Manual Segmentation Research Articles

A novel CNN-based image segmentation pipeline for individualized feline spinal cord stimulation modeling

Objective. Spinal cord stimulation (SCS) is a well-established treatment for managing certain chronic pain conditions. More recently, it has also garnered attention as a means of modulating neural activity to restore lost autonomic or sensory-motor function. Personalized modeling and treatment planning are critical aspects of safe and effective SCS (Rowald and Amft 2022 Front. Neurorobotics 16 983072, Wagner et al 2018 Nature 563 65–71). However, the generation of spine models at the required level of detail and accuracy requires time and labor intensive manual image segmentation by human experts. This study aims to develop a maximally automated segmentation routine capable of producing high-quality anatomical models, even with limited data, to facilitate safe and effective personalized SCS treatment planning. Approach. We developed an automated image segmentation and model generation pipeline based on a novel convolutional neural network (CNN) architecture trained on feline spinal cord magnetic resonance imaging data. The pipeline includes steps for image preprocessing, data augmentation, transfer learning, and cleanup. To assess the relative importance of each step in the pipeline and our choice of CNN architecture, we systematically dropped steps or substituted architectures, quantifying the downstream effects in terms of tissue segmentation quality (Jaccard index and Hausdorff distance) and predicted nerve recruitment (estimated axonal depolarization). Main results. The leave-one-out analysis demonstrated that each pipeline step contributed a small but measurable increment to mean segmentation quality. Surprisingly, minor differences in segmentation accuracy translated to significant deviations (ranging between 4% and 13% for each pipeline step) in predicted nerve recruitment, highlighting the importance of careful workflow design. Additionally, transfer learning techniques enhanced segmentation metric consistency and allowed generalization to a completely different spine region with minimal additional training data. Significance. To our knowledge, this work is the first to assess the downstream impacts of segmentation quality differences on neurostimulation predictions. It highlights the role of each step in the pipeline and paves the way towards fully automated, personalized SCS treatment planning in clinical settings.

Improving the Feasibility of Mitigating Phase Errors in 4DCT caused by a Random Reference Breathing Pattern in the Quasar Phantom and the Role of Slice Thickness.

The study aimed to validate a method for minimizing phase errors by combining full-length lung 4DCT (f4DCT) scans with shorter tumor-restricted 4DCT (s4DCT) scans. It assessed the feasibility of integrating two scans one covering the entire phantom length and the other focused on the tumor area. The study also evaluated the impact of Maximum Intensity Projection (MIP) volume and imaging dose for different slice thicknesses (2.5mm and 1.25mm) in both full-length and short target-restricted 4DCT scans. The study utilized the Quasar Programmable Respiratory Motion Phantom, simulating tumor motion with a variable lung insert. The setup included a tumor replica and a six-dot IR reflector marker on the breathing platform. The objective was to analyze volume differences in fMIP_2.5mm compared to sMIP_1.25mm within their respective 4D_MIP CT series. This involved varying breathing periods (2.5s, 3.0s, 4.0s, and 5.0s) and longitudinal tumor sizes (6mm, 8mm, and 10mm). The study also assessed exposure time and expected CTDIvol of s4D_2.5mm and s4D_1.25mm for different breathing periods (5.0s to 2.0s) in the sinusoidal wave motion of the six-dot marker on the breathing platform. Conducting two consecutive 4DCT scans is viable for patients with challenging breathing patterns or when the initial lung tumor scan is in close proximity to the tumor location, eliminating the need for an additional full-length 4DCT. The analysis involves assessing MIP volume, imaging dose (CTDIvol), and exposure time. Longitudinal tumor shifts for 6mm are [16.6-17.2] in fMIP_2.5mm and [16.8-17.5] in sMIP_1.25mm, for 8mm [17.2-18.3] in fMIP_2.5mm and [17.8-18.4] in sMIP_1.25mm, and for 10mm [19-19.9] in fMIP_2.5mm and [19.4-20] in sMIP_1.25mm (p≥ 0.005), respectively. The Quasar Programmable Respiratory Motion Phantom accurately replicated varied breathing patterns and tumor motions. Comprehensive analysis was facilitated through detailed manual segmentation of Internal Target Volumes and Internal Gross Target Volumes.

