Feasibility of Deep Learning Algorithms for Reporting in Routine Spine Magnetic Resonance Imaging

Deep learning algorithms to assist in imaging diagnosis in individuals with disc herniation or spondylolisthesis: A scoping review

BACKGROUND

Deep learning applications in medical imaging have advanced significantly, supporting the diagnosis of spinal disorders such as disc herniation and spondylolisthesis. This study aimed to review deep learning algorithms used in diagnostic imaging for these conditions.

METHODS

A scoping review was conducted following PRISMA-ScR guidelines and registered in the Open Science Framework. Literature searches were performed in PubMed, Lilacs, ScienceDirect, Web of Science, Wiley Online Library, Embase, IEEE Xplore, and Google Scholar. Studies published in the last ten years in English, Portuguese, or Spanish applying deep learning to lumbar spine imaging were included. Exclusions comprised reviews, expert opinions, and studies not focusing on lumbar imaging. Of 258 identified records, 71 duplicates were removed, leaving 187 for screening. After full-text assessment, 18 met eligibility criteria.

RESULTS

Nine studies investigated disc herniation, primarily using magnetic resonance imaging (MRI), while the remaining nine focused on spondylolisthesis based on X-ray imaging. Convolutional neural networks (CNNs), particularly ResNet-based architectures, were the most frequently used models, demonstrating high accuracy and sensitivity in classification tasks. MRI was predominant for disc herniation, while X-ray was preferred for spondylolisthesis. However, limitations included small dataset sizes, lack of external validation, and challenges in generalizing findings across populations.

CONCLUSION

While deep learning holds promise for enhancing diagnostic accuracy and efficiency, further research is needed to standardize evaluation methods, expand dataset diversity, and improve model robustness for real-world clinical applications.

Artificial Intelligence in Spine Imaging: A Paradigm Shift in Diagnosis and Care

Recent advancements in artificial intelligence (AI) can significantly improve radiologists' workflow, improving efficiency and diagnostic accuracy. Current AI applications within spine imaging are approved to accelerate image acquisition time, improve MR imaging quality, triage studies with urgent findings, and aid with image interpretation and report generation. Radiologists should stay up to date on the latest AI advancements and know how to use these tools to improve their own practice. We review current practical applications of AI as well as cutting edge research for future workflow integration.

Evaluating the reproducibility of a deep learning algorithm for the prediction of retinal age

Recently, a deep learning algorithm (DLA) has been developed to predict the chronological age from retinal images. The Retinal Age Gap (RAG), a deviation between predicted age from retinal images (Retinal Age, RA) and chronological age, correlates with mortality and age-related diseases. This study evaluated the reliability and accuracy of RA predictions and analyzed various factors that may influence them. We analyzed two groups of participants: Intravisit and Intervisit, both imaged by color fundus photography. RA was predicted using an established algorithm. The Intervisit group comprised 26 subjects, imaged in two sessions. The Intravisit group had 41 subjects, of whom each eye was photographed twice in one session. The mean absolute test-retest difference in predicted RA was 2.39 years for Intervisit and 2.13 years for Intravisit, with the latter showing higher prediction variability. The chronological age was predicted accurately from fundus photographs. Subsetting image pairs based on differential image quality reduced test-retest discrepancies by up to 50%, but mean image quality was not correlated with retest outcomes. Marked diurnal oscillations in RA predictions were observed, with a significant overestimation in the afternoon compared to the morning in the Intravisit cohort. The order of image acquisition across imaging sessions did not influence RA prediction and subjective age perception did not predict RAG. Inter-eye consistency exceeded 3 years. Our study is the first to explore the reliability of RA predictions. Consistent image quality enhances retest outcomes. The observed diurnal variations in RA predictions highlight the need for standardized imaging protocols, but RAG could soon be a reliable metric in clinical investigations.

GPT4LFS (generative pretrained transformer 4 omni for lumbar foramina stenosis): enhancing lumbar foraminal stenosis image classification through large multimodal models

BACKGROUND CONTEXT

Lumbar foraminal stenosis (LFS) is a common spinal condition that requires accurate assessment. Current magnetic resonance imaging (MRI) reporting processes are often inefficient, and while deep learning has potential for improvement, challenges in generalization and interpretability limit its diagnostic effectiveness compared to physician expertise.

PURPOSE

The present study aimed to leverage a multimodal large language model to improve the accuracy and efficiency of LFS image classification, thereby enabling rapid and precise automated diagnosis, reducing the dependence on manually annotated data, and enhancing diagnostic efficiency.

STUDY DESIGN/SETTING

Retrospective study conducted from April 2017 to March 2023.

PATIENT SAMPLE

Sagittal T1-weighted MRI data for the lumbar spine were collected from 1,200 patients across 3 medical centers. A total of 810 patient cases were included in the final analysis, with data collected from 7 different MRI devices.

OUTCOME MEASURES

Automated classification of LFS using the multi modal large language model. Accuracy, sensitivity, Specificity and Cohen's Kappa coefficient were calculated.

METHODS

An advanced multimodal fusion framework GPT4LFS was developed with the primary objective of integrating imaging data and natural language descriptions to comprehensively capture the complex LFS features. The model employed a pretrained ConvNeXt as the image processing module for extracting high-dimensional imaging features. Concurrently, medical descriptive texts generated by the multimodal large language model GPT-4o and encoded and feature-extracted using RoBERTa were utilized to optimize the model's contextual understanding capabilities. The Mamba architecture was implemented during the feature fusion stage, effectively integrating imaging and textual features and thereby enhancing the performance of the classification task. Finally, the stability of the model's detection results was validated by evaluating classification task metrics, such as the accuracy, sensitivity, specificity, and Kappa coefficients.

