RESUMEN

BACKGROUND: The responsible use of 3D-printing in medicine includes a context-based quality assurance. Considerable literature has been published in this field, yet the quality of assessment varies widely. The limited discriminatory power of some assessment methods challenges the comparison of results. The total error for patient specific anatomical models comprises relevant partial errors of the production process: segmentation error (SegE), digital editing error (DEE), printing error (PrE). The present review provides an overview to improve the general understanding of the process specific errors, quantitative analysis, and standardized terminology. METHODS: This review focuses on literature on quality assurance of patient-specific anatomical models in terms of geometric accuracy published before December 4th, 2022 (n = 139). In an attempt to organize the literature, the publications are assigned to comparable categories and the absolute values of the maximum mean deviation (AMMD) per publication are determined therein. RESULTS: The three major examined types of original structures are teeth or jaw (n = 52), skull bones without jaw (n = 17) and heart with coronary arteries (n = 16). VPP (vat photopolymerization) is the most frequently employed basic 3D-printing technology (n = 112 experiments). The median values of AMMD (AMMD: The metric AMMD is defined as the largest linear deviation, based on an average value from at least two individual measurements.) are 0.8 mm for the SegE, 0.26 mm for the PrE and 0.825 mm for the total error. No average values are found for the DEE. CONCLUSION: The total error is not significantly higher than the partial errors which may compensate each other. Consequently SegE, DEE and PrE should be analyzed individually to describe the result quality as their sum according to rules of error propagation. Current methods for quality assurance of the segmentation are often either realistic and accurate or resource efficient. Future research should focus on implementing models for cost effective evaluations with high accuracy and realism. Our system of categorization may be enhancing the understanding of the overall process and a valuable contribution to the structural design and reporting of future experiments. It can be used to educate specialists for risk assessment and process validation within the additive manufacturing industry.

RESUMEN

Despite the advancement in deep learning-based semantic segmentation methods, which have achieved accuracy levels of field experts in many computer vision applications, the same general approaches may frequently fail in 3D medical image segmentation due to complex tissue structures, noisy acquisition, disease-related pathologies, as well as the lack of sufficiently large datasets with associated annotations. For expeditious diagnosis and quantitative image analysis in large-scale clinical trials, there is a compelling need to predict segmentation quality without ground truth. In this paper, we propose a deep learning framework to locate erroneous regions on the boundary surfaces of segmented objects for quality control and assessment of segmentation. A Convolutional Neural Network (CNN) is explored to learn the boundary related image features of multi-objects that can be used to identify location-specific inaccurate segmentation. The predicted error locations can facilitate efficient user interaction for interactive image segmentation (IIS). We evaluated the proposed method on two data sets: Osteoarthritis Initiative (OAI) 3D knee MRI and 3D calf muscle MRI. The average sensitivity scores of 0.95 and 0.92, and the average positive predictive values of 0.78 and 0.91 were achieved, respectively, for erroneous surface region detection of knee cartilage segmentation and calf muscle segmentation. Our experiment demonstrated promising performance of the proposed method for segmentation quality assessment by automated detection of erroneous surface regions in medical images.

Asunto(s)

RESUMEN

Purpose: To assess the percentage of published articles reporting optical coherence tomography angiography (OCTA) metrics regarding the report of segmentation error correction. Methods: A comprehensive search was conducted using the PubMed database for articles on OCTA imaging published between January 1, 2015, and January 1, 2021. All original articles reporting at least one of the OCTA metrics were extracted. The article text was reviewed for the segmentation correction strategy. In addition, the number of articles that mentioned the lack of segmentation error correction as a limitation of the study was recorded. Results: From the initial 5288 articles, 1559 articles were included for detailed review. One hundred ninety-six articles (12.57%) used manual correction for segmentation errors. Of the remaining articles, 589 articles (37.8%) excluded images with significant segmentation errors, and 99 articles (6.3%) mentioned segmentation errors as a limitation of their study. The rest of the articles (675, 43.3%) did not address the segmentation error. Multiple logistic regression analysis revealed that ignorance of segmentation error was significantly associated with lower journal ranks, earlier years of publication and disease category of age-related macular degeneration, and glaucoma (all P < 0.001). Conclusions: A significant proportion of peer-reviewed articles in PubMed, disregarded the segmentation error correction. The conclusions of such studies should be interpreted with caution. Editors, reviewers, and authors of OCTA articles should pay special attention to the correction of segmentation errors.