White matter tract density index is associated with disability in multiple sclerosis

BackgroundThe association between common neuroradiological markers of multiple sclerosis (MS) and clinical disability is weak. Given that the disability in patients with MS may depend on the underlying structural connectivity of the brain, our study aimed to examine the association between white matter tracts affected by MS and the patients' disability using a new tract density index (TDI). MethodThis study included 53 patients diagnosed with MS, examined between 2019 and 2020. Manual lesion segmentation was performed on fluid-attenuated inversion recovery (FLAIR) images, and the density of white matter tracts encompassing the lesion (i.e., TDI) was calculated. Correlation analysis was employed to assess the association between TDI and disability. Additionally, the relationship between disability, TDI, and lesion-derived network metrics was examined by computing a partial correlation network. ResultsThe TDI significantly correlated with the expanded disability status scale (EDSS) (r = 0.30, p = 0.03). Furthermore, the patient's disability is linked solely through TDI to lesion-derived network metrics —a key metric that ‘bridges’ the gap between the brain lesion and disability. ConclusionsIn this study, MS lesions encompassing regions with high white matter tract density were associated and linked with severe physical disability. These findings indicate that TDI may be an outcome predictor that may connect radiologic findings to clinical practice.

Optimizing cardiovascular image segmentation through integrated hierarchical features and attention mechanisms.

Cardiovascular diseases are the top cause of death in China. Manual segmentation of cardiovascular images, prone to errors, demands an automated, rapid, and precise solution for clinical diagnosis. The paper highlights deep learning in automatic cardiovascular image segmentation, efficiently identifying pixel regions of interest for auxiliary diagnosis and research in cardiovascular diseases. In our study, we introduce innovative Region Weighted Fusion (RWF) and Shape Feature Refinement (SFR) modules, utilizing polarized self-attention for significant performance improvement in multiscale feature integration and shape fine-tuning. The RWF module includes reshaping, weight computation, and feature fusion, enhancing high-resolution attention computation and reducing information loss. Model optimization through loss functions offers a more reliable solution for cardiovascular medical image processing. Our method excels in segmentation accuracy, emphasizing the vital role of the RWF module. It demonstrates outstanding performance in cardiovascular image segmentation, potentially raising clinical practice standards. Our method ensures reliable medical image processing, guiding cardiovascular segmentation for future advancements in practical healthcare and contributing scientifically to enhanced disease diagnosis and treatment.

Improving assessment of lesions in longitudinal CT scans: a bi-institutional reader study on an AI-assisted registration and volumetric segmentation workflow

PurposeAI-assisted techniques for lesion registration and segmentation have the potential to make CT-based tumor follow-up assessment faster and less reader-dependent. However, empirical evidence on the advantages of AI-assisted volumetric segmentation for lymph node and soft tissue metastases in follow-up CT scans is lacking. The aim of this study was to assess the efficiency, quality, and inter-reader variability of an AI-assisted workflow for volumetric segmentation of lymph node and soft tissue metastases in follow-up CT scans. Three hypotheses were tested: (H1) Assessment time for follow-up lesion segmentation is reduced using an AI-assisted workflow. (H2) The quality of the AI-assisted segmentation is non-inferior to the quality of fully manual segmentation. (H3) The inter-reader variability of the resulting segmentations is reduced with AI assistance.Materials and methodsThe study retrospectively analyzed 126 lymph nodes and 135 soft tissue metastases from 55 patients with stage IV melanoma. Three radiologists from two institutions performed both AI-assisted and manual segmentation, and the results were statistically analyzed and compared to a manual segmentation reference standard.ResultsAI-assisted segmentation reduced user interaction time significantly by 33% (222 s vs. 336 s), achieved similar Dice scores (0.80–0.84 vs. 0.81–0.82) and decreased inter-reader variability (median Dice 0.85–1.0 vs. 0.80–0.82; ICC 0.84 vs. 0.80), compared to manual segmentation.ConclusionThe findings of this study support the use of AI-assisted registration and volumetric segmentation for lymph node and soft tissue metastases in follow-up CT scans. The AI-assisted workflow achieved significant time savings, similar segmentation quality, and reduced inter-reader variability compared to manual segmentation.

