Semi-automatic Segmentation Algorithm Research Articles

Optimal time to definitive enucleation of large cysts following marsupialization: A single center, retrospective study

ObjectivesOptimal time to enucleation following marsupialization of large odontogenic mandibular cysts is undefined. We aim to assess volume reduction throughout follow-up, to indicate optimal time to enucleation. Secondary objectives include the identification of factors influencing cyst reduction. Study designWe retrospectively enrolled 15 patients with mandibular cysts of different histological types treated with marsupialization at our center between 2018 and 2022. Cyst volume was assessed with cone-beam computed tomography (CBCT) and a semi-automatic segmentation algorithm, at baseline and between 6 and 8 months post marsupialization. ResultsThe overall mean cyst volume reduction percent (VR%) was 57.7 % or 0.2 % per day. VR% at 8 months was significantly higher than those assessed at 6 and 7 months (67.1% vs 47.1 %, p = 0.003). Time to CBCT was the only independent variable influencing cyst VR%. ConclusionOur study proves that the optimal time to enucleation for mandibular cyst is 8 months, independent of histological cyst type, patient age, baseline cyst volume and the number of pre-operative residual bone walls.

Radiomics: A Powerful Tool

The Artificial Intelligence based technique of radiomics is an evolving modality that employs data characterization algorithms to extract a variety of useful features from medical images [1].Tumoral patterns are revealed that cannot be appreciated by the naked eye [2]. This can aid in assessing prognosis and gauging the response of tumor cells to therapy [3]. Various imaging modalities like CT, PET MR provide essential raw data. Extraction tools then use the raw data volumes to analyze pixel/voxel characteristics. Using these images, “volumes of interest” can be generated since such segmentation entails handling and processing of large image data; automatic and semiautomatic segmentation algorithms are employed enabling automation [4]. However, thorough testing and quality assurance are vital to ensure that the algorithm used is not only accurate, consistent, and reproducible but also time-efficient [5].

Integration of Swin UNETR and statistical shape modeling for a semi-automated segmentation of the knee and biomechanical modeling of articular cartilage

Simulation studies, such as finite element (FE) modeling, provide insight into knee joint mechanics without patient involvement. Generic FE models mimic the biomechanical behavior of the tissue, but overlook variations in geometry, loading, and material properties of a population. Conversely, subject-specific models include these factors, resulting in enhanced predictive precision, but are laborious and time intensive. The present study aimed to enhance subject-specific knee joint FE modeling by incorporating a semi-automated segmentation algorithm using a 3D Swin UNETR for an initial segmentation of the femur and tibia, followed by a statistical shape model (SSM) adjustment to improve surface roughness and continuity. For comparison, a manual FE model was developed through manual segmentation (i.e., the de-facto standard approach). Both FE models were subjected to gait loading and the predicted mechanical response was compared. The semi-automated segmentation achieved a Dice similarity coefficient (DSC) of over 98% for both the femur and tibia. Hausdorff distance (mm) between the semi-automated and manual segmentation was 1.4 mm. The mechanical results (max principal stress and strain, fluid pressure, fibril strain, and contact area) showed no significant differences between the manual and semi-automated FE models, indicating the effectiveness of the proposed semi-automated segmentation in creating accurate knee joint FE models. We have made our semi-automated models publicly accessible to support and facilitate biomechanical modeling and medical image segmentation efforts (https://data.mendeley.com/datasets/k5hdc9cz7w/1).

Visualization and Quantitative Evaluation of Functional Structures of Soybean Root Nodules via Synchrotron X-ray Imaging.

