Defect Shape Research Articles

A Study on the Effects of Offset and Welding Speed on Bead Shape and Welding Defects in the FCA Fillet Welding Process

Many industries, such as automobile, aerospace, heavy industries, etc, have been interested in welding automation due to cost reduction and improving productivity. For welding automation, seam tracking plays an important role for the quality of welds. If the seam is misaligned, it can cause troubles such as weld defects and poor appearance. Most of previous studies have analyzed the influence on the bead shape and weld defects by current, voltage, welding speed, but there is lack of research regarding the effects of misaligned seam, called offset. Thus, in this study, fillet welds were conducted with flux-cored arc welding, which has high welding efficiency and low cost. To find out the guideline of offset, various offsets were intentionally applied to the welding experiments, and the changes in bead shape were observed and weld defects were detected for various combination of offset and welding speed. In addition, the grades of weld defect in each condition were evaluated by ISO 5817, which illustrates the international standard of weld defects. Based on the results, the guidelines of offset was suggested to avoid weld defects.

D2-SPDM: Faster R-CNN-Based Defect Detection and Surface Pixel Defect Mapping with Label Enhancement in Steel Manufacturing Processes

The steel manufacturing process is inherently continuous, meaning that if defects are not effectively detected in the initial stages, they may propagate through subsequent stages, resulting in high costs for corrections in the final product. Therefore, detecting surface defects and obtaining segmentation information is critical in the steel manufacturing industry to ensure product quality and enhance production efficiency. Specifically, segmentation information is essential for accurately understanding the shape and extent of defects, providing the necessary details for subsequent processes to address these defects. However, the time-consuming and costly process of generating segmentation annotations poses a significant barrier to practical industrial applications. This paper proposes a cost-efficient segmentation labeling framework that combines deep learning-based anomaly detection and label enhancement to address these challenges in the steel manufacturing process. Using ResNet-50, defects are classified, and faster region convolutional neural networks (faster R-CNNs) are employed to identify defect types and generate bounding boxes indicating the defect locations. Subsequently, recursive learning is performed using the GrabCut algorithm and the DeepLabv3+ model based on the generated bounding boxes, significantly reducing annotation costs by generating segmentation labels. The proposed framework effectively detects defects and accurately defines them, even in randomly collected images from the steel manufacturing process, contributing to both quality control and cost reduction. This study presents a novel approach for improving the quality of the steel manufacturing process and is expected to enhance overall efficiency in the steel manufacturing industry.

A Candy Defect Detection Method Based on StyleGAN2 and Improved YOLOv7 for Imbalanced Data.

Quality management in the candy industry is a vital part of food quality management. Defective candies significantly affect subsequent packaging and consumption, impacting the efficiency of candy manufacturers and the consumer experience. However, challenges exist in candy defect detection on food production lines due to the small size of the targets and defects, as well as the difficulty of batch sampling defects from automated production lines. A high-precision candy defect detection method based on deep learning is proposed in this paper. Initially, pseudo-defective candy images are generated based on Style Generative Adversarial Network-v2 (StyleGAN2), thereby enhancing the authenticity of these synthetic defect images. Following the separation of the background based on the color characteristics of the defective candies on the conveyor belt, a GAN is utilized for negative sample data enhancement. This effectively reduces the impact of data imbalance between complete and defective candies on the model's detection performance. Secondly, considering the challenges brought by the small size and random shape of candy defects to target detection, the efficient target detection method YOLOv7 is improved. The Spatial Pyramid Pooling Fast Cross Stage Partial Connection (SPPFCSPC) module, the C3C2 module, and the global attention mechanism are introduced to enhance feature extraction precision. The improved model achieves a 3.0% increase in recognition accuracy and a 3.7% increase in recall rate while supporting real-time recognition scenery. This method not only enhances the efficiency of food quality management but also promotes the application of computer vision and deep learning in industrial production.

