Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net

Preoperative fracture reduction planning for image-guided pelvic trauma surgery: A comprehensive pipeline with learning

Pelvic fractures are among the most complex challenges in orthopedic trauma, which usually involve hipbone and sacrum fractures, as well as joint dislocations. Traditional preoperative surgical planning relies on the operator's subjective interpretation of CT images, which is both time-consuming and prone to inaccuracies. This study introduces an automated preoperative planning solution for pelvic fracture reduction, addressing the limitations of conventional methods. The proposed solution includes a novel multi-scale distance-weighted neural network for segmenting pelvic fracture fragments from CT scans, and a learning-based approach to restore pelvic structure, combining a morphable model-based method for single-bone fracture reduction and a recursive pose estimation module for joint dislocation reduction. Comprehensive experiments on a clinical dataset of 30 fracture cases demonstrated the efficacy of our methods. Our segmentation network outperformed traditional max-flow segmentation and networks without distance weighting, achieving a Dice similarity coefficient (DSC) of 0.986 ± 0.055 and a local DSC of 0.940 ± 0.056 around the fracture sites. The proposed reduction method surpassed mirroring and mean template techniques, and an optimization-based joint matching method, achieving a target reduction error of (3.265 ± 1.485) mm, rotation errors of (3.476 ± 1.995)°, and translation errors of (2.773 ± 1.390) mm. In the proof-of-concept cadaver studies, our method achieved a DSC of 0.988 in segmentation and 3.731 mm error in reduction planning, which senior experts deemed excellent. In conclusion, our automated approach significantly improves traditional preoperative planning, enhancing both efficiency and accuracy in pelvic fracture reduction.

Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT

PURPOSE

To develop a deep learning system for automatic segmentation of compression fracture vertebral bodies on thoracolumbar CT and differentiate between fresh and old fractures.

METHODS

We included patients with thoracolumbar fractures treated at our Hospital South Campus from January 2020 to December 2023, with prospective validation from January to June 2024, and used data from the North Campus from January to December 2023 for external validation. Fresh fractures were defined as back pain lasting less than 4 weeks, with MRI showing bone marrow edema (BME). We utilized a 3D V-Net for image segmentation and several ResNet and DenseNet models for classification, evaluating performance with ROC curves, accuracy, sensitivity, specificity, precision, F1 score, and AUC. The optimal model was selected to construct deep learning system and its diagnostic efficacy was compared with that of two clinicians.

RESULTS

The training dataset included 238 vertebras (man/women: 55/183; age: 72.11 ± 11.55), with 59 in internal validation (man/women: 13/46; age: 74.76 ± 8.96), 34 in external validation, and 48 in prospective validation. The 3D V-Net model achieved a DSC of 0.90 on the validation dataset. ResNet18 performed best among classification models, with an AUC of 0.96 in validation, 0.89 in external dataset, and 0.87 in prospective validation, surpassing the two clinicians in both external and prospective validations.

CONCLUSION

The deep learning model can automatically and accurately segment the vertebral bodies with compression fractures and classify them as fresh or old fractures, thereby assisting clinicians in making clinical decisions.

Applications of deep learning in trauma radiology: A narrative review

Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.

Deep Learning for Discrimination of Early Spinal Tuberculosis from Acute Osteoporotic Vertebral Fracture on CT

Background

Early differentiation between spinal tuberculosis (STB) and acute osteoporotic vertebral compression fracture (OVCF) is crucial for determining the appropriate clinical management and treatment pathway, thereby significantly impacting patient outcomes.

Objective

To evaluate the efficacy of deep learning (DL) models using reconstructed sagittal CT images in the differentiation of early STB from acute OVCF, with the aim of enhancing diagnostic precision, reducing reliance on MRI and biopsies, and minimizing the risks of misdiagnosis.

Methods

Data were collected from 373 patients, with 302 patients recruited from a university-affiliated hospital serving as the training and internal validation sets, and an additional 71 patients from another university-affiliated hospital serving as the external validation set. MVITV2, Efficient-Net-B5, ResNet101, and ResNet50 were used as the backbone networks for DL model development, training, and validation. Model evaluation was based on accuracy, precision, sensitivity, F1 score, and area under the curve (AUC). The performance of the DL models was compared with the diagnostic accuracy of two spine surgeons who performed a blinded review.

Results

The MVITV2 model outperformed other architectures in the internal validation set, achieving accuracy of 98.98%, precision of 100%, sensitivity of 97.97%, F1 score of 98.98%, and AUC of 0.997. The performance of the DL models notably exceeded that of the spine surgeons, who achieved accuracy rates of 77.38% and 93.56%. The external validation confirmed the models' robustness and generalizability.

Conclusion

The DL models significantly improved the differentiation between STB and OVCF, surpassing experienced spine surgeons in diagnostic accuracy. These models offer a promising alternative to traditional imaging and invasive procedures, potentially promoting early and accurate diagnosis, reducing healthcare costs, and improving patient outcomes. The findings underscore the potential of artificial intelligence for revolutionizing spinal disease diagnostics, and have substantial clinical implications.

Spine X-ray image segmentation based on deep learning and marker controlled watershed

BACKGROUND

The development of automatic methods for vertebral segmentation provides the objective analysis of each vertebra in the spine image, which is important for the diagnosis of various spinal diseases. However, vertebrae have inter-class similarity and intra-class variability, and some adjacent vertebrae exhibit adhesion.