The efficiency of N2-fixation in legume-rhizobia symbiosis is a function of root nodule activity. Nodules consist of 2 functionally important tissues: (a) a central infected zone (CIZ), colonized by rhizobia bacteria, which serves as the site of N2-fixation, and (b) vascular bundles (VBs), serving as conduits for the transport of water, nutrients, and fixed nitrogen compounds between the nodules and plant. A quantitative evaluation of these tissues is essential to unravel their functional importance in N2-fixation. Employing synchrotron-based x-ray microcomputed tomography (SR-μCT) at submicron resolutions, we obtained high-quality tomograms of fresh soybean root nodules in a non-invasive manner. A semi-automated segmentation algorithm was employed to generate 3-dimensional (3D) models of the internal root nodule structure of the CIZ and VBs, and their volumes were quantified based on the reconstructed 3D structures. Furthermore, synchrotron x-ray fluorescence imaging revealed a distinctive localization of Fe within CIZ tissue and Zn within VBs, allowing for their visualization in 2 dimensions. This study represents a pioneer application of the SR-μCT technique for volumetric quantification of CIZ and VB tissues in fresh, intact soybean root nodules. The proposed methods enable the exploitation of root nodule's anatomical features as novel traits in breeding, aiming to enhance N2-fixation through improved root nodule activity.

Dynamic Changes in Lymph Node Size and Skin Scoring Predict Response to Treatment in CTCL: An Interim Analysis

Cutaneous T-cell lymphoma (CTCL) is a heterogenous group of non-Hodgkin T-cell lymphomas with predominant skin involvement. Mycosis fungoides and Sézary syndrome are the most common subtypes and present with a wide spectrum of cutaneous and extra-cutaneous manifestations. Early-stage disease is often controlled with skin-directed therapies while advanced-stage disease can be treatment-refractory and often requires multiple lines of systemic therapy. It is therefore of great interest to identify early predictors of treatment response to tailor therapeutic management decisions. Modified Severity-Weighted Assessment Tool (mSWAT) scoring and lymph node evaluation are important components of treatment response assessment in clinical practice and in trials. A major limitation of current assessment methods is the use of relative changes in mSWAT and lymph node size which do not account for heterogeneous treatment effects. Novel assessment techniques that reflect the dynamic changes occurring within the tumor environment during treatment have the potential to offer more accurate insights into treatment response than current methods. Among these novel approaches is kinetic modeling of tumor growth rate ( g), which has been validated as a biomarker for treatment response and survival in other types of cancer but has never been used in CTCL. Kinetic modeling provides the benefit of evaluating the simultaneous rates of growth of treatment-resistant cells and regression of treatment-responsive cells. We hypothesized that dynamic changes in lymph node size and mSWAT scores over time could predict response to treatment in CTCL patients. We retrospectively analyzed clinical data and computed tomography scans from 119 patients enrolled in the MAVORIC trial. An open-source imaging platform with integrated semi-automated segmentation algorithms was used to quantify lymph node volumes for each patient. Kinetic modeling was applied to estimate the simultaneous rates of growth ( g) and regression ( d) of lymph node size and mSWAT scores during treatment. Patients were divided into two groups based on g and correlation with time to treatment failure (TTF) was evaluated. Tumor doubling times were estimated using the equation dt = 0.693/ g. For most patients, g and d could be estimated, and these values could be determined early in the treatment course. Volumetric lymph node growth rate had an inverse correlation with TTF (p < 0.0001). Patients with with faster rates of nodal growth (median g = 0.0077 d -1, doubling time = 90 days) had a median TTF of 2.9 months, whereas patients with slower rates of nodal growth (median g = 0.0013 d -1, doubling time = 533 days) had a median TTF of 8.8 months. Rate of growth of mSWAT scores also had an inverse correlation with TTF (p < 0.0001). Those with the fastest rate of increase in mSWAT scores (median g = 0.0057 d -1, doubling time = 122 days) had a median TTF of 2.9 months while those with the slowest rate of increase (median g = 0.0013 d -1, doubling time = 533 days) had a median TTF of 8.5 months. In this interim analysis, we use a novel kinetic model to demonstrate that g correlates with time to treatment failure, suggesting that lymph node and mSWAT growth kinetics may be early predictors of treatment response in CTCL. Our findings have potential implications for both clinical practice and trials. Lymph node and mSWAT growth rates may support clinicians in making early decisions about adapting treatment regimens for individual patients. In clinical trials and early drug development, the incorporation of g as an endpoint may accelerate the recognition of promising drug candidates. Our findings require validation in a larger cohort as well as prospective studies.