Research on tire appearance defect detection algorithm based on efficient multi-scale convolution

Abstract Due to the large randomness of tire appearance defect size and the complex and diverse defect shapes, the existing target detection algorithm is prone to missing and misidentifying targets, the accuracy is limited, and the detection model is large, which is not conducive to deployment on embedded devices. In this paper, the efficient multi-scale convolution (EMC) mode is proposed, and the C2f-EMC module is designed on this basis, which improves the network structure of YOLOv8, improves the accuracy of tire appearance defect detection, and reduces the number of parameters in the model. EMC convolution first divides the input feature images into four parts on average and carries out multi-scale convolution with convolution cores of 1×1, 3×3, 5×5 and 7×7 sizes respectively. Then, the obtained results are stacked, and cross-channel feature fusion is realized by point-by-point convolution. After determining the network structure of C2f-EMC, the best improvement position of C2f-EMC module is determined through comparative experiments. Experiments show that after the above improvements, the parameter number of the model is reduced by 4.85%, the calculation amount by 2.82%, the model size by 4.44%, the recall rate by 2.8%, the mAP50 by 1.0%, the mAP50-95 by 1.3%, and the F1 by 2%. The defect detection task can be completed more accurately and the model size requirements of embedded devices can be better met.

Theoretical Study of Asymmetric Bending Force on Metal Deformation in Cold Rolling

A three-dimensional elastic–plastic finite element model of a six-roll cold rolling mill has been developed using the finite element software ABAQUS. The actual parameters of the rolling mill have been incorporated into the finite element model, with the working conditions applied as boundary constraints and load conditions. Subsequently, a non-symmetrical bending force is introduced to the finite element model. Through simulation calculations, this study analyzes the patterns of change in the transverse pressure of the rolling mill and roller pressure during non-symmetrical bending, as well as the variations in strip thickness, crown, edge drop, and flatness. Additionally, the regulating function of the bending force is examined. Each adjustment of 5 t in the asymmetric bending force results in an increase of approximately 0.01 mm in the thickness of the positive bending side of the strip while causing a decrease of about 0.01 mm in the thickness of the negative bending side. Therefore, the application of asymmetric bending forces proves to be effective in controlling the shape of lateral wave defects on the edges of steel strips.

Fatigue properties of a Ti–5Al–5Mo-5 V–3Cr alloy manufactured by electron beam powder bed fusion

AbstractAdditive manufacturing (AM) is a modern way of manufacturing structures, which tends to have fewer design limitations than those manufactured by conventional processes such as casting or forging. A combination of high-strength materials and small and complex structures opens up a wide range of potential applications, especially in the fields of medicine and aerospace. Titanium and its alloys show a very beneficial combination of density and mechanical properties. One of these alloys is the metastable β titanium alloy Ti– 5Al–5Mo–5 V–3Cr (Ti-5553), which is currently used mainly for large forged structures like landing gears of airplanes. In this study, for the first time the fatigue behavior of electron beam powder bed fused (PBF-EB) Ti-5553 was investigated with a focus on the defects created by the layer wise manufacturing. To understand the defect structure and its respective influence on the fatigue behavior, all specimens were scanned prior to fatigue testing using a state-of-the-art µ-focus CT. The specimens were subjected to two heat treatment procedures commonly used in technical applications, which were aiming for high strength (solution treated and aged—STA) as well as high ductility (beta annealed, slow cooled and aged—BASCA). Results indicate that the fatigue strength of PBF-EB manufactured Ti-5553 is significantly reduced compared to conventionally manufactured Ti-5553. The main reason for this are defects, which have varying critical effects depending on the heat treatment of the specimen and the defect size, shape, location and type.

