Stefan Lang, Moritz Jokeit, Ji Hyun Kim, Lukas Urbanschitz, Luca Fisler, Carlos Torrez, Frédéric Cornaz, Jess G Snedeker, Mazda Farshad, Jonas Widmer
{"title":"在双平面X光片上检测解剖地标,以预测脊柱骨盆参数。","authors":"Stefan Lang, Moritz Jokeit, Ji Hyun Kim, Lukas Urbanschitz, Luca Fisler, Carlos Torrez, Frédéric Cornaz, Jess G Snedeker, Mazda Farshad, Jonas Widmer","doi":"10.1007/s43390-024-00990-0","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Accurate landmark detection is essential for precise analysis of anatomical structures, supporting diagnosis, treatment planning, and monitoring in patients with spinal deformities. Conventional methods rely on laborious landmark identification by medical experts, which motivates automation. The proposed deep learning pipeline processes bi-planar radiographs to determine spinopelvic parameters and Cobb angles without manual supervision.</p><p><strong>Methods: </strong>The dataset used for training and evaluation consisted of 555 bi-planar radiographs from un-instrumented patients, which were manually annotated by medical professionals. The pipeline performed a pre-processing step to determine regions of interest, including the cervical spine, thoracolumbar spine, sacrum, and pelvis. For each ROI, a segmentation network was trained to identify vertebral bodies and pelvic landmarks. The U-Net architecture was trained on 455 bi-planar radiographs using binary cross-entropy loss. The post-processing algorithm determined spinal alignment and angular parameters based on the segmentation output. We evaluated the pipeline on a test set of 100 previously unseen bi-planar radiographs, using the mean absolute difference between annotated and predicted landmarks as the performance metric. The spinopelvic parameter predictions of the pipeline were compared to the measurements of two experienced medical professionals using intraclass correlation coefficient (ICC) and mean absolute deviation (MAD).</p><p><strong>Results: </strong>The pipeline was able to successfully predict the Cobb angles in 61% of all test cases and achieved mean absolute differences of 3.3° (3.6°) and averaged ICC of 0.88. For thoracic kyphosis, lumbar lordosis, sagittal vertical axis, sacral slope, pelvic tilt, and pelvic incidence, the pipeline produced reasonable outputs in 69%, 58%, 86%, 85%, 84%, and 84% of the cases. The MAD was 5.6° (7.8°), 4.7° (4.3°), 2.8 mm (3.0 mm), 4.5° (7.2°), 1.8° (1.8°), and 5.3° (7.7°), while the ICC was measured at 0.69, 0.82, 0.99, 0.61, 0.96, and 0.70, respectively.</p><p><strong>Conclusion: </strong>Despite limitations in patients with severe pathologies and high BMI, the pipeline automatically predicted coronal and sagittal spinopelvic parameters, which has the potential to simplify clinical routines and large-scale retrospective data analysis.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":" ","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Anatomical landmark detection on bi-planar radiographs for predicting spinopelvic parameters.\",\"authors\":\"Stefan Lang, Moritz Jokeit, Ji Hyun Kim, Lukas Urbanschitz, Luca Fisler, Carlos Torrez, Frédéric Cornaz, Jess G Snedeker, Mazda Farshad, Jonas Widmer\",\"doi\":\"10.1007/s43390-024-00990-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Accurate landmark detection is essential for precise analysis of anatomical structures, supporting diagnosis, treatment planning, and monitoring in patients with spinal deformities. Conventional methods rely on laborious landmark identification by medical experts, which motivates automation. The proposed deep learning pipeline processes bi-planar radiographs to determine spinopelvic parameters and Cobb angles without manual supervision.</p><p><strong>Methods: </strong>The dataset used for training and evaluation consisted of 555 bi-planar radiographs from un-instrumented patients, which were manually annotated by medical professionals. The pipeline performed a pre-processing step to determine regions of interest, including the cervical spine, thoracolumbar spine, sacrum, and pelvis. For each ROI, a segmentation network was trained to identify vertebral bodies and pelvic landmarks. The U-Net architecture was trained on 455 bi-planar radiographs using binary cross-entropy loss. The post-processing algorithm determined spinal alignment and angular parameters based on the segmentation output. We evaluated the pipeline on a test set of 100 previously unseen bi-planar radiographs, using the mean absolute difference between annotated and predicted landmarks as the performance metric. The spinopelvic parameter predictions of the pipeline were compared to the measurements of two experienced medical professionals using intraclass correlation coefficient (ICC) and mean absolute deviation (MAD).