Computed Tomography Scan Imaging Research Articles

A pneumatic reconfigurable socket for transtibial amputees.

Many transtibial amputees rate the fit between their residual limb and prosthetic socket as the most critical factor in satisfaction with using their prosthesis. This study aims to address the issue of prosthetic socket fit by reconfiguring the socket shape at the interface of the residual limb and socket. The proposed reconfigurable socket shifts pressure from sensitive areas and compensates for residual limb volume fluctuations, the most important factors in determining a good socket fit. Computed tomography scan images are employed to create the phantom limb of an amputee and to manufacture the reconfigurable socket. The performance of the reconfigurable socket was evaluated both experimentally and numerically using finite element modelling. The study showed that the reconfigurable socket can reduce interface pressure at targeted areas by up to 61%.

DIAGNOSIS OF KIDNEY CYST, TUMOR AND STONE FROM CT SCAN IMAGESUSING FEATURE FUSION HYPERGRAPH CONVOLUTIONAL NEURAL NETWORK (F2HCN2)

The development of a computational tool to diagnose kidney disorders in their early stages is necessary due to the rise in chronic kidney diseases (CKDs) and the global shortage of nephrologists. The three common renal disorders covered in this study are kidney stones, cysts, and tumors. Early diagnosis of these diseases from the computed tomography (CT) images is a challenging task. Yet, present graph convolutional neural network (GCNN) approaches have the issue of overdependence on the adjacency matrix. Moreover, compared to deep convolutional neural network (CNN) models, a single modal feature results in low accuracy and robustness. In this paper, we proposed the feature fusion hypergraph CNN (F<sup>2</sup>HCN<sup>2</sup>) to accurately diagnose kidney diseases in the early stage based on CT scan images. The discriminative features of the images are extracted using DarkNet19 and residual features are extracted using ResNet50. The extracted features are classified using feature fusion hypergraph CNN. The proposed model is trained with 12,446 CT whole urogram and abdomen images. The hypergraph representation learning is performed to train the network with the fused features. Deep learning metrics including accuracy, F1 score (F1), recall, positive predictive value (PPV), receiver operating characteristic curve, and area under curve (AUC) are used to validate the proposed model. It outperforms compared to other state-of-the-art algorithms with accuracy of 99.71%. The proposed F<sup>2</sup>HCN<sup>2</sup> is a robust computer-aided tool for the early diagnosis of kidney diseases. It will assist the radiologist for better prognosis for kidney related abnormalities.

Anatomical assessment of foramen magnum among the South Indian population – A CT scan comparative study

Background: Foramen magnum (FM) is the most prominent opening in the floor of the posterior cranial fossa. Occipital condyle (OC) protrusion into the FM alters the measurements and produces an impact on the surgical access. Diagnostic modalities such as computed tomography (CT) and magnetic resonance imaging scan made revolutionary changes in assessing the skull base. Aims and Objectives: The aim of our study is to measure the morphometric measurements of FM, OC and assess the shapes of the FM. Materials and Methods: An observational descriptive study on morphometric measurements of FM and OC is conducted in dry skulls and CT scan images. Area, index, and shapes of FM were calculated and tabulated. Relationship between the FM dimensions was statistically analyzed using student t-test (P < 0.05). Results: There was no significant difference of means (P > 0.05) between the FM and OC parameters with respect to dry skulls and CT measurements. The study results showed that CT is good in predicting the measurements of FM. Our results on shapes of FM showed highest occurrence of the hexagonal (28.57%) followed by diamond shape (22.8%) in dry skulls and CT images. On applying the kappa statistics, there was no agreement in shapes of FM between dry skulls and CT images. Conclusion: Our study hopes to provide extensive knowledge of FM and OC for the operative surgeons and aids in the reduction of iatrogenic complications.

