Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography

Achieving precise pedicle screw placement in posterior lumbar interbody fusion (PLIF) is essential but difficult due to the intricacies of manual preoperative planning with CT scans. We analyzed CT data from 316 PLIF patients, using Mimics software for manual planning by two surgeons. A deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Baodong Wang, Congying Zou, Xingyu Liu, Dong Liu, Yiling Zhang, Lei Zang
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/11/1094
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850216804969873408
author Baodong Wang
Congying Zou
Xingyu Liu
Dong Liu
Yiling Zhang
Lei Zang
author_facet Baodong Wang
Congying Zou
Xingyu Liu
Dong Liu
Yiling Zhang
Lei Zang
author_sort Baodong Wang
collection DOAJ
description Achieving precise pedicle screw placement in posterior lumbar interbody fusion (PLIF) is essential but difficult due to the intricacies of manual preoperative planning with CT scans. We analyzed CT data from 316 PLIF patients, using Mimics software for manual planning by two surgeons. A deep learning model was trained on 228 patients and validated on 88 patients, assessing planning efficiency and accuracy. Automatic planning successfully segmented and placed screws in all 316 cases, significantly outperforming manual planning in speed. The Dice coefficient for segmentation accuracy was 0.95. The difference in mean pedicle transverse angle (PTA) and pedicle sagittal angle (PSA) for automatic planning screws compared to manual planning screws was 1.63 ± 0.83° and 1.39 ± 1.03°, respectively, and these differences were either statistically comparable or not significantly different compared to the variability of manual planning screws. The average Dice coefficient of implanted screws was 0.63 ± 0.08, and the consistency between automatic screws and manual reference screws was higher than that of internal screws (Dice 0.62 ± 0.09). Compared with manual screws, automatic screws were shorter (46.58 ± 3.09 mm) and thinner (6.24 ± 0.35 mm), and the difference was statistically significant. In qualitative validation, 97.7% of the automatic planning screws were rated Gertzbein–Robbins (GR) Class A and 97.3% of the automatic planning screws were rated Badu Class 0. Deep learning software automates lumbosacral pedicle screw planning, enhancing surgical efficiency and accuracy.
format Article
id doaj-art-9f7a394c77f94c0385da8e82f1bef8bd
institution OA Journals
issn 2306-5354
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-9f7a394c77f94c0385da8e82f1bef8bd2025-08-20T02:08:12ZengMDPI AGBioengineering2306-53542024-10-011111109410.3390/bioengineering11111094Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed TomographyBaodong Wang0Congying Zou1Xingyu Liu2Dong Liu3Yiling Zhang4Lei Zang5Department of Orthopedics, Beijing Chao-Yang Hospital, Capital Medical University, Beijing 100043, ChinaDepartment of Orthopedics, Beijing Chao-Yang Hospital, Capital Medical University, Beijing 100043, ChinaSchool of Life Sciences, Tsinghua University, Beijing 100084, ChinaLongwood Valley Medical Technology Co., Ltd., Beijing 101111, ChinaSchool of Biomedical Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Orthopedics, Beijing Chao-Yang Hospital, Capital Medical University, Beijing 100043, ChinaAchieving precise pedicle screw placement in posterior lumbar interbody fusion (PLIF) is essential but difficult due to the intricacies of manual preoperative planning with CT scans. We analyzed CT data from 316 PLIF patients, using Mimics software for manual planning by two surgeons. A deep learning model was trained on 228 patients and validated on 88 patients, assessing planning efficiency and accuracy. Automatic planning successfully segmented and placed screws in all 316 cases, significantly outperforming manual planning in speed. The Dice coefficient for segmentation accuracy was 0.95. The difference in mean pedicle transverse angle (PTA) and pedicle sagittal angle (PSA) for automatic planning screws compared to manual planning screws was 1.63 ± 0.83° and 1.39 ± 1.03°, respectively, and these differences were either statistically comparable or not significantly different compared to the variability of manual planning screws. The average Dice coefficient of implanted screws was 0.63 ± 0.08, and the consistency between automatic screws and manual reference screws was higher than that of internal screws (Dice 0.62 ± 0.09). Compared with manual screws, automatic screws were shorter (46.58 ± 3.09 mm) and thinner (6.24 ± 0.35 mm), and the difference was statistically significant. In qualitative validation, 97.7% of the automatic planning screws were rated Gertzbein–Robbins (GR) Class A and 97.3% of the automatic planning screws were rated Badu Class 0. Deep learning software automates lumbosacral pedicle screw planning, enhancing surgical efficiency and accuracy.https://www.mdpi.com/2306-5354/11/11/1094posterior lumbar interbody fusiondeep learningcomputed tomographypedicle screwsGertzbein–Robbins classificationBadu grading
spellingShingle Baodong Wang
Congying Zou
Xingyu Liu
Dong Liu
Yiling Zhang
Lei Zang
Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
Bioengineering
posterior lumbar interbody fusion
deep learning
computed tomography
pedicle screws
Gertzbein–Robbins classification
Badu grading
title Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
title_full Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
title_fullStr Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
title_full_unstemmed Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
title_short Development and Validation of Deep Learning Preoperative Planning Software for Automatic Lumbosacral Screw Selection Using Computed Tomography
title_sort development and validation of deep learning preoperative planning software for automatic lumbosacral screw selection using computed tomography
topic posterior lumbar interbody fusion
deep learning
computed tomography
pedicle screws
Gertzbein–Robbins classification
Badu grading
url https://www.mdpi.com/2306-5354/11/11/1094
work_keys_str_mv AT baodongwang developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography
AT congyingzou developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography
AT xingyuliu developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography
AT dongliu developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography
AT yilingzhang developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography
AT leizang developmentandvalidationofdeeplearningpreoperativeplanningsoftwareforautomaticlumbosacralscrewselectionusingcomputedtomography