Semi-automatic Segmentation Research Articles

Fetal face shape analysis from prenatal 3D ultrasound images

3D ultrasound imaging of fetal faces has been predominantly confined to qualitative assessment. Many genetic conditions evade diagnosis and identification could assist with parental counselling, pregnancy management and neonatal care planning. We describe a methodology to build a shape model of the third trimester fetal face from 3D ultrasound and show how it can objectively describe morphological features and gestational-age related changes of normal fetal faces. 135 fetal face 3D ultrasound volumes (117 appropriately grown, 18 growth-restricted) of 24-34 weeks gestation were included. A 3D surface model of each face was obtained using a semi-automatic segmentation workflow. Size normalisation and rescaling was performed using a growth model giving the average size at every gestation. The model demonstrated a similar growth rate to standard head circumference reference charts. A landmark-free morphometry model was estimated to characterize shape differences using non-linear deformations of an idealized template face. Advancing gestation is associated with widening/fullness of the cheeks, contraction of the chin and deepening of the eyes. Fetal growth restriction is associated with a smaller average facial size but no morphological differences. This model may eventually be used as a reference to assist in the prenatal diagnosis of congenital anomalies with characteristic facial dysmorphisms.

POINT CLOUD SEGMENTATION IN HERITAGE PRESERVATION. ADVANCED DIGITAL PROCESS FOR HISTORICAL HOUSES

Abstract. This paper discusses the use of point cloud segmentation, both automatic and semi-automatic, in heritage conservation processes, with the aim of consciously integrating traditional and innovative methods. Thus, the research explores the potential of open-source software tools for semi-automatic point-cloud segmentation in enriching heritage knowledge and contributing to the inspection of its state of conservation. This ensures a 3D geometric view of reality and enables the identification of criticalities that may not be visible to the naked eye through colorimetric attributes. The study was conducted on Villa Leonardi, a historical house located in the city of Treia in the Marche Region (Italy) as a pilot test. The investigation focused on the east and south elevations of the building, which were suitable for two distinct trials: a semi-automatic procedure for analyzing the quality of mortar joints in an exposed masonry, and a semi-automatic procedure for mapping alterations and decay in a plastered masonry. To validate the results, manual and semi-automatic maps were compared using both qualitative and quantitative assessments. Qualitative assessment involved overlay and visual analysis, while quantitative assessment involved transforming the segmented point cloud into a mesh and calculating the resulting surface area. The critical interpretation of the two trials revealed both advantages and disadvantages; overall, experimentation highlighted the added value that advanced digital process can bring to the issue of heritage preservation.

20. IMPLEMENTATION OF A SEMI-AUTOMATED SEGMENTATION TOOL FOR COLON SURGICAL PLANNING

Abstract Introduction This study outlines the design and implementation of an application focused on optimizing surgical planning for colon surgery through the automated segmentation process of Computed Axial Tomography (CT) images. The tool provides continuous assistance to the user, enhancing the overall process management and efficiency. Methods A module has been developed for the 3DSlicer image computing platform. The algorithm was programmed in Python, primarily utilizing the Slicer, MRML, and VTK libraries. Additionally, DICOM images obtained from a publicly available database were used as samples for the study. Results The implementation of the semi-automatic segmentation method has proved to be successful, achieving the creation of a three-dimensional (3D) model of the colon with satisfactory results. The user has the facility to upload a CT image from a DICOM study, and through few interactions, a 3D model of the colon is generated, optimizing the surgical planning process. Conclusion Although we have successfully developed a semi-automatic segmentation method, the process requires certain specific conditions. For the image to be interpreted correctly, the patient must be treated with iodinated contrast medium prior to the CT study. In addition, an insufflation of the colon should be performed. These prerequisites are essential to ensure the quality and accuracy of the resulting images, which in turn will impact the efficiency of the planning process.