</p><p><strong>Results: </strong>The pipeline was able to successfully predict the Cobb angles in 61% of all test cases and achieved mean absolute differences of 3.3° (3.6°) and averaged ICC of 0.88. For thoracic kyphosis, lumbar lordosis, sagittal vertical axis, sacral slope, pelvic tilt, and pelvic incidence, the pipeline produced reasonable outputs in 69%, 58%, 86%, 85%, 84%, and 84% of the cases. The MAD was 5.6° (7.8°), 4.7° (4.3°), 2.8 mm (3.0 mm), 4.5° (7.2°), 1.8° (1.8°), and 5.3° (7.7°), while the ICC was measured at 0.69, 0.82, 0.99, 0.61, 0.96, and 0.70, respectively.</p><p><strong>Conclusion: </strong>Despite limitations in patients with severe pathologies and high BMI, the pipeline automatically predicted coronal and sagittal spinopelvic parameters, which has the potential to simplify clinical routines and large-scale retrospective data analysis.</p>\",\"PeriodicalId\":21796,\"journal\":{\"name\":\"Spine deformity\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Spine deformity\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s43390-024-00990-0\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Spine deformity","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s43390-024-00990-0","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
Anatomical landmark detection on bi-planar radiographs for predicting spinopelvic parameters.
Introduction: Accurate landmark detection is essential for precise analysis of anatomical structures, supporting diagnosis, treatment planning, and monitoring in patients with spinal deformities. Conventional methods rely on laborious landmark identification by medical experts, which motivates automation. The proposed deep learning pipeline processes bi-planar radiographs to determine spinopelvic parameters and Cobb angles without manual supervision.
Methods: The dataset used for training and evaluation consisted of 555 bi-planar radiographs from un-instrumented patients, which were manually annotated by medical professionals. The pipeline performed a pre-processing step to determine regions of interest, including the cervical spine, thoracolumbar spine, sacrum, and pelvis. For each ROI, a segmentation network was trained to identify vertebral bodies and pelvic landmarks. The U-Net architecture was trained on 455 bi-planar radiographs using binary cross-entropy loss. The post-processing algorithm determined spinal alignment and angular parameters based on the segmentation output. We evaluated the pipeline on a test set of 100 previously unseen bi-planar radiographs, using the mean absolute difference between annotated and predicted landmarks as the performance metric. The spinopelvic parameter predictions of the pipeline were compared to the measurements of two experienced medical professionals using intraclass correlation coefficient (ICC) and mean absolute deviation (MAD).
Results: The pipeline was able to successfully predict the Cobb angles in 61% of all test cases and achieved mean absolute differences of 3.3° (3.6°) and averaged ICC of 0.88. For thoracic kyphosis, lumbar lordosis, sagittal vertical axis, sacral slope, pelvic tilt, and pelvic incidence, the pipeline produced reasonable outputs in 69%, 58%, 86%, 85%, 84%, and 84% of the cases. The MAD was 5.6° (7.8°), 4.7° (4.3°), 2.8 mm (3.0 mm), 4.5° (7.2°), 1.8° (1.8°), and 5.3° (7.7°), while the ICC was measured at 0.69, 0.82, 0.99, 0.61, 0.96, and 0.70, respectively.
Conclusion: Despite limitations in patients with severe pathologies and high BMI, the pipeline automatically predicted coronal and sagittal spinopelvic parameters, which has the potential to simplify clinical routines and large-scale retrospective data analysis.
期刊介绍:
Spine Deformity the official journal of the?Scoliosis Research Society is a peer-refereed publication to disseminate knowledge on basic science and clinical research into the?etiology?biomechanics?treatment?methods and outcomes of all types of?spinal deformities. The international members of the Editorial Board provide a worldwide perspective for the journal's area of interest.The?journal?will enhance the mission of the Society which is to foster the optimal care of all patients with?spine?deformities worldwide. Articles published in?Spine Deformity?are Medline indexed in PubMed.? The journal publishes original articles in the form of clinical and basic research. Spine Deformity will only publish studies that have institutional review board (IRB) or similar ethics committee approval for human and animal studies and have strictly observed these guidelines. The minimum follow-up period for follow-up clinical studies is 24 months.