Atlas Morphometry: A Radiologic- Anatomical Study

Abstract Introduction: Atlas is an atypical cervical vertebra with unique anatomy and related to many vital structures. Any surgical intervention at this level, especially transpedicular and transarticular screw placement, requires in detail assessment of the structure of the atlas. Certain measurements considered surgically important were measured on computerized tomography (CT) scans and compared with corresponding measurements on dry bones. Methodology: The study was carried out in KVG Medical College and Hospital, Sullia, including 100 CT scans of 43 females and 57 males with a mean age of 31.4 years and 40 dried atlas vertebrae available in the Department of Anatomy. Lengths and widths of superior and inferior articular facets were measured on both CT scans and dry bones and compared. Length, width, and heights of lateral masses, along with height below the posterior arch (HBPA), maximum medialization and cranialization angles were assessed on CT scans. The mean, standard deviation, and significance of differences were calculated using an independent t-test. Results: Mean value and standard deviation were calculated for the measured parameters. Superior and inferior facet measurements were compared between CT scan images and dry bones and no significant difference was found. Conclusion: Morphometric measurements of atlas on CT images are useful for planning of screw fixation surgeries, particularly to avoid injury to vital structures. Values of measurements, especially maximum medialization angle, maximum cranialization angle, and HBPA, are in agreement with other studies and are proposed to be included as part of preoperative workup.

Integrated global and local feature extraction and classification from computerized tomography (CT) images for lung cancer classification.

Despite being the second most often diagnosed form of cancer, lung cancers are rarely found in the general population. It is proposed in this study to employ amethodology of extracting both global and local features from CT scan images for the identification of lung cancer. Data gathering, globalised and localised training as well as testing the model are all part of this structure. This study makes use of 800 CT scan images. Images are pre-processed by warping and cropping in advance of the global testing step. Each image is represented by afeature vector employing eight distinct types of image characteristics, which are taken from the images. After creating feature vectors, three machine learning methods are employed to create detection models. Every medical image has been partitioned over aseries of simple divisions throughout the training and testing process locally. To describe each block, feature vectors are derived from the image features that worked effectively in the general phase of the experiment. Similar extracted features are then used to build detection systems for all picture blocks using the learning strategies that were effective in the global stage. SVM using Haar Wavelet characteristics had an accuracy, sensitivity, and specificity of 89%, 90%, and 89%, respectively. One might get 90%‑accurate results with SVM and 91%‑sensitive and 91%‑specific results using SVM plus HOG features. Finally, the utilisation of SVM with Gabor Filter characteristics achieved the greatest correctness, specificity, and sensitivity values, particularly 87%, 86%, and 87%, respectively (Tab. 3, Fig. 7, Ref. 18). Keywords: feature extraction, support vector machine, lung cancer, classification, machine learning.

Lacrimal gland enlargement in inactive thyroid eye disease: a case series and literature review.

This study aimed to evaluate the morphometric and volumetric dimensions of the lacrimal gland in patients with inactive thyroid eye disease and compare them with the values reported in the literature. This case series evaluated consecutive patients with inactive thyroid eye disease treated at a tertiary eye hospital from 2015 to 2020. The patients' baseline demographics and clinical characteristics were obtained. The axial and coronal length, width, and volume of the lacrimal gland were measured on computed tomography scan images, and the results were statistically analyzed. A total of 21 patients (42 orbits) with inactive thyroid eye disease were evaluated. Their mean age was 49.0 ± 14.6 years, and 12 (57.1%) of them were men. The main complaint was dryness, and the majority of the patients had good vision and mild proptosis. The mean axial length and width of the lacrimal gland were 19.3 ± 3.9 mm and 7.5 ± 2.1 mm, respectively; coronal length and width, 20.4 ± 4.5 mm and 7.5 ± 2.1 mm, respectively; and lacrimal gland volume, 0.825 ± 0.326 mm3. Age, sex, or laterality were not found to be determinants of lacrimal gland enlargement. Patients with thyroid eye disease have enlarged lacrimal gland even in the nonactive phase of the disease multifactorial aspects influence the lacrimal gland in thyroid eye disease, making it difficult to establish a clear correlation with predisposing factors. Further studies are warranted to better understand the association between thyroid eye disease and the lacrimal gland.

Use of radiologic imaging to differentiate lipoma from atypical lipomatous tumor/well-differentiated liposarcoma: Systematic review.

