Complex Defects Research Articles

Explainable attention-based fused convolutional neural network (XAFCNN) for tire defect detection: an industrial case study

Ensuring tire quality is crucial in the manufacturing industry, particularly for race cars, where defective tires present a significant safety risk. Visual inspection for defects in tires is crucial; however, identifying defects in complex, textured tires has been proven to be a challenging task. This paper tackles this challenge by introducing XAFCNN, an Explainable Attention-based Fused Convolutional Neural Network for tire defect detection. XAFCNN’s novel architecture, including a Special Attention Module (SAM) and custom CNN structure, coupled with Grad-CAM visualization, prevents overfitting, enhances local feature mapping, enables detection of small defects, and proffers valuable insights into the model’s reasoning, enabling confident interpretation of its predictions. The model was trained on a dataset from a leading global tire manufacturer, including 38,710 x-ray images of defective tires and 83,985 defect-free tire images, covering 15 defect types and 50 design patterns. The results demonstrate the model’s exceptional performance compared to literature, achieving a recall rate of 86.85%, a precision of 98.5%, an F1 score of 92.31%, and an overall accuracy of 95.40%. This research, with its substantial dataset and high-performing model, advances automated tire defect detection, satisfying the industry’s need for accurate and reliable inspections, ultimately enhancing human safety.

Controlled Growth of Metal Atom Arrays on Graphdiyne for Seawater Oxidation.

Advanced atomic-level heterointerface engineering provides a promising method for the preparation of next-generation catalysts. Traditional carbon-based heterointerface catalytic performance rely heavily on the undetermined defects in complex and demanding preparation processes, rendering it impossible to control the catalytic performance. Here, we present a general method for the controlled growth of metal atom arrays on graphdiyne (GDY/IrCuOx), and we are surprised to find strong heterointerface strains during the growth. We successfully controlled the thickness of GDY to regulate the heterointerface metal atoms and achieved compressive strain at the interface. Experimental and density functional theory calculation results show that the unique incomplete charge transfer between GDY and metal atoms leads to the formation of strong interactions and significant heterointerface compressive strain between GDY and IrCuOx, which results in high oxidation performances with 1000 mA cm-2 at a low overpotential of 283 mV and long-term stability at large current densities in alkaline simulated seawater. We anticipate that this finding will contribute to construction of high-performance heterogeneous interface structures, leading to the development of new generation of GDY-based heterojunction catalysts in the field of catalysis for future promising performance.

Enhanced performance CdZnTe single crystal with few surface damages via solution based annealing

In this study, heat treatments were employed using a CdCl2 solution as the annealing medium to investigate the evolution of internal defects and photoelectric properties of CdZnTe crystals. It was observed that CdCl2 crystals formed on the surface of the annealed crystals, and their size increased exponentially with prolonged annealing time. It could be a medium for Cl transport. The liquid-phase annealing process was found to be gentle, resulting in minimal damage and the absence of large defects migrating or accumulating dislocations and less nano-defects on the crystal surface than sample annealed in vapor condition. After a 30 hour annealing, the infrared (IR) transmittance reached 55%, and the resistivity increased to 1.36×1010 Ω·cm. The presence of Cd2+ facilitated the filling of Cd vacancies (VCd) defects through diffusion reduction, while the diffusion of Cl- introduced complex defect with extra VCd, causing the Fermi level to approach the center of the band gap. Consequently, a high-resistance CdZnTe material was achieved.

Enhancing manufacturing operations with synthetic data: a systematic framework for data generation, accuracy, and utility

Addressing the challenges of data scarcity and privacy, synthetic data generation offers an innovative solution that advances manufacturing assembly operations and data analytics. Serving as a viable alternative, it enables manufacturers to leverage a broader and more diverse range of machine learning models by incorporating the creation of artificial data points for training and evaluation. Current methods lack generalizable framework for researchers to follow and solve these issues. The development of synthetic data sets, however, can make up for missing samples and enable researchers to understand existing issues within the manufacturing process and create data-driven tools for reducing manufacturing costs. This paper systematically reviews both discrete and continuous manufacturing process data types with their applicable synthetic generation techniques. The proposed framework entails four main stages: Data collection, pre-processing, synthetic data generation, and evaluation. To validate the framework’s efficacy, a case study leveraging synthetic data enabled an exploration of complex defect classification challenges in the packaging process. The results show enhanced prediction accuracy and provide a detailed comparative analysis of various synthetic data strategies. This paper concludes by highlighting our framework’s transformative potential for researchers, educators, and practitioners and provides scalable guidance to solve the data challenges in the current manufacturing sector.