A prior knowledge-embedded deformable convolutional network for vision-based fabric defect detection

The vision-based defect detection of textile surface is an essential problem in evaluating the appearance quality. In previous studies on vision-based defect detection, the following two points were neglected: (1) The proportion of defects on fabric is small, resulting in a low signal-to-noise ratio of defect images and a lack of sampling features; (2) the irregular shape of defects can overlap in position, leading to localization difficulty. In this paper, we propose a prior knowledge-embedded deformable convolutional network (PKE-DCNet) based on deep learning to address these two issues. First, a feature extraction method with prior information is designed with a shape-matching deep clustering module and a region-biased sampling module for detecting defects with complex shape. Then, a defect boundary boxes adaptive generation method is proposed with an anchor-free search mechanism and irregular edge contour computation to detect the key points in the region. Extensive experiments with mixed fabric defect datasets demonstrated that PKE-DCNet reached an overall mAP of 95.36% for six types of defects within a detection speed of 322 FPS, which was better than state-of-the-art methods.

Ultrasonic characterization of defects in polycrystalline materials based on TFM image reconstruction using denoising diffusion probabilistic models

This paper presents a refined ultrasonic total focusing method (TFM) for accurately characterizing key defect parameters including size, orientation, and location in complex materials. The proposed approach aims to accurately reconstruct the defect shape in images compromised by grain interference. First, a TFM image database was generated with varying defect parameters and grain noise levels by adopting a custom forward modeling process based on superposition of defect and grain scattering data. Second, a new architecture called TFM-DDPM was then proposed which incorporates TFM and the conditional denoising diffusion probabilistic model (DDPM). Third, pixel-level uncertainty can be quantified through repeated sampling of noise which follows a standard normal distribution. An acceptance criterion for the reconstruction was further established by analyzing the quantified uncertainty. In simulation, the median Dice coefficient between the de-noised TFMs of 30° cracks and their corresponding ground truth images increased from 0.5585 to 0.9137 using the proposed approach, and the median IoU metric rose from 0.3875 to 0.8408. By applying the 6-dB drop approach to the reconstructed images, the root mean squared errors (RMSEs) of size, angle and location were decreased by 93.59%, 86.90% and 86.25%, respectively. It is also demonstrated that our method can reject 69.19% of incorrect characterization results caused by high levels of noise and/or images with steeply inclined (e.g., 45°) cracks, while accepting 97.29% accurate results. Experimental results obtained on nickel-based alloy K403 specimens also exhibited significant improvements. For 2–3 mm cracks, the average sizing error reduced from 0.46 mm to 0.13 mm, and the error in crack angle decreased from 28.63° to 1.50°. Comparable performance enhancements were observed for 4–5 mm cracks using the proposed approach.

Improved YOLOv5s Fabric Defect Detection Algorithm Based on the Fusion of Global Attention Mechanism and Decoupling Head

During fabric production, machine malfunctions and yarn breakages can lead to defects, affecting product quality. Thus, fabric defect detection is crucial for quality control. Existing detection systems struggle with speed and accuracy, especially for small defects, due to the diversity of defect types and shapes. This paper introduces an improved YOLOv5s algorithm, YOLOv5s-GSD, which enhances detection performance by integrating a Global Attention Mechanism (GAM), the SIOU loss function, and a decoupling head. The GAM enhances focus on relevant features, improving detection accuracy; the SIOU loss function replaces the GIOU loss function to optimize the vector angle of regressions, enhancing convergence speed and accuracy; and the decoupling head separates classification and regression tasks, further improving detection performance. Experimental results show the improved algorithm achieves an accuracy of 97.6% and a recognition rate of 36 frames per second, effectively reducing the miss rate of small targets.

