SLAP Injury of the Shoulder Joint: Application Value of Deep Learning in Diagnosis
29. juni 2021 opdateret af: Peking University Third Hospital
This study intends to study the shoulder SLAP injury through deep learning technology and establish a deep learning model through the combination of axial and oblique coronal images to establish a deep learning method that can accurately identify and grade shoulder SLAP injury.
Studieoversigt
Status
Ikke rekrutterer endnu
Intervention / Behandling
Detaljeret beskrivelse
- Recognition of labrum images based on LeNet: axial and oblique coronal T2-fs images were used, and all images were corrected and standardized. LeNet identified the images with labrum of the shoulder joint, and the images with labrum structure of shoulder joint were selected from the complete sequence. In contrast, the images without labrum structure were deleted. All the data are divided into a training set (70%, 30% in training set as verification set), and the remaining 30% as a test set to evaluate the accuracy of model recognition. Enter the obtained results into the next step.
- Recognition and segmentation of glenoid lip of shoulder joint based on DenseNet: the labrum is recognized by DenseNet in the selected image. The labelimg software based on Python was used to locate the labrum coordinates and then input them into Python for recognition learning. All the data were divided into a training set (70% and 30% of the training set were selected as the verification set). The remaining 30% was used as the test set to evaluate the accuracy of model recognition. After identifying the labrum structure, the labrum structure is locally cut and enlarged to remove the redundant information and improve the recognition efficiency and accuracy. Finally, input the result to the next step.
- Recognition and grading of shoulder SLAP injury based on 3D-CNN: recognition and grading of input data through 3D-CNN model. 3D-CNN is divided into eight layers: input layer, hard wire layer H1, convolution layer C2, downsampling layer S3, convolution layer C4, downsampling layer S5, convolution layer C6 and output layer. 3D-CNN constructs a cube by stacking multiple consecutive frames and then uses a 3D convolution kernel in the cube. Through this structure, the feature images in the convolution layer will be connected with multiple adjacent frames in the previous layer to realize the information acquisition of continuous images. Similarly, the data is divided into a training set (70%, and then 30% of the training set is selected as the verification set), and the remaining 30% is used as the test set to evaluate the classification accuracy to identify whether there is labrum injury and grade the image with injury.
- Establish CNN combined model: after establishing the model for the axial and oblique coronal view according to the above process (1-3), according to the output characteristics of the CNN classification model, predict the probability of different grades before the output results, and the output results are based on these probabilities to select the expression form of the maximum possible probability. Our combined model averages the probabilities of these different classifications, calculates the final prediction probability, and then obtains the final joint model. The test set of the third step (including the mixed data of axial and coronal images) was used to verify the joint model.
Undersøgelsestype
Observationel
Tilmelding (Forventet)
800
Kontakter og lokationer
Dette afsnit indeholder kontaktoplysninger for dem, der udfører undersøgelsen, og oplysninger om, hvor denne undersøgelse udføres.
Studiekontakt
- Navn: huishu Yuan, MD
- Telefonnummer: 15810245738
- E-mail: huishuy@bjmu.edu.cn
Undersøgelse Kontakt Backup
- Navn: Ming Ni, MD
- Telefonnummer: +8613884794867
- E-mail: sdyingxiang2017@163.com
Studiesteder
-
-
Beijing
-
Beijing, Beijing, Kina, 010
- Peking University Third Hospital
-
-
Deltagelseskriterier
Forskere leder efter personer, der passer til en bestemt beskrivelse, kaldet berettigelseskriterier. Nogle eksempler på disse kriterier er en persons generelle helbredstilstand eller tidligere behandlinger.
Berettigelseskriterier
Aldre berettiget til at studere
- Barn
- Voksen
- Ældre voksen
Tager imod sunde frivillige
N/A
Køn, der er berettiget til at studere
Alle
Prøveudtagningsmetode
Ikke-sandsynlighedsprøve
Studiebefolkning
Collect and analyze patients who underwent shoulder MR examinations in the Department of Radiology, Peking University Third Hospital from September 2018 to September 2020.
