An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes
Abstract We intended to compare the doctors with a convolutional neural network (CNN) that we had trained using our own unique method for the Lateral Pillar Classification (LPC) of Legg–Calve–Perthes Disease (LCPD). Thousands of training data sets are frequently required for artificial intelligence...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-34176-x |
| _version_ | 1797836518047350784 |
|---|---|
| author | Zafer Soydan Yavuz Saglam Sefa Key Yusuf Alper Kati Murat Taskiran Seyfullah Kiymet Tuba Salturk Ahmet Serhat Aydin Fuat Bilgili Cengiz Sen |
| author_facet | Zafer Soydan Yavuz Saglam Sefa Key Yusuf Alper Kati Murat Taskiran Seyfullah Kiymet Tuba Salturk Ahmet Serhat Aydin Fuat Bilgili Cengiz Sen |
| author_sort | Zafer Soydan |
| collection | DOAJ |
| description | Abstract We intended to compare the doctors with a convolutional neural network (CNN) that we had trained using our own unique method for the Lateral Pillar Classification (LPC) of Legg–Calve–Perthes Disease (LCPD). Thousands of training data sets are frequently required for artificial intelligence (AI) applications in medicine. Since we did not have enough real patient radiographs to train a CNN, we devised a novel method to obtain them. We trained the CNN model with the data we created by modifying the normal hip radiographs. No real patient radiographs were ever used during the training phase. We tested the CNN model on 81 hips with LCPD. Firstly, we detected the interobserver reliability of the whole system and then the reliability of CNN alone. Second, the consensus list was used to compare the results of 11 doctors and the CNN model. Percentage agreement and interobserver analysis revealed that CNN had good reliability (ICC = 0.868). CNN has achieved a 76.54% classification performance and outperformed 9 out of 11 doctors. The CNN, which we trained with the aforementioned method, can now provide better results than doctors. In the future, as training data evolves and improves, we anticipate that AI will perform significantly better than physicians. |
| first_indexed | 2024-04-09T15:11:16Z |
| format | Article |
| id | doaj.art-ef20b4822ea64b26964e897e6b89cafc |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T15:11:16Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ef20b4822ea64b26964e897e6b89cafc2023-04-30T11:14:03ZengNature PortfolioScientific Reports2045-23222023-04-0113111110.1038/s41598-023-34176-xAn AI based classifier model for lateral pillar classification of Legg–Calve–PerthesZafer Soydan0Yavuz Saglam1Sefa Key2Yusuf Alper Kati3Murat Taskiran4Seyfullah Kiymet5Tuba Salturk6Ahmet Serhat Aydin7Fuat Bilgili8Cengiz Sen9Orthopedics and Traumatology, Bhtclinic İstanbul Tema Hastanesi, Nisantası UniversityOrthopedics and Traumatology, Istanbul University Istanbul Faculty of MedicineOrthopedics and Traumatology, Bingol State HospitalOrthopedics and Traumatology, Antalya Egitim ve Arastirma HastanesiDepartment of Electronics and Communication Engineering, Yildiz Technical UniversityDepartment of Electronics and Communication Engineering, Yildiz Technical UniversityDepartment of Informatics, Yildiz Technical UniversityOrthopedics and Traumatology, Istanbul University Istanbul Faculty of MedicineOrthopedics and Traumatology, Istanbul University Istanbul Faculty of MedicineOrthopedics and Traumatology, Istanbul University Istanbul Faculty of MedicineAbstract We intended to compare the doctors with a convolutional neural network (CNN) that we had trained using our own unique method for the Lateral Pillar Classification (LPC) of Legg–Calve–Perthes Disease (LCPD). Thousands of training data sets are frequently required for artificial intelligence (AI) applications in medicine. Since we did not have enough real patient radiographs to train a CNN, we devised a novel method to obtain them. We trained the CNN model with the data we created by modifying the normal hip radiographs. No real patient radiographs were ever used during the training phase. We tested the CNN model on 81 hips with LCPD. Firstly, we detected the interobserver reliability of the whole system and then the reliability of CNN alone. Second, the consensus list was used to compare the results of 11 doctors and the CNN model. Percentage agreement and interobserver analysis revealed that CNN had good reliability (ICC = 0.868). CNN has achieved a 76.54% classification performance and outperformed 9 out of 11 doctors. The CNN, which we trained with the aforementioned method, can now provide better results than doctors. In the future, as training data evolves and improves, we anticipate that AI will perform significantly better than physicians.https://doi.org/10.1038/s41598-023-34176-x |
| spellingShingle | Zafer Soydan Yavuz Saglam Sefa Key Yusuf Alper Kati Murat Taskiran Seyfullah Kiymet Tuba Salturk Ahmet Serhat Aydin Fuat Bilgili Cengiz Sen An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes Scientific Reports |
| title | An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes |
| title_full | An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes |
| title_fullStr | An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes |
| title_full_unstemmed | An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes |
| title_short | An AI based classifier model for lateral pillar classification of Legg–Calve–Perthes |
| title_sort | ai based classifier model for lateral pillar classification of legg calve perthes |
| url | https://doi.org/10.1038/s41598-023-34176-x |
| work_keys_str_mv | AT zafersoydan anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT yavuzsaglam anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT sefakey anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT yusufalperkati anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT murattaskiran anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT seyfullahkiymet anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT tubasalturk anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT ahmetserhataydin anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT fuatbilgili anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT cengizsen anaibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT zafersoydan aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT yavuzsaglam aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT sefakey aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT yusufalperkati aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT murattaskiran aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT seyfullahkiymet aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT tubasalturk aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT ahmetserhataydin aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT fuatbilgili aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes AT cengizsen aibasedclassifiermodelforlateralpillarclassificationofleggcalveperthes |