Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: Classification guides the surgical approach and predicts prognosis. However, existing classifications of spinal schwannomas often result in a high ‘unclassified’ rate. Here, we aim to develop a new comprehensive classification for spinal schwannomas based on their presumed origin. We compared the new classification with the existing classifications regarding the rate of ‘unclassified’. Finally, we assessed the surgical strategies, outcomes, and complications according to each type of the new classification. Methods: A new classification with 9 types was created by analyzing the anatomy of spinal nerves and the origin of significant tumor portions and cystic components in preoperative magnetic resonance images. A total of 482 patients with spinal schwannomas were analyzed to compare our new classification with the existing classifications. We defined ‘unclassified’ as the inability to classify a patient with spinal schwannoma using the classification criteria. Surgical approaches and outcomes were also aligned with our new classification. Results: Our classification uniquely reported no ‘unclassified’ cases, indicating full applicability. Also, the classification has demonstrated usefulness in predicting the surgical outcome with the approach planned. Gross total removal rates reached 88.0% overall, with type 1 and type 2 tumors at 95.3% and 96.0% respectively. The approach varied with tumor type, with laminectomy predominantly used for types 1, 2, and 9, and facetectomy with posterior fixation used for type 3 tumors. Conclusion The new classification for spinal schwannomas based on presumed origin is applicable to all spinal schwannomas. It could help plan a surgical approach and predict its outcome, compared with existing classifications.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: Classification guides the surgical approach and predicts prognosis. However, existing classifications of spinal schwannomas often result in a high ‘unclassified’ rate. Here, we aim to develop a new comprehensive classification for spinal schwannomas based on their presumed origin. We compared the new classification with the existing classifications regarding the rate of ‘unclassified’. Finally, we assessed the surgical strategies, outcomes, and complications according to each type of the new classification. Methods: A new classification with 9 types was created by analyzing the anatomy of spinal nerves and the origin of significant tumor portions and cystic components in preoperative magnetic resonance images. A total of 482 patients with spinal schwannomas were analyzed to compare our new classification with the existing classifications. We defined ‘unclassified’ as the inability to classify a patient with spinal schwannoma using the classification criteria. Surgical approaches and outcomes were also aligned with our new classification. Results: Our classification uniquely reported no ‘unclassified’ cases, indicating full applicability. Also, the classification has demonstrated usefulness in predicting the surgical outcome with the approach planned. Gross total removal rates reached 88.0% overall, with type 1 and type 2 tumors at 95.3% and 96.0% respectively. The approach varied with tumor type, with laminectomy predominantly used for types 1, 2, and 9, and facetectomy with posterior fixation used for type 3 tumors. Conclusion The new classification for spinal schwannomas based on presumed origin is applicable to all spinal schwannomas. It could help plan a surgical approach and predict its outcome, compared with existing classifications.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: Classification guides the surgical approach and predicts prognosis. However, existing classifications of spinal schwannomas often result in a high ‘unclassified’ rate. Here, we aim to develop a new comprehensive classification for spinal schwannomas based on their presumed origin. We compared the new classification with the existing classifications regarding the rate of ‘unclassified’. Finally, we assessed the surgical strategies, outcomes, and complications according to each type of the new classification. Methods: A new classification with 9 types was created by analyzing the anatomy of spinal nerves and the origin of significant tumor portions and cystic components in preoperative magnetic resonance images. A total of 482 patients with spinal schwannomas were analyzed to compare our new classification with the existing classifications. We defined ‘unclassified’ as the inability to classify a patient with spinal schwannoma using the classification criteria. Surgical approaches and outcomes were also aligned with our new classification. Results: Our classification uniquely reported no ‘unclassified’ cases, indicating full applicability. Also, the classification has demonstrated usefulness in predicting the surgical outcome with the approach planned. Gross total removal rates reached 88.0% overall, with type 1 and type 2 tumors at 95.3% and 96.0% respectively. The approach varied with tumor type, with laminectomy predominantly used for types 1, 2, and 9, and facetectomy with posterior fixation used for type 3 tumors. Conclusion The new classification for spinal schwannomas based on presumed origin is applicable to all spinal schwannomas. It could help plan a surgical approach and predict its outcome, compared with existing classifications.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: Classification guides the surgical approach and predicts prognosis. However, existing classifications of spinal schwannomas often result in a high ‘unclassified’ rate. Here, we aim to develop a new comprehensive classification for spinal schwannomas based on their presumed origin. We compared the new classification with the existing classifications regarding the rate of ‘unclassified’. Finally, we assessed the surgical strategies, outcomes, and complications according to each type of the new classification. Methods: A new classification with 9 types was created by analyzing the anatomy of spinal nerves and the origin of significant tumor portions and cystic components in preoperative magnetic resonance images. A total of 482 patients with spinal schwannomas were analyzed to compare our new classification with the existing classifications. We defined ‘unclassified’ as the inability to classify a patient with spinal schwannoma using the classification criteria. Surgical approaches and outcomes were also aligned with our new classification. Results: Our classification uniquely reported no ‘unclassified’ cases, indicating full applicability. Also, the classification has demonstrated usefulness in predicting the surgical outcome with the approach planned. Gross total removal rates reached 88.0% overall, with type 1 and type 2 tumors at 95.3% and 96.0% respectively. The approach varied with tumor type, with laminectomy predominantly used for types 1, 2, and 9, and facetectomy with posterior fixation used for type 3 tumors. Conclusion The new classification for spinal schwannomas based on presumed origin is applicable to all spinal schwannomas. It could help plan a surgical approach and predict its outcome, compared with existing classifications.

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise. Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model. Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees. Conclusion The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

Objective: Classification guides the surgical approach and predicts prognosis. However, existing classifications of spinal schwannomas often result in a high ‘unclassified’ rate. Here, we aim to develop a new comprehensive classification for spinal schwannomas based on their presumed origin. We compared the new classification with the existing classifications regarding the rate of ‘unclassified’. Finally, we assessed the surgical strategies, outcomes, and complications according to each type of the new classification. Methods: A new classification with 9 types was created by analyzing the anatomy of spinal nerves and the origin of significant tumor portions and cystic components in preoperative magnetic resonance images. A total of 482 patients with spinal schwannomas were analyzed to compare our new classification with the existing classifications. We defined ‘unclassified’ as the inability to classify a patient with spinal schwannoma using the classification criteria. Surgical approaches and outcomes were also aligned with our new classification. Results: Our classification uniquely reported no ‘unclassified’ cases, indicating full applicability. Also, the classification has demonstrated usefulness in predicting the surgical outcome with the approach planned. Gross total removal rates reached 88.0% overall, with type 1 and type 2 tumors at 95.3% and 96.0% respectively. The approach varied with tumor type, with laminectomy predominantly used for types 1, 2, and 9, and facetectomy with posterior fixation used for type 3 tumors. Conclusion The new classification for spinal schwannomas based on presumed origin is applicable to all spinal schwannomas. It could help plan a surgical approach and predict its outcome, compared with existing classifications.