Lipomas and atypical lipomatous tumors or well-differentiated liposarcomas (ALTs/WDLs), pose a diagnostic challenge due to their overlapping clinical and imaging features. Accurate differentiation is crucial as treatment strategies differ significantly between benign lipomas and malignant ALTs/WDLs. In recent years, medical imaging techniques have shown promise in distinguishing lipomas from ALTs/WDLs by providing enhanced visualization and assessment of various imaging parameters. This systematic review aimed to investigate the use of magnetic resonance (MR) imaging and computed tomography (CT) scan to differentiate lipomas from ALTs/WDLs. A systematic review was conducted by using MEDLINE, PubMed, PubMed Central, Cochrane Library, Google Scholar, and clinical trail.gov to identify imaging studies published between 2001 and 2022. Two independent reviewers reviewed 221 record to scrutinize the studies. The methodological quality of each included studies was assessed the using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Thirteen retrospective cohort studies included 1,390 of total patients. Among them, 11 studies used MR imaging, 2 studies used CT scan and MR imaging both to differentiate lipoma from ALTs/WDLs. The significant diagnostic variables identified in the included studies were age, size, texture, mean intensity, contrast enhancement, location, septation, and nodularity. The overall, sensitivity, specificity, and accuracy of the included studies for diagnosis of lesions range from 66% to 100%, 37% to 100%, and 76% to 95%, respectively. The positive and negative predictive values range from 46.9% to 90% and 86% to 100%, respectively. The most frequent diagnostic features of ALTs/ WDLs include tumors ⩾110 mm in size, often in patients over 60, predominantly in the lower extremities, with an irregular shape, incomplete fat suppression, contrast enhancement, nodularity, septation >2 mm, and predictive markers such as lactate dehydrogenase >220 and a short tau inversion recovery-signal intensity ratio >1.18.

Hybrid healthcare unit recommendation system using computational techniques with lung cancer segmentation.

Our research addresses the critical need for accurate segmentation in medical healthcare applications, particularly in lung nodule detection using Computed Tomography (CT). Our investigation focuses on determining the particle composition of lung nodules, a vital aspect of diagnosis and treatment planning. Our model was trained and evaluated using several deep learning classifiers on the LUNA-16 dataset, achieving superior performance in terms of the Probabilistic Rand Index (PRI), Variation of Information (VOI), Region of Interest (ROI), Dice Coecient, and Global Consistency Error (GCE). The evaluation demonstrated a high accuracy of 91.76% for parameter estimation, confirming the effectiveness of the proposed approach. Our investigation focuses on determining the particle composition of lung nodules, a vital aspect of diagnosis and treatment planning. We proposed a novel segmentation model to identify lung disease from CT scans to achieve this. We proposed a learning architecture that combines U-Net with a Two-parameter logistic distribution for accurate image segmentation; this hybrid model is called U-Net++, leveraging Contrast Limited Adaptive Histogram Equalization (CLAHE) on a 5,000 set of CT scan images.

Heterogenous liver parenchymal enhancement in CT is a favorable prognosis of HCC after hepatic resection.

This study aimed to define the role of heterogeneity of liver parenchymal enhancement on computed tomography (CT) in the survival of patients with hepatocellular carcinoma (HCC) after hepatic resection. The medical records of patients with HCCs and who had undergone hepatic resection were retrospectively reviewed. The standard deviation (SD) of three different enhanced CT scan images was used to estimate the heterogeneity of liver parenchymal enhancement: SD of > 5.6, heterogenous enhancement, and SD of ≤ 5.6, homogeneous enhancement. A total of 57 patients had heterogenous enhancement, and 143 patients had homogeneous enhancement. The patients with heterogenous enhancement had longer disease-free and overall survivals than those with other enhancements (log-rank test, P < 0.001 and P = 0.036). The pathologic exam showed that heterogenous enhancement tended to develop septa in the peritumoral liver tissues. The prevalence of CD8+ cells was significantly higher in the peritumor liver tissues with septa than in those without (0.83% vs. 0.26%, P < 0.001). The peritumoral CD8/Foxp3 ratio was higher in the liver tissues with septa than in those without (1.22 vs. 0.47, P = 0.001), and patients with CD8/Foxp3 of > 0.8 had better overall survival than those with CD8/Foxp3 of ≤ 0.8 (log-rank test, P = 0.028). In conclusion, patients who had undergone hepatic resection with a heterogenous liver parenchymal enhancement tended to develop hepatic septa, which was associated with a higher CD8/Foxp3 ratio and longer survival. Therefore, contrast-enhanced CT scans might be a useful tool to predict the outcome of HCC.