RESUMEN

BACKGROUND AND OBJECTIVES: Arrhythmia is a heart disease characterized by the change in the regularity of the heartbeat. Since this disorder can occur sporadically, Holter devices are used for continuous long-term monitoring of the subject's electrocardiogram (ECG). In this process, a large volume of data is generated. Consequently, the use of an automated system for detecting arrhythmias is highly desirable. In this work, an automated system for classifying arrhythmias using single-lead ECG signals is proposed. METHODS: The proposed system uses a combination of three groups of features: RR intervals, signal morphology, and higher-order statistics. To validate the method, the MIT-BIH database was employed using the inter-patient paradigm. Besides, the robustness of the system against segmentation errors was tested by adding jitter to the R-wave positions given by the MIT-BIH database. Additionally, each group of features had its robustness against segmentation error tested as well. RESULTS: The experimental results of the proposed classification system with jitter show that the sensitivities for the classes N, S, and V are 93.7, 89.7, and 87.9, respectively. Also, the corresponding positive predictive values are 99.2, 36.8, and 93.9, respectively. CONCLUSIONS: The proposed method was able to outperform several state-of-the-art methods, even though the R-wave position was synthetically corrupted by added jitter. The obtained results show that our approach can be employed in real scenarios where segmentation errors and the inter-patient paradigm are present.

Asunto(s)

RESUMEN

Purpose: To investigate the error rate of segmentation in the automatic measurement of anterior chamber volume (ACV) and iris volume (IV) by swept-source anterior segment optical coherence tomography (SS-ASOCT) in narrow-angle and wide-angle eyes. Methods: In this study, fifty eyes from 25 narrow-angle subjects and fifty eyes from 25 wide-angle subjects were enrolled. SS-ASOCT examinations were performed and each SS-ASOCT scan was reviewed, and segmentation errors in the automatic measurement of ACV and IV were classified and manually corrected. Error rates were compared between the narrow-angle and the wide-angle groups, and ACV and IV before and after manual correction were compared. Results: A total of 12,800 SS-ASOCT scans were reviewed. Segmentation error rates of angle recess, iris root, posterior surface of the iris, pupil margin, and anterior surface of the lens were 84.06, 93.30, 13.15, 59.21, and 25.27%, respectively. Segmentation errors of angle recess, iris root, posterior surface of the iris, and pupil margin occurred more frequently in narrow-angle eyes, while more segmentation errors of the anterior surface of the lens were found in wide-angle eyes (all P < 0.001). ACV decreased and IV increased significantly after manual correction of segmentation errors in both groups (all P < 0.01). Conclusion: Segmentation errors were prevalent in the volumetric measurement by SS-ASOCT, particularly in narrow-angle eyes, leading to mismeasurement of ACV and IV.

RESUMEN

AIM: To determine the minimum number of optical coherence tomography B-scan corrections required to provide acceptable vessel density measurements on optical coherence tomography angiography images in eyes with diabetic macular edema. METHODS: In this prospective, noninterventional case series, the optical coherence tomography angiography images of eyes with center-involving diabetic macular edema were assessed. Optical coherence tomography angiography imaging was performed using RTVue Avanti spectral-domain optical coherence tomography system with the AngioVue software (V.2017.1.0.151; Optovue, Fremont, CA, USA). Segmentation error was recorded and manually corrected in the inner retinal layers in the central foveal, 100th and 200th optical coherence tomography B-scans. The segmentation error correction was then continued until all optical coherence tomography B-scans in whole en face image were corrected. At each step, the manual correction of each optical coherence tomography B-scan was propagated to whole image. The vessel density and retinal thickness were recorded at baseline and after each optical coherence tomography B-scan correction. RESULTS: A total of 36 eyes of 26 patients were included. To achieve full segmentation error correction in whole en face image, an average of 1.72 ± 1.81 and 5.57 ± 3.87 B-scans was corrected in inner plexiform layer and outer plexiform layer, respectively. The change in the vessel density measurements after complete segmentation error correction was statistically significant after inner plexiform layer correction. However, no statistically significant change in vessel density was found after manual correction of the outer plexiform layer. The vessel density measurements were statistically significantly different after single central foveal B-scan correction of inner plexiform layer compared with the baseline measurements (p = 0.03); however, it remained unchanged after further segmentation corrections of inner plexiform layer. CONCLUSION: Multiple optical coherence tomography B-scans should be manually corrected to address segmentation error in whole images of en face optical coherence tomography angiography in eyes with diabetic macular edema. Correction of central foveal B-scan provides the most significant change in vessel density measurements in eyes with diabetic macular edema.