Segment anything with inception module for automated segmentation of endometrium in ultrasound images.

Accurate segmentation of the endometrium in ultrasound images is essential for gynecological diagnostics and treatment planning. Manual segmentation methods are time-consuming and subjective, prompting the exploration of automated solutions. We introduce "segment anything with inception module" (SAIM), a specialized adaptation of the segment anything model, tailored specifically for the segmentation of endometrium structures in ultrasound images. SAIM incorporates enhancements to the image encoder structure and integrates point prompts to guide the segmentation process. We utilized ultrasound images from patients undergoing hysteroscopic surgery in the gynecological department to train and evaluate the model. Our study demonstrates SAIM's superior segmentation performance through quantitative and qualitative evaluations, surpassing existing automated methods. SAIM achieves a dice similarity coefficient of 76.31% and an intersection over union score of 63.71%, outperforming traditional task-specific deep learning models and other SAM-based foundation models. The proposed SAIM achieves high segmentation accuracy, providing high diagnostic precision and efficiency. Furthermore, it is potentially an efficient tool for junior medical professionals in education and diagnosis.

Uncertainty quantification in multi-class segmentation: Comparison between Bayesian and non-Bayesian approaches in a clinical perspective.

Automatic segmentation techniques based on Convolutional Neural Networks (CNNs) are widely adopted to automatically identify any structure of interest from a medical image, as they are not time consuming and not subject to high intra- and inter-operator variability. However, the adoption of these approaches in clinical practice is slowed down by some factors, such as the difficulty in providing an accurate quantification of their uncertainty. This work aims to evaluate the uncertainty quantification provided by two Bayesian and two non-Bayesian approaches for a multi-class segmentation problem, and to compare the risk propensity among these approaches, considering CT images of patients affected by renal cancer (RC). Four uncertainty quantification approaches were implemented in this work, based on a benchmark CNN currently employed in medical image segmentation: two Bayesian CNNs with different regularizations (Dropout and DropConnect), named BDR and BDC, an ensemble method (Ens) and a test-time augmentation (TTA) method. They were compared in terms of segmentation accuracy, using the Dice score, uncertainty quantification, using the ratio of correct-certain pixels (RCC) and incorrect-uncertain pixels (RIU), and with respect to inter-observer variability in manual segmentation. They were trained with the Kidney and Kidney Tumor Segmentation Challenge launched in 2021 (Kits21), for which multi-class segmentations of kidney, RC, and cyst on 300 CT volumes are available. Moreover, they were tested considering this and other two public renal CT datasets. Accuracy results achieved large differences across the structures of interest for all approaches, with an average Dice score of 0.92, 0.58, and 0.21 for kidney, tumor, and cyst, respectively. In terms of uncertainties, TTA provided the highest uncertainty, followed by Ens and BDC, whereas BDR provided the lowest, and minimized the number of incorrect certain pixels worse than the other approaches. Again, large differences were seen across the three structures in terms of RCC and RIU. These metrics were associated with different risk propensity, as BDR was the most risk-taking approach, able to provide higher accuracy in its prediction, but failing to assign uncertainty on incorrect segmentation in every case. The other three approaches were more conservative, providing large uncertainty regions, with the drawback of giving alert also on correct areas. Finally, the analysis of the inter-observer segmentation variability showed a significant variation among the four approaches on the external dataset, with BDR reporting the lowest agreement (Dice = 