MPF-net: An effective framework for automated cobb angle estimation

Deep learning in Cobb angle automated measurement on X-rays: a systematic review and meta-analysis

PURPOSE

This study aims to provide an overview of different deep learning algorithms (DLAs), identify the limitations, and summarize potential solutions to improve the performance of DLAs.

METHODS

We reviewed eligible studies on DLAs for automated Cobb angle estimation on X-rays and conducted a meta-analysis. A systematic literature search was conducted in six databases up until September 2023. Our meta-analysis included an evaluation of reported circular mean absolute error (CMAE) from the studies, as well as a subgroup analysis of implementation strategies. Risk of bias was assessed using the revised Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). This study was registered in PROSPERO prior to initiation (CRD42023403057).

RESULTS

We identified 120 articles from our systematic search (n = 3022), eventually including 50 studies in the systematic review and 17 studies in the meta-analysis. The overall estimate for CMAE was 2.99 (95% CI 2.61-3.38), with high heterogeneity (94%, p < 0.01). Segmentation-based methods showed greater accuracy (p < 0.01), with a CMAE of 2.40 (95% CI 1.85-2.95), compared to landmark-based methods, which had a CMAE of 3.31 (95% CI 2.89-3.72).

CONCLUSIONS

According to our limited meta-analysis results, DLAs have shown relatively high accuracy for automated Cobb angle measurement. In terms of CMAE, segmentation-based methods may perform better than landmark-based methods. We also summarized potential ways to improve model design in future studies. It is important to follow quality guidelines when reporting on DLAs.

Validity of machine learning algorithms for automatically extract growing rod length on radiographs in children with early-onset scoliosis

The magnetically controlled growing rod technique is an effective surgical treatment for children who have early-onset scoliosis. The length of the instrumented growing rods is adjusted regularly to compensate for the normal growth of these patients. Manual measurement of rod length on posteroanterior spine radiographs is subjective and time-consuming. A machine learning (ML) system using a deep learning approach was developed to automatically measure the adjusted rod length. Three ML models-rod model, 58 mm model, and head-piece model-were developed to extract the rod length from radiographs. Three-hundred and eighty-seven radiographs were used for model development, and 60 radiographs with 118 rods were separated for final testing. The average precision (AP), the mean absolute difference (MAD) ± standard deviation (SD), and the inter-method correlation coefficient (ICC[2,1]) between the manual and artificial intelligence (AI) adjustment measurements were used to evaluate the developed method. The AP of the 3 models were 67.6%, 94.8%, and 86.3%, respectively. The MAD ± SD of the rod length change was 0.98 ± 0.88 mm, and the ICC[2,1] was 0.90. The average time to output a single rod measurement was 6.1 s. The developed AI provided an accurate and reliable method to detect the rod length automatically.

Comparison of three artificial intelligence algorithms for automatic cobb angle measurement using teaching data specific to three disease groups

Spinal deformities, including adolescent idiopathic scoliosis (AIS) and adult spinal deformity (ASD), affect many patients. The measurement of the Cobb angle on coronal radiographs is essential for their diagnosis and treatment planning. To enhance the precision of Cobb angle measurements for both AIS and ASD, we developed three distinct artificial intelligence (AI) algorithms: AIS/ASD-trained AI (trained with both AIS and ASD cases); AIS-trained AI (trained solely on AIS cases); ASD-trained AI (trained solely on ASD cases). We used 1612 whole-spine radiographs, including 1029 AIS and 583 ASD cases with variable postures, as teaching data. We measured the major and two minor curves. To assess the accuracy, we used 285 radiographs (159 AIS and 126 ASD) as a test set and calculated the mean absolute error (MAE) and intraclass correlation coefficient (ICC) between each AI algorithm and the average of manual measurements by four spine experts. The AIS/ASD-trained AI showed the highest accuracy among the three AI algorithms. This result suggested that learning across multiple diseases rather than disease-specific training may be an efficient AI learning method. The presented AI algorithm has the potential to reduce errors in Cobb angle measurements and improve the quality of clinical practice.

A Dual Coordinate System Vertebra Landmark Detection Network with Sparse-to-Dense Vertebral Line Interpolation

Precise surveillance and assessment of spinal disorders are important for improving health care and patient survival rates. The assessment of spinal disorders, such as scoliosis assessment, depends heavily on precise vertebra landmark localization. However, existing methods usually search for only a handful of keypoints in a high-resolution image. In this paper, we propose the S2D-VLI VLDet network, a unified end-to-end vertebra landmark detection network for the assessment of scoliosis. The proposed network considers the spatially relevant information both from inside and between vertebrae. The new vertebral line interpolation method converts the training labels from sparse to dense, which can improve the network learning process and method performance. In addition, through the combined use of the Cartesian and polar coordinate systems in our method, the symmetric mean absolute percentage error (SMAPE) in scoliosis assessment can be reduced substantially. Specifically, as shown in the experiments, the SMAPE value decreases from 9.82 to 8.28. The experimental results indicate that our proposed approach is beneficial for estimating the Cobb angle and identifying landmarks in X-ray scans with low contrast.

