Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray

Improved Detection Accuracy of Chronic Vertebral Compression Fractures by Integrating Height Loss Ratio and Deep Learning Approaches

OBJECTIVES

This study aims to assess the limitations of the height loss ratio (HLR) method and introduce a new approach that integrates a deep learning (DL) model to enhance vertebral compression fracture (VCF) detection performance.

METHODS

We conducted a retrospective study on 589 patients with chronic VCFs. We compared four different methods: HLR-only, DL-only, a combination of HLR and DL for positive VCF, and a combination of HLR and DL for negative VCF. The models were evaluated using dice similarity coefficient, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC).

RESULTS

The combined method (HLR + DL, positive) demonstrated the best performance with an AUROC of 0.968, sensitivity (94.95%), and specificity (90.59%). The HLR-only and the HLR + DL (negative) also showed strong discriminatory power, with AUROCs of 0.948 and 0.947, respectively. The DL-only model achieved the highest specificity (95.92%) but exhibited lower sensitivity (82.83%).

CONCLUSIONS

Our study highlights the limitations of the HLR method in detecting chronic VCFs and demonstrates the improved performance of combining HLR with DL models.

Using an Ensemble of Segmentation Methods to Detect Vertebral Bodies on Radiographs

BACKGROUND AND PURPOSE

Vertebral compression fractures may indicate osteoporosis but are underdiagnosed and underreported by radiologists. We have developed an ensemble of vertebral body (VB) segmentation models for lateral radiographs as a critical component of an automated, opportunistic screening tool. Our goal is to detect the approximate location of thoracic and lumbar VBs, including fractured vertebra, on lateral radiographs.

MATERIALS AND METHODS

The Osteoporotic Fractures in Men Study (MrOS) data set includes spine radiographs of 5994 men aged ≥65 years from 6 clinical centers. Two segmentation models, U-Net and Mask-RCNN (Region-based Convolutional Neural Network), were independently trained on the MrOS data set retrospectively, and an ensemble was created by combining them. Primary performance metrics for VB detection success included precision, recall, and F1 score for object detection on a held-out test set. Intersection over union (IoU) and Dice coefficient were also calculated as secondary metrics of performance for the test set. A separate external data set from a quaternary health care enterprise was acquired to test generalizability, comprising diagnostic clinical radiographs from men and women aged ≥65 years.

RESULTS

The trained models achieved F1 score of U-Net = 83.42%, Mask-RCNN = 86.30%, and ensemble = 88.34% in detecting all VBs, and F1 score of U-Net = 87.88%, Mask-RCNN = 92.31%, and ensemble = 97.14% in detecting severely fractured vertebrae. The trained models achieved an average IoU per VB of 0.759 for U-Net and 0.709 for Mask-RCNN. The trained models achieved F1 score of U-Net = 81.11%, Mask-RCNN = 79.24%, and ensemble = 87.72% in detecting all VBs in the external data set.

CONCLUSIONS

An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development.

Deep learning application of vertebral compression fracture detection using mask R-CNN

Vertebral compression fractures (VCFs) of the thoracolumbar spine are commonly caused by osteoporosis or result from traumatic events. Early diagnosis of vertebral compression fractures can prevent further damage to patients. When assessing these fractures, plain radiographs are used as the primary diagnostic modality. In this study, we developed a deep learning based fracture detection model that could be used as a tool for primary care in the orthopedic department. We constructed a VCF dataset using 487 lateral radiographs, which included 598 fractures in the L1-T11 vertebra. For detecting VCFs, Mask R-CNN model was trained and optimized, and was compared to three other popular models on instance segmentation, Cascade Mask R-CNN, YOLOACT, and YOLOv5. With Mask R-CNN we achieved highest mean average precision score of 0.58, and were able to locate each fracture pixel-wise. In addition, the model showed high overall sensitivity, specificity, and accuracy, indicating that it detected fractures accurately and without misdiagnosis. Our model can be a potential tool for detecting VCFs from a simple radiograph and assisting doctors in making appropriate decisions in initial diagnosis.

Deep Learning-Assisted Quantitative Measurement of Thoracolumbar Fracture Features on Lateral Radiographs

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.

A spine segmentation method based on scene aware fusion network

BACKGROUND

Intervertebral disc herniation, degenerative lumbar spinal stenosis, and other lumbar spine diseases can occur across most age groups. MRI examination is the most commonly used detection method for lumbar spine lesions with its good soft tissue image resolution. However, the diagnosis accuracy is highly dependent on the experience of the diagnostician, leading to subjective errors caused by diagnosticians or differences in diagnostic criteria for multi-center studies in different hospitals, and inefficient diagnosis. These factors necessitate the standardized interpretation and automated classification of lumbar spine MRI to achieve objective consistency. In this research, a deep learning network based on SAFNet is proposed to solve the above challenges.