OBJECTIVE

To solve the adhesion problem of adjacent vertebrae and ensure that the boundary between adjacent vertebrae can be accurately demarcated, we propose an image segmentation method based on deep learning and marker controlled watershed.

METHODS

This method consists of a dual-path model of localization path and segmentation path to achieve automatic vertebral segmentation. For the vertebral localization path, a high-resolution network (HRNet) is used to locate vertebral center. Moreover, based on spine posture, a new bone direction loss (BD-Loss) is designed to constrain HRNet. For the vertebral segmentation path, we proposed a VU-Net network to achieve vertebral preliminary segmentation. Additionally, a position information perception module (PIPM) is introduced to realize the guidance of HRNet to VU-Net. Finally, we novelly use the outputs of HR-Net and VU-Net deep learning networks to initialize the marker controlled watershed algorithm to suppress the adhesion of adjacent vertebrae and achieve vertebral fine segmentation.

RESULTS

The proposed method was evaluated on two spine X-ray datasets using four metrics. The first dataset contains sagittal images of the cervical spine, while the second dataset contains coronal images of the whole spine, both with different health conditions. Our method achieved Recall of 96.82% and 94.38%, Precision of 97.24% and 98.14%, Dice coefficient of 97.03% and 96.22%, Intersection over Union of 94.24% and 92.72% on the cervical spine and whole spine datasets respectively, outperforming current state-of-the-art techniques.

Explainable fully automated CT scoring of interstitial lung disease for patients suspected of systemic sclerosis by cascaded regression neural networks and its comparison with experts

Visual scoring of interstitial lung disease in systemic sclerosis (SSc-ILD) from CT scans is laborious, subjective and time-consuming. This study aims to develop a deep learning framework to automate SSc-ILD scoring. The automated framework is a cascade of two neural networks. The first network selects the craniocaudal positions of the five scoring levels. Subsequently, for each level, the second network estimates the ratio of three patterns to the total lung area: the total extent of disease (TOT), ground glass (GG) and reticulation (RET). To overcome the score imbalance in the second network, we propose a method to augment the training dataset with synthetic data. To explain the network's output, a heat map method is introduced to highlight the candidate interstitial lung disease regions. The explainability of heat maps was evaluated by two human experts and a quantitative method that uses the heat map to produce the score. The results show that our framework achieved a κ of 0.66, 0.58, and 0.65, for the TOT, GG and RET scoring, respectively. Both experts agreed with the heat maps in 91%, 90% and 80% of cases, respectively. Therefore, it is feasible to develop a framework for automated SSc-ILD scoring, which performs competitively with human experts and provides high-quality explanations using heat maps. Confirming the model's generalizability is needed in future studies.

Development and reporting of artificial intelligence in osteoporosis management

An abundance of medical data and enhanced computational power have led to a surge in artificial intelligence (AI) applications. Published studies involving AI in bone and osteoporosis research have increased exponentially, raising the need for transparent model development and reporting strategies. This review offers a comprehensive overview and systematic quality assessment of AI articles in osteoporosis while highlighting recent advancements. A systematic search in the PubMed database, from December 17, 2020 to February 1, 2023 was conducted to identify AI articles that relate to osteoporosis. The quality assessment of the studies relied on the systematic evaluation of 12 quality items derived from the minimum information about clinical artificial intelligence modeling checklist. The systematic search yielded 97 articles that fell into 5 areas; bone properties assessment (11 articles), osteoporosis classification (26 articles), fracture detection/classification (25 articles), risk prediction (24 articles), and bone segmentation (11 articles). The average quality score for each study area was 8.9 (range: 7-11) for bone properties assessment, 7.8 (range: 5-11) for osteoporosis classification, 8.4 (range: 7-11) for fracture detection, 7.6 (range: 4-11) for risk prediction, and 9.0 (range: 6-11) for bone segmentation. A sixth area, AI-driven clinical decision support, identified the studies from the 5 preceding areas that aimed to improve clinician efficiency, diagnostic accuracy, and patient outcomes through AI-driven models and opportunistic screening by automating or assisting with specific clinical tasks in complex scenarios. The current work highlights disparities in study quality and a lack of standardized reporting practices. Despite these limitations, a wide range of models and examination strategies have shown promising outcomes to aid in the earlier diagnosis and improve clinical decision-making. Through careful consideration of sources of bias in model performance assessment, the field can build confidence in AI-based approaches, ultimately leading to improved clinical workflows and patient outcomes.