Reconfiguration and loss of peritubular capillaries in chronic kidney disease

Functional and structural alterations of peritubular capillaries (PTCs) are a major determinant of chronic kidney disease (CKD). Using a software-based algorithm for semiautomatic segmentation and morphometric quantification, this study analyzes alterations of PTC shape associated with chronic tubulointerstitial injury in three mouse models and in human biopsies. In normal kidney tissue PTC shape was predominantly elongated, whereas the majority of PTCs associated with chronic tubulointerstitial injury had a rounder shape. This was reflected by significantly reduced PTC luminal area, perimeter and diameters as well as by significantly increased circularity and roundness. These morphological alterations were consistent in all mouse models and human kidney biopsies. The mean circularity of PTCs correlated significantly with categorized glomerular filtration rates and the degree of interstitial fibrosis and tubular atrophy (IFTA) and classified the presence of CKD or IFTA. 3D reconstruction of renal capillaries revealed not only a significant reduction, but more importantly a substantial simplification and reconfiguration of the renal microvasculature in mice with chronic tubulointerstitial injury. Computational modelling predicted that round PTCs can deliver oxygen more homogeneously to the surrounding tissue. Our findings indicate that alterations of PTC shape represent a common and uniform reaction to chronic tubulointerstitial injury independent of the underlying kidney disease.

Retracted: Application of MRI Image Based on Computer Semiautomatic Segmentation Algorithm in the Classification Prediction of Breast Cancer Histology.

[This retracts the article DOI: 10.1155/2021/6088322.].

Clinical and radiomics feature-based outcome analysis in lumbar disc herniation surgery

BackgroundLow back pain is a widely prevalent symptom and the foremost cause of disability on a global scale. Although various degenerative imaging findings observed on magnetic resonance imaging (MRI) have been linked to low back pain and disc herniation, none of them can be considered pathognomonic for this condition, given the high prevalence of abnormal findings in asymptomatic individuals. Nevertheless, there is a lack of knowledge regarding whether radiomics features in MRI images combined with clinical features can be useful for prediction modeling of treatment success. The objective of this study was to explore the potential of radiomics feature analysis combined with clinical features and artificial intelligence-based techniques (machine learning/deep learning) in identifying MRI predictors for the prediction of outcomes after lumbar disc herniation surgery.MethodsWe included n = 172 patients who underwent discectomy due to disc herniation with preoperative T2-weighted MRI examinations. Extracted clinical features included sex, age, alcohol and nicotine consumption, insurance type, hospital length of stay (LOS), complications, operation time, ASA score, preoperative CRP, surgical technique (microsurgical versus full-endoscopic), and information regarding the experience of the performing surgeon (years of experience with the surgical technique and the number of surgeries performed at the time of surgery). The present study employed a semiautomatic region-growing volumetric segmentation algorithm to segment herniated discs. In addition, 3D-radiomics features, which characterize phenotypic differences based on intensity, shape, and texture, were extracted from the computed magnetic resonance imaging (MRI) images. Selected features identified by feature importance analyses were utilized for both machine learning and deep learning models (n = 17 models).ResultsThe mean accuracy over all models for training and testing in the combined feature set was 93.31 ± 4.96 and 88.17 ± 2.58. The mean accuracy for training and testing in the clinical feature set was 91.28 ± 4.56 and 87.69 ± 3.62.ConclusionsOur results suggest a minimal but detectable improvement in predictive tasks when radiomics features are included. However, the extent of this advantage should be considered with caution, emphasizing the potential of exploring multimodal data inputs in future predictive modeling.

Ultrahigh Resolution OCT Markers of Normal Aging and Early Age-related Macular Degeneration.