A xonotlite nanofiber bioactive 3D-printed hydrogel scaffold based on osteo-/angiogenesis and osteoimmune microenvironment remodeling accelerates vascularized bone regeneration

BackgroundCoordination between osteo-/angiogenesis and the osteoimmune microenvironment is essential for effective bone repair with biomaterials. As a highly personalized and precise biomaterial suitable for repairing complex bone defects in clinical practice, it is essential to endow 3D-printed scaffold the above key capabilities.ResultsHerein, by introducing xonotlite nanofiber (Ca6(Si6O17) (OH)2, CS) into the 3D-printed silk fibroin/gelatin basal scaffold, a novel bone repair system named SGC was fabricated. It was noted that the incorporation of CS could greatly enhance the chemical and mechanical properties of the scaffold to match the needs of bone regeneration. Besides, benefiting from the addition of CS, SGC scaffolds could accelerate osteo-/angiogenic differentiation of bone mesenchymal stem cells (BMSCs) and meanwhile reprogram macrophages to establish a favorable osteoimmune microenvironment. In vivo experiments further demonstrated that SGC scaffolds could efficiently stimulate bone repair and create a regeneration-friendly osteoimmune microenvironment. Mechanistically, we discovered that SGC scaffolds may achieve immune reprogramming in macrophages through a decrease in the expression of Smad6 and Smad7, both of which participate in the transforming growth factor-β (TGF-β) signaling pathway.ConclusionOverall, this study demonstrated the clinical potential of the SGC scaffold due to its favorable pro-osteo-/angiogenic and osteoimmunomodulatory properties. In addition, it is a promising strategy to develop novel bone repair biomaterials by taking osteoinduction and osteoimmune microenvironment remodeling functions into account.Graphical

(196) Reconstruction of Complex Midline Septal Corporal Defect in a Distal Crossover Penile Implant Cylinder: A Step-by-step Demonstration of Surgical Technique

Abstract Introduction Inflatable penile prosthesis (IPP) placement is a common and effective treatment for erectile dysfunction. Around 20,000 procedures are performed annually. Complications can arise after the procedure, with non-infectious complications occurring in approximately 4% of cases. One rare non-infectious complication is complete cylinder crossover, which can happen due to variable windows in the corporal septum. Objective This case report presents a complex distal septal defect caused by distal cylinder crossover and its repair using Tutoplast graft. Methods The patient, a 59-year-old African American male, had a history of prostate cancer and underwent robotic-assisted laparoscopic prostatectomy in 2018. He received an IPP in September 2020. In 2022, the patient experienced painful leftward penile curvature during erections and incomplete deflation of the penile prosthesis. A physical examination revealed crossover of the right prosthesis cylinder to the left. After a thorough discussion of the risks and benefits, the patient opted for surgical revision and reconstruction of the penile prosthesis. The procedure involved a right corporotomy, septal corporal reconstruction using a 5 × 2 cm Tutoplast graft, and redirection of the uninfected, functioning cylinder into the neocorporal space. Results The surgery was successfully completed without any complications, and the IPP functioned well at the end of the procedure. During the 6-week clinic follow-up, the patient reported proper cycling of the device, excellent erectile function, the ability to orgasm, and minimal pain. Conclusions In conclusion, our case demonstrates that Tutoplast graft, along with appropriate seating and redirection of the displaced cylinder without replacing the functional hardware, is a viable surgical approach for IPP revision, even in complex cases involving septal defects. Disclosure No.

The Cyst Epithelium in Polycystic Kidney Disease Patients Displays Normal Apical-Basolateral Cell Polarity.

The main characteristic of polycystic kidney disease is the development of multiple fluid-filled renal cysts. The discovery of mislocalized sodium-potassium pump (Na,K-ATPase) in the apical membrane of cyst-lining epithelia alluded to reversal of polarity as a possible explanation for the fluid secretion. The topic of apical Na,K-ATPase in cysts remains controversial. We investigated the localization of the Na,K-ATPase and assessed the apical-basolateral polarization of cyst-lining epithelia by means of immunohistochemistry in kidney tissue from six polycystic kidney disease patients undergoing nephrectomy. The Na,K-ATPase α1 subunit was conventionally situated in the basolateral membrane of all immunoreactive cysts. Proteins of the Crumbs and partitioning defective (Par) complexes were localized to the apical membrane domain in cyst epithelial cells. The apical targeting protein Syntaxin-3 also immunolocalized to the apical domain of cyst-lining epithelial cells. Proteins of the basolateral Scribble complex immunolocalized to the basolateral domain of cysts. Thus, no deviations from the typical epithelial distribution of basic cell polarity proteins were observed in the cysts from the six patients. Furthermore, we confirmed that cysts can originate from virtually any tubular segment with preserved polarity. In conclusion, we find no evidence of a reversal in apical-basolateral polarity in cyst-lining epithelia in polycystic kidney disease.