RESUMEN

PURPOSE: To evaluate the impact of segmentation error on vessel density measurements in healthy eyes and eyes with diabetic macular oedema (DMO). METHODS: In this prospective, comparative, non-interventional study, enface optical coherence tomography angiography (OCTA) images of the macula from healthy eyes and eyes with DMO were acquired. Two expert graders assessed and corrected the segmentation error. The rate of segmentation error and the changes in vessel density and inner retinal thickness after correction of the segmentation error were recorded and compared between the two groups. RESULTS: 20 eyes with DMO and 24 healthy eyes were evaluated. Intergrader agreement was excellent (intraclass correlation coefficient ≥0.9) for all parameters in both groups. The rate of segmentation error was 33% and 100% in healthy and diabetic eyes, respectively (p<0.001). Nine healthy eyes (37.5%) and all eyes with DMO (100%) were noted to exhibit a change in at least one of the foveal or parafoveal vessel density measurements. The rate of any change in foveal and parafoveal vessel densities in both the superficial and deep capillary plexus was statistically significantly higher in the diabetic group (all p<0.001). No statistically significant change was observed in mean vessel density (superficial and deep capillary plexuses) after correction of the segmentation error in healthy and DMO eyes (All p>0.05). However, the mean absolute change in the vessel density measurements was statistically significantly higher in the diabetic group (all p<0.05). The mean absolute change in superficial and deep inner retinal thickness was statistically significantly higher in DMO (p=0.02 and p=0.002, respectively). CONCLUSIONS: In this study, misidentification of retinal layers and consequent vessel density measurement error occurred in all eyes with DMO and in one-third of healthy eyes. The segmentation error should be checked and manually corrected in the OCTA vessel density measurements, especially in the presence of macular oedema.

Asunto(s)

RESUMEN

PURPOSE: To analyze imaging artifacts and segmentation errors with wide-field swept-source optical coherence tomography angiography (SS-OCTA) in diabetic retinopathy (DR). METHODS: We conducted a prospective, observational study at Massachusetts Eye and Ear from December 2018 to March 2019. Proliferative diabetic retinopathy (PDR), nonproliferative diabetic retinopathy (NPDR), diabetic patients with no diabetic retinopathy (DR), and healthy control eyes were included. All patients were imaged with a SS-OCTA and the Montage Angio (15 × 9 mm) was used for analysis. Images were independently evaluated by two graders using the motion artifact score (MAS). All statistical analyses were performed using SPSS 25.0 and R software. RESULTS: One hundred thirty-six eyes in 98 participants with the montage image were included in the study. Patients with more severe stages of DR had higher MAS by trend test analysis (P < 0.05). The occurrence of segmentation error was 0% in the healthy group, 10.53% in the no DR group, 10.00% in the NPDR group, and 50% in the PDR group. Multivariate regression analysis showed that the severity of DR and dry eye were the major factors affecting MAS (P < 0.05). There were some modifiable artifacts that could be corrected to improve image quality. CONCLUSIONS: Wide field SS-OCTA assesses retinal microvascular changes by noninvasive techniques, yet distinguishing real alterations from artifacts is paramount to accurate interpretations. DR severity and dry eye correlated with MAS. TRANSLATIONAL RELEVANCE: Understanding contributing factors and methods to reduce artifacts is critical to routine use and clinical trial with wide-field SS-OCTA.