Volumetric Parameters Derived from CXCR4-Directed PET/CT Predict Outcome in Patients with Gastrointestinal Neuroendocrine Carcinomas

BackgroundGastro-entero-pancreatic neuroendocrine carcinomas (GEP-NECs) are an aggressive subgroup of neuroendocrine neoplasms (NENs). In patients affected with NEN, there is a growing body of evidence that increased C-X-C motif chemokine receptor (CXCR4) expression is linked to decreasing overall survival (OS) in an ex-vivo setting. Thus, we aimed to determine whether the in-vivo-derived CXCR4-directed whole-body PET signal can also determine GEP-NEC patients with shorter OS.MethodsWe retrospectively included 16 patients with histologically proven GEP-NEC, who underwent CXCR4-directed PET/CT for staging and therapy planning. We assessed maximum, peak, and mean standardized uptake values as well as whole-body tumor volume (TV) and total-lesion uptake (TLU = SUVmean × TV) using a semi-automatic segmentation tool with a 50% threshold. Association of PET-based biomarkers and OS or radiographic progression-free survival (rPFS; according to RECIST 1.1 criteria) was analyzed using univariable and multivariable cox regression.ResultsMedian OS and rPFS was 7.5 and 7 months, respectively. A significant correlation between TV and TLU was found for OS (TV: hazard ratio (HR) 1.007 95% confidence interval (CI) 1.000–1.014, p = 0.0309; TLU: HR 1.002 95% CI 1.000–1.003, p = 0.0350) and rPFS (TV: HR 1.010 95% CI 1.002–1.021; p = 0.0275; TLU: HR 1.002 95% CI 1.000–1.004, p = 0.0329), respectively. No significant correlation with OS or rPFS was found for non-volumetric parameters (p > 0.4). TV remained a significant predictive marker for OS and rPFS in multivariable analysis (OS: HR 1.012 95%, CI 1.003–1.022, p = 0.0084; rPFS: HR 1.009, 95% CI 0.9999–1.019, p = 0.0491), whereas TLU remained only prognostic for OS (HR 1.009, 95% CI 0.9999–1.019, p = 0.0194) but narrowly failed significance for rPFS (p = 0.0559).ConclusionIn-vivo assessment of CXCR4 PET-derived volumetric parameters is predictive for outcome of patients with GEP-NEC and could be used as a risk stratification tool, which detects patients prone to early progression.

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).

Abstract TP96: Association Between Infarct Volume, Neighborhood-Level Deprivation, and Outcomes in Pediatric Stroke

Introduction: Recent studies in adults have reported an association between neighborhood-level deprivation, infarct volume and outcome. However, this is yet to be investigated in pediatric arterial ischemic stroke (AIS). Our study aimed to assess the relationship between neighborhood-level deprivation, infarct volume, and neurological outcome in children diagnosed with AIS. Methods: We conducted a study of a consecutive cohort of children aged > 28 days-18 years and diagnosed with AIS between 2004 and 2019 at a comprehensive stroke center. Patient demographic, clinical characteristics and neighborhood material deprivation data including household income, parental educational attainment, the proportion of single-parent families, and housing quality were collected. Lesion volumes were determined by conducting semi-automatic segmentation of diffusion-weighted MRI brain scans at stroke presentation. Neurological outcome was assessed using the Pediatric Stroke Outcome Measure Severity Classification System wherein poor outcome was defined as moderate-to-severe deficit at 18 months post-stroke. Wilcoxon rank sum test was conducted. Results: Seventy-two patients were included in the study (62% male, median age of stroke onset 6.1 years [IQR 1.0-12.7]). 39% of patients were White, 72% lived in an urban region, and 64% in highly deprived neighborhoods. 70% of patients arrived within 6 hours from onset of stroke. Cardiac disease and other risk factors including infection and head trauma represented the most common risk factor. 55% presented with moderate stroke severity (as per the PedNIHSS). Median lesion volume was 14 cm 3 (IQR 2-51) and a mean infarct volume of 3% was reported. Race, rurality, and neighborhood-level material deprivation were not significantly associated with either percent infarct volume or neurological outcome; however, percent infarct volume was significantly associated with neurological outcome at 18 months post-stroke (W = 79, p = 0.025). Conclusion: Our study findings confirm the relationship between infarct volume and pediatric AIS outcomes. Future multi-center studies are warranted to further understand the interplay between material deprivation, infarct volume, and post-AIS neurological outcomes in children.