Ultrahigh resolution spectral domain-OCT (UHR SD-OCT) enables invivo visualization of micrometric structural markers which differentially associate with normal aging versus age-related macular degeneration (AMD). This study explores the hypothesis that UHR SD-OCT can detect and quantify sub-retinal pigment epithelium (RPE) deposits in early AMD, separating AMD pathology from normal aging. Prospective cross-sectional study. A total of 53 nonexudative (dry) AMD eyes from 39 patients, and 63 normal eyes from 39 subjects. Clinical UHR SD-OCT scans were performed using a high-density protocol. Exemplary high-resolution histology and transmission electron microscopy images were obtained from archive donor eyes. Three trained readers evaluated and labeled outer retina morphological features, including the appearance of a hyporeflective split within the RPE-RPE basal lamina (RPE-BL)-Bruch's membrane (BrM) complex on UHR brightness (B)-scans. A semi-automatic segmentation algorithm measured the thickness of the RPE-BL-BrM split/hyporeflective band. Qualitative description of outer retinal morphological changes on UHR SD-OCT B-scans; the proportion of the RPE-BL-BrM complex with visible split (%) and the thickness of the resulting hyporeflective band (μm). In young normal eyes, UHR SD-OCT consistently revealed an RPE-BL-BrM split/hyporeflective band. Its visibility and thickness were less in eyes of advanced age. However, the split/hyporeflective band was again visible in early AMD eyes. Both qualitative reading and quantitative thickness measurements showed significantly elevated visibility and thickness of the RPE-BL-BrM split/hyporeflective in early AMD eyes compared to age-matched controls. Our imaging results strongly support the hypothesis that appearance of the RPE-BL-BrM split/hyporeflective band in older subjects is dominated by the BL deposit, an indicator of early AMD well known from histology. Ultrahigh resolution SD-OCT can be used to investigate physiological aging as well as early AMD pathology in clinical imaging studies. Developing quantifiable markers associated with disease pathogenesis and progression can facilitate drug discovery, as well as reduce clinical trial times. Proprietary or commercial disclosure may be found after the references.

Automatic Segmentation and Mechanical Characterisation of the Intraluminal Thrombus and Arterial Wall of Abdominal Aortic Aneurysms Using Time Resolved 3D Ultrasound Images

This study proposes a method for semi-automatic segmentation of abdominal aortic aneurysms (AAAs) and their intraluminal thrombus (ILT), based on time resolved 3D ultrasound (US), and validates results with computed tomography (CT). Moreover, mechanical properties of both wall and ILT are determined, and possible correlations with ILT size and blood pressure are investigated. A semi-automatic segmentation algorithm was developed combining a star-Kalman approach with a 3D snake algorithm. The segmented geometries of both lumen and inner vessel wall were validated with both manual US based segmentations and CT based segmentations. Finally, the lumen and vessel wall distensibility and ILT compressibility were estimated, and correlated to ILT size and blood pressure. For the vessel wall and lumen, the median Similarity Index (SI) was 92% (IQR 90, 94%) and 83% (IQR 75, 87%), respectively. The distensibility of the vessel wall could be determined in 37 out of 40 cases, and had a median value of 0.28 10-5 Pa-1 (IQR 0.18, 0.51⋅10-5). The median systolic-diastolic volume change of the ILT was determined successfully in 21 out of 40 patients, and was -0.57% (IQR -1.1, 1.2%). The vessel and lumen distensibility showed a strong correlation with the systolic pressure (p < .010), rather than with the diastolic pressure. Besides, the lumen distensibility was strongly correlated with the ILT thickness (p = .023). The performance of the semi-automatic segmentation algorithm was shown to be as good as the manual segmentations and highly dependent on the visibility of the ILT (limited contrast in seven patients and clutter in nine patients). This study shows promising results for mechanical characterisation of the vessel, and ILT, including a correlation between distensibility, ILT size, and blood pressure. For future work, inclusion rate needs to be increased by improving the image contrast with novel US techniques.

Optical coherence tomography for in vivo longitudinal monitoring of artificial dermal scaffold.