Neutron Displaced Computed Tomography Scanning Imaging Method Considering Calibration Error of Center of Rotation

Neutron Displaced Computed Tomography Scanning Imaging Method Considering Calibration Error of Center of Rotation

Data augmentation and denoising of computed tomography scan images in training deep learning models for rapid COVID-19 detection

Data augmentation and denoising of computed tomography scan images in training deep learning models for rapid COVID-19 detection

Detection and Classification of Lung Nodule in CT Scan Images Using CNN

The Identification of lung malignant cells at premature stage remain as remarkable research area for researchers. Lung nodules are account as a normal reason for death in people all over the world. Identification of lung nodules at the initial stage can build the pace of endurance of patients. In this article computed tomography (CT) scan images as input to classify lung malignant cells of non-small cell lung cancer and categories according to subtypes of cancer by using the image processing technique with a convolutional neural network (CNN). The segmentation of the CT scan is performed to simplify the representation for meaningful and easier analysis. The feature extraction technique is used which is independent from the size and rotation of the image. These extracted features will use as an input to convolutional neural network (CNN), it pass through different layer of neural network at the end output layer classifies the affected and non-affected areas of the lung nodule with respect to subtypes (adenocarcinoma, squamous cell carcinoma, and large cell carcinoma). The deep learning algorithms VGG 16 show accuracy 85.01% while another deep learning algorithms VGG 19 show best accuracy 98.74% to correctly classify the nodules and subtypes.

Evaluation of the accuracy of an augmented reality-based tumor-targeting guide for breast-conserving surgery

Background and ObjectivesAlthough magnetic resonance imaging (MRI) is commonly used for breast tumor detection, significant challenges remain in determining and presenting the three-dimensional (3D) morphology of tumors to guide breast-conserving surgery. To address this challenge, we have developed the augmented reality-breast surgery guide (AR-BSG) and compared its performance with that of a traditional 3D-printed breast surgical guide (3DP-BSG). MethodsBased on the MRI results of a breast cancer patient, a breast phantom made of skin, body, and tumor was fabricated through 3D printing and silicone-casting. AR-BSG and 3DP-BSG were executed using surgical plans based on the breast phantom's computed tomography scan images. Three operators independently inserted a catheter into the phantom using each guide. Their targeting accuracy was then evaluated using Bland–Altman analysis with limits of agreement (LoA). Differences between the users of each guide were evaluated using the intraclass correlation coefficient (ICC). ResultsThe entry and end point errors associated with AR-BSG were −0.34±0.68 mm (LoA: −1.71–1.01 mm) and 0.81±1.88 mm (LoA: −4.60–3.00 mm), respectively, whereas 3DP-BSG was associated with entry and end point errors of −0.28±0.70 mm (LoA: −1.69–1.11 mm) and −0.62±1.24 mm (LoA: −3.00–1.80 mm), respectively. The AR-BSG's entry and end point ICC values were 0.99 and 0.97, respectively, whereas 3DP-BSG was associated with entry and end point ICC values of 0.99 and 0.99, respectively. ConclusionsAR-BSG can consistently and accurately localize tumor margins for surgeons without inferior guiding accuracy AR-BSG can consistently and accurately localize tumor margins for surgeons without inferior guiding accuracy compared to 3DP-BSG. Additionally, when compared with 3DP-BSG, AR-BSG can offer better spatial perception and visualization, lower costs, and a shorter setup time.

Analyzing CT Scan Images towards the Early Detection of Lung Cancer using Medical Images based Edge Feature Preserving CT Scan Medical Image Coder (EZWT - EFPIC)

With the current improvements in virtual image processing techniques have received several benefits. Today, all of the scientific techniques produce virtual scientific pictures, through healthcare specialists analyze and diagnose the abnormality. The frequent view of scientific picture processing might also additionally appear simpler; however, it entails many challenges. As the scientific pics are interconnected with human lives, the laptop-aided scientific image processing structures have to be overcautious, if we want to eliminate inaccuracy rates. The utility of medical image processing techniques for the analysis of CT scan images similar to lung cancer cells has been gaining momentum in recent years. This paper discusses the use of a Transform Edge Feature preserving CT scan Medical Image Coder (EZWT - EFPIC) using Computed Tomography (CT) images to help in the early diagnosis of lung cancer. We discuss and explore the design and significance of an EZWT-EFPIC-CT image-processed model in cancer diagnosis.