Deep learning-based segmentation of breast masses using convolutional neural networks

Automatic breast tumor segmentation based on convolutional neural networks (CNNs) is significant for the diagnosis and monitoring of breast cancers. CNNs have become an important method for early diagnosis of breast cancer and, thus, can help decrease the mortality rate. In order to assist medical professionals in breast cancer investigation a computerized system based on two encoder-decoder architectures for breast tumor segmentation has been developed. Two pre-trained DeepLabV3+ and U-Net models are proposed. The encoder generates a high-dimensional feature vector while the decoder analyses the low-resolution feature vector provided by the encoder and generates a semantic segmentation mask. Semantic segmentation based on deep learning techniques can overcome the limitations of traditional algorithms. To assess the efficiency of breast ultrasound image segmentation, we compare the segmentation results provided by CNNs against the Local Graph Cut technique (a semi-automatic segmentation method) in the Image Segmenter application. The output segmentation results have been evaluated by using the Dice similarity coefficient that compares the ground truth images provided by the specialists against the predicted segmentation results provided by the CNNs and Local Graph Cut algorithm. The proposed approach is validated on 780 breast ultrasonographic images of the BUSI public database of which 437 are benign and 210 are malignant. The BUSI database provides classification (benign or malignant) labels for ground truth in binary mask images. The average Dice scores computed between the ground truth images against CNNs were as follows: 0.9360 (malignant) and 0.9325 (benign) for the DeepLabV3+ architecture and of 0.6251 (malignant) and 0.6252 (benign) for the U-Net, respectively. When the segmentation results provided by CNNs were compared with the Local Graph Cut segmented images, the Dice scores were 0.9377 (malignant) and 0.9204 (benign) for DeepLabV3+ architecture and 0.6115 (malignant) and 0.6119 (benign) for U-Net, respectively. The results show that the DeepLabV3+ has significantly better segmentation performance and outperforms the U-Net network.

Fatty infiltration and morphology of cervical muscles in patients with temporomandibular disorders: A case-control study.

Changes in the fatty infiltration and/or muscle volume of neck muscles can alter cervical spine alignment and cranial load distribution, which may cause pain in the orofacial region. The aim of the study was to examine the muscle volume and fatty infiltration of neck muscles in patients with temporomandibular disorders (TMD). This case-control study included 18 patients with TMD and 18 ageand sex-matched controls. The muscle volume and fatty infiltration of the neck muscles of the participants were measured using magnetic resonance imaging (MRI) and ITK-SNAP software. The 3D models of the sternocleidomastoid (SCM), splenius capitis (SPLC), semispinalis cervicis (SC)-semispinalis capitis (SCP), and multifidus (M) muscles within the C3-C7 range were created using ITK-SNAP, a semi-automatic segmentation software. The models were used to determine the volumes and fatty infiltration levels. The Neck Disability Index (NDI) was used to assess neck pain-related disability. The severity of TMD was determined using the Fonseca Anamnestic Index (FAI), while jaw-related disability was measured with the Jaw Functional Limitation Scale-20 (JFLS-20). Pain levels were recorded at rest and during chewing using the numeric rating scale (NRS). There were no statistically significant differences in total muscle volume, fatty infiltration volume and fatty infiltration percentage of the SCM, SPLC, SCP, SC, and M muscles between the 2 groups (p > 0.05). The patient group had higher NDI scores compared to the controls (p < 0.001). The NDI scores correlated positively with the JFLS-20 (r = 0.831, p < 0.001), FAI (r = 0.815, p < 0.001) and NRS scores at rest (r = 0.753, p < 0.001) and during chewing (r = 0.686, p < 0.001). The present study did not identify any significant differences in the neck muscle volume or fatty infiltration between the TMD patients and controls. However, the severity of neck disability was found to correlate with jaw function, pain and TMD levels.

Deep learning-based bronchial tree-guided semi-automatic segmentation of pulmonary segments in computed tomography images.

Pulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach. The proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation. For the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm. This study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.