Artificial dermal scaffold (ADS) has undergone rapid development and been increasingly used for treating skin wound in clinics due to its good biocompatibility, controllable degradation, and low risk of disease infection. To obtain good treatment efficacy, ADS needs to be monitored longitudinally during the treatment process. For example, scaffold-tissue fit, cell in-growth, vascular regeneration, and scaffold degradation are the key properties to be inspected. However, to date, there are no effective, real-time, and noninvasive techniques to meet the requirement of the scaffold monitoring above. In this study, we propose to use optical coherence tomography (OCT) to monitor ADS in vivo through three-dimensional imaging. A swept source OCT system with a handheld probe was developed for in vivo skin imaging. Moreover, a cell in-growth, vascular regeneration, and scaffold degradation rate (IRDR) was defined with the volume reduction rate of the scaffold's collagen sponge layer. To measure the IRDR, a semiautomatic image segmentation algorithm was designed based on U-Net to segment the collagen sponge layer of the scaffold from OCT images. The results show that the scaffold-tissue fit can be clearly visualized under OCT imaging. The IRDR can be computed based on the volume of the segmented collagen sponge layer. It is observed that the IRDR appeared to a linear function of the time and in addition, the IRDR varied among different skin parts. Overall, it can be concluded that OCT has a good potential to monitor ADS in vivo. This can help guide the clinicians to control the treatment with ADS to improve the therapy.

A fast and reliable method for semi-automated planimetric quantification of dental plaque in clinical trials.

To develop a simple and reproducible method for semi-automated planimetric quantification of dental plaque. Plaque from 20 healthy volunteers was disclosed using erythrosine, and fluorescence images of the first incisors, first premolars, and first molars were recorded after 1, 7, and 14 days of de novo plaque formation. The planimetric plaque index (PPI) was determined using a semi-automated threshold-based image segmentation algorithm and compared with manually determined PPI and the Turesky modification of the Quigley-Hein plaque index (TM-QHPI). The decrease of tooth autofluorescence in plaque-covered areas was quantified as an index of plaque thickness (TI). Data were analysed by analysis of variance (ANOVA) and Pearson correlations. The high contrast between teeth, disclosed plaque, and soft tissues in fluorescence images allowed for a fast threshold-based image segmentation. Semi-automated PPI is strongly correlated with manual planimetry (r=0.92; p < .001) and TM-QHPI recordings (r=0.88; p < .001), and may exhibit a higher discriminatory power than TM-QHPI due to its continuous scale. TI values corresponded to optically perceived plaque thickness, and no differences were observed over time (p > .05, ANOVA). The proposed semi-automated planimetric analysis based on fluorescence images is a simple and efficient method for dental plaque quantification in multiple images with reduced human input.

Clinical validation of a semi-automated segmentation algorithm for target volume definition on planning CT and CBCT in stereotactic body radiotherapy (SBRT) for peripheral lung lesions.

Stereotactic body radiotherapy (SBRT) is an ablative method for lung malignancies. Here, the definition of the gross target volume (GTV) is subject to interobserver variation. In this study, we aimed to evaluate the interobserver variability during SBRT and its dosimetric impact, as well as to introduce a semi-automated delineation tool for both planning computer tomography (P-CT) and cone beam CT (CBCT) to help to standardise GTV delineation and adaptive volume-change registration. The interobserver variation of GTV manual contours from five physicians was analysed in 15 patients after lung SBRT on free breathing (FB) P-CT (n=15) and CBCT (n=90) before and after each fraction. The dosimetric impact from interobserver variations of GTV based on the original treatment plan was analysed. Next, the accuracy of an in-house easy-to-use semi-automated-segmentation algorithm for pulmonary lesions was compared with gold standard contours in FB P-CT and CBCT, as well as 4D P-CT of additional 10 patients. The interobserver variability in manual contours resulted in violations of dose coverage of the planning target volume (PTV), which, in turn, resulted in compromised tumour control probability in contours from four physicians. The validation of the semi-automated delineation algorithm using thorax phantom led to a highly reliable accuracy in defining GTVs. Comparing the unsupervised auto-contours with the gold standard delineation revealed high equal high concordance for FB P-CT, 4D P-CT and CBCT, with a DSC of 0.83, 0.76 and 0.8, respectively. The supervised use of the semi-automated delineation tool improved its accuracy, with DSCs of 0.86, 0.86 and 0.8 for FB P-CT, 4D P-CT and CBCT, respectively. The use of the algorithm was associated with a significantly shorter working time. The semi-automated delineation tool can accurately register volume changes in CBCTs. The segmentation algorithm provides a reliable, standardised and time-saving alternative for manual delineation in lung SBRT in P-CT and CBCT.