Defect characterization from magnetic field leakage signals in petroleum and natural gas pipelines

Pipelines transport invaluable energy resources such as crude oil and natural gas over long distances. The integrity of the piping system in terms of safety of the process is then of high importance. However, pipes are prone by time to defects that may degrade their properties and lead to failures. In this paper, we study the effect of defect parameters on the magnetic field leakage captured by Hall sensors operating along the pipe. In fact, the obtained results show that the defect parameters influence directly the MFL amplitude and shape. For this reason, the inversion problem allowing us to reconstruct the defect from the MFL signals became fast and easier in comparison to the deterministic and probabilistic algorithm inversion procedure. However, the simplified system cannot describe the real defects and the three-dimensional numerical study became necessary. In tank floor inspection domain, as our recent published work, we have studied the performance of defect shape reconstruction from MFL array sensor imaging and depth estimation while using an iterative inversion method. Indeed, the first stage consists of determining the defect width and length from magnetic flux leakage mapping reconstructed from the recorded signals of the micro-integrated magnetic sensors. Then, after coupling Comsol and Matlab software, the defect depth is obtained by coupling the 3D finite elements method and a fast iterative algorithm recently developed. Consequently, the defect shape and size are obtained after a few iterations with high precision. Furthermore, this method of defect reconstruction and seizing can be extended for irregular defect shapes encountered in pipeline such as cracks and corrosion.

Developing flaw sizing methodology in Total Focusing Method (TFM) by EDM calibration blocks

The Total Focusing Method (TFM) represents a significant advancement in ultrasonic inspection, delivering high-resolution imaging by leveraging phased array technology combined with sophisticated data processing algorithms. This synergy enables detailed visualization of flaws in various materials, thereby improving flaw detection and characterization. Despite TFM's capabilities, the lack of a standardized methodology for flaw sizing limits its potential for flaw evaluation. This paper seeks to establish a new paradigm in flaw sizing by introducing a custom methodology specifically designed for TFM, using electrical discharge machined (EDM) calibration blocks that reflect a range of flaw shapes. The research highlights the limitations of conventional side-drilled holes (SDH) for capturing realistic flaw nuances and emphasizes the superior ability of EDM notches to simulate the complex geometries inherent in typical flaws. By investigating the influence of different TFM modes, the study provides insight into their effectiveness in improving the accuracy of flaw characterization. Our approach addresses the challenges of existing TFM practices, with EDM notches serving as an essential tool in methodological advancement. This work contributes to the continued development of best practices in TFM application, paving the way for more accurate, reliable, and versatile nondestructive testing.

Discrete element simulation of ground collapse induced by buried sewage pipeline breakage and soil leakage

The rupture of buried sewage pipelines constitutes a primary triggering factor of ground collapse. To investigate the phenomenon of ground collapse resulting from buried sewage pipeline breakage and soil particle leakage, numerical simulations employing the discrete element method (DEM) are utilized. The study focuses on examining the ground collapse mechanisms in both dry and water-rich sand stratum scenarios. A positive correlation is identified between the particle loss rate (PLR) and the magnitude of ground collapse, and a microscopic analysis of the mechanism of particle loss is carried out to visualize the soil arching process. The entire collapse process shows that the formation and destruction of soil arching are clearly accompanied by the particle loss phenomena. Additionally, the computational fluid dynamics (CFD) module is incorporated into the DEM to investigate the collapse of water-rich sand stratum. Parametric studies involving the burial depth of the pipeline, water pressure, the defect radius of the pipeline breakage, and the defect shapes are comprehensively conducted. It is found that the water pressure is the primary factor influencing the PLR, which progressively increases with higher water pressure, larger radius of pipe defect, and shallower burial depth.

OpgH is an essential regulator of Caulobacter morphology.