Towards a fully automatic workflow for investigating the dynamics of lung cancer cachexia during radiotherapy using cone beam computed tomography

Objective.Cachexia is a devastating condition, characterized by involuntary loss of muscle mass with or without loss of adipose tissue mass. It affects more than half of patients with lung cancer, diminishing treatment effects and increasing mortality. Cone-beam computed tomography (CBCT) images, routinely acquired during radiotherapy treatment, might contain valuable anatomical information for monitoring body composition changes associated with cachexia. For this purpose, we propose an automatic artificial intelligence (AI)-based workflow, consisting of CBCT to CT conversion, followed by segmentation of pectoralis muscles.Approach.Data from 140 stage III non-small cell lung cancer patients was used. Two deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation (CUT), were used for unpaired training of CBCT to CT conversion, to generate synthetic CT (sCT) images. The no-new U-Net (nnU-Net) model was used for automatic pectoralis muscle segmentation. To evaluate tissue segmentation performance in the absence of ground truth labels, an uncertainty metric (UM) based on Monte Carlo dropout was developed and validated.Main results.Both CycleGAN and CUT restored the Hounsfield unit fidelity of the CBCT images compared to the planning CT (pCT) images and visually reduced streaking artefacts. The nnU-Net model achieved a Dice similarity coefficient (DSC) of 0.93, 0.94, 0.92 for the CT, sCT and CBCT images, respectively, on an independent test set. The UM showed a high correlation with DSC with a correlation coefficient of -0.84 for the pCT dataset and -0.89 for the sCT dataset.Significance.This paper shows a proof-of-concept for automatic AI-based monitoring of the pectoralis muscle area of lung cancer patients during radiotherapy treatment based on CBCT images, which provides an unprecedented time resolution of muscle mass loss during cachexia progression. Ultimately, the proposed workflow could provide valuable information for early intervention of cachexia, ideally resulting in improved cancer treatment outcome.

Deep learning-based quantification of osteonecrosis using magnetic resonance images in Gaucher disease

Gaucher disease is one of the most common lysosomal storage disorders. Osteonecrosis is a principal clinical manifestation of Gaucher disease and often leads to joint collapse and fractures. T1-weighted (T1w) modality in MRI is widely used to monitor bone involvement in Gaucher disease and to diagnose osteonecrosis. However, objective and quantitative methods for characterizing osteonecrosis are still limited. In this work, we present a deep learning-based quantification approach for the segmentation of osteonecrosis and the extraction of characteristic parameters. We first constructed two independent U-net models to segment the osteonecrosis and bone marrow unaffected by osteonecrosis (UBM) in spine and femur respectively, based on T1w images from patients in the UK national Gaucherite study database. We manually delineated parcellation maps including osteonecrosis and UBM from 364 T1w images (176 for spine, 188 for femur) as the training datasets, and the trained models were subsequently applied to all the 917 T1w images in the database. To quantify the segmentation, we calculated morphological parameters including the volume of osteonecrosis, the volume of UBM, and the fraction of total marrow occupied by osteonecrosis. Then, we examined the correlation between calculated features and the bone marrow burden score for marrow infiltration of the corresponding image, and no strong correlation was found. In addition, we analyzed the influence of splenectomy and the interval between the age at first symptom and the age of onset of treatment on the quantitative measurements of osteonecrosis. The results are consistent with previous studies, showing that prior splenectomy is closely associated with the fractional volume of osteonecrosis, and there is a positive relationship between the duration of untreated disease and the quantifications of osteonecrosis. We propose this technique as an efficient and reliable tool for assessing the extent of osteonecrosis in MR images of patients and improving prediction of clinically important adverse events.

VerFormer: Vertebrae-Aware Transformer for Automatic Spine Segmentation from CT Images

The accurate and efficient segmentation of the spine is important in the diagnosis and treatment of spine malfunctions and fractures. However, it is still challenging because of large inter-vertebra variations in shape and cross-image localization of the spine. In previous methods, convolutional neural networks (CNNs) have been widely applied as a vision backbone to tackle this task. However, these methods are challenged in utilizing the global contextual information across the whole image for accurate spine segmentation because of the inherent locality of the convolution operation. Compared with CNNs, the Vision Transformer (ViT) has been proposed as another vision backbone with a high capacity to capture global contextual information. However, when the ViT is employed for spine segmentation, it treats all input tokens equally, including vertebrae-related tokens and non-vertebrae-related tokens. Additionally, it lacks the capability to locate regions of interest, thus lowering the accuracy of spine segmentation. To address this limitation, we propose a novel Vertebrae-aware Vision Transformer (VerFormer) for automatic spine segmentation from CT images. Our VerFormer is designed by incorporating a novel Vertebrae-aware Global (VG) block into the ViT backbone. In the VG block, the vertebrae-related global contextual information is extracted by a Vertebrae-aware Global Query (VGQ) module. Then, this information is incorporated into query tokens to highlight vertebrae-related tokens in the multi-head self-attention module. Thus, this VG block can leverage global contextual information to effectively and efficiently locate spines across the whole input, thus improving the segmentation accuracy of VerFormer. Driven by this design, the VerFormer demonstrates a solid capacity to capture more discriminative dependencies and vertebrae-related context in automatic spine segmentation. The experimental results on two spine CT segmentation tasks demonstrate the effectiveness of our VG block and the superiority of our VerFormer in spine segmentation. Compared with other popular CNN- or ViT-based segmentation models, our VerFormer shows superior segmentation accuracy and generalization.