Abstract 42: Validation of a New Plaque-RADS Classification System to a Cohort of Embolic Stroke of Undetermined Source Patients

Introduction: A new Plaque-RADS classification (I-IV) is proposed to categorize the degree of carotid plaque instability and risk of embolic ischemic stroke. We tested the Plaque-RADS classification in a cohort of patients with embolic stroke of undetermined source (ESUS) and imaged with neck CTAs. Methods: Patients with unilateral anterior circulation ischemic stroke due to ESUS and neck CTAs showing &lt;50% carotid stenosis were retrospectively identified. Carotid total plaque thickness and ulceration were scored by a neuroradiologist blinded to stroke side. A semiautomated segmentation software measured intraplaque hemorrhage (IPH) volumes. The Plaque-RADS classification is defined as: I: no plaque; II: plaque thickness &lt;3mm ; III: plaque thickness ≥ 3mm or ulcerated; and IV: plaque with IPH&gt;50mL irrespective of thickness. Prevalence of Plaque-RADS subtypes was analyzed ipsilateral versus contralateral to stroke side. The proportion of low (subtypes I/II) versus high-risk (III/IV) carotid plaques on the ipsilateral versus contralateral stroke-side was tested using a McNemar’s test. Results: Ninety-four patients (N=52 female, mean age 65.4; N=188 plaques) met criteria. Plaque-RADS distribution was classified as: Plaque-RADS I: 18.1%; II: 44.7%; III: 36.7% (III ulc : 1.6%); IV: 0.5%. High-risk Plaque-RADS subtypes were significantly more prevalent on the ipsilateral (42.6%) compared to the contralateral side of stroke (31.9%, p=0.008). Conclusions: Carotid plaque ipsilateral to stroke side showed a higher proportion of Plaque-RADS III/IV subtypes. The Plaque-RADS classification may be used to risk-stratify carotid plaque phenotypes in patients with ESUS.

P067 Volumetric Assessment of Treatment Response in Newly Diagnosed Crohn Disease: A Pilot Study

Abstract Background Traditionally, mural thickness and disease length have been the radiological standards for assessing Crohn's Disease (CD) severity and treatment response. Our study aimed to evaluate and compare these linear measurements with volumetric ones in newly diagnosed pediatric CD, as well as to assess the concordance between manual and semi-automated volumetric methods. Methods In this single-center, prospective study, 20 children with newly diagnosed ileal CD treated with anti-TNF therapy from Dec 2018 to Oct 2021 (8 females; median age=14.5 years) underwent dedicated research MRI examinations at three timepoints – diagnosis (baseline) as well as 6 weeks and 6 months into therapy. For each exam and using T2-weighted Single Shot Fast Spin Echo (SSFSE) images, a single radiologist measured maximum bowel wall thickness (BWT, mm) and length of disease (cm). The inflamed ileum was manually segmented to measure tissue volume (ml) (Entrolytics; Motilent, London, UK). Semi-automated 3D volumetric measurements of the inflamed ileum (GI Seg tool) were created using the same platform. Estimated maximum BWT also was automatically calculated from manually-edited algorithmically generated masks. Mixed-effects models evaluated measurement changes over time. Intra-class correlation assessed absolute agreement between manual and automated volumetric assessments. Results BWT decreased over time with treatment (0.76 vs. 0.58 vs. 0.45 cm; p&amp;lt;0.0001), with a 24% decrease from baseline to 6 weeks and a 41% decrease from baseline to 6 months. Similarly, there was a significant decrease in length of disease over time (19.2 vs. 12.2 vs. 8.0 cm; p=0.002), with a 36% decrease from baseline to 6 weeks and a 58% decrease from baseline to 6 months. Manual volumetric measurements also showed a significant treatment response (19.8 vs. 11.6 vs. 5.1 ml; p&amp;lt;0.0001), with a 41% decrease from baseline to 6 weeks and a 74% decrease from baseline to 6 months. Using the semi-automated segmentation tool, the volume of inflamed bowel also decreased significantly over time (24.0 vs. 15.1 vs. 9.1 ml; p=0.0007), decreasing 37% between baseline and 6 weeks and 62% between baseline and 6 months. There was good agreement between manual and semi-automated volumetric bowel assessments (ICC=0.78 [95% CI: 0.57-0.88]). ICC between manual and code-estimated Max BWT was 0.60 [95% CI: 0.42, 0.72] with a strong positive correlation (r=0.839; p &amp;lt;0.001) between these two methods as shown in the Figure. Conclusion Volumetric assessments, along with automatic measurements of bowel wall thickness, show promise in accurately assessing treatment response in pediatric CD. These methods might provide more consistent and repeatable measurements, essential for long-term disease monitoring and management.