In Situ Photo-Crosslinkable Protein Bioadhesive for Bone Graft Fixation

Bone grafting is a fundamental dental surgery procedure widely used for implant placement and periodontal disease management treatments. Despite its broad applications, vertical bone augmentation presents unique challenges, including the risk of graft displacement due to gravitational and masticatory forces. Traditional physical stabilization methods introduce additional complexities and risks, underscoring the need for innovative fixation technologies. This study aimed to develop an in situ photo-crosslinkable bioadhesive hydrogel (iPBAH) as a multifunctional bone graft binder to enhance the process of bone reconstruction. The bioadhesive is composed of mussel-derived adhesive protein (MAP) fused with the cell-adhesive peptide RGD. The numerous tyrosine residues in MAP facilitate rapid photo-crosslinking, enabling efficient hydrogel formation using visible blue light. Subsequently, iPBAH underwent comprehensive characterization to evaluate its suitability as a multifunctional bone graft binder. iPBAH efficiently underwent in situ crosslinking through harmless exposure to visible light within minutes and displayed several exceptional properties, including a microporous structure, underwater adhesion, extended durability, high compressive strength, and biocompatibility. In vivo assessments, using male Sprague-Dawley rats, demonstrated that iPBAH binder significantly enhanced bone regeneration in a rat calvarial bone defect model. The in situ crosslinking of the iPBAH binder during bone graft transplantation can effectively fill irregular and complex defect shapes while simultaneously preventing graft material leakage. The improved physical attributes of the bound graft material can enhance its resistance to external forces, thereby ensuring sustained retention over time. Moreover, the interaction between iPBAH and surrounding tissues promotes adhesion and integration of the graft material with host tissues in the defect area. In addition, the included RGD peptide in iPBAH can augment inherent cell recruitment, adhesion, and growth, consequently expediting osteogenesis.

Comment on: Conjoined thoracodorsal perforator-supercharged dorsal intercostal artery perforator propeller flap for reconstruction of a complex upper back defect: Case report and review of the literature on supercharged pedicled perforator flaps.

Comment on: Conjoined thoracodorsal perforator-supercharged dorsal intercostal artery perforator propeller flap for reconstruction of a complex upper back defect: Case report and review of the literature on supercharged pedicled perforator flaps.

Modification of Ce3+ luminescence in Li+ and Mg2+ codoped GAGG:Ce scintillators: A comparative study using synchrotron radiation

The luminescence characteristics of Gd3Al2Ga3O12:Ce3+ garnet scintillator crystals codoped with Li+ and Mg2+ ions were investigated. The excitation and emission spectra were obtained within the energy range of 3.6-21.6 eV, at both liquid helium and room temperature conditions to examine the effects of Li+ and Mg2+ codoping on cerium valence states, gadolinium-cerium energy transfer, and defect formation. Codoping with Mg2+ was found to efficiently convert Ce3+ to Ce4+, evidenced by significant changes in the shapes of the excitation spectra profile for Ce3+ luminescence in the exciton range, while Li+ had little impact. The presence of the high concentration of Ce4+ ions hampered the Gd3+→Ce4+ energy transfer. Redshifts in Ce3+ emission peaks indicated codopant-induced perturbations to the crystal field environment. The significant changes in the location of the Ce3+ excitation bands of Ce3+ luminescence in the exciton range further suggested alterations in the elemental distributions by the creation of complex defect clusters, particularly with Mg2+ codoping. The results demonstrate that Li+ and Mg2+ uniquely impact cerium valence, energy transfer processes, and structural properties in GAGG:Ce crystals.