METHODS

In this research, low-level features, mid-level features, and high-level features of spine MRI are extracted. ASPP is used to process the high-level features. The multi-scale feature fusion method is used to increase the scene perception ability of the low-level features and mid-level features. The high-level features are further processed using global adaptive pooling and Sigmoid function to obtain new high-level features. The processed high-level features are then point-multiplied with the mid-level features and low-level features to obtain new high-level features. The new high-level features, low-level features, and mid-level features are all sampled to the same size and concatenated in the channel dimension to output the final result.

RESULTS

The DSC of SAFNet for segmenting 17 vertebral structures among 5 folds are 79.46 ± 4.63%, 78.82 ± 7.97%, 81.32 ± 3.45%, 80.56 ± 5.47%, and 80.83 ± 3.48%, with an average DSC of 80.32 ± 5.00%. The average DSC was 80.32 ± 5.00%. Compared to existing methods, our SAFNet provides better segmentation results and has important implications for the diagnosis of spinal and lumbar diseases.

CONCLUSIONS

This research proposes SAFNet, a highly accurate and robust spine segmentation deep learning network capable of providing effective anatomical segmentation for diagnostic purposes. The results demonstrate the effectiveness of the proposed method and its potential for improving radiological diagnosis accuracy.

Automatic Spine Segmentation and Parameter Measurement for Radiological Analysis of Whole-Spine Lateral Radiographs Using Deep Learning and Computer Vision

Radiographic examination is essential for diagnosing spinal disorders, and the measurement of spino-pelvic parameters provides important information for the diagnosis and treatment planning of spinal sagittal deformities. While manual measurement methods are the golden standard for measuring parameters, they can be time consuming, inefficient, and rater dependent. Previous studies that have used automatic measurement methods to alleviate the downsides of manual measurements showed low accuracy or could not be applied to general films. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning. A total of 1807 lateral radiographs were used for the training (n = 1607) and validation (n = 200) of the spine segmentation model. An additional 200 radiographs, which were also used for validation, were examined by three surgeons to evaluate the performance of the pipeline. Parameters automatically measured by the algorithm in the test set were statistically compared to parameters measured manually by the three surgeons. The Mask R-CNN model achieved an average precision at 50% intersection over union (AP50) of 96.2% and a Dice score of 92.6% for the spine segmentation task in the test set. The mean absolute error values of the spino-pelvic parameters measurement results were within the range of 0.4° (pelvic tilt) to 3.0° (lumbar lordosis, pelvic incidence), and the standard error of estimate was within the range of 0.5° (pelvic tilt) to 4.0° (pelvic incidence). The intraclass correlation coefficient values ranged from 0.86 (sacral slope) to 0.99 (pelvic tilt, sagittal vertical axis).

Detection of Lumbar Spondylolisthesis from X-ray Images Using Deep Learning Network

Spondylolisthesis refers to the displacement of a vertebral body relative to the vertrabra below it, which can cause radicular symptoms, back pain or leg pain. It usually occurs in the lower lumbar spine, especially in women over the age of 60. The prevalence of spondylolisthesis is expected to rise as the global population ages, requiring prudent action to promptly identify it in clinical settings. The goal of this study was to develop a computer-aided diagnostic (CADx) algorithm, LumbarNet, and to evaluate the efficiency of this model in automatically detecting spondylolisthesis from lumbar X-ray images. Built upon U-Net, feature fusion module (FFM) and collaborating with (i) a P-grade, (ii) a piecewise slope detection (PSD) scheme, and (iii) a dynamic shift (DS), LumbarNet was able to analyze complex structural patterns on lumbar X-ray images, including true lateral, flexion, and extension lateral views. Our results showed that the model achieved a mean intersection over union (mIOU) value of 0.88 in vertebral region segmentation and an accuracy of 88.83% in vertebral slip detection. We conclude that LumbarNet outperformed U-Net, a commonly used method in medical image segmentation, and could serve as a reliable method to identify spondylolisthesis.

Attention Gate based dual-pathway Network for Vertebra Segmentation of X-ray Spine images

Automatic spine and vertebra segmentation from X-ray spine images is a critical and challenging problem in many computer-aid spinal image analysis and disease diagnosis applications. In this paper, a two-stage automatic segmentation framework for spine X-ray images is proposed, which can firstly locate the spine regions (including backbone, sacrum and illum) in the coarse stage and then identify eighteen vertebrae (i.e., cervical vertebra 1, thoracic vertebra 1-12 and lumbar vertebra 1-5) with isolate and clear boundary in the fine stage. A novel Attention Gate based dual-pathway Network (AGNet) composed of context and edge pathways is designed to extract semantic and boundary information for segmentation of both spine and vertebra regions. Multi-scale supervision mechanism is applied to explore comprehensive features and an Edge aware Fusion Mechanism (EFM) is proposed to fuse features extracted from the two pathways. Some other image processing skills, such as centralized backbone clipping, patch cropping and convex hull detection are introduced to further refine the vertebra segmentation results. Experimental validations on spine X-ray images dataset and vertebrae dataset suggest that the proposed AGNet achieves superior performance compared with state-of-the-art segmentation methods, and the coarse-to-fine framework can be implemented in real spinal diagnosis systems.