Association between type 2 diabetes mellitus and body composition based on MRI fat fraction mapping.

To explore the association between type 2 diabetes mellitus (T2DM) and body composition based on magnetic resonance fat fraction (FF) mapping. A total of 341 subjects, who underwent abdominal MRI examination with FF mapping were enrolled in this study, including 68 T2DM patients and 273 non-T2DM patients. The FFs and areas of visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT) and abdominal muscle (AM) were measured at the level of the L1-L2 vertebral. The FF of bone marrow adipose tissue (BMAT) was determined by the averaged FF values measured at the level of T12 and L1 vertebral, respectively. The whole hepatic fat fraction (HFF) and pancreatic fat fraction (PFF) were measured based on 3D semi-automatic segmentation on the FF mapping. All data were analyzed by GraphPad Prism and MedCalc. VAT area, VAT FF, HFF, PFF of T2DM group were higher than those of non-T2DM group after adjusting for age and sex (P < 0.05). However, there was no differences in SAT area, SAT FF, BMAT FF, AM area and AM FF between the two groups (P > 0.05). VAT area and PFF were independent risk factors of T2DM (all P < 0.05). The area under the curve (AUC) of the receiver operating characteristic (ROC) for VAT area and PFF in differentiating between T2DM and non-T2DM were 0.685 and 0.787, respectively, and the AUC of PFF was higher than VAT area (P < 0.05). Additionally, in seemingly healthy individuals, the SAT area, VAT area, and AM area were found to be significantly associated with being overweight and/or obese (BMI ≥ 25) (all P < 0.05). In this study, it was found that there were significant associations between T2DM and VAT area, VAT FF, HFF and PFF. In addition, VAT area and PFF were the independent risk factors of T2DM. Especially, PFF showed a high diagnostic performance in discrimination between T2DM and non-T2DM. These findings may highlight the crucial role of PFF in the pathophysiology of T2DM, and it might be served as a potential imaging biomarker of the prevention and treatment of T2DM. Additionally, in individuals without diabetes, focusing on SAT area, VAT area and AM area may help identify potential health risks and provide a basis for targeted weight management and prevention measures.

Combined Prognostic Impact of Low Muscle Mass and Hypoalbuminemia in Patients Hospitalized for Heart Failure: ARetrospective Cohort Study.

Sarcopenia and hypoalbuminemia have been identified as independent predictors of increased adverse outcomes, including mortality and readmissions, in hospitalized older adults with acute decompensated heart failure (ADHF). However, the impact of coexisting sarcopenia and hypoalbuminemia on morbidity and death in adults with ADHF has not yet been investigated. We aimed to investigate the combined effects of lower muscle mass (LMM) as a surrogate for sarcopenia and hypoalbuminemia on in-hospital and postdischarge outcomes of patients hospitalized for ADHF. A total of 385 patients admitted for ADHF between 2017 and 2020 at a single institution were retrospectively identified. Demographic and clinical data were collected, including serum albumin levels at admission and discharge. Skeletal muscle indices were derived from semi-automated segmentation software analysis on axial chest computed tomography at the twelfth vertebral level. Our analysis revealed that patients who had LMM with admission hypoalbuminemia experienced increased diagnoses of infection and delirium with longer hospital length of stay and more frequent discharge to a facility. Upon discharge, 27.9% of patients had higher muscle mass without discharge hypoalbuminemia (reference group), 9.7% had LMM without discharge hypoalbuminemia, 38.4% had higher muscle mass with discharge hypoalbuminemia, and 24.0% had LMM with discharge hypoalbuminemia; mortality rates were 37.6%, 51.4%, 48.9%, and 63.2%, respectively. 1- and 3-year mortality risks were highest in those with LMM and discharge hypoalbuminemia; this relationship remained significant over a median 23.6 (3.1-33.8) months follow-up time despite multivariable adjustments (hazard ratio, 2.03 [95% CI, 1.31-3.16]; P=0.002). Hospitalization with ADHF, LMM, and hypoalbuminemia portend heightened mortality risk.