COVID-19 infection segmentation using hybrid deep learning and image processing techniques

The coronavirus disease 2019 (COVID-19) epidemic has become a worldwide problem that continues to affect people’s lives daily, and the early diagnosis of COVID-19 has a critical importance on the treatment of infected patients for medical and healthcare organizations. To detect COVID-19 infections, medical imaging techniques, including computed tomography (CT) scan images and X-ray images, are considered some of the helpful medical tests that healthcare providers carry out. However, in addition to the difficulty of segmenting contaminated areas from CT scan images, these approaches also offer limited accuracy for identifying the virus. Accordingly, this paper addresses the effectiveness of using deep learning (DL) and image processing techniques, which serve to expand the dataset without the need for any augmentation strategies, and it also presents a novel approach for detecting COVID-19 virus infections in lung images, particularly the infection prediction issue. In our proposed method, to reveal the infection, the input images are first preprocessed using a threshold then resized to 128 × 128. After that, a density heat map tool is used for coloring the resized lung images. The three channels (red, green, and blue) are then separated from the colored image and are further preprocessed through image inverse and histogram equalization, and are subsequently fed, in independent directions, into three separate U-Nets with the same architecture for segmentation. Finally, the segmentation results are combined and run through a convolution layer one by one to get the detection. Several evaluation metrics using the CT scan dataset were used to measure the performance of the proposed approach in comparison with other state-of-the-art techniques in terms of accuracy, sensitivity, precision, and the dice coefficient. The experimental results of the proposed approach reached 99.71%, 0.83, 0.87, and 0.85, respectively. These results show that coloring the CT scan images dataset and then dividing each image into its RGB image channels can enhance the COVID-19 detection, and it also increases the U-Net power in the segmentation when merging the channel segmentation results. In comparison to other existing segmentation techniques employing bigger 512 × 512 images, this study is one of the few that can rapidly and correctly detect the COVID-19 virus with high accuracy on smaller 128 × 128 images using the metrics of accuracy, sensitivity, precision, and dice coefficient.

Post-malaria neurological syndrome (PMNS): a rare case report with brain biopsy findings

Post-malaria neurological syndrome (PMNS) is a rare, self-limiting condition that presents with a wide range of neurological manifestations after clearance of malarial infection, especially \U0001d617\U0001d62d\U0001d622\U0001d634\U0001d62e\U0001d630\U0001d625\U0001d62a\U0001d636\U0001d62e f\U0001d622\U0001d62d\U0001d624\U0001d62a\U0001d631\U0001d622\U0001d633\U0001d636\U0001d62e, most patients recover without residual deficits. Here we present a case of a 29-year-old, male with a recent history of malaria treated successfully, who presented due to a generalized tonic-clonic seizure, without any other neurological symptoms, the examination and labs were unremarkable, he underwent a computer tomography (CT) scan and Magnetic resonant imaging (MRI) which both showed two areas of vasogenic edema involving the subcortical white matter of left frontal and right posterior parasagittal regions, all autoimmune screens, infection workup from blood and CSF were negative, he underwent a brain biopsy that showed intense perivascular inflammation with neuronal loss and gliosis, findings are nonspecific and can be seen in a variety of condition. The patient’s condition improved, and he was discharged without any complications.

Phase angle - A screening tool for malnutrition, sarcopenia, and complications in gastric cancer

Patients with gastric cancer (GC) are more likely to experience malnutrition and muscle wasting. This study aims to investigate the potential of phase angle (PhA) as a screening tool for identifying malnutrition and sarcopenia in GC patients, as well as its association with short-term outcomes after radical gastrectomy. This cross-sectional study enrolled patients diagnosed with GC at The Affiliated People's Hospital of Jiangsu University from October 2021 to September 2022. PhA was measured using bioelectrical impedance analysis. Computed tomography scan images were analyzed for body composition at the level of the third lumbar vertebra. Malnutrition was diagnosed using Global Leadership Initiative on Malnutrition (GLIM) criteria. Sarcopenia diagnosis was based on the Asian Working Group for Sarcopenia (AWGS) 2019 criteria. A total of 248 patients with GC were analyzed, including 188 patients who underwent radical gastrectomy. Of these, 71.4% (n=177) were male and 28.6% (n=71) were female and the median overall age was 68 years (IQR: 61-72 years). According to GLIM criteria, 49.2% (n=122) of patients were malnourished and 19.8% (n=49) had sarcopenia based on AWGS criteria. A one-degree decrease in PhA was significantly associated with GLIM malnutrition (Odds Ratio [OR]=8.108, 95% CI:3.181-20.665) and sarcopenia (OR=2.903, 95% CI:1.170-7.206). PhA exhibited fair to good diagnostic accuracy in identifying GLIM malnutrition (male: AUC=0.797; female: AUC=0.816) and sarcopenia (male: AUC=0.814; female: AUC=0.710). Low PhA (OR=3.632, 95% CI: 1.686-7.824) and operation time (OR=2.434, 95% CI:1.120-5.293) were independently associated with the risk of postoperative complications. PhA can serve as a reliable screening tool for identifying patients at risk of malnutrition, sarcopenia, and postoperative complications in GC.