RESUMEN

The aim of the present study was to evaluate the accuracy of the Topcon 3D optical coherence tomography (OCT)-2000 built-in algorithm in analyzing OCT data acquired using the Topcon 3D OCT-1000 instrument. Raw data of 3D macular 512×128 scans acquired using the Topcon 3D OCT-1000 instrument were analyzed using the Topcon 3D OCT-2000. The occurrence and severity of segmentation error (SE) were compared between the built-in algorithms of the two instruments. Agreement in retinal thickness measurement between the two systems was evaluated in normal and abnormal eyes. A total of 87 eyes from 87 patients were included. The image quality score evaluated by Topcon OCT-2000 software was lower than that of OCT-1000. No statistically significant difference was identified in the SE rate (77.01 vs. 74.71%; P=0.864) or mean SE score (15.97 vs. 16.30; P=0.763) of the total scan area between the two algorithms. Intraclass correlation coefficient values for retinal thickness were high (0.951-0.995). The mean paired difference in retinal thickness was 3.72-5.77 µm (P<0.05) in normal and 0.61-9.52 µm (P<0.05) in abnormal eyes. No significant difference in retinal segmentation performance was identified between OCT-2000 and OCT-1000 when analyzing OCT-1000 raw data. In conclusion, retinal thickness measurements analyzed by the two OCT algorithms may be used interchangeably in normal eyes. Abnormal eyes required investigations as big differences in retinal thickness measurements may occur due to severe SEs.

RESUMEN

BACKGROUND: To determine the impact of retinal pigment epithelium (RPE) pathology on intersession repeatability of retinal thickness and volume metrics derived from Spectralis spectral-domain optical coherence tomography (Heidelberg Engineering, Heidelberg, Germany). DESIGN: Prospective cross-sectional single centre study. PARTICIPANTS: A total of 56 eyes of 56 subjects were divided into three groups: (i) normal RPE band (25 eyes); (ii) RPE elevation: macular soft drusen (13 eyes); and (iii) RPE attenuation: geographic atrophy or inherited retinal diseases (18 eyes). METHODS: Each subject underwent three consecutive follow-up macular raster scans (61 B-scans at 119 µm separation) at 1-month intervals. MAIN OUTCOME MEASURES: Retinal thicknesses and volumes for each zone of the macular subfields before and after manual correction of segmentation error. Coefficients of repeatability (CR) were calculated. RESULTS: Mean (range) age was 57 (21-88) years. Mean central subfield thickness (CST) and total macular volume were 264 and 258 µm (P = 0.62), and 8.0 and 7.8 mm3 (P = 0.31), before and after manual correction. Intersession CR (95% confidence interval) for CST and total macular volume were reduced from 40 (38-41) to 8.3 (8.1-8.5) and 0.62 to 0.16 mm3 after manual correction of segmentation lines. CR for CST were 7.4, 23.5 and 66.7 µm before and 7.0, 10.9 and 7.6 µm after manual correction in groups i, ii and iii. CONCLUSIONS: Segmentation error in eyes with RPE disease has a significant impact on intersession repeatability of Spectralis spectral-domain optical coherence tomography macular thickness and volume metrics. Careful examination of each B-scan and manual adjustment can enhance the utility of quantitative measurement. Improved automated segmentation algorithms are needed.

Asunto(s)

RESUMEN

Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature's ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

RESUMEN

PURPOSE: To report the frequency, severity and various types of artifacts associated with spectral-domain optical coherence tomography (SD-OCT) based on macular pathologies. METHODS: Data was collected retrospectively from 116 eyes of 116 subjects. SD-OCT (3D-1000, Topcon Corp., Japan) imaging was performed in 40 healthy eyes, 45 eyes with intraretinal pathology (IRP) and 31 eyes with subretinal pathology (SRP). The scan protocol was 12x6 mm radial scan. The frequency and types of artifacts were investigated in each scan and were analyzed based on macular disease. Additionally, the effect of artifacts on the measurement of macular thickness was studied. RESULTS: Errors occurred in 77 eyes (66.38%). Inner retinal boundary misidentification (IRBM) was the most common error (25.86%), with the frequencies of other types of artifacts being 10.34% for off-center fixation, 15.52% for degraded image and 8.6% for outer retinal boundary misidentification (ORBM). The overall error rate of SD-OCT in the retinal pathology group was much higher than that in the normal group. Macular thickness was underestimated in the IRP group because the outer retinal boundary of the IRP group tended to be misidentified toward the inner retina (p<0.01). CONCLUSIONS: SD-OCT can frequently cause various types of artifacts in patients with macular disease. When interpreting OCT images, the artifacts of SD-OCT should be considered in order to obtain accurate macular thickness and to prevent erroneous clinical decisions.

Asunto(s)