Robust semi-automatic segmentation method: an expert assistant tool for muscles in CT and MR data

ABSTRACT Image muscle segmentation is useful to quantitatively assess musculoskeletal diseases by extracting biomarkers such as shape, texture and water diffusivity metrics. Although volumetric manual segmentation is time consuming and a bottleneck in practice, fully automatic approaches are still in progress to reach an acceptable accuracy. In this paper, we provide a robust semi-automated tool to segment two musculoskeletal systems, i.e. thigh and shoulder in MRI and CT modalities, respectively. The tool only needs a few manually labelled cross-sections to build a directed graph-structure of corresponding points between the successive spaced slices. The boundaries of each muscle are obtained by performing a spline interpolation based on the directed graph-structure. Each muscle label and its corresponding 3D mesh are deduced using post-processing techniques. We evaluated the tool on 26 MRI thighs and 16 CT shoulders. Three metrics along with inter-muscle overlapping were employed to evaluate the tool by comparison to an expert manual segmentation and a publicly available tools (ITK-SNAP, 3D Slicer). The results showed a mean Dice 0.988 ± 0.003 , and Hausdorff Distance 4.86 ± 1.67 mm in comparison to the manual reference for thigh muscle segmentation, and a mean Dice 0.961 ± 0.005 and Hausdorff Distance 2.42 ± 0.79 mm for shoulder muscle segmentation, outperformed the other methods. The tool is proposed as slicer module available at https://github.com/latimagine/SlicerSpline.

A Quantitative Method for the Evaluation of Deep Vein Thrombosis in a Murine Model Using Three-Dimensional Ultrasound Imaging.

Deep vein thrombosis (DVT) is a life-threatening condition that can lead to its sequelae pulmonary embolism (PE) or post-thrombotic syndrome (PTS). Murine models of DVT are frequently used in early-stage disease research and to assess potential therapies. This creates the need for the reliable and easy quantification of blood clots. In this paper, we present a novel high-frequency 3D ultrasound approach for the quantitative evaluation of the volume of DVT in an in vitro model and an in vivo murine model. The proposed method involves the use of a high-resolution ultrasound acquisition system and semiautomatic segmentation of the clot. The measured 3D volume of blood clots was validated to be correlated with in vitro blood clot weights with an R2 of 0.89. Additionally, the method was confirmed with an R2 of 0.91 in the in vivo mouse model with a cylindrical volume from macroscopic measurement. We anticipate that the proposed method will be useful in pharmacological or therapeutic studies in murine models of DVT.

Spherical harmonics analysis reveals cell shape-fate relationships in zebrafish lateral line neuromasts.

Cell shape is a powerful readout of cell state, fate and function. We describe a custom workflow to perform semi-automated, 3D cell and nucleus segmentation, and spherical harmonics and principal components analysis to distill cell and nuclear shape variation into discrete biologically meaningful parameters. We apply these methods to analyze shape in the neuromast cells of the zebrafish lateral line system, finding that shapes vary with cell location and identity. The distinction between hair cells and support cells accounted for much of the variation, which allowed us to train classifiers to predict cell identity from shape features. Using transgenic markers for support cell subpopulations, we found that subtypes had different shapes from each other. To investigate how loss of a neuromast cell type altered cell shape distributions, we examined atoh1a mutants that lack hair cells. We found that mutant neuromasts lacked the cell shape phenotype associated with hair cells, but did not exhibit a mutant-specific cell shape. Our results demonstrate the utility of using 3D cell shape features to characterize, compare and classify cells in a living developing organism.