Tuning enhanced dielectric properties of (Sc3+–Ta5+) substituted TiO2 via insulating surface layers

In this study, we achieved significantly enhanced giant dielectric properties (EG-DPs) in Sc3+–Ta5+ co-doped rutile-TiO2 (STTO) ceramics with a low loss tangent (tanδ ≈ 0.05) and high dielectric permittivity (ε′ ≈ 2.4 × 104 at 1 kHz). We focused on investigating the influence of insulating surface layers on the nonlinear electrical properties and the giant dielectric response. Our experimental observations revealed that these properties are not directly correlated with the grain size of the ceramics. Furthermore, first-principles calculations indicated the preferred formation of complex defects, specifically 2Ta diamond and 2ScVo triangular-shaped complexes, within the rutile structure of STTO; however, these too showed no correlation. Consequently, the non-Ohmic properties and EG-DPs of STTO ceramics cannot be predominantly attributed to the grain boundary barrier layer capacitor model or to electron-pinned defect-dipole effects. We also found that the semiconducting grains in STTO ceramics primarily arise from Ta5+, while Sc3+ plays a crucial role in forming a highly resistive outer surface layer. Notably, a significant impact of grain boundary resistance on the nonlinear electrical properties was observed only at lower co-dopant concentrations in STTO ceramics (1 at%). The combination of low tanδ values and high ε′ in these ceramics is primarily associated with a highly resistive, thin outer-surface layer, which substantially influences their non-Ohmic characteristics.

Anterior component separation technique for abdominal wall closure among patients undergoing colorectal surgery: Short-term outcomes and initial experience

IntroductionThe anterior component separation (ACS) is a technique used for abdominal wall closure performed by dissecting and medially advancing the musculature to achieve tension-free closure. Methodsand Materials:This study reviewed our experience with this procedure as used for complex abdominal wall defects encountered during colorectal surgery in a 7-year period. ResultsSixteen patients were included, with 12 having malignancies and the rest for infectious or inflammatory conditions. Defects ranged from 16–400 cm2 and were mostly located at the midline (56%, n = 9). Five cases required additional flaps for closure, attributed either to the size or area of abdominal involvement where benefits of component separation is more limited. Complications include surgical site infection (n = 4), hematoma (n = 2), seroma (n = 1), and wound dehiscence (n = 2). None required ICU admission or assisted ventilation post-operatively. One patient died who had a preexisting cardiac pathology, and the rest were discharged improved. ConclusionThis study demonstrates use of this modality for autologous reconstruction of complex appropriately sized abdominal wall defects from multiple etiologies. Adjunct flaps may be used to achieve reconstruction particularly in areas wherein the effectiveness of ACS is limited. While the study is able to describe immediate outcomes, long-term follow-up is recommended.

Over 10% Efficient Sb2(S,Se)3 Solar Cells Enabled by CsI-Doping Strategy.

Antimony selenosulfide (Sb2(S,Se)3) is an emerging quasi-1D photovoltaic semiconductor with exceptional photoelectric properties. The low-symmetry chain structure contains complex defects and makes it difficult to improve electrical properties via doping method. This article reports a doping strategy to enhance the efficiency of Sb2(S,Se)3 solar cells by using alkali halide (CsI) as the hydrothermal reaction precursor. It is found that the Cs and I ions are effectively doped and atomically coordinate with Sb ions and S/Se ions. The CsI-doping Sb2(S,Se)3 absorbers exhibit enhanced grain morphologies and reduced trap densities. The consequential CsI-doping Sb2(S,Se)3 based solar cells demonstrate favorable band alignment, suppressed carrier recombination, and improved device performance. An efficiency as high as 10.05% under standard AM1.5 illumination irradiance is achieved. This precursor-based alkali halide doping strategy provides a useful guidance for high-efficiency antimony selenosulfide solar cells.

Machine learning potential assisted exploration of complex defect potential energy surfaces

Atomic-scale defects generated in materials under both equilibrium and irradiation conditions can significantly impact their physical and mechanical properties. Unraveling the energetically most favorable ground-state configurations of these defects is an important step towards the fundamental understanding of their influence on the performance of materials ranging from photovoltaics to advanced nuclear fuels. Here, using fluorite-structured thorium dioxide (ThO2) as an exemplar, we demonstrate how density functional theory and machine learning interatomic potential can be synergistically combined into a powerful tool that enables exhaustive exploration of the large configuration spaces of small point defect clusters. Our study leads to several unexpected discoveries, including defect polymorphism and ground-state structures that defy our physical intuitions. Possible physical origins of these unexpected findings are elucidated using a local cluster expansion model developed in this work.