Automated detection, labelling and radiological grading of clinical spinal MRIs

Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful information from these scans can be challenging, time-consuming and hard to reproduce across different radiologists. In this paper, we alleviate these problems by introducing a multi-stage automated pipeline for analysing spinal MR scans. This pipeline first detects and labels vertebral bodies across several commonly used sequences (e.g. T1w, T2w and STIR) and fields of view (e.g. lumbar, cervical, whole spine). Using these detections it then performs automated diagnosis for several spinal disorders, including intervertebral disc degenerative changes in T1w and T2w lumbar scans, and spinal metastases, cord compression and vertebral fractures. To achieve this, we propose a new method of vertebrae detection and labelling, using vector fields to group together detected vertebral landmarks and a language-modelling inspired beam search to determine the corresponding levels of the detections. We also employ a new transformer-based architecture to perform radiological grading which incorporates context from multiple vertebrae and sequences, as a real radiologist would. The performance of each stage of the pipeline is tested in isolation on several clinical datasets, each consisting of 66 to 421 scans. The outputs are compared to manual annotations of expert radiologists, demonstrating accurate vertebrae detection across a range of scan parameters. Similarly, the model's grading predictions for various types of disc degeneration and detection of spinal metastases closely match those of an expert radiologist. To aid future research, our code and trained models are made publicly available.

Measurement of distances and locations of thoracic and lumbar vertebral bodies from CT scans in cases of spinal deformation

BACKGROUND

Spinal deformations, except for acute injuries, are among the most frequent reasons for visiting an orthopaedic specialist and musculoskeletal treatment in adults and adolescents. Data on the morphology and anatomical structures of the spine are therefore of interest to orthopaedics, physicians, and medical scientists alike, in the broad field from diagnosis to therapy and in research.

METHODS

Along the course of developing supplementary methods that do not require the use of ionizing radiation in the assessment of scoliosis, twenty CT scans from females and males with various severity of spinal deformations and body shape have been analysed with respect to the transverse distances between the vertebral body and the spinous process end tip and the skin, respectively, at thoracic and lumbar vertebral levels. Further, the locations of the vertebral bodies have been analysed in relation to the patient's individual body shape and shown together with those from other patients by normalization to the area encompassed by the transverse body contour.

RESULTS

While the transverse distance from the vertebral body to the skin varies between patients, the distances from the vertebral body to the spinous processes end tips tend to be rather similar across different patients of the same gender. Tables list the arithmetic mean distances for all thoracic and lumbar vertebral levels and for different regions upon grouping into mild, medium, and strong spinal deformation and according to the range of spinal deformation.

CONCLUSIONS

The distances, the clustering of the locations of the vertebral bodies as a function of the vertebral level, and the trends therein could in the future be used in context with biomechanical modeling of a patient's individual spinal deformation in scoliosis assessment using 3D body scanner images during follow-up examinations.

Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance.

Using Augmented Reality Technology to Optimize Transfacet Lumbar Interbody Fusion: A Case Report

The transfacet minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) is a novel approach available for the management of lumbar spondylolisthesis. It avoids the need to manipulate either of the exiting or traversing nerve roots, both protected by the bony boundaries of the approach. With the advancement in operative technologies such as navigation, mapping, segmentation, and augmented reality (AR), surgeons are prompted to utilize these technologies to enhance their surgical outcomes. A 36-year-old male patient was complaining of chronic progressive lower back pain. He was found to have grade 2 L4/5 spondylolisthesis. We studied the feasibility of a trans-Kambin or a transfacet MIS-TLIF, and decided to proceed with the latter given the wider corridor it provides. Preoperative trajectory planning and level segmentation in addition to intraoperative navigation and image merging were all utilized to provide an AR model to guide us through the surgery. The use of AR can build on the safety and learning of novel surgical approaches to spine pathologies. However, larger high-quality studies are needed to further objectively analyze its impact on surgical outcomes and to expand on its application.

A Spinal MRI Image Segmentation Method Based on Improved Swin-UNet

As the number of patients increases, physicians are dealing with more and more cases of degenerative spine pathologies on a daily basis. To reduce the workload of healthcare professionals, we propose a modified Swin-UNet network model. Firstly, the Swin Transformer Blocks are improved using a residual post-normalization and scaling cosine attention mechanism, which makes the training process of the model more stable and improves the accuracy. Secondly, we use the log-space continuous position biasing method instead of the bicubic interpolation position biasing method. This method solves the problem of performance loss caused by the large difference between the resolution of the pretraining image and the resolution of the spine image. Finally, we introduce a segmentation smooth module (SSM) at the decoder stage. The SSM effectively reduces redundancy, and enhances the segmentation edge processing to improve the model's segmentation accuracy. To validate the proposed method, we conducted experiments on a real dataset provided by hospitals. The average segmentation accuracy is no less than 95%. The experimental results demonstrate the superiority of the proposed method over the original model and other models of the same type in segmenting the spinous processes of the vertebrae and the posterior arch of the spine.

