Automatic semantic segmentation of the lumbar spine: Clinical applicability in a multi-parametric and multi-center study on magnetic resonance images

Saenz-Gamboa, Jhon Jairo; Doménech, Julio; Alonso-Manjarrés, Antonio; Gómez, Jon Ander; Vayá, María de la Iglesia

doi:10.1016/j.artmed.2023.102559

Cited by 10 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results thus support the findings of [19] regarding HarDNet MSEG generalization and accuracy with sparse training data. The pipeline described here achieves comparable or superior results to those shown in [46,52,56] while requiring less data-a benefit to segmentation applications beyond the current study. The improved performance partly results from extending the original network architecture by providing a modified network that reads MR input layers and predicts several output tissues at once.…”

Section: Machine Learning For Image Processingmentioning

confidence: 57%

“…In addition to speed, automated labeling tools promise a degree of objectivity by relying less on the 'art' of the human expert. Significant efforts have already established the broad utility of machine learning (ML) techniques in the field of medical imaging [30], and specifically the application of convolutional neural networks (CNNs) for spinal MR data segmentation [16,27,52]. In general, the robustness and quality of network predictions depend sensitively on the quality, resolution and quantity of available training data, making the acquisition of sufficient applicationspecific data an important bottleneck.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel CNN-based image segmentation pipeline for individualized feline spinal cord stimulation modeling

Fasse,

Newton,

Liang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Spinal cord stimulation (SCS) is a well-established treatment for the management of certain chronic pain conditions. More recently, it has also garnered attention as a means of modulating neural activity with the goal of restoring lost autonomic or sensory-motor function. Personalized modeling and treatment planning are critical aspects of safe and effective SCS [46, 60]. However, the generation of spine models at the required level of detail and accuracy requires time and labor intensive manual image segmentation by human experts. Hence, there is a need for maximally automated segmentation routines capable of producing high-quality anatomical models that can be used even in cases where available data is limited. To this end, we developed an automated image segmentation and model generation pipeline based on a novel Convolutional Neural Network (CNN) architecture trained on feline spinal cord magnetic resonance imaging (MRI) data. The pipeline includes steps for image preprocessing, data augmentation, transfer learning and cleanup. To assess the relative importance of each step in the pipeline and of our choice of CNN architecture, we systematically dropped steps or substituted architectures, quantifying the downstream effects in terms of tissue segmentation quality (Jaccard index and Hausdorff distance) and predicted nerve recruitment (estimated axonal depolarization). This leaveone-out analysis demonstrated that each pipeline step contributed a small but measurable increment to mean segmentation quality. Surprisingly, minor differences in segmentation accuracy translated to significant deviations (ranging between 4% and 13% for each pipeline step) in predicted nerve recruitment, highlighting the importance of careful workflow design. To our knowledge, this is the first analysis to also assess the downstream impact of segmentation quality differences on neurostimulation predictions. Furthermore, transfer learning techniques enhanced segmentation metric consistency and allowed generalization to a completely different spine region with minimal additional training data. This work helps pave the way towards fully automated, personalized SCS treatment planning in clinical settings.

show abstract

Section: Machine Learning For Image Processingmentioning

confidence: 57%

Section: Introductionmentioning

confidence: 99%

A novel CNN-based image segmentation pipeline for individualized feline spinal cord stimulation modeling

Fasse,

Newton,

Liang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…By leveraging deep learning algorithms 6 , 7 , computer vision technology can effectively identify and localize target objects in images or videos. This technology has been widely applied in various detection tasks, such as industrial inspection 8 , face detection 9 , pedestrian detection 10 , vehicle detection 11 , medical detection 12 , and human action recognition 13 , achieving good results.…”

Section: Introductionmentioning

confidence: 99%

Post-secondary classroom teaching quality evaluation using small object detection model

Wang,

Chen,

Tian

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The classroom video has a complex background and dense targets. This study utilizes small object detection technology to analyze and evaluate students’ behavior in the classroom, aiming to objectively and accurately assess classroom quality. Firstly, noise is removed from the images using a median filter, and the contrast of the images is enhanced through histogram equalization. Label smoothing is applied to reduce the model’s sensitivity to labels. Then, features are extracted from the preprocessed images, and multi-scale feature fusion is employed to enhance semantic expression across multiple scales. Finally, a combination loss function is utilized to improve the accuracy of multi-object recognition tasks. Real-time detection of students’ behaviors in the classroom is performed based on the small object detection model. The average head-up rate in the classroom is calculated, and the quality of teaching is evaluated and analyzed. This study explores the methods and applications of small object detection technology based on actual teaching cases and analyzes and evaluates its effectiveness in evaluating the quality of higher education classroom teaching. The research findings demonstrate the significant importance of small object detection technology in effectively evaluating students’ learning conditions in higher education classrooms, leading to improved teaching quality and personalized education.

show abstract

Neural network segmentation of disc volume from magnetic resonance images and the effect of degeneration and spinal level

Markhali,

Peloquin,

Meadows

et al. 2024

JOR Spine

View full text Add to dashboard Cite

BackgroundMagnetic resonance imaging (MRI) noninvasively quantifies disc structure but requires segmentation that is both time intensive and susceptible to human error. Recent advances in neural networks can improve on manual segmentation. The aim of this study was to establish a method for automatic slice‐wise segmentation of 3D disc volumes from subjects with a wide range of age and degrees of disc degeneration. A U‐Net convolutional neural network was trained to segment 3D T1‐weighted spine MRI.MethodsLumbar spine MRIs were acquired from 43 subjects (23–83 years old) and manually segmented. A U‐Net architecture was trained using the TensorFlow framework. Two rounds of model tuning were performed. The performance of the model was measured using a validation set that did not cross over from the training set. The model version with the best Dice similarity coefficient (DSC) was selected in each tuning round. After model development was complete and a final U‐Net model was selected, performance of this model was compared between disc levels and degeneration grades.ResultsPerformance of the final model was equivalent to manual segmentation, with a mean DSC = 0.935 ± 0.014 for degeneration grades I–IV. Neither the manual segmentation nor the U‐Net model performed as well for grade V disc segmentation. Compared with the baseline model at the beginning of round 1, the best model had fewer filters/parameters (75%), was trained using only slices with at least one disc‐labeled pixel, applied contrast stretching to its input images, and used a greater dropout rate.ConclusionThis study successfully trained a U‐Net model for automatic slice‐wise segmentation of 3D disc volumes from populations with a wide range of ages and disc degeneration. The final trained model is available to support scientific use.

show abstract

Automatic semantic segmentation of the lumbar spine: Clinical applicability in a multi-parametric and multi-center study on magnetic resonance images

Cited by 10 publications

References 53 publications

A novel CNN-based image segmentation pipeline for individualized feline spinal cord stimulation modeling

A novel CNN-based image segmentation pipeline for individualized feline spinal cord stimulation modeling

Post-secondary classroom teaching quality evaluation using small object detection model

Neural network segmentation of disc volume from magnetic resonance images and the effect of degeneration and spinal level

Contact Info

Product

Resources

About