Beskrivelse
Inclusion Criteria:
- Without any treatment before imaging examination;
- MR of the shoulder joint was performed within 3 months before the operation and the image quality was good;
- Arthroscopic operation was performed in our hospital, and the operation records were complete.
Exclusion Criteria:
- History of shoulder surgery, tumor, or previous fracture;
- Unclear image, serious artifact, or incomplete clinical data.
Studieplan
Dette afsnit indeholder detaljer om studieplanen, herunder hvordan undersøgelsen er designet, og hvad undersøgelsen måler.
Hvordan er undersøgelsen tilrettelagt?
Design detaljer
- Observationsmodeller: Case-Control
- Tidsperspektiver: Tilbagevirkende kraft
Kohorter og interventioner
Gruppe / kohorte |
Intervention / Behandling |
|---|---|
|
Normal control group-Grade 0
Arthroscopic examination of the labrum was normal, and the labrum was intact without injury or tear.
|
The results of shoulder arthroscopy were taken as the gold standard, and MRI examination was taken as the research object.
|
|
Ligament injury -Grade 1
Arthroscopic examination of the shoulder showed labrum degeneration or injury, but no local or complete tear.
|
The results of shoulder arthroscopy were taken as the gold standard, and MRI examination was taken as the research object.
|
|
Ligament tear-Grade 2
Arthroscopy of the shoulder revealed partial or complete loss of labrum.
|
The results of shoulder arthroscopy were taken as the gold standard, and MRI examination was taken as the research object.
|
Hvad måler undersøgelsen?
Primære resultatmål
Resultatmål |
Foranstaltningsbeskrivelse |
Tidsramme |
|---|---|---|
|
SLAP Injury of the Shoulder Joint: Application Value of Deep Learning in Diagnosis
Tidsramme: 2021.10.1-2022.7.1
|
The model of deep learning was obtained for diagnosis and grading of SLAP injury and compared with the radiologists of different stages.
|
2021.10.1-2022.7.1
|
Samarbejdspartnere og efterforskere
Det er her, du vil finde personer og organisationer, der er involveret i denne undersøgelse.
Sponsor
Datoer for undersøgelser
Disse datoer sporer fremskridtene for indsendelser af undersøgelsesrekord og resumeresultater til ClinicalTrials.gov. Studieregistreringer og rapporterede resultater gennemgås af National Library of Medicine (NLM) for at sikre, at de opfylder specifikke kvalitetskontrolstandarder, før de offentliggøres på den offentlige hjemmeside.
Studer store datoer
Studiestart (Forventet)
1. oktober 2021
Primær færdiggørelse (Forventet)
1. juni 2022
Studieafslutning (Forventet)
1. juli 2022
Datoer for studieregistrering
Først indsendt
29. juni 2021
Først indsendt, der opfyldte QC-kriterier
29. juni 2021
Først opslået (Faktiske)
7. juli 2021
Opdateringer af undersøgelsesjournaler
Sidste opdatering sendt (Faktiske)
7. juli 2021
Sidste opdatering indsendt, der opfyldte kvalitetskontrolkriterier
29. juni 2021
Sidst verificeret
1. juni 2021
Mere information
Begreber relateret til denne undersøgelse
Nøgleord
Yderligere relevante MeSH-vilkår
Andre undersøgelses-id-numre
- M2020458
Plan for individuelle deltagerdata (IPD)
Planlægger du at dele individuelle deltagerdata (IPD)?
Ingen
Lægemiddel- og udstyrsoplysninger, undersøgelsesdokumenter
Studerer et amerikansk FDA-reguleret lægemiddelprodukt
Ingen
Studerer et amerikansk FDA-reguleret enhedsprodukt
Ingen
Disse oplysninger blev hentet direkte fra webstedet clinicaltrials.gov uden ændringer. Hvis du har nogen anmodninger om at ændre, fjerne eller opdatere dine undersøgelsesoplysninger, bedes du kontakte register@clinicaltrials.gov. Så snart en ændring er implementeret på clinicaltrials.gov, vil denne også blive opdateret automatisk på vores hjemmeside .