Application of Multitask Deep Learning Model in Grading the Severity of Spinal Facet Joint Degeneration

Sponsor
Hai Lv (Other)
Overall Status
Not yet recruiting
CT.gov ID
NCT05635006
Collaborator
(none)
700
1

Study Details

Study Description

Brief Summary

Spinal facet joint osteoarthritis is a disease with high incidence among people over 40 years old. It is a disease characterized by a series of degenerative pathological changes and clinical features of synovium, articular cartilage, subchondral bone, joint space and accessory tissues of spinal facet joints under the action of multiple factors. Some physiological or pathological factors can lead to osteoarthritis of spinal facet joints. Patients with spinal facet osteoarthritis often have different degrees of clinical manifestations such as back pain and dyskinesia, which significantly affect the physical and mental health of patients. The severity of spinal facet osteoarthritis not only has a certain impact on low back pain and changes in low back muscle density, but also affects patient management and treatment plan. At present, different doctors have certain subjectivity in the grading reading of lumbar facet osteoarthritis, and the consistency and repeatability of the results are poor. Moreover, doctors need to read image images and judge the grading is very time-consuming and repetitive work. In recent years, the application of deep learning technology in medical image analysis has been widely concerned by clinicians. Deep learning has great potential benefits in medical imaging diagnosis. It can provide semi-automatic reports under the supervision of radiologists, so as to improve the accuracy, consistency, objectivity and rapidity of disease degree assessment, and further support clinical decision-making on this basis. This project plans to develop an intelligent diagnosis and classification system for degenerative diseases of small joints of the spine with multi task and in-depth learning, and verify its clinical feasibility, aiming to help clinicians improve the accuracy, consistency, objectivity and rapidity of the corresponding disease degree evaluation, and further support the follow-up clinical decision-making.

Condition or Disease Intervention/Treatment Phase

    Detailed Description

    This project is a retrospective clinical study. from 2019 to 2022, the DICOM format images and basic information of imaging X ray, CT, and MR of outpatient and inpatients suspected of low back and in the Fifth Affiliated Hospital of Sun Yat sen University were collected. Get DICOM image mode, and the information section will export the data after the OA batch is successfully submitted; Basic patient information is collected from inpatient medical history. 700 patients are planned to be included. Those projects are randomly divided into training set, verification set and test set according to the ratio of 7:1.5:1.5 for automatic diagnosis of computer in-depth learning model to test the stability and reliability of the model. In 700 projects, two junior doctors and two senior doctors with ten years of film reading experience respectively took grading readings of joint stenosis, hypertrophy, osteophyte, articular surface erosion and subchondral cyst. The inconsistent results in the junior doctors group were jointly decided by the two doctors. The reference standard group was decided by the senior doctors group. By comparing the diagnosis results of clinicians and models, To evaluate the performance and clinical feasibility of the deep learning model for automatic diagnosis of lumbar facet degeneration.Compare the results of doctor's judgment and model prediction, and statistically analyze the performance of automatic diagnosis of the model. Performance evaluation indicators include accuracy, sensitivity, specificity, accuracy, recall, F1 value and AUC value. F1 value and AUC value are the main indicators for comprehensive evaluation of model performance. The higher F1 value and AUC value, the stronger the model performance.

    Study Design

    Study Type:
    Observational
    Anticipated Enrollment :
    700 participants
    Observational Model:
    Other
    Time Perspective:
    Retrospective
    Official Title:
    Application of Multitask Deep Learning Model in Grading the Severity of Spinal Facet Joint Degeneration
    Anticipated Study Start Date :
    Dec 31, 2022
    Anticipated Primary Completion Date :
    Jan 31, 2023
    Anticipated Study Completion Date :
    Jan 31, 2023

    Arms and Interventions

    Arm Intervention/Treatment
    Training group

    70% of the participants were randomly divided into training groups to train the learning performance of the machine

    Validation group

    15% of the participants were randomly divided into validation groups to enhance the learning performance of the machine and avoid over fitting

    Test group

    15% of the participants were randomly divided into test groups to test the learning performance of the machine and draw research conclusions

    Outcome Measures

    Primary Outcome Measures

    1. To compare the accuracy of multitask deep learning model and clinicians in judging spinal facet joint degeneration [2022.12.01-2023.07.31]

      It is mainly used to indicate the number of correctly predicted samples in the total number of samples.True Positive(TP),False Negative(FN), False Positive(FP),True Negative(TN).Accuracy = (TP + TN) / (TP + FN + FP +TN)

    2. To compare the precision of multitask deep learning model and clinicians in judging spinal facet joint degeneration [2022.12.01-2023.07.31]

      True Positive(TP),False Negative(FN), False Positive(FP),True Negative(TN).Precision = TP / (TP+FP)

    3. To compare the sensitivity of multitask deep learning model and clinicians in assessing spinal facet joint degeneration [2022.12.01-2023.07.31]

      True Positive(TP),False Negative(FN), False Positive(FP),True Negative(TN).Sensitivity=TP / (TP+FN)

    4. To compare the specificity of multitask deep learning model and clinicians in assessing spinal facet joint degeneration [2022.12.01-2023.07.31]

      True Positive(TP),False Negative(FN), False Positive(FP),True Negative(TN).Specificity=TN / (TN+FP)

    5. Calculate the F1 score for evaluating the severity of facet joints degeneration in the multitask deep learning model [2022.12.01-2023.07.31]

      F1 score is an important evaluation indicator for automatic classification,F1 =2*Precision*Sensitivity/(Precision+Sensitivity)=2TP/(2TP+FP+FN)

    6. ROC (Receiver Operation Characteristic) is called receiver operation characteristic curve, which is an index to evaluate the performance of deep learning model [2022.12.01-2023.07.31]

      ROC (Receiver Operation Characteristic) is called receiver operation characteristic curve. The closer the curve is to the upper left corner, the better the classifier is. The area under the ROC curve is called AUC. The larger the AUC is, the better the classification effect of the classifier will be.

    Eligibility Criteria

    Criteria

    Ages Eligible for Study:
    N/A and Older
    Sexes Eligible for Study:
    All
    Accepts Healthy Volunteers:
    No
    Inclusion Criteria:
    • From 2019 to 2022, data of patients receiving lumbar imaging examination in the Fifth Affiliated Hospital of Sun Yat sen University
    Exclusion Criteria:
    • Lumbar spondylolisthesis

    • Previous vertebral fracture

    • Have a history of vertebral surgery

    • Severe artifacts at lumbar images

    Contacts and Locations

    Locations

    No locations specified.

    Sponsors and Collaborators

    • Hai Lv

    Investigators

    None specified.

    Study Documents (Full-Text)

    None provided.

    More Information

    Publications

    None provided.
    Responsible Party:
    Hai Lv, Chief physician, Fifth Affiliated Hospital, Sun Yat-Sen University
    ClinicalTrials.gov Identifier:
    NCT05635006
    Other Study ID Numbers:
    • ZDWY.JZWK.004
    First Posted:
    Dec 2, 2022
    Last Update Posted:
    Dec 20, 2022
    Last Verified:
    Dec 1, 2022
    Individual Participant Data (IPD) Sharing Statement:
    No
    Plan to Share IPD:
    No
    Studies a U.S. FDA-regulated Drug Product:
    No
    Studies a U.S. FDA-regulated Device Product:
    No

    Study Results

    No Results Posted as of Dec 20, 2022