8. Conclusion The application of the DLR algorithm in shoulder MRI examination can improve image quality, shorten image acquisition time, ensure diagnostic efficacy, and improve examination efficiency, demonstrating good clinical value.

Authors and Affiliations

WANG Xuan, WANG Hao, WAN Yuntian, CHEN Youfang, NIE Chunyan, DU Yusheng, HE Jian (*Department of Medical Imaging Department, Jiangbei Branch of Zhongda Hospital, Southeast University, Nanjing, Jiangsu 210048, China)

Keywords

Related Articles

Effect of sagittal imbalance of the spine on the new fracture in osteoporotic vertebral compression fractures after percutaneous kyphoplasty

<b>Objective</b> To explore the correlation between sagittal imbalance of the spine and new fractures after percutaneous kyphoplasty (PKP) in patients with osteoporotic vertebral compression fracture (OVCF), providing a...

Proteomics-based screening and validation of key targets in chronic obstructive pulmonary disease complicated with lung cancer

<b>Objective</b> To preliminarily predict and verify the biological mechanism and potential core therapeutic targets of chronic obstructive pulmonary disease (COPD)-associated lung cancer (COPD-LC) based on proteomics...

Effect progress of complement system in neural repair after spinal cord injury

Spinal cord injury has the characteristics of high mortality and disability rates, and the treatment of spinal cord injury has been a worldwide problem. With the deepening of spinal cord injury research and the advanceme...

Claudin18.2: an emerging target for the treatment of gastric cancer

Gastric cancer is a malignant tumor that seriously endangers human health. Claudin18.2 (CLDN18.2) is a transmembrane protein and a main component of tight junctions that plays an important role in maintaining barrier fun...

Study on the medication rule of Chinese medicine compound oral administration for the treatment of alopecia areata based on the national patent database

<b>Objective</b> To explore the medication rules of patented Chinese medicine compounds for oral administration in treating alopecia areata (AA), and provide reference for the treatment of AA with Chinese medicine and t...

Download PDF file
  • EP ID EP743103
  • DOI 10.13429/j.cnki.cjcr.2024.08.020
  • Views 12
  • Downloads 0

How To Cite

WANG Xuan, WANG Hao, WAN Yuntian, CHEN Youfang, NIE Chunyan, DU Yusheng, HE Jian (*Department of Medical Imaging Department, Jiangbei Branch of Zhongda Hospital, Southeast University, Nanjing, Jiangsu 210048, China) (2024). Feasibility and clinical value of deep learning reconstruction in accelerated MRI of shoulder. Chinese Journal of Clinical Research, 37(8), -. https://europub.co.uk/articles/-A-743103