Evaluation of Volumetric Lymph Node Measurements in Cutaneous T-Cell Lymphoma Patients Enrolled in the Mavoric Trial: An Interim Analysis

Lymph node assessment is an important component of staging, classification, and treatment response assessment in cutaneous T-cell lymphoma (CTCL). Although a biopsy is the only definitive way to assess nodal involvement, radiologic evaluation is commonly used in practice given its practicality. Current radiologic criteria are adapted from guidelines for lymphomas with primarily nodal involvement and have not been validated in CTCL patients. These criteria are limited by linear measurements which fail to accurately capture small and/or asymmetric nodal involvement in CTCL and may lead to flawed estimations of the overall disease burden. Furthermore, unidimensional and bidimensional measurements are subject to significant inter- and intra-observer variability. More accurate methods of lymph node evaluation are needed to improve risk stratification and treatment response assessment in CTCL. Recent advances in digital imaging techniques have made it possible to obtain volumetric tumor measurements. This technique has shown promise as a more accurate imaging biomarker than unidimensional measurements in several solid cancer types, offering improved sensitivity for changes in tumor burden during treatment. Volumetric lymph node measurements have been shown to be superior to unidimensional measurements in distinguishing between benign and malignant lymph nodes in systemic lymphoma, however volumetric measurements have never been studied in CTCL. The aim of this study was to assess the utility of volumetric lymph node measurements in CTCL using this novel imaging technique. We analyzed imaging and clinical data from the mogamulizumab versus vorinostat in previously treated cutaneous T-cell lymphoma (MAVORIC) trial which included 372 CTCL patients randomized to receive either mogalizumab or vorinostat. The majority of patients randomized to vorinostat crossed over to mogalizumab due to disease progression or intolerance. As part of the trial, patients underwent computed tomography (CT) scans at baseline and regular follow-up intervals to assess for lymph node response to treatment. In our study, target lymph nodes in serial CT scans were measured by a team of radiologists using a response assessment system built on open-source software known as the Weasis imaging platform. Semi-automated segmentation algorithms were used to quantify unidimensional and bidimensional measurements as well as lymph node volumes. Our preliminary data suggests that there is a correlation between unidimensional, bidimensional, and volumetric lymph node measurements. For the first time, we validate volumetric lymph node measurement as a viable method of lymph node assessment in CTCL. This implicates lymph node volume as an alternative metric for lymph node assessment in CTCL that has the potential to improve the accuracy of current nodal assessment criteria. Additional research is underway to determine whether volumetric lymph node measurements are superior to uni- and bidimensional measurements in assessing treatment response and predicting clinical outcomes in CTCL.

Hypothalamic volume in pedophilia with or without child sexual offense

The hypothalamus regulates sexual behavior and is simultaneously associated with aggression and violence. Consequently, this brain region is relevant in research of pedophilia and child sexual offenses (CSO). The distinction between these two phenomena is of great importance and was the object of consideration of this study. We analyzed exclusively men, including 73 pedophilic offenders who committed CSO, an equal number of people with pedophilia but without such offenses, and 133 non-pedophilic, non-offending subjects who formed the control group. All data were collected in a multicenter in vivo study and analyzed using a semi-automated segmentation algorithm for 3-Tesla magnetic resonance images. Men with pedophilia who committed CSO on average had a 47 mm3 smaller hypothalamus per side than people without committed CSO. This effect was driven by both the group of non-offending people with pedophilia and the control group. By contrast, the exploratory comparison of pedophilic persons without CSO with the control group showed no significant difference. The present study demonstrates a deviant hypothalamic structure as a neurobiological correlate of CSO in pedophiles, but not in people with pedophilia who have not committed CSO. Thus, it strengthens the argument to distinguish between sexual offending and paraphilic sexual preferences.