DeepmdQCT: A multitask network with domain invariant features and comprehensive attention mechanism for quantitative computer tomography diagnosis of osteoporosis

In the medical field, the application of machine learning technology in the automatic diagnosis and monitoring of osteoporosis often faces challenges related to domain adaptation in drug therapy research. The existing neural networks used for the diagnosis of osteoporosis may experience a decrease in model performance when applied to new data domains due to changes in radiation dose and equipment. To address this issue, in this study, we propose a new method for multi domain diagnostic and quantitative computed tomography (QCT) images, called DeepmdQCT. This method adopts a domain invariant feature strategy and integrates a comprehensive attention mechanism to guide the fusion of global and local features, effectively improving the diagnostic performance of multi domain CT images. We conducted experimental evaluations on a self-created OQCT dataset, and the results showed that for dose domain images, the average accuracy reached 91%, while for device domain images, the accuracy reached 90.5%. our method successfully estimated bone density values, with a fit of 0.95 to the gold standard. Our method not only achieved high accuracy in CT images in the dose and equipment fields, but also successfully estimated key bone density values, which is crucial for evaluating the effectiveness of osteoporosis drug treatment. In addition, we validated the effectiveness of our architecture in feature extraction using three publicly available datasets. We also encourage the application of the DeepmdQCT method to a wider range of medical image analysis fields to improve the performance of multi-domain images.

VertXNet: an ensemble method for vertebral body segmentation and identification from cervical and lumbar spinal X-rays

Accurate annotation of vertebral bodies is crucial for automating the analysis of spinal X-ray images. However, manual annotation of these structures is a laborious and costly process due to their complex nature, including small sizes and varying shapes. To address this challenge and expedite the annotation process, we propose an ensemble pipeline called VertXNet. This pipeline currently combines two segmentation mechanisms, semantic segmentation using U-Net, and instance segmentation using Mask R-CNN, to automatically segment and label vertebral bodies in lateral cervical and lumbar spinal X-ray images. VertXNet enhances its effectiveness by adopting a rule-based strategy (termed the ensemble rule) for effectively combining segmentation outcomes from U-Net and Mask R-CNN. It determines vertebral body labels by recognizing specific reference vertebral instances, such as cervical vertebra 2 ('C2') in cervical spine X-rays and sacral vertebra 1 ('S1') in lumbar spine X-rays. Those references are commonly relatively easy to identify at the edge of the spine. To assess the performance of our proposed pipeline, we conducted evaluations on three spinal X-ray datasets, including two in-house datasets and one publicly available dataset. The ground truth annotations were provided by radiologists for comparison. Our experimental results have shown that the proposed pipeline outperformed two state-of-the-art (SOTA) segmentation models on our test dataset with a mean Dice of 0.90, vs. a mean Dice of 0.73 for Mask R-CNN and 0.72 for U-Net. We also demonstrated that VertXNet is a modular pipeline that enables using other SOTA model, like nnU-Net to further improve its performance. Furthermore, to evaluate the generalization ability of VertXNet on spinal X-rays, we directly tested the pre-trained pipeline on two additional datasets. A consistently strong performance was observed, with mean Dice coefficients of 0.89 and 0.88, respectively. In summary, VertXNet demonstrated significantly improved performance in vertebral body segmentation and labeling for spinal X-ray imaging. Its robustness and generalization were presented through the evaluation of both in-house clinical trial data and publicly available datasets.

SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation

Liver occupying lesions can profoundly impact an individual's health and well-being. To assist physicians in the diagnosis and treatment of abnormal areas in the liver, we propose a novel network named SEU2-Net by introducing the channel attention mechanism into U2-Net for accurate and automatic liver occupying lesion segmentation. We design the Residual U-block with Squeeze-and-Excitation (SE-RSU), which is to add the Squeeze-and-Excitation (SE) attention mechanism at the residual connections of the Residual U-blocks (RSU, the component unit of U2-Net). SEU2-Net not only retains the advantages of U2-Net in capturing contextual information at multiple scales, but can also adaptively recalibrate channel feature responses to emphasize useful feature information according to the channel attention mechanism. In addition, we present a new abdominal CT dataset for liver occupying lesion segmentation from Peking University First Hospital's clinical data (PUFH dataset). We evaluate the proposed method and compare it with eight deep learning networks on the PUFH and the Liver Tumor Segmentation Challenge (LiTS) datasets. The experimental results show that SEU2-Net has state-of-the-art performance and good robustness in liver occupying lesions segmentation.

Automatization of CT Annotation: Combining AI Efficiency with Expert Precision

The integration of artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) algorithms, marks a transformative progression in medical imaging diagnostics. This technical note elucidates a novel methodology for semantic segmentation of the vertebral column in CT scans, exemplified by a dataset of 250 patients from Riga East Clinical University Hospital. Our approach centers on the accurate identification and labeling of individual vertebrae, ranging from C1 to the sacrum-coccyx complex. Patient selection was meticulously conducted, ensuring demographic balance in age and sex, and excluding scans with significant vertebral abnormalities to reduce confounding variables. This strategic selection bolstered the representativeness of our sample, thereby enhancing the external validity of our findings. Our workflow streamlined the segmentation process by eliminating the need for volume stitching, aligning seamlessly with the methodology we present. By leveraging AI, we have introduced a semi-automated annotation system that enables initial data labeling even by individuals without medical expertise. This phase is complemented by thorough manual validation against established anatomical standards, significantly reducing the time traditionally required for segmentation. This dual approach not only conserves resources but also expedites project timelines. While this method significantly advances radiological data annotation, it is not devoid of challenges, such as the necessity for manual validation by anatomically skilled personnel and reliance on specialized GPU hardware. Nonetheless, our methodology represents a substantial leap forward in medical data semantic segmentation, highlighting the potential of AI-driven approaches to revolutionize clinical and research practices in radiology.