SpineHRformer: A Transformer-Based Deep Learning Model for Automatic Spine Deformity Assessment with Prospective Validation

The Cobb angle (CA) serves as the principal method for assessing spinal deformity, but manual measurements of the CA are time-consuming and susceptible to inter- and intra-observer variability. While learning-based methods, such as SpineHRNet+, have demonstrated potential in automating CA measurement, their accuracy can be influenced by the severity of spinal deformity, image quality, relative position of rib and vertebrae, etc. Our aim is to create a reliable learning-based approach that provides consistent and highly accurate measurements of the CA from posteroanterior (PA) X-rays, surpassing the state-of-the-art method. To accomplish this, we introduce SpineHRformer, which identifies anatomical landmarks, including the vertices of endplates from the 7th cervical vertebra (C7) to the 5th lumbar vertebra (L5) and the end vertebrae with different output heads, enabling the calculation of CAs. Within our SpineHRformer, a backbone HRNet first extracts multi-scale features from the input X-ray, while transformer blocks extract local and global features from the HRNet outputs. Subsequently, an output head to generate heatmaps of the endplate landmarks or end vertebra landmarks facilitates the computation of CAs. We used a dataset of 1934 PA X-rays with diverse degrees of spinal deformity and image quality, following an 8:2 ratio to train and test the model. The experimental results indicate that SpineHRformer outperforms SpineHRNet+ in landmark detection (Mean Euclidean Distance: 2.47 pixels vs. 2.74 pixels), CA prediction (Pearson correlation coefficient: 0.86 vs. 0.83), and severity grading (sensitivity: normal-mild; 0.93 vs. 0.74, moderate; 0.74 vs. 0.77, severe; 0.74 vs. 0.7). Our approach demonstrates greater robustness and accuracy compared to SpineHRNet+, offering substantial potential for improving the efficiency and reliability of CA measurements in clinical settings.

Integrating biplane information and context for spine landmark detection

Spine landmark detection is of great significance for spinal morphological parameter assessment and three-dimensional reconstruction of the human spine. This detection task generally involves locating spine landmarks in the anterior-posterior (AP) and lateral (LAT) X-rays of the spine. Recently, the two-stage methods for AP spine landmark detection achieve better performance. However, these methods perform poorly in LAT landmark detection because of poor detection accuracy of LAT vertebra due to occlusion. To solve this problem, this paper proposes a new two-stage spine landmark detection method. In the first stage, this paper propose a biplane vertebra detection network for vertebra detection on AP and X-rays simultaneously. Then an epipolar module and a context enhancement module are proposed to assist LAT vertebra detection by using the biplane information and the context information of the vertebrae respectively. In the second stage, the landmarks can be obtained in the detected vertebrae area. Extensive experiment results conducted on a dataset containing 328 pairs of X-rays demonstrate that our method improves the vertebra and landmark detection accuracy.

FSA-Net: Rethinking the attention mechanisms in medical image segmentation from releasing global suppressed information

Attention mechanism-based medical image segmentation methods have developed rapidly recently. For the attention mechanisms, it is crucial to accurately capture the distribution weights of the effective features contained in the data. To accomplish this task, most attention mechanisms prefer using the global squeezing approach. However, it will lead to a problem of over-focusing on the global most salient effective features of the region of interest, while suppressing the secondary salient ones. Making partial fine-grained features are abandoned directly. To address this issue, we propose to use a multiple-local perception method to aggregate global effective features, and design a fine-grained medical image segmentation network, named FSA-Net. This network consists of two key components: 1) the novel Separable Attention Mechanisms which replace global squeezing with local squeezing to release the suppressed secondary salient effective features. 2) a Multi-Attention Aggregator (MAA) which can fuse multi-level attention to efficiently aggregate task-relevant semantic information. We conduct extensive experimental evaluations on five publicly available medical image segmentation datasets: MoNuSeg, COVID-19-CT100, GlaS, CVC-ClinicDB, ISIC2018, and DRIVE datasets. Experimental results show that FSA-Net outperforms state-of-the-art methods in medical image segmentation.

Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation

PURPOSE

To summarize and critically evaluate the existing studies for spinopelvic measurements of sagittal balance that are based on deep learning (DL).

METHODS

Three databases (PubMed, WoS and Scopus) were queried for records using keywords related to DL and measurement of sagittal balance. After screening the resulting 529 records that were augmented with specific web search, 34 studies published between 2017 and 2022 were included in the final review, and evaluated from the perspective of the observed sagittal spinopelvic parameters, properties of spine image datasets, applied DL methodology and resulting measurement performance.

RESULTS

Studies reported DL measurement of up to 18 different spinopelvic parameters, but the actual number depended on the image field of view. Image datasets were composed of lateral lumbar spine and whole spine X-rays, biplanar whole spine X-rays and lumbar spine magnetic resonance cross sections, and were increasing in size or enriched by augmentation techniques. Spinopelvic parameter measurement was approached either by landmark detection or structure segmentation, and U-Net was the most frequently applied DL architecture. The latest DL methods achieved excellent performance in terms of mean absolute error against reference manual measurements (~ 2° or ~ 1 mm).

CONCLUSION

Although the application of relatively complex DL architectures resulted in an improved measurement accuracy of sagittal spinopelvic parameters, future methods should focus on multi-institution and multi-observer analyses as well as uncertainty estimation and error handling implementations for integration into the clinical workflow. Further advances will enhance the predictive analytics of DL methods for spinopelvic parameter measurement.

LEVEL OF EVIDENCE I

Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.