Supervised learning and reinforcement learning of feedback models for reactive behaviors: Tactile feedback testbed

Robots need to be able to adapt to unexpected changes in the environment such that they can autonomously succeed in their tasks. However, hand-designing feedback models for adaptation is tedious, if at all possible, making data-driven methods a promising alternative. In this paper, we introduce a full framework for learning feedback models for reactive motion planning. Our pipeline starts by segmenting demonstrations of a complete task into motion primitives via a semi-automated segmentation algorithm. Then, given additional demonstrations of successful adaptation behaviors, we learn initial feedback models through learning-from-demonstrations. In the final phase, a sample-efficient reinforcement learning algorithm fine-tunes these feedback models for novel task settings through few real system interactions. We evaluate our approach on a real anthropomorphic robot in learning a tactile feedback task.

Mammographic Classification of Breast Cancer Microcalcifications through Extreme Gradient Boosting

In this paper, we proposed an effective and efficient approach to the classification of breast cancer microcalcifications and evaluated the mathematical model for calcification on mammography with a large medical dataset. We employed several semi-automatic segmentation algorithms to extract 51 calcification features from mammograms, including morphologic and textural features. We adopted extreme gradient boosting (XGBoost) to classify microcalcifications. Then, we compared other machine learning techniques, including k-nearest neighbor (kNN), adaboostM1, decision tree, random decision forest (RDF), and gradient boosting decision tree (GBDT), with XGBoost. XGBoost showed the highest accuracy (90.24%) for classifying microcalcifications, and kNN demonstrated the lowest accuracy. This result demonstrates that it is essential for the classification of microcalcification to use the feature engineering method for the selection of the best composition of features. One of the contributions of this study is to present the best composition of features for efficient classification of breast cancers. This paper finds a way to select the best discriminative features as a collection to improve the accuracy. This study showed the highest accuracy (90.24%) for classifying microcalcifications with AUC = 0.89. Moreover, we highlighted the performance of various features from the dataset and found ideal parameters for classifying microcalcifications. Furthermore, we found that the XGBoost model is suitable both in theory and practice for the classification of calcifications on mammography.

Correlation Between Bioelectrical Impedance Analysis and Chest CT-Measured Erector Spinae Muscle Area: A Cross-Sectional Study.

BackgroundSkeletal muscle mass (SMM) plays an important part in diverse health and disease states. Bioelectrical impedance analysis (BIA) and computed tomography (CT) are available for its assessment. However, muscle mass assessed by BIA may be influenced by multiple factors. The erector spinae muscle area (ESA) on chest CT is recently presumed to be representative of SMM. This study aimed to derive BIA from the ESA and evaluate the magnitude of association (between ESA measured from chest CT) and BIA.MethodsSubjects hospitalized for health checkups between December 2020 and December 2021, having undergone both BIA (50 kHz, 0.8 mA) and chest CT, were included. ESA was quantified at the level of the 12th thoracic vertebra (T12-ESA) by a standardized semi-automated segmentation algorithm. Low SMM was defined using the Asian Working Group for Sarcopenia criteria. The association between T12-ESA and BIA was then evaluated. Stratified analyses by sex and BMI were also performed.ResultsAmong 606 included subjects (59.7 ± 16.6 years, 63.5% male), 110 (18.2%) had low SMM. BMI in low and normal SMM groups was 20.1 and 24.7 kg/m2, respectively. Current smoking, drinking, chronic obstructive pulmonary disease, and chronic renal dysfunction were more frequently seen in the low SMM group than in the normal SMM group. The final regression model included T12-ESA, weight, BMI, and age, and had an adjusted R 2 of 0.806 with BIA. In the validation group, the correlation between T12-ESA-derived BIA and BIA remained high (Pearson correlation = 0.899). Stratified analysis disclosed a stronger correlation between T12-ESA and BIA in male subjects than in female subjects (adjusted R 2 = 0.790 vs. adjusted R 2 = 0.711, p < 0.05), and a better correlation was observed in obese (BMI ≥ 30 kg/m2) compared with underweight (BMI < 18.5 kg/m2) subjects (adjusted R 2 = 0.852 vs. adjusted R 2 = 0.723, p < 0.05). Additional analysis revealed a significant correlation between T12-ESA and skeletal muscle cross-sectional area at the 3rd lumbar vertebra (L3-CSA) (adjusted R 2 = 0.935, p < 0.001).ConclusionsCT-based assessment of ESA at the T12 level is feasible and correlated well with BIA, especially in male subjects and obese subjects.