Implementing a deep learning model for automatic tongue tumour segmentation in ex-vivo 3-dimensional ultrasound volumes

Three-dimensional (3D) ultrasound can assess the margins of resected tongue carcinoma during surgery. Manual segmentation (MS) is time-consuming, labour-intensive, and subject to operator variability. This study aims to investigate use of a 3D deep learning model for fast intraoperative segmentation of tongue carcinoma in 3D ultrasound volumes. Additionally, it investigates the clinical effect of automatic segmentation. A 3D No New U-Net (nnUNet) was trained on 113 manually annotated ultrasound volumes of resected tongue carcinoma. The model was implemented on a mobile workstation and clinically validated on 16 prospectively included tongue carcinoma patients. Different prediction settings were investigated. Automatic segmentations with multiple islands were adjusted by selecting the best-representing island. The final margin status (FMS) based on automatic, semi-automatic, and manual segmentation was computed and compared with the histopathological margin. The standard 3D nnUNet resulted in the best-performing automatic segmentation with a mean (SD) Dice volumetric score of 0.65 (0.30), Dice surface score of 0.73 (0.26), average surface distance of 0.44 (0.61) mm, Hausdorff distance of 6.65 (8.84) mm, and prediction time of 8 seconds. FMS based on automatic segmentation had a low correlation with histopathology (r = 0.12, p = 0.67); MS resulted in a moderate but insignificant correlation with histopathology (r = 0.4, p = 0.12, n = 16).Implementing the 3D nnUNet yielded fast, automatic segmentation of tongue carcinoma in 3D ultrasound volumes. Correlation between FMS and histopathology obtained from these segmentations was lower than the moderate correlation between MS and histopathology.

Deep learning driven segmentation of maxillary impacted canine on cone beam computed tomography images

The process of creating virtual models of dentomaxillofacial structures through three-dimensional segmentation is a crucial component of most digital dental workflows. This process is typically performed using manual or semi-automated approaches, which can be time-consuming and subject to observer bias. The aim of this study was to train and assess the performance of a convolutional neural network (CNN)-based online cloud platform for automated segmentation of maxillary impacted canine on CBCT image. A total of 100 CBCT images with maxillary canine impactions were randomly allocated into two groups: a training set (n = 50) and a testing set (n = 50). The training set was used to train the CNN model and the testing set was employed to evaluate the model performance. Both tasks were performed on an online cloud-based platform, ‘Virtual patient creator’ (Relu, Leuven, Belgium). The performance was assessed using voxel- and surface-based comparison between automated and semi-automated ground truth segmentations. In addition, the time required for segmentation was also calculated. The automated tool showed high performance for segmenting impacted canines with a dice similarity coefficient of 0.99 ± 0.02. Moreover, it was 24 times faster than semi-automated approach. The proposed CNN model achieved fast, consistent, and precise segmentation of maxillary impacted canines.

A Geometric Flow Approach for Segmentation of Images with Inhomongeneous Intensity and Missing Boundaries

Image segmentation is a complex mathematical problem, especially for images that contain intensity inhomogeneity and tightly packed objects with missing boundaries in between. For instance, Magnetic Resonance (MR) muscle images often contain both issues, making muscle segmentation especially difficult. In this paper we propose a novel intensity correction and a semi-automatic active contour-based segmentation approach. The approach uses a geometric flow that incorporates a Reproducing Kernel Hilbert Space (RKHS) edge detector and a geodesic distance penalty term from a set of markers and anti-markers. We test the proposed scheme on MR muscle segmentation and compare with some state-of-the-art methods. To help deal with the intensity inhomogeneity in this kind of image, a new approach to estimate the bias field using a fat fraction image, called Prior Bias-Corrected Fuzzy C-means (PBCFCM), is introduced. Numerical experiments show that the proposed scheme leads to significantly better results than compared ones. The average dice values of the proposed method are 92.5%, 85.3%, 85.3% for quadriceps, hamstrings and other muscle groups while other approaches are at least 10% worse.

Quantitative Analysis of Whole-Mount Fluorescence-Stained Tumor Spheroids in Phenotypic Drug Screens.

Three-dimensional cell cultures, such as spheroids or organoids, serve as important models for drug screening purposes. Optical tissue clearing (OTC) enhances the visualization of fluorescence stainings and enables in toto microscopy of 3D cell culture models. Furthermore, subsequent automated image analysis tools convert qualitative confocal image sets into quantitative data. In this chapter, we describe a detailed protocol for preparation of HT29 cancer spheroids, 3D in toto immunostaining, glycerol-based OTC, whole-mount imaging, and semi-automated downstream image processing and segmentation for nuclear image analysis using open-source software.