Bacterial growth and division rely on intricate regulation of morphogenetic complexes to remodel the cell envelope without compromising envelope integrity. Significant progress has been made in recent years towards understanding the regulation of cell wall metabolic enzymes. However, other cell envelope components play a role in morphogenesis as well. A primary factor required to protect envelope integrity in low osmolarity environments is OpgH, the synthase of osmoregulated periplasmic glucans (OPGs). Here, we demonstrate that OpgH is essential in the α-proteobacterium Caulobacter crescentus. Unexpectedly, depletion of OpgH or attempted complementation with a catalytically dead OpgH variant results in striking asymmetric bulging and cell lysis. These shape defects are accompanied by reduced cell wall synthesis and mislocalization of morphogenetic complexes. Interestingly, overactivation of the CenKR two-component system that has been implicated in cell envelope stress homeostasis in α-proteobacteria phenocopies the morphogenetic defects associated with OpgH depletion. Each of these perturbations leads to an increase in the levels of the elongasome protein, MreB, and decreases in the levels of divisome proteins FtsZ and MipZ as well as OpgH, itself. Constitutive production of OpgH during CenKR overactivation prevents cell bulging, but cells still exhibit morphogenetic defects. We propose that OPG depletion activates CenKR, leading to changes in the expression of cell envelope-related genes, but that OPGs also exert CenKR-independent effects on morphogenesis. Our data establish a surprising function for an OpgH homolog in morphogenesis and reveal an essential role of OpgH in maintaining cell morphology in Caulobacter.IMPORTANCEBacteria must synthesize and fortify the cell envelope in a tightly regulated manner to orchestrate growth and adaptation. Osmoregulated periplasmic glucans (OPGs) are important, but poorly understood, constituents of Gram-negative cell envelopes that contribute to envelope integrity and protect against osmotic stress. Here, we determined that the OPG synthase OpgH plays a surprising, essential role in morphogenesis in Caulobacter crescentus. Loss of OpgH causes asymmetric cell bulging and lysis via misregulation of the localization and activity of morphogenetic complexes. Overactivation of the CenKR two-component system involved in envelope homeostasis phenocopies OpgH depletion, suggesting that depletion of OpgH activates CenKR. Because cell envelope integrity is critical for bacterial survival, understanding how OpgH activity contributes to morphogenesis and maintenance of envelope integrity could aid in the development of antibiotic therapies.

Effects of size and shape of hole defects on mechanical properties of biphenylene: a molecular dynamics study

The distinctive multi-ring structure and remarkable electrical characteristics of biphenylene render it a material of considerable interest, notably for its prospective utilization as an anode material in lithium-ion batteries. However, understanding the mechanical traits of biphenylene is essential for its application, particularly due to the volumetric fluctuations resulting from lithium ion insertion and extraction during charging and discharging cycles. In this regard, this study investigates the performance of pristine biphenylene and materials embedded with various types of hole defects under uniaxial tension utilizing molecular dynamics simulations. Specifically, from the stress‒strain curves, we obtained key mechanical properties, including toughness, strength, Young's modulus and fracture strain. It was observed that various near-circular hole (including circular, square, hexagonal, and octagonal) defects result in remarkably similar properties. A more quantitative scaling analysis revealed that, in comparison with the exact shape of the defect, the area of the defect is more critical for determining the mechanical properties of biphenylene. Our finding might be beneficial to the defect engineering of two-dimensional materials.

A Novel End-to-End Deep Learning Framework for Chip Packaging Defect Detection.

As semiconductor chip manufacturing technology advances, chip structures are becoming more complex, leading to an increased likelihood of void defects in the solder layer during packaging. However, identifying void defects in packaged chips remains a significant challenge due to the complex chip background, varying defect sizes and shapes, and blurred boundaries between voids and their surroundings. To address these challenges, we present a deep-learning-based framework for void defect segmentation in chip packaging. The framework consists of two main components: a solder region extraction method and a void defect segmentation network. The solder region extraction method includes a lightweight segmentation network and a rotation correction algorithm that eliminates background noise and accurately captures the solder region of the chip. The void defect segmentation network is designed for efficient and accurate defect segmentation. To cope with the variability of void defect shapes and sizes, we propose a Mamba model-based encoder that uses a visual state space module for multi-scale information extraction. In addition, we propose an interactive dual-stream decoder that uses a feature correlation cross gate module to fuse the streams' features to improve their correlation and produce more accurate void defect segmentation maps. The effectiveness of the framework is evaluated through quantitative and qualitative experiments on our custom X-ray chip dataset. Furthermore, the proposed void defect segmentation framework for chip packaging has been applied to a real factory inspection line, achieving an accuracy of 93.3% in chip qualification.