Spine Deformity Assessment for Scoliosis Diagnostics Utilizing Image Processing Techniques: A Systematic Review

Spinal deformity refers to a range of disorders that are defined by anomalous curvature of the spine and may be classified as scoliosis, hypo/hyperlordosis, or hypo/hyperkyphosis. Among these, scoliosis stands out as the most common type of spinal deformity in human beings, and it can be distinguished by abnormal lateral spine curvature accompanied by axial rotation. Accurate identification of spinal deformity is crucial for a person’s diagnosis, and numerous assessment methods have been developed by researchers. Therefore, the present study aims to systematically review the recent works on spinal deformity assessment for scoliosis diagnosis utilizing image processing techniques. To gather relevant studies, a search strategy was conducted on three electronic databases (Scopus, ScienceDirect, and PubMed) between 2012 and 2022 using specific keywords and focusing on scoliosis cases. A total of 17 papers fully satisfied the established criteria and were extensively evaluated. Despite variations in methodological designs across the studies, all reviewed articles obtained quality ratings higher than satisfactory. Various diagnostic approaches have been employed, including artificial intelligence mechanisms, image processing, and scoliosis diagnosis systems. These approaches have the potential to save time and, more significantly, can reduce the incidence of human error. While all assessment methods have potential in scoliosis diagnosis, they possess several limitations that can be ameliorated in forthcoming studies. Therefore, the findings of this study may serve as guidelines for the development of a more accurate spinal deformity assessment method that can aid medical personnel in the real diagnosis of scoliosis.

Attractive deep morphology-aware active contour network for vertebral body contour extraction with extensions to heterogeneous and semi-supervised scenarios

Automatic vertebral body contour extraction (AVBCE) from heterogeneous spinal MRI is indispensable for the comprehensive diagnosis and treatment of spinal diseases. However, AVBCE is challenging due to data heterogeneity, image characteristics complexity, and vertebral body morphology variations, which may cause morphology errors in semantic segmentation. Deep active contour-based (deep ACM-based) methods provide a promising complement for tackling morphology errors by directly parameterizing the contour coordinates. Extending the target contours' capture range and providing morphology-aware parameter maps are crucial for deep ACM-based methods. For this purpose, we propose a novel Attractive Deep Morphology-aware actIve contouR nEtwork (ADMIRE) that embeds an elaborated contour attraction term (CAT) and a comprehensive contour quality (CCQ) loss into the deep ACM-based framework. The CAT adaptively extends the target contours' capture range by designing an all-to-all force field to enable the target contours' energy to contribute to farther locations. Furthermore, the CCQ loss is carefully designed to generate morphology-aware active contour parameters by simultaneously supervising the contour shape, tension, and smoothness. These designs, in cooperation with the deep ACM-based framework, enable robustness to data heterogeneity, image characteristics complexity, and target contour morphology variations. Furthermore, the deep ACM-based ADMIRE is able to cooperate well with semi-supervised strategies such as mean teacher, which enables its function in semi-supervised scenarios. ADMIRE is trained and evaluated on four challenging datasets, including three spinal datasets with more than 1000 heterogeneous images and more than 10000 vertebrae bodies, as well as a cardiac dataset with both normal and pathological cases. Results show ADMIRE achieves state-of-the-art performance on all datasets, which proves ADMIRE's accuracy, robustness, and generalization ability.

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation

In recent years, more attention paid to the spine caused by related diseases, spinal parsing (the multi-class segmentation of vertebrae and intervertebral disc) is an important part of the diagnosis and treatment of various spinal diseases. The more accurate the segmentation of medical images, the more convenient and quick the clinicians can evaluate and diagnose spinal diseases. Traditional medical image segmentation is often time consuming and energy consuming. In this paper, an efficient and novel automatic segmentation network model for MR spine images is designed. The proposed Inception-CBAM Unet++ (ICUnet++) model replaces the initial module with the Inception structure in the encoder-decoder stage base on Unet++ , which uses the parallel connection of multiple convolution kernels to obtain the features of different receptive fields during in the feature extraction. According to the characteristics of the attention mechanism, Attention Gate module and CBAM module are used in the network to make the attention coefficient highlight the characteristics of the local area. To evaluate the segmentation performance of network model, four evaluation metrics, namely intersection over union (IoU), dice similarity coefficient(DSC), true positive rate(TPR), positive predictive value(PPV) are used in the study. The published SpineSagT2Wdataset3 spinal MRI dataset is used during the experiments. In the experiment results, IoU reaches 83.16%, DSC is 90.32%, TPR is 90.40%, and PPV is 90.52%. It can be seen that the segmentation indicators have been significantly improved, which reflects the effectiveness of the model.

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

Vertebrae localization, segmentation and identification in CT images is key to numerous clinical applications. While deep learning strategies have brought to this field significant improvements over recent years, transitional and pathological vertebrae are still plaguing most existing approaches as a consequence of their poor representation in training datasets. Alternatively, proposed non-learning based methods take benefit of prior knowledge to handle such particular cases. In this work we propose to combine both strategies. To this purpose we introduce an iterative cycle in which individual vertebrae are recurrently localized, segmented and identified using deep-networks, while anatomic consistency is enforced using statistical priors. In this strategy, the transitional vertebrae identification is handled by encoding their configurations in a graphical model that aggregates local deep-network predictions into an anatomically consistent final result. Our approach achieves the state-of-the-art results on the VerSe20 challenge benchmark, and outperforms all methods on transitional vertebrae as well as the generalization to the VerSe19 challenge benchmark. Furthermore, our method can detect and report inconsistent spine regions that do not satisfy the anatomic consistency priors. Our code and model are openly available for research purposes.¹.