Assessment of the accuracy of imaging software for 3D rendering of the upper airway, usable in orthodontic and craniofacial clinical settings

BackgroundSeveral semi-automatic software are available for the three-dimensional reconstruction of the airway from DICOM files. The aim of this study was to evaluate the accuracy of the segmentation of the upper airway testing four free source and one commercially available semi-automatic software. A total of 20 cone-beam computed tomography (CBCT) were selected to perform semi-automatic segmentation of the upper airway. The software tested were Invesalius, ITK-Snap, Dolphin 3D, 3D Slicer and Seg3D. The same upper airway models were manually segmented (Mimics software) and set as the gold standard (GS) reference of the investigation. A specific 3D imaging technology was used to perform the superimposition between the upper airway model obtained with semi-automatic software and the GS model, and to perform the surface-to-surface matching analysis. The accuracy of semi-automatic segmentation was evaluated calculating the volumetric mean differences (mean bias and limits of agreement) and the percentage of matching of the upper airway models compared to the manual segmentation (GS). Qualitative assessments were performed using color-coded maps. All data were statistically analyzed for software comparisons.ResultsStatistically significant differences were found in the volumetric dimensions of the upper airway models and in the matching percentage among the tested software (p < 0.001). Invesalius was the most accurate software for 3D rendering of the upper airway (mean bias = 1.54 cm3; matching = 90.05%) followed by ITK-Snap (mean bias = − 2.52 cm3; matching = 84.44%), Seg 3D (mean bias = 3.21 cm3, matching = 87.36%), 3D Slicer (mean bias = − 4.77 cm3; matching = 82.08%) and Dolphin 3D (difference mean = − 6.06 cm3; matching = 78.26%). According to the color-coded map, the dis-matched area was mainly located at the most anterior nasal region of the airway. Volumetric data showed excellent inter-software reliability (GS vs semi-automatic software), with coefficient values ranging from 0.904 to 0.993, confirming proportional equivalence with manual segmentation.ConclusionDespite the excellent inter-software reliability, different semi-automatic segmentation algorithms could generate different patterns of inaccuracy error (underestimation/overestimation) of the upper airway models. Thus, is unreasonable to expect volumetric agreement among different software packages for the 3D rendering of the upper airway anatomy.

Design and validation of a semi-automatic bone segmentation algorithm from MRI to improve research efficiency

Segmentation of medical images into different tissue types is essential for many advancements in orthopaedic research; however, manual segmentation techniques can be time- and cost-prohibitive. The purpose of this work was to develop a semi-automatic segmentation algorithm that leverages gradients in spatial intensity to isolate the patella bone from magnetic resonance (MR) images of the knee that does not require a training set. The developed algorithm was validated in a sample of four human participants (in vivo) and three porcine stifle joints (ex vivo) using both magnetic resonance imaging (MRI) and computed tomography (CT). We assessed the repeatability (expressed as mean ± standard deviation) of the semi-automatic segmentation technique on: (1) the same MRI scan twice (Dice similarity coefficient = 0.988 ± 0.002; surface distance = − 0.01 ± 0.001 mm), (2) the scan/re-scan repeatability of the segmentation technique (surface distance = − 0.02 ± 0.03 mm), (3) how the semi-automatic segmentation technique compared to manual MRI segmentation (surface distance = − 0.02 ± 0.08 mm), and (4) how the semi-automatic segmentation technique compared when applied to both MRI and CT images of the same specimens (surface distance = − 0.02 ± 0.06 mm). Mean surface distances perpendicular to the cartilage surface were computed between pairs of patellar bone models. Critically, the semi-automatic segmentation algorithm developed in this work reduced segmentation time by approximately 75%. This method is promising for improving research throughput and potentially for use in generating training data for deep learning algorithms.