Detecting meso-damage and subsurface cracks in a hard rock using frequency-modulated thermal wave imaging (FMTWI)

Mines, tunnels, and hillside roadways that are subjected to high levels of stress are prone to massive and violent occurrences of rock failures. It results in a multitude of irreversible consequences, including the loss of human lives. Nevertheless, preceding rock failures, the development of micro and macrocracks, which are sometimes not discernible on the surface, takes place. Subsurface cracks indicate the degradation of rock and can be employed as a means to anticipate occurrences of rock failures and bursts. Therefore, the utilization of subsurface imaging techniques for rocks facilitates the estimation of the true strength of the rock mass. Nevertheless, in many instances, rock masses are not easily reachable, posing difficulties for standard techniques such as ground-penetrating radar or computed tomography (CT) scan imaging, to identify the cracks. Hence, this research endeavours to explore the feasibility of employing frequency-modulated thermal wave imaging (FMTWI) for identifying subsurface cracks and their coalescence in hard rocks through the utilization of numerical simulation and experimental methods. A model was constructed using the finite element method wherein artificial cracks were intentionally introduced into a cylindrical granite specimen based on the CT scan data acquired during the meso-damage analysis. The thermograms obtained were subjected to pre-processing and post-processing techniques, and afterwards compared with the CT scan images. The FMTWI tests were conducted in the laboratory to calibrate and validate the simulation results. The findings derived from the analyses of temperature profiles and thermograms indicate that this particular technology is a promising one and offers several advantages in comparison to alternative methods for detecting micro- or macrocracks in deep mines and tunnels.

Covariations between scapular shape and bone density in B-glenoids: A statistical shape and density modeling-approach.

B-type glenoids arecharacterized by posterior humeral head migration and/or bony-erosion-induced glenoid retroversion. Patients with this type of osteoarthritic glenoids are known to be at increased risk of glenoid component loosening after anatomic total shoulder arthroplasty (aTSA). One of the main challenges in B glenoid surgical planning is to find a balance between correcting the bony shape and maintaining the quality of the bone support. This study aims to systematically quantify variabilities in terms of scapular morphology and bone mineral density in patients with B glenoids and to identify patterns of covariation between these two features. Using computed tomography scan images of 62 patients, three-dimensionalscapular surface models were constructed. Rigid and nonrigid surface registration of the scapular surfaces, followed by volumetric registration and material mapping, enabled us to develop statistical shapemodel(SSM) and statistical density model(SDM). Partial least square correlation (PLSC) was used to identify patterns of covariation. The developed SSM and SDM represented 85.9% and 56.6% of variabilities in terms of scapular morphology and bone density, respectively. PLSC identified four modes of covariation, explaining 66.0% of the correlation between these two variations. Covariation of posterior-inferior glenoid erosion with posterior sclerotic bone formation in association with reduction of bone density in the anterior and central part of the glenoid was detected as the primary mode of covariation. Identification of these asymmetrical distribution of bone density can inform us about possible reasons behind glenoid component loosening in B glenoids and surgical guidelines in terms of the compromise between bony shape correction and bone support quality.

An improved meta heuristic IT2 fuzzy model for nondestructive failure evaluation of metal additive manufacturing lattice structure

Metal Additive Manufacturing (AM) lattice structure is widely used in various fields because of its lightweight and one-time forming characteristics. Nondestructive reliability evaluation still presents a challenge that requires immediate attention, especially in light of the service setting and when structural failure is used as an evaluation criterion. In this paper, the failure evaluation problem of structure is discussed based on the defects that affect yield stress, and the yield stress as the index. Firstly, a Computed Tomography (CT) scanner is used for non-destructive testing of metal AM lattice structure samples, and improved YOLO V7 is used to identify and count defects in CT scan images. The interval type 2 (IT2) fuzzy model is then enhanced using the irregular Gaussian function, and a meta-heuristic algorithm (particle swarm optimization) is added to enhance the model’s predictive capabilities. Finally, simulation and experiment are used to validate the AM lattice structure’s failure evaluation. The improved model’s superiority in the simulation exercise is demonstrated by contrasts with IT2 and the Type 1 fuzzy model. The yield stress prediction deviation of the sample during application verification is 1.12%, which attests to the validity of the failure prediction technique suggested in this paper.