NIR-Responsive Deployable and Self-Fitting 4D-Printed Bone Tissue Scaffold.

The treatment of irregular-shaped and critical-sized bone defects poses a clinical challenge. Deployable, self-fitting tissue scaffolds that can be implanted by minimally invasive procedures are a promising solution. Toward this, we fabricated NIR-responsive and programmable polylactide-co-trimethylene carbonate (PLMC) scaffolds nanoengineered with polydopamine nanoparticles (PDA) by extrusion-based three-dimensional (3D) printing. The 3D-printed scaffolds demonstrated excellent (>99%), fast (under 30 s), and tunable shape recovery under NIR irradiation. PLMC-PDA composites demonstrated significantly higher osteogenic potential in vitro as revealed by the significantly enhanced alkaline phosphatase (ALP) secretion and mineral deposition in contrast to neat PLMC. Intraoperative deployability and in vivo bone regeneration ability of PLMC-PDA composites were demonstrated, using self-fitting scaffolds in critical-sized cranial bone defects in rabbits. The 3D-printed scaffolds were deformed into compact shapes that could self-fit into the defect shape intraoperatively under low power intensity (0.76 W cm-2) NIR. At 6 and 12 weeks postsurgical implantation, near-complete bone regeneration was observed in PLMC-PDA composites, unlike neat PLMC through microcomputed tomography (micro-CT) analysis. The potential clinical utility of the 3D-printed composites to secure complex defects was confirmed through self-fitting of the scaffolds into irregular defects in ex vivo models of rabbit tibia, mandible, and tooth models. Taken together, the composite scaffolds fabricated here offer an innovative strategy for minimally invasive deployment to fit irregular and complex tissue defects for bone tissue regeneration.

Multi-grooved channel design in continuous casting mold for enhancing heat transfer efficiency considering pressure drop and flow rate loss

An efficient, speedy, multi-grooved (ESMG) mold was designed and manufactured for optimization to address issues such as low heat transfer rate, slow casting speed, and quality defects in traditional continuous casting molds. The flow resistance mechanism of multi-grooved channels with varying parameters was investigated by considering the ESMG geometric model, the convective heat transfer characteristic variation trends were revealed with different channel designs. Considering constraints of the dimensional chain and supply pressure, variation trends and mechanisms of the pressure drop, flow rate loss, and convective heat transfer coefficient of the ESMG mold were explored using multiple channel variables. Based on the numerical model of the ESMG channel, temperature variation trends in the copper mold were verified by comparison with relevant literature data, supporting the convective-heat-transfer model and variation trends of the ESMG mold. A high-efficiency heat-transfer ESMG assembly that casts U71Mn high-carbon large rectangular billets was fabricated, achieving a closed-loop dimensional chain and replacing traditional molds. Experimental validation on the continuous casting machine (CCM) proved directly that redesigning the ESMG mold cooling channel improved heat transfer efficiency and reduced CO2 emissions. After 504 h on the CCM, the ESMG mold casting speed increased from 1.1 to 1.6 m/min, the heat transfer efficiency was 17.6% higher than that of traditional molds and CO2 emissions were estimated to decrease by 31.2%. The billets produced by the ESMG mold had no quality defects in shape or surface with the original casting conditions, which provided enhanced support for accelerating continuous casting lines.