NASAL RECONSTRUCTION AFTER MOHS SURGERY: MANAGEMENT OF DEFECTS ACCCORDING TO ANATOMICAL UNITS AND DIMENSIONS

Objectives: Skin cancer frequently affects the nose, particularly in sun-exposed areas such as the ala, apex, root, and bridge. Even minor nasal lesions can pose aesthetic and psychosocial challenges for patients, necessitating nasal reconstruction tailored to anatomical units and defect size. The primary goal of reconstructive surgery is to restore the original shape, emphasizing three-dimensional space, symmetry, color, and compatibility with surrounding tissue structures. Despite numerous options for post-cancer surgery reconstruction, establishing a gold standard for nasal defect management remains elusive. Materials and Methods: A retrospective study was conducted in 41 patients following Mohs surgery for basal cell carcinoma. Defects are approached based on rhinoplasty principles, considering anatomical units, defect size, and location to select appropriate reconstruction methods. Results: Among the patients, 17 (41.5%) had nasal alar defects, 5 (12.2%) had nasal apex defects, 4 (9.8%) had nasal root defects, 7 (17.1%) had nasal bridge defects, and 9 (22%) had complex defects involving multiple anatomical units. Patients with nasal alar defects <1.5cm underwent reconstruction using the nasolabial flap, while those with larger defects (>1.5cm) underwent forehead flap reconstruction, including auricular cartilage grafts for nasal alar defects. Complex lesions (22%) were reconstructed using a combination of forehead flap and rotation or V-Y flap. Nasal root defects (7.3%) were reconstructed using the glabellar flap. Conclusion: Nasal reconstruction, employing local or regional flaps, consistently yields positive functional and aesthetic outcomes due to the similarity in color and skin flap thickness with adjacent structures. The forehead flap, with its constant blood supply, vitality, and versatile design, is particularly effective for complex nasal lesions. Received 29 June 2023Revised 27 September 2023Accepted 29 November 2023

Deep Learning on Atomistic Physical Fields of Graphene for Strain and Defect Engineering

Strain and defect engineering have profound applications in two‐dimensional materials, where it is important to determine the equilibrated atomistic structures with defect conditions under mechanical deformations for computational materials design. Nevertheless, how to efficiently predict relaxed atomistic structures and the associated physical fields on each atom or bond under evolving mechanical deformations remains as an essential challenge. To address this issue, a deep neural network architecture is designed to embed the state of applied strains into the defect‐engineered atomistic geometry, so that deformation‐coupled physical fields of interests on atoms or bonds can be predicted or derived over continuous state of deformations. For demonstration, the combination of applied tensile strains and shear strain on monolayer graphene with random distribution of Stone–Wales defects and vacancy defects is considered. The unique advantage of this framework is the development of strain‐embedding concept combined with generative adversarial network, which can be feasibly extended to other material and other conditions. The computational approach sheds light on boosting the efficiency of evaluating physical properties of 2D materials under complex strain and defect states.

The universal suppressor mutation restores membrane budding defects in the HSV-1 nuclear egress complex by stabilizing the oligomeric lattice.

Nuclear egress is an essential process in herpesvirus replication whereby nascent capsids translocate from the nucleus to the cytoplasm. This initial step of nuclear egress-budding at the inner nuclear membrane-is coordinated by the nuclear egress complex (NEC). Composed of the viral proteins UL31 and UL34, NEC deforms the membrane around the capsid as the latter buds into the perinuclear space. NEC oligomerization into a hexagonal membrane-bound lattice is essential for budding because NEC mutants designed to perturb lattice interfaces reduce its budding ability. Previously, we identified an NEC suppressor mutation capable of restoring budding to a mutant with a weakened hexagonal lattice. Using an established in-vitro budding assay and HSV-1 infected cell experiments, we show that the suppressor mutation can restore budding to a broad range of budding-deficient NEC mutants thereby acting as a universal suppressor. Cryogenic electron tomography of the suppressor NEC mutant lattice revealed a hexagonal lattice reminiscent of wild-type NEC lattice instead of an alternative lattice. Further investigation using x-ray crystallography showed that the suppressor mutation promoted the formation of new contacts between the NEC hexamers that, ostensibly, stabilized the hexagonal lattice. This stabilization strategy is powerful enough to override the otherwise deleterious effects of mutations that destabilize the NEC lattice by different mechanisms, resulting in a functional NEC hexagonal lattice and restoration of membrane budding.

Routine Echocardiography is not Required in Neonates with Arterial Ischemic Stroke.