Opportunistic Screening Techniques for Analysis of CT Scans

PURPOSE OF REVIEW

Opportunistic screening is a combination of techniques to identify subjects of high risk for osteoporotic fracture using routine clinical CT scans prescribed for diagnoses unrelated to osteoporosis. The two main components are automated detection of vertebral fractures and measurement of bone mineral density (BMD) in CT scans, in which a phantom for calibration of CT to BMD values is not used. This review describes the particular challenges of opportunistic screening and provides an overview and comparison of current techniques used for opportunistic screening. The review further outlines the performance of opportunistic screening.

RECENT FINDINGS

A wide range of technologies for the automatic detection of vertebral fractures have been developed and successfully validated. Most of them are based on artificial intelligence algorithms. The automated differentiation of osteoporotic from traumatic fractures and vertebral deformities unrelated to osteoporosis, the grading of vertebral fracture severity, and the detection of mild vertebral fractures is still problematic. The accuracy of automated fracture detection compared to classical radiological semi-quantitative Genant scoring is about 80%. Accuracy errors of alternative BMD calibration methods compared to simultaneous phantom-based calibration used in standard quantitative CT (QCT) range from below 5% to about 10%. The impact of contrast agents, frequently administered in clinical CT on the determination of BMD and on fracture risk determination is still controversial. Opportunistic screening, the identification of vertebral fracture and the measurement of BMD using clinical routine CT scans, is feasible but corresponding techniques still need to be integrated into the clinical workflow and further validated with respect to the prediction of fracture risk.

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

By leveraging the recent development of artificial intelligence algorithms, several medical sectors have benefited from using automatic segmentation tools from bioimaging to segment anatomical structures. Segmentation of the musculoskeletal system is key for studying alterations in anatomical tissue and supporting medical interventions. The clinical use of such tools requires an understanding of the proper method for interpreting data and evaluating their performance. The current systematic review aims to present the common bottlenecks for musculoskeletal structures analysis (e.g., small sample size, data inhomogeneity) and the related strategies utilized by different authors. A search was performed using the PUBMED database with the following keywords: deep learning, musculoskeletal system, segmentation. A total of 140 articles published up until February 2022 were obtained and analyzed according to the PRISMA framework in terms of anatomical structures, bioimaging techniques, pre/post-processing operations, training/validation/testing subset creation, network architecture, loss functions, performance indicators and so on. Several common trends emerged from this survey; however, the different methods need to be compared and discussed based on each specific case study (anatomical region, medical imaging acquisition setting, study population, etc.). These findings can be used to guide clinicians (as end users) to better understand the potential benefits and limitations of these tools.

Automated detection and classification of acute vertebral body fractures using a convolutional neural network on computed tomography

BACKGROUND

Acute vertebral fracture is usually caused by low-energy injury with osteoporosis and high-energy trauma. The AOSpine thoracolumbar spine injury classification system (AO classification) plays an important role in the diagnosis and treatment of the disease. The diagnosis and description of vertebral fractures according to the classification scheme requires a great deal of time and energy for radiologists.

PURPOSE

To design and validate a multistage deep learning system (multistage AO system) for the automatic detection, localization and classification of acute thoracolumbar vertebral body fractures according to AO classification on computed tomography.

MATERIALS AND METHODS

The CT images of 1,217 patients who came to our hospital from January 2015 to December 2019 were collected retrospectively. The fractures were marked and classified by 2 junior radiology residents according to the type A standard in the AO classification. Marked fracture sites included the upper endplate, lower endplate and posterior wall. When there were inconsistent opinions on classification labels, the final result was determined by a director radiologist. We integrated different networks into different stages of the overall framework. U-net and a graph convolutional neural network (U-GCN) are used to realize the location and classification of the thoracolumbar spine. Next, a classification network is used to detect whether the thoracolumbar spine has a fracture. In the third stage, we detect fractures in different parts of the thoracolumbar spine by using a multibranch output network and finally obtain the AO types.

RESULTS

The mean age of the patients was 61.87 years with a standard deviation of 17.04 years, consisting of 760 female patients and 457 male patients. On vertebrae level, sensitivity for fracture detection was 95.23% in test dataset, with an accuracy of 97.93% and a specificity of 98.35%. For the classification of vertebral body fractures, the balanced accuracy was 79.56%, with an AUC of 0.904 for type A1, 0.945 for type A2, 0.878 for type A3 and 0.942 for type A4.

CONCLUSION

The multistage AO system can automatically detect and classify acute vertebral body fractures in the thoracolumbar spine on CT images according to AO classification with high accuracy.

A novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images

In recent years, fast and precise lumbar vertebrae segmentation technology have been one of the important topics in practical medical diagnosis and assisted medical surgery scenarios. However, most of the existing vertebral segmentation methods are based on the whole vertebral scanning space, which, up to some extent, is difficult to meet the clinical needs because of its large time complexity and space complexity. Different from the existing methods, for better exploiting the real time of lumbar segmentation, meanwhile ensuring its accuracy, a novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images (LVLS-HVPFE) is proposed in this paper. Firstly, a 2D projection location network of lumbar vertebrae based on fusion envelope of hybrid visual projection images is proposed to obtain the accurate location of each intact lumbar vertebra in the coronal and sagittal planes respectively. Among them, the envelope dataset of hybrid visual projection images (ED^HVPs) is established to enhance feature representation and suppress interference in the process of dimensionality reduction projection. An envelope deep neural network (EDNN) for ED^HVPs is established to effectively obtain depth envelope structure features with three different sizes, and a dimension reduction fusion mechanism is proposed to increase the sampling density of features and ensure the mutual independence of multi-scale features. Secondly, the concept of 3D localization criterion with spatial dimensionality reduction (SDRLC) is first proposed as a measure to verify the distribution consistency of vertebral targets in coronal and sagittal planes of a CT scan, and it can directionally guide for the subsequent 3D lumbar segmentation. Thirdly, under the condition of 3D positioning subspace of each intact lumbar vertebra, the 3D segmentation network based on spatial orientation guidance is used to realize an accurate segmentation of corresponding lumbar vertebra. The proposed method is evaluated with three representative datasets, and experimental results show that it is superior to the state-of-the-art methods.

Improved distinct bone segmentation from upper-body CT using binary-prediction-enhanced multi-class inference

PURPOSE

Automated distinct bone segmentation has many applications in planning and navigation tasks. 3D U-Nets have previously been used to segment distinct bones in the upper body, but their performance is not yet optimal. Their most substantial source of error lies not in confusing one bone for another, but in confusing background with bone-tissue.

METHODS

In this work, we propose binary-prediction-enhanced multi-class (BEM) inference, which takes into account an additional binary background/bone-tissue prediction, to improve the multi-class distinct bone segmentation. We evaluate the method using different ways of obtaining the binary prediction, contrasting a two-stage approach to four networks with two segmentation heads. We perform our experiments on two datasets: An in-house dataset comprising 16 upper-body CT scans with voxelwise labelling into 126 distinct classes, and a public dataset containing 50 synthetic CT scans, with 41 different classes.

RESULTS

The most successful network with two segmentation heads achieves a class-median Dice coefficient of 0.85 on cross-validation with the upper-body CT dataset. These results outperform both our previously published 3D U-Net baseline with standard inference, and previously reported results from other groups. On the synthetic dataset, we also obtain improved results when using BEM-inference.

CONCLUSION

Using a binary bone-tissue/background prediction as guidance during inference improves distinct bone segmentation from upper-body CT scans and from the synthetic dataset. The results are robust to multiple ways of obtaining the bone-tissue segmentation and hold for the two-stage approach as well as for networks with two segmentation heads.

A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation

PURPOSE

To propose a fully automated deep learning (DL) framework for the vertebral morphometry and Cobb angle measurement from three-dimensional (3D) computed tomography (CT) images of the spine, and validate the proposed framework on an external database.

METHODS

The vertebrae were first localized and segmented in each 3D CT image using a DL architecture based on an ensemble of U-Nets, and then automated vertebral morphometry in the form of vertebral body (VB) and intervertebral disk (IVD) heights, and spinal curvature measurements in the form of coronal and sagittal Cobb angles (thoracic kyphosis and lumbar lordosis) were performed using dedicated machine learning techniques. The framework was trained on 1725 vertebrae from 160 CT images and validated on an external database of 157 vertebrae from 15 CT images.

RESULTS

The resulting mean absolute errors (± standard deviation) between the obtained DL and corresponding manual measurements were 1.17 ± 0.40 mm for VB heights, 0.54 ± 0.21 mm for IVD heights, and 3.42 ± 1.36° for coronal and sagittal Cobb angles, with respective maximal absolute errors of 2.51 mm, 1.64 mm, and 5.52°. Linear regression revealed excellent agreement, with Pearson's correlation coefficient of 0.943, 0.928, and 0.996, respectively.

CONCLUSION

The obtained results are within the range of values, obtained by existing DL approaches without external validation. The results therefore confirm the scalability of the proposed DL framework from the perspective of application to external data, and time and computational resource consumption required for framework training.

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.

Rule and Neural Network-Based Image Segmentation of Mice Vertebrae Images

Background

Image segmentation is a fundamental technique that allows researchers to process images from various sources into individual components for certain applications, such as visual or numerical evaluations. Image segmentation is beneficial when studying medical images for healthcare purposes. However, existing semantic image segmentation models like the U-net are computationally intensive. This work aimed to develop less complicated models that could still accurately segment images.

Methodology

Rule-based and linear layer neural network models were developed in Mathematica and trained on mouse vertebrae micro-computed tomography scans. These models were tasked with segmenting the cortical shell from the whole bone image. A U-net model was also set up for comparison.

Results

It was found that the linear layer neural network had comparable accuracy to the U-net model in segmenting the mice vertebrae scans.

Conclusions

This work provides two separate models that allow for automated segmentation of mouse vertebral scans, which could be potentially valuable in applications such as pre-processing the murine vertebral scans for further evaluations of the effect of drug treatment on bone micro-architecture.