Effect of forming strategies on the microstructure and mechanical properties of thin-walled CuCrZr alloy fabricated by selective laser melting

Thin-walled structures are widely used in industrial fields such as radiators and critical aerospace components due to their advantages in lightweight design. However, traditional manufacturing techniques struggle to meet the high-precision requirements for complex components. Selective Laser Melting (SLM) technology, characterized by high design flexibility and high geometric production freedom, is a promising alternative. This study employs SLM technology to fabricate CuCrZr alloy thin walls and systematically investigates the effects of interlayer rotation angles and placement strategies on the forming quality and mechanical properties of the thin walls produced by SLM. The results indicate that different interlayer rotation angles and placement strategies lead to variations in defect types and shapes. When the interlayer rotation angle is 0° and the specimens are placed perpendicular to the recoater blade, numerous lack-of-fusion (LOF) defects are observed on the specimens. These lack-of-fusion defects are caused by factors such as low scanning line flatness and uneven energy distribution when the interlayer rotation angle is 0°. In contrast to the 0° interlayer rotation angle, the specimens with a 67° rotation angle exhibit significantly more curved columnar grains in the growth direction. The thin-walled specimens with a 67° interlayer rotation angle and placed parallel to the recoater blade show the best mechanical performance, with a maximum tensile strength of 254.19 MPa and an elongation of 48.81 %.

Study on fatigue properties with composite waveform and variable amplitude of TC21 titanium alloy pulsed laser-arc hybrid welded joints

TC21 titanium alloy is widely used in the manufacturing of key components such as aerospace industry, its welded structure in actual service is often subjected to the cyclic loading with composite waveform and variable amplitude and leads to fatigue failure. Therefore, in this work, the composite waveform and variable amplitude fatigue properties of TC21 titanium alloy pulsed laser-arc hybrid welded joints were investigated in this paper, and the micro-deformation mechanism and crack initiation mechanism of welded joints under different initial maximum cyclic stresses were revealed. The results indicated that the micro-deformation mechanism was the competition between twinning and dislocation slip in the α′ phase at low stress. When the initial maximum cyclic stress increased, the generation and slip of dislocation dominated, and the main distribution of dislocations gradually transitioned from the α′ phase to the β phase. This caused the phase transition in the β phase to the α phase, which increased the energy at the α/β phase interface and reduced the resistance of fatigue microcrack initiation accordingly, thus promoting fatigue failure. In addition, pores were the main factor of fatigue failure for welded joints. Therefore, in this work, the influence of defect size, location and shape on the fatigue life of welded joints was considered to develop a fatigue life prediction model based on the control parameter Z-parameter and equivalent stress amplitude. The predicted composite waveform and variable amplitude fatigue life of TC21 titanium alloy welded joints was within the triple error band.

Association between MRI measurements of lumbar spine alterations and self-reported outcomes of pain and disability in subjects with non-specific low back pain.

This study aims to elucidate the association between MRI measurements of spine alterations and self-reported outcomes of pain and disability in individuals with non-specific low back pain, using a comprehensive perspective based on machine learning algorithm. 246 consecutive subjects were assessed. Pain severity in cervical, lumbar, and leg regions was determined using visual analogue scale, and functional disability was acquired by Oswestry Disability Index. Sagittal and axial MRI scans of the thoracolumbar spine were evaluated. Severity of disc degeneration, spinal canal stenosis, and presence of vertebral endplate lesions based on two different classification schemes involving the extent and the shape of defects were quantified at the levels from T12L1 to L5S1. The following parameters describing the lumbar region as a whole were calculated: maximum value along spinal levels, sum of values along levels, number of levels characterized by severe condition. The association with pain and disability was assessed by generalized multiple linear regression modelling. Disc degeneration was identified as a predictor of disability and partially of pain, whereas canal stenosis was found associated with changes in pain in the leg region. Partial correlation values ranged from 0.11 to 0.32. Endplate lesions did not show significant associations. A partial association between MRI measurements and self-reported outcomes of pain and disability was confirmed. Disc degeneration was the most correlated with the reported indexes, while canal stenosis mainly affected the pain levels in the leg region. The presence of endplate lesions did not demonstrate any significant relationships.