Current guidelines suggest routine echocardiography (ECHO) in the acute phase to exclude a cardiac source for neonatal arterial ischemic stroke (NAIS). However, the commonly assumed embolic origin from a cardiac source for NAIS is challenged and the need for ECHO in NAIS remains questionable, especially during the era of standard fetal anomaly scanning. Our hypothesis is that any complex cardiac defects potentially causing NAIS would likely be detected during routine prenatal scans, thus possibly making routine postnatal ECHO redundant. This study aimed to determine the prevalence of significant cardiac risk factors and evaluate the necessity of routine postnatal ECHO in NAIS during the routine use of prenatal fetal sonography. Retrospective review of 54 infants diagnosed with NAIS via brain magnetic resonance imaging who underwent an ECHO evaluation during the acute period to exclude potential cardiac origins for NAIS. Postnatal ECHO revealed no intracardiac thrombus or vegetation, and only identified structural heart anomalies in three (5%) infants. Interestingly, these three cases had already been diagnosed with syndromic conditions or chromosomal malformations prenatally. In the remaining infants, postnatal ECHO was either normal or showed minor abnormalities unlikely to have contributed to the stroke. The detection rates of complex cardiac anomalies from prenatal scans and postnatal ECHO were statistically similar (p = 0.617). The probability of ECHO to exclude cardiac sources for NAIS is so low that in the era of standard fetal anomaly scanning, routine postnatal ECHO may not be necessary for all NAIS infants, except when chromosomal malformations are detected. · Guidelines recommend an acute phase ECHO to identify a cardiac source of NAIS.. · ECHO not effective at excluding NAIS's cardiac origin for infants with normal fetal scans.. · Routine postnatal ECHO is unnecessary in NAIS infants, except with genetic abnormalities..

Guided Customization and Fixation of Allogenic Cortical Lamina in Alveolar Bone Regeneration. A Case Report.

Bone reconstruction surgeries such as the autogenous and allogenic shell techniques where cortical laminates are used to regenerate bone defects, requires time and expertise to adapt and fix the laminated cortical blocks onto the defect area. This case report illustrates the process of customizing and fixing an allogenic cortical laminate (ACL) to reconstruct a horizontal bone defect with guided surgical stents. Two types of surgical stents were designed: one to aid in cutting a prefabricated ACL into the desired shape for the defect to be regenerated, and the other type of stent, was used to assist in the positioning and fixation of the resulting laminates. These stents enabled the clinician to regenerate a horizontal defect with reduced surgical time, increased precision and safety during laminate fixation. After 5 months of healing a dental implant could be placed in the regenerated site. The use of surgical stents in this type of bone regeneration surgeries can be helpful specially in more complex bone defects where precision is key. Further clinical studies are needed to validate this technique.

FastSegFormer: A knowledge distillation-based method for real-time semantic segmentation of surface defects in navel oranges

Navel oranges are valued citrus fruits with a strong market presence, and detecting defects is crucial in their sorting due to common diseases and abnormalities during growth and transport. Deep learning, particularly semantic segmentation, is revolutionizing the fruit sorting industry by overcoming the limitations of traditional defect detection and enhancing the accuracy of classifying complex defects in navel oranges. The FastSegFormer network, enabling real-time fruit defect detection, addresses this challenge with our introduced Multi-scale Pyramid (MSP) module for its architecture and a semi-resolution reconstruction branch post-feature fusion. We suggested a multi-resolution knowledge distillation strategy to further increase the network’s segmentation accuracy. We developed a navel orange defect segmentation dataset, trained, and evaluated our FastSegFormer-E model, designed for memory-constrained devices. It outperforms ENet by 3.15%, achieving a mIoU of 88.78% on the test set. The FastSegFormer-P model, tailored for high-speed detection, was tested on the mid-range RTX3060 graphics card, surpassing ENet by 3.7% with a mIoU of 89.33% and reaching 108 frames/s. The results demonstrate that the FastSegFormer-E model attains enhanced detection accuracy with reduced memory usage, whereas the FastSegFormer-P model stands out by striking an optimal balance between top-tier detection accuracy and rapid processing speed. Deploying the algorithm system on the same platform as pipeline sorting, 20 frame/s was achieved on a Jetson Nano with very low computational power. The model significantly improves the detection of subtle and intricate edge defects, achieving real-time speeds. Our proposed algorithm enhances the fineness of fruit sorting, resolves the limitation of existing algorithms that apply to a narrow range of fruit sorting scenarios, and provides an efficient and accurate solution for large-scale navel orange defect detection.