RESULTS

The training set comprised 6,299 images from 635 patients, the internal test set included 820 images from 82 patients, and the external test set was composed of 930 images from 93 patients. The GPT4LFS model demonstrated an overall accuracy of 93.7%, sensitivity of 95.8%, and specificity of 94.5% in the internal test set (Kappa=0.89, 95% confidence interval (CI): 0.84-0.96, p<.001). In the external test set, the overall accuracy was 92.2%, with a sensitivity of 92.2% and a specificity of 97.4% (Kappa=0.88, 95% CI: 0.84-0.89, p<.001). Both the internal and external test sets showed excellent consistency in the model. The code is freely accessible on GitHub at the following repository: https://github.com/ElzatElham/GPT4LFS.

CONCLUSIONS

Using the GPT4LFS model for LFS image categorization demonstrated accuracy and the capacity for feature description at a level commensurate with that of professional clinicians.

Artificial Intelligence-Assisted MRI Diagnosis in Lumbar Degenerative Disc Disease: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

Lumbar degenerative disc disease (DDD) poses a significant global health care challenge, with accurate diagnosis being difficult using conventional methods. Artificial intelligence (AI), particularly machine learning and deep learning, offers promising tools for improving diagnostic accuracy and workflow in lumbar DDD. This study aims to review AI-assisted magnetic resonance imaging (MRI) diagnosis in lumbar DDD and discuss current research for clinical use.

METHODS

A systematic search of electronic databases identified studies on AI applications in MRI-based lumbar DDD diagnosis, following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Search terms included combinations of "Artificial Intelligence," "Machine Learning," "Deep Learning," "Low Back Pain," "Lumbar," "Disc," "Degeneration," and "MRI," targeting studies in English from January 1, 2010, to January 1, 2024. Inclusion criteria encompassed experimental and observational studies in peer-reviewed journals. Data extraction focused on study characteristics, AI techniques, performance metrics, and diagnostic outcomes, with quality assessed using predefined criteria.

RESULTS

Twenty studies met the inclusion criteria, employing various AI methodologies, including machine learning and deep learning, to diagnose lumbar DDD manifestations such as disc degeneration, herniation, and bulging. AI models consistently outperformed conventional methods in accuracy, sensitivity, and specificity, with performance metrics ranging from 71.5% to 99% across different diagnostic objectives.

CONCLUSION

The algorithm model provides a structured framework for integrating AI into routine clinical practice, enhancing diagnostic precision and patient outcomes in lumbar DDD management. Further research and validation are needed to refine AI algorithms for real-world application in lumbar DDD diagnosis.

Artificial intelligence for segmentation and classification in lumbar spinal stenosis: an overview of current methods

PURPOSE

Lumbar spinal stenosis (LSS) is a frequently occurring condition defined by narrowing of the spinal or nerve root canal due to degenerative changes. Physicians use MRI scans to determine the severity of stenosis, occasionally complementing it with X-ray or CT scans during the diagnostic work-up. However, manual grading of stenosis is time-consuming and induces inter-reader variability as a standardized grading system is lacking. Machine Learning (ML) has the potential to aid physicians in this process by automating segmentation and classification of LSS. However, it is unclear what models currently exist to perform these tasks.

METHODS

A systematic review of literature was performed by searching the Cochrane Library, Embase, Emcare, PubMed, and Web of Science databases for studies describing an ML-based algorithm to perform segmentation or classification of the lumbar spine for LSS. Risk of bias was assessed through an adjusted version of the Newcastle-Ottawa Quality Assessment Scale that was more applicable to ML studies. Qualitative analyses were performed based on type of algorithm (conventional ML or Deep Learning (DL)) and task (segmentation or classification).

RESULTS

A total of 27 articles were included of which nine on segmentation, 16 on classification and 2 on both tasks. The majority of studies focused on algorithms for MRI analysis. There was wide variety among the outcome measures used to express model performance. Overall, ML algorithms are able to perform segmentation and classification tasks excellently. DL methods tend to demonstrate better performance than conventional ML models. For segmentation the best performing DL models were U-Net based. For classification U-Net and unspecified CNNs powered the models that performed the best for the majority of outcome metrics. The number of models with external validation was limited.

CONCLUSION

DL models achieve excellent performance for segmentation and classification tasks for LSS, outperforming conventional ML algorithms. However, comparisons between studies are challenging due to the variety in outcome measures and test datasets. Future studies should focus on the segmentation task using DL models and utilize a standardized set of outcome measures and publicly available test dataset to express model performance. In addition, these models need to be externally validated to assess generalizability.

Classification of lumbar spine disorders using large language models and MRI segmentation

BACKGROUND

MRI is critical for diagnosing lumbar spine disorders but its complexity challenges diagnostic accuracy. This study proposes a BERT-based large language model (LLM) to enhance precision in classifying lumbar spine disorders through the integration of MRI data, textual reports, and numerical measurements.

METHODS

The segmentation quality of MRI data is evaluated using dice coefficients (cut-off: 0.92) and intersection over union (IoU) metrics (cut-off: 0.88) to ensure precise anatomical feature extraction. The CNN extracts key lumbar spine features, such as lumbar lordotic angle (LLA) and disc heights, which are tokenized as direct scalar values representing positional relationships. A data source of 28,065 patients with various disorders, including degenerative disc disease, spinal stenosis, and spondylolisthesis, is used to establish diagnostic standards. These standards are refined through post-CNN processing of MRI texture features. The BERT-based spinal LLM model integrates these CNN-extracted MRI features and numerical values through early fusion layers.

RESULTS

Segmentation analysis illustrate various lumbar spine disorders and their anatomical changes. The model achieved high performance, with all key metrics nearing 0.9, demonstrating its effectiveness in classifying conditions like spondylolisthesis, herniated disc, and spinal stenosis. External validation further confirmed the model's generalizability across different populations. External validation on 514 expert-validated MRI cases further confirms the model's clinical relevance and generalizability. The BERT-based model classifies 61 combinations of lumbar spine disorders.

CONCLUSIONS

The BERT-based spinal LLM significantly improves the precision of lumbar spine disorder classification, supporting accurate diagnosis and treatment planning.

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

Semantic contrast with uncertainty-aware pseudo label for lumbar semi-supervised classification

BACKGROUND

Lumbar disc herniation (LDH) is a prevalent spinal disease that can result in severe pain, with Magnetic resonance imaging (MRI) serving as a commonly diagnostic tool. However, annotating numerous MRI images, necessary for deep learning based LDH diagnosis, can be challenging and labor-intensive. Semi-supervised learning, mainly utilizing pseudo labeling and consistency regularization, can leverage limited labeled images and abundant unlabeled images. However, consistency regularization solely focuses on maintaining the semantic consistency of transformed unlabeled data but fails to utilize the semantic information from labeled data to guide the unlabeled data, and additionally, pseudo labeling is prone to confirmation bias.

METHOD

We propose SeCoFixMatch, an innovative approach that seamlessly integrates semantic contrast and uncertainty-aware pseudo labeling into semi-supervised learning. Semantic contrast constraints the semantic consistency between labeled and unlabeled images. Pseudo labels are generated by combining predictive confidence and uncertainty, with uncertainty computing by optimizing the Kullback-Leibler (KL) loss between predictive and target Dirichlet distribution.

RESULTS

Comparison with other semi-supervised models and ablation experiment with varying labeled data demonstrate the effectiveness and generalization of proposed model. Notably, SeCoFixMatch, trained with just 40 labels, outperforms the baseline model trained with 200 labels, reducing the annotation effort by a remarkable 80%.

CONCLUSIONS

Proposed pseudo labeling algorithm generates more precise pseudo labels for semantic contrastive learning and semantic contrastive learning facilitates better feature representation, thereby further improving the prediction accuracy of pseudo label. The mutual reinforcement of pseudo labeling and semantic contrast constraints boosts the performance of semi-supervised algorithm.

Exploring Pathways for Pain Relief in Treatment and Management of Lumbar Foraminal Stenosis: A Review of the Literature

BACKGROUND

Lumbar foraminal stenosis (LFS) involves the narrowing of neural foramina, leading to nerve compression, significant lower back pain and radiculopathy, particularly in the aging population. Management includes physical therapy, medications and potentially invasive surgeries such as foraminotomy. Advances in diagnostic and treatment strategies are essential due to LFS's complexity and prevalence, which underscores the importance of a multidisciplinary approach in optimizing patient outcomes.

METHOD

This literature review on LFS employed a systematic methodology to gather and synthesize recent scientific data. A comprehensive search was conducted across PubMed, Scopus and Cochrane Library databases using specific keywords related to LFS. The search, restricted to English language articles from 1 January 2000 to 31 December 2023, focused on peer-reviewed articles, clinical trials and reviews. Due to the heterogeneity among the studies, data were qualitatively synthesized into themes related to diagnosis, treatment and pathophysiology.

RESULTS

This literature review on LFS analyzed 972 articles initially identified, from which 540 remained after removing duplicates. Following a rigorous screening process, 20 peer-reviewed articles met the inclusion criteria and were reviewed. These studies primarily focused on evaluating the diagnostic accuracy, treatment efficacy and pathophysiological insights into LFS.

CONCLUSION

The comprehensive review underscores the necessity for precise diagnostic and management strategies for LFS, highlighting the role of a multidisciplinary approach and the utility of a unified classification system in enhancing patient outcomes in the face of this condition's increasing prevalence.

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.

Artificial intelligence: a new cutting-edge tool in spine surgery

The purpose of this narrative review was to comprehensively elaborate the various components of artificial intelligence (AI), their applications in spine surgery, practical concerns, and future directions. Over the years, spine surgery has been continuously transformed in various aspects, including diagnostic strategies, surgical approaches, procedures, and instrumentation, to provide better-quality patient care. Surgeons have also augmented their surgical expertise with rapidly growing technological advancements. AI is an advancing field that has the potential to revolutionize many aspects of spine surgery. We performed a comprehensive narrative review of the various aspects of AI and machine learning in spine surgery. To elaborate on the current role of AI in spine surgery, a review of the literature was performed using PubMed and Google Scholar databases for articles published in English in the last 20 years. The initial search using the keywords "artificial intelligence" AND "spine," "machine learning" AND "spine," and "deep learning" AND "spine" extracted a total of 78, 60, and 37 articles and 11,500, 4,610, and 2,270 articles on PubMed and Google Scholar. After the initial screening and exclusion of unrelated articles, duplicates, and non-English articles, 405 articles were identified. After the second stage of screening, 93 articles were included in the review. Studies have shown that AI can be used to analyze patient data and provide personalized treatment recommendations in spine care. It also provides valuable insights for planning surgeries and assisting with precise surgical maneuvers and decisionmaking during the procedures. As more data become available and with further advancements, AI is likely to improve patient outcomes.

Fast high-quality MRI protocol of the lumbar spine with deep learning-based algorithm: an image quality and scanning time comparison with standard protocol

OBJECTIVE

The objective of this study is to prospectively compare quantitative and subjective image quality, scanning time, and diagnostic confidence between a new deep learning-based reconstruction(DLR) algorithm and standard MRI protocol of lumbar spine.

MATERIALS AND METHODS

Eighty healthy volunteers underwent 1.5T MRI examination of lumbar spine from September 2021 to May 2023. Protocol acquisition comprised sagittal T1- and T2-weighted fast spin echo and short-tau inversion recovery images and axial multislices T2-weighted fast spin echo images. All sequences were acquired with both DLR algorithm and standard protocols. Two radiologists, blinded to the reconstruction technique, performed quantitative and qualitative image quality analysis in consensus reading; diagnostic confidence was also assessed. Quantitative image quality analysis was assessed by calculating signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Qualitative image quality analysis and diagnostic confidence were assessed with a five-point Likert scale. Scanning times were also compared.

RESULTS

DLR SNR was higher in all sequences (all p<0.001). CNR of the DLR was superior to conventional dataset only for axial and sagittal T2-weighted fast spin echo images (p<0.001). Qualitative analysis showed DLR had higher overall quality in all sequences (all p<0.001), with an inter-rater agreement of 0.83 (0.78-0.86). DLR total protocol scanning time was lower compared to standard protocol (6:26 vs 12:59 min, p<0.001). Diagnostic confidence for DLR algorithm was not inferior to standard protocol.

CONCLUSION

DLR applied to 1.5T MRI is a feasible method for lumbar spine imaging providing morphologic sequences with higher image quality and similar diagnostic confidence compared with standard protocol, enabling a remarkable time saving (up to 50%).

Are current machine learning applications comparable to radiologist classification of degenerate and herniated discs and Modic change? A systematic review and meta-analysis

INTRODUCTION

Low back pain is the leading contributor to disability burden globally. It is commonly due to degeneration of the lumbar intervertebral discs (LDD). Magnetic resonance imaging (MRI) is the current best tool to visualize and diagnose LDD, but places high time demands on clinical radiologists. Automated reading of spine MRIs could improve speed, accuracy, reliability and cost effectiveness in radiology departments. The aim of this review and meta-analysis was to determine if current machine learning algorithms perform well identifying disc degeneration, herniation, bulge and Modic change compared to radiologists.

METHODS

A PRISMA systematic review protocol was developed and four electronic databases and reference lists were searched. Strict inclusion and exclusion criteria were defined. A PROBAST risk of bias and applicability analysis was performed.

RESULTS

1350 articles were extracted. Duplicates were removed and title and abstract searching identified original research articles that used machine learning (ML) algorithms to identify disc degeneration, herniation, bulge and Modic change from MRIs. 27 studies were included in the review; 25 and 14 studies were included multi-variate and bivariate meta-analysis, respectively. Studies used machine learning algorithms to assess LDD, disc herniation, bulge and Modic change. Models using deep learning, support vector machine, k-nearest neighbors, random forest and naïve Bayes algorithms were included. Meta-analyses found no differences in algorithm or classification performance. When algorithms were tested in replication or external validation studies, they did not perform as well as when assessed in developmental studies. Data augmentation improved algorithm performance when compared to models used with smaller datasets, there were no performance differences between augmented data and large datasets.

DISCUSSION

This review highlights several shortcomings of current approaches, including few validation attempts or use of large sample sizes. To the best of the authors' knowledge, this is the first systematic review to explore this topic. We suggest the utilization of deep learning coupled with semi- or unsupervised learning approaches. Use of all information contained in MRI data will improve accuracy. Clear and complete reporting of study design, statistics and results will improve the reliability and quality of published literature.

Deep learning-based detection and classification of lumbar disc herniation on magnetic resonance images

Background

The severity assessment of lumbar disc herniation (LDH) on MR images is crucial for selecting suitable surgical candidates. However, the interpretation of MR images is time-consuming and requires repetitive work. This study aims to develop and evaluate a deep learning-based diagnostic model for automated LDH detection and classification on lumbar axial T2-weighted MR images.

Methods

A total of 1115 patients were analyzed in this retrospective study; both a development dataset (1015 patients, 15 249 images) and an external test dataset (100 patients, 1273 images) were utilized. According to the Michigan State University (MSU) classification criterion, experts labeled all images with consensus, and the final labeled results were regarded as the reference standard. The automated diagnostic model comprised Faster R-CNN and ResNeXt101 as the detection and classification network, respectively. The deep learning-based diagnostic performance was evaluated by calculating mean intersection over union (IoU), accuracy, precision, sensitivity, specificity, F1 score, the area under the receiver operating characteristics curve (AUC), and intraclass correlation coefficient (ICC) with 95% confidence intervals (CIs).

Results

High detection consistency was obtained in the internal test dataset (mean IoU = 0.82, precision = 98.4%, sensitivity = 99.4%) and external test dataset (mean IoU = 0.70, precision = 96.3%, sensitivity = 97.8%). Overall accuracy for LDH classification was 87.70% (95% CI: 86.59%-88.86%) and 74.23% (95% CI: 71.83%-76.75%) in the internal and external test datasets, respectively. For internal testing, the proposed model achieved a high agreement in classification (ICC = 0.87, 95% CI: 0.86-0.88, P < 0.001), which was higher than that of external testing (ICC = 0.79, 95% CI: 0.76-0.81, P < 0.001). The AUC for model classification was 0.965 (95% CI: 0.962-0.968) and 0.916 (95% CI: 0.908-0.925) in the internal and external test datasets, respectively.

Conclusions

The automated diagnostic model achieved high performance in detecting and classifying LDH and exhibited considerable consistency with experts' classification.

Deep Learning for Multi-Tissue Segmentation and Fully Automatic Personalized Biomechanical Models from BACPAC Clinical Lumbar Spine MRI

STUDY DESIGN

In vivo retrospective study of fully automatic quantitative imaging feature extraction from clinically acquired lumbar spine magnetic resonance imaging (MRI).

OBJECTIVE

To demonstrate the feasibility of substituting automatic for human-demarcated segmentation of major anatomic structures in clinical lumbar spine MRI to generate quantitative image-based features and biomechanical models.

SETTING

Previous studies have demonstrated the viability of automatic segmentation applied to medical images; however, the feasibility of these networks to segment clinically acquired images has not yet been demonstrated, as they largely rely on specialized sequences or strict quality of imaging data to achieve good performance.

METHODS

Convolutional neural networks were trained to demarcate vertebral bodies, intervertebral disc, and paraspinous muscles from sagittal and axial T1-weighted MRIs. Intervertebral disc height, muscle cross-sectional area, and subject-specific musculoskeletal models of tissue loading in the lumbar spine were then computed from these segmentations and compared against those computed from human-demarcated masks.

RESULTS

Segmentation masks, as well as the morphological metrics and biomechanical models computed from those masks, were highly similar between human- and computer-generated methods. Segmentations were similar, with Dice similarity coefficients of 0.77 or greater across networks, and morphological metrics and biomechanical models were similar, with Pearson R correlation coefficients of 0.69 or greater when significant.

CONCLUSIONS

This study demonstrates the feasibility of substituting computer-generated for human-generated segmentations of major anatomic structures in lumbar spine MRI to compute quantitative image-based morphological metrics and subject-specific musculoskeletal models of tissue loading quickly, efficiently, and at scale without interrupting routine clinical care.

The role of Artificial intelligence in the assessment of the spine and spinal cord

Artificial intelligence (AI) application development is underway in all areas of radiology where many promising tools are focused on the spine and spinal cord. In the past decade, multiple spine AI algorithms have been created based on radiographs, computed tomography, and magnetic resonance imaging. These algorithms have wide-ranging purposes including automatic labeling of vertebral levels, automated description of disc degenerative changes, detection and classification of spine trauma, identification of osseous lesions, and the assessment of cord pathology. The overarching goals for these algorithms include improved patient throughput, reducing radiologist workload burden, and improving diagnostic accuracy. There are several pre-requisite tasks required in order to achieve these goals, such as automatic image segmentation, facilitating image acquisition and postprocessing. In this narrative review, we discuss some of the important imaging AI solutions that have been developed for the assessment of the spine and spinal cord. We focus on their practical applications and briefly discuss some key requirements for the successful integration of these tools into practice. The potential impact of AI in the imaging assessment of the spine and cord is vast and promises to provide broad reaching improvements for clinicians, radiologists, and patients alike.

Natural language processing in low back pain and spine diseases: A systematic review

Natural Language Processing (NLP) is a discipline at the intersection between Computer Science (CS), Artificial Intelligence (AI), and Linguistics that leverages unstructured human-interpretable (natural) language text. In recent years, it gained momentum also in health-related applications and research. Although preliminary, studies concerning Low Back Pain (LBP) and other related spine disorders with relevant applications of NLP methodologies have been reported in the literature over the last few years. It motivated us to systematically review the literature comprised of two major public databases, PubMed and Scopus. To do so, we first formulated our research question following the PICO guidelines. Then, we followed a PRISMA-like protocol by performing a search query including terminologies of both technical (e.g., natural language and computational linguistics) and clinical (e.g., lumbar and spine surgery) domains. We collected 221 non-duplicated studies, 16 of which were eligible for our analysis. In this work, we present these studies divided into sub-categories, from both tasks and exploited models’ points of view. Furthermore, we report a detailed description of techniques used to extract and process textual features and the several evaluation metrics used to assess the performance of the NLP models. However, what is clear from our analysis is that additional studies on larger datasets are needed to better define the role of NLP in the care of patients with spinal disorders.

A Proposed Personalized Spine Care Protocol (SpineScreen) to Treat Visualized Pain Generators: An Illustrative Study Comparing Clinical Outcomes and Postoperative Reoperations between Targeted Endoscopic Lumbar Decompression Surgery, Minimally Invasive TLIF and Open Laminectomy

Background: Endoscopically visualized spine surgery has become an essential tool that aids in identifying and treating anatomical spine pathologies that are not well demonstrated by traditional advanced imaging, including MRI. These pathologies may be visualized during endoscopic lumbar decompression (ELD) and categorized into primary pain generators (PPG). Identifying these PPGs provides crucial information for a successful outcome with ELD and forms the basis for our proposed personalized spine care protocol (SpineScreen). Methods: a prospective study of 412 patients from 7 endoscopic practices consisting of 207 (50.2%) males and 205 (49.8%) females with an average age of 63.67 years and an average follow-up of 69.27 months was performed to compare the durability of targeted ELD based on validated primary pain generators versus image-based open lumbar laminectomy, and minimally invasive lumbar transforaminal interbody fusion (TLIF) using Kaplan-Meier median survival calculations. The serial time was determined as the interval between index surgery and when patients were censored for additional interventional and surgical treatments for low back-related symptoms. A control group was recruited from patients referred for a surgical consultation but declined interventional and surgical treatment and continued on medical care. Control group patients were censored when they crossed over into any surgical or interventional treatment group. Results: of the 412 study patients, 206 underwent ELD (50.0%), 61 laminectomy (14.8%), and 78 (18.9%) TLIF. There were 67 patients in the control group (16.3% of 412 patients). The most common surgical levels were L4/5 (41.3%), L5/S1 (25.0%), and L4-S1 (16.3%). At two-year f/u, excellent and good Macnab outcomes were reported by 346 of the 412 study patients (84.0%). The VAS leg pain score reduction was 4.250 ± 1.691 (p < 0.001). No other treatment during the available follow-up was required in 60.7% (125/206) of the ELD, 39.9% (31/78) of the TLIF, and 19.7% (12/61 of the laminectomy patients. In control patients, only 15 of the 67 (22.4%) control patients continued with conservative care until final follow-up, all of which had fair and poor functional Macnab outcomes. In patients with Excellent Macnab outcomes, the median durability was 62 months in ELD, 43 in TLIF, and 31 months in laminectomy patients (p < 0.001). The overall survival time in control patients was eight months with a standard error of 0.942, a lower boundary of 6.154, and an upper boundary of 9.846 months. In patients with excellent Macnab outcomes, the median durability was 62 months in ELD, 43 in TLIF, and 31 months in laminectomy patients versus control patients at seven months (p < 0.001). The most common new-onset symptom for censoring was dysesthesia ELD (9.4%; 20/206), axial back pain in TLIF (25.6%;20/78), and recurrent pain in laminectomy (65.6%; 40/61) patients (p < 0.001). Transforaminal epidural steroid injections were tried in 11.7% (24/206) of ELD, 23.1% (18/78) of TLIF, and 36.1% (22/61) of the laminectomy patients. The secondary fusion rate among ELD patients was 8.8% (18/206). Among TLIF patients, the most common additional treatments were revision fusion (19.2%; 15/78) and multilevel rhizotomy (10.3%; 8/78). Common follow-up procedures in laminectomy patients included revision laminectomy (16.4%; 10/61), revision ELD (11.5%; 7/61), and multilevel rhizotomy (11.5%; 7/61). Control patients crossed over into ELD (13.4%), TLIF (13.4%), laminectomy (10.4%) and interventional treatment (40.3%) arms at high rates. Most control patients treated with spinal injections (55.5%) had excellent and good functional outcomes versus 40.7% with fair and poor (3.7%), respectively. The control patients (93.3%) who remained in medical management without surgery or interventional care (14/67) had the worst functional outcomes and were rated as fair and poor. Conclusions: clinical outcomes were more favorable with lumbar surgeries than with non-surgical control groups. Of the control patients, the crossover rate into interventional and surgical care was 40.3% and 37.2%, respectively. There are longer symptom-free intervals after targeted ELD than with TLIF or laminectomy. Additional intervention and surgical treatments are more often needed to manage new-onset postoperative symptoms in TLIF- and laminectomy compared to ELD patients. Few ELD patients will require fusion in the future. Considering the rising cost of surgical spine care, we offer SpineScreen as a simplified and less costly alternative to traditional image-based care models by focusing on primary pain generators rather than image-based criteria derived from the preoperative lumbar MRI scan.

Current development and prospects of deep learning in spine image analysis: a literature review

BACKGROUND AND OBJECTIVE

As the spine is pivotal in the support and protection of human bodies, much attention is given to the understanding of spinal diseases. Quick, accurate, and automatic analysis of a spine image greatly enhances the efficiency with which spine conditions can be diagnosed. Deep learning (DL) is a representative artificial intelligence technology that has made encouraging progress in the last 6 years. However, it is still difficult for clinicians and technicians to fully understand this rapidly evolving field due to the diversity of applications, network structures, and evaluation criteria. This study aimed to provide clinicians and technicians with a comprehensive understanding of the development and prospects of DL spine image analysis by reviewing published literature.

METHODS

A systematic literature search was conducted in the PubMed and Web of Science databases using the keywords "deep learning" and "spine". Date ranges used to conduct the search were from 1 January, 2015 to 20 March, 2021. A total of 79 English articles were reviewed.

KEY CONTENT AND FINDINGS

The DL technology has been applied extensively to the segmentation, detection, diagnosis, and quantitative evaluation of spine images. It uses static or dynamic image information, as well as local or non-local information. The high accuracy of analysis is comparable to that achieved manually by doctors. However, further exploration is needed in terms of data sharing, functional information, and network interpretability.

CONCLUSIONS

The DL technique is a powerful method for spine image analysis. We believe that, with the joint efforts of researchers and clinicians, intelligent, interpretable, and reliable DL spine analysis methods will be widely applied in clinical practice in the future.

Artificial Intelligence and Computer Aided Diagnosis in Chronic Low Back Pain: A Systematic Review

Low Back Pain (LBP) is currently the first cause of disability in the world, with a significant socioeconomic burden. Diagnosis and treatment of LBP often involve a multidisciplinary, individualized approach consisting of several outcome measures and imaging data along with emerging technologies. The increased amount of data generated in this process has led to the development of methods related to artificial intelligence (AI), and to computer-aided diagnosis (CAD) in particular, which aim to assist and improve the diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of CAD in the diagnosis and treatment of chronic LBP. A systematic research of PubMed, Scopus, and Web of Science electronic databases was performed. The search strategy was set as the combinations of the following keywords: “Artificial Intelligence”, “Machine Learning”, “Deep Learning”, “Neural Network”, “Computer Aided Diagnosis”, “Low Back Pain”, “Lumbar”, “Intervertebral Disc Degeneration”, “Spine Surgery”, etc. The search returned a total of 1536 articles. After duplication removal and evaluation of the abstracts, 1386 were excluded, whereas 93 papers were excluded after full-text examination, taking the number of eligible articles to 57. The main applications of CAD in LBP included classification and regression. Classification is used to identify or categorize a disease, whereas regression is used to produce a numerical output as a quantitative evaluation of some measure. The best performing systems were developed to diagnose degenerative changes of the spine from imaging data, with average accuracy rates >80%. However, notable outcomes were also reported for CAD tools executing different tasks including analysis of clinical, biomechanical, electrophysiological, and functional imaging data. Further studies are needed to better define the role of CAD in LBP care.

Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI

OBJECTIVES

To compare interobserver agreement and image quality of 3D T2-weighted fast spin echo (T2w-FSE) L-spine MRI images processed with a deep learning reconstruction (DLRecon) against standard-of-care (SOC) reconstruction, as well as against 2D T2w-FSE images. The hypothesis was that DLRecon 3D T2w-FSE would afford improved image quality and similar interobserver agreement compared to both SOC 3D and 2D T2w-FSE.

METHODS

Under IRB approval, patients who underwent routine 3-T lumbar spine (L-spine) MRI from August 17 to September 17, 2020, with both isotropic 3D and 2D T2w-FSE sequences, were retrospectively included. A DLRecon algorithm, with denoising and sharpening properties was applied to SOC 3D k-space to generate 3D DLRecon images. Four musculoskeletal radiologists blinded to reconstruction status evaluated randomized images for motion artifact, image quality, central/foraminal stenosis, disc degeneration, annular fissure, disc herniation, and presence of facet joint cysts. Inter-rater agreement for each graded variable was evaluated using Conger's kappa (κ).

RESULTS

Thirty-five patients (mean age 58 ± 19, 26 female) were evaluated. 3D DLRecon demonstrated statistically significant higher median image quality score (2.0/2) when compared to SOC 3D (1.0/2, p < 0.001), 2D axial (1.0/2, p < 0.001), and 2D sagittal sequences (1.0/2, p value < 0.001). κ ranges (and 95% CI) for foraminal stenosis were 0.55-0.76 (0.32-0.86) for 3D DLRecon, 0.56-0.73 (0.35-0.84) for SOC 3D, and 0.58-0.71 (0.33-0.84) for 2D. Mean κ (and 95% CI) for central stenosis at L4-5 were 0.98 (0.96-0.99), 0.97 (0.95-0.99), and 0.98 (0.96-0.99) for 3D DLRecon, 3D SOC and 2D, respectively.

CONCLUSIONS

DLRecon 3D T2w-FSE L-spine MRI demonstrated higher image quality and similar interobserver agreement for graded variables of interest when compared to 3D SOC and 2D imaging.

KEY POINTS

• 3D DLRecon T2w-FSE isotropic lumbar spine MRI provides improved image quality when compared to 2D MRI, with similar interobserver agreement for clinical evaluation of pathology. • 3D DLRecon images demonstrated better image quality score (2.0/2) when compared to standard-of-care (SOC) 3D (1.0/2), p value < 0.001; 2D axial (1.0/2), p value < 0.001; and 2D sagittal sequences (1.0/2), p value < 0.001. • Interobserver agreement for major variables of interest was similar among all sequences and reconstruction types. For foraminal stenosis, κ ranged from 0.55 to 0.76 (95% CI 0.32-0.86) for 3D DLRecon, 0.56-0.73 (95% CI 0.35-0.84) for standard-of-care (SOC) 3D, and 0.58-0.71 (95% CI 0.33-0.84) for 2D.

Novel Magnetic Resonance Imaging Tools for the Diagnosis of Degenerative Disc Disease: A Narrative Review

Low back pain (LBP) is one of the leading causes of disability worldwide, with a significant socioeconomic burden on healthcare systems. It is mainly caused by degenerative disc disease (DDD), a progressive, chronic, and age-related process. With its capacity to accurately characterize intervertebral disc (IVD) and spinal morphology, magnetic resonance imaging (MRI) has been established as one of the most valuable tools in diagnosing DDD. However, existing technology cannot detect subtle changes in IVD tissue composition and cell metabolism. In this review, we summarized the state of the art regarding innovative quantitative MRI modalities that have shown the capacity to discriminate and quantify changes in matrix composition and integrity, as well as biomechanical changes in the early stages of DDD. Validation and implementation of this new technology in the clinical setting will allow for an early diagnosis of DDD and ideally guide conservative and regenerative treatments that may prevent the progression of the degenerative process rather than intervene at the latest stages of the disease.

Whole-body Composition Profiling Using a Deep Learning Algorithm: Influence of Different Acquisition Parameters on Algorithm Performance and Robustness

OBJECTIVES

To develop, test, and validate a body composition profiling algorithm for automated segmentation of body compartments in whole-body magnetic resonance imaging (wbMRI) and to investigate the influence of different acquisition parameters on performance and robustness.

MATERIALS AND METHODS

A segmentation algorithm for subcutaneous and visceral adipose tissue (SCAT and VAT) and total muscle mass (TMM) was designed using a deep learning U-net architecture convolutional neuronal network. Twenty clinical wbMRI scans were manually segmented and used as training, validation, and test datasets. Segmentation performance was then tested on different data, including different magnetic resonance imaging protocols and scanners with and without use of contrast media. Test-retest reliability on 2 consecutive scans of 16 healthy volunteers each as well as impact of parameters slice thickness, matrix resolution, and different coil settings were investigated. Sorensen-Dice coefficient (DSC) was used to measure the algorithms' performance with manual segmentations as reference standards. Test-retest reliability and parameter effects were investigated comparing respective compartment volumes. Abdominal volumes were compared with published normative values.

RESULTS

Algorithm performance measured by DSC was 0.93 (SCAT) to 0.77 (VAT) using the test dataset. Dependent from the respective compartment, similar or slightly reduced performance was seen for other scanners and scan protocols (DSC ranging from 0.69-0.72 for VAT to 0.83-0.91 for SCAT). No significant differences in body composition profiling was seen on repetitive volunteer scans (P = 0.88-1) or after variation of protocol parameters (P = 0.07-1).

CONCLUSIONS

Body composition profiling from wbMRI by using a deep learning-based convolutional neuronal network algorithm for automated segmentation of body compartments is generally possible. First results indicate that robust and reproducible segmentations equally accurate to a manual expert may be expected also for a range of different acquisition parameters.

AI MSK clinical applications: spine imaging

Recent investigations have focused on the clinical application of artificial intelligence (AI) for tasks specifically addressing the musculoskeletal imaging routine. Several AI applications have been dedicated to optimizing the radiology value chain in spine imaging, independent from modality or specific application. This review aims to summarize the status quo and future perspective regarding utilization of AI for spine imaging. First, the basics of AI concepts are clarified. Second, the different tasks and use cases for AI applications in spine imaging are discussed and illustrated by examples. Finally, the authors of this review present their personal perception of AI in daily imaging and discuss future chances and challenges that come along with AI-based solutions.

A deep learning model for detection of cervical spinal cord compression in MRI scans

Magnetic Resonance Imaging (MRI) evidence of spinal cord compression plays a central role in the diagnosis of degenerative cervical myelopathy (DCM). There is growing recognition that deep learning models may assist in addressing the increasing volume of medical imaging data and provide initial interpretation of images gathered in a primary-care setting. We aimed to develop and validate a deep learning model for detection of cervical spinal cord compression in MRI scans. Patients undergoing surgery for DCM as a part of the AO Spine CSM-NA or CSM-I prospective cohort studies were included in our study. Patients were divided into a training/validation or holdout dataset. Images were labelled by two specialist physicians. We trained a deep convolutional neural network using images from the training/validation dataset and assessed model performance on the holdout dataset. The training/validation cohort included 201 patients with 6588 images and the holdout dataset included 88 patients with 2991 images. On the holdout dataset the deep learning model achieved an overall AUC of 0.94, sensitivity of 0.88, specificity of 0.89, and f1-score of 0.82. This model could improve the efficiency and objectivity of the interpretation of cervical spine MRI scans.

The Clinical Diagnostic Value of Lumbar Intervertebral Disc Herniation Based on MRI Images

MRI was used to measure the changes in the angle of the facet joints of the lumbar spine and analyze the relationship between it and the herniated lumbar intervertebral disc. Analysis of the causes of lumbar disc herniation from the anatomy and morphology of the spine provides a basis for the early diagnosis and prevention of lumbar disc herniation. There is a certain correlation between the changes shown in MRI imaging of lumbar disc herniation and the TCM syndromes of lumbar intervertebral disc herniation. There is a correlation between the syndromes of lumbar disc herniation and the direct signs of MRI: pathological type, herniated position, and degree of herniation. Indirect signs with MR, nerve root compression and dural sac compression, are related. The MRI examination results can help syndrome differentiation to improve its accuracy to a certain extent. MRI has high sensitivity for the measurement of the angle of the facet joints of the lumbar spine and can be used to study the correlation between the changes of the facet joint angles and the herniated disc. Facet joint asymmetry is closely related to lateral lumbar disc herniation, which may be one of its pathogenesis factors. The herniated intervertebral disc is mostly on the sagittal side of the facet joint, and the facet joint angle on the side of the herniated disc is more sagittal. The asymmetry of the facet joints is not related to the central lumbar disc herniation, and the angle of the facet joints on both sides of the central lumbar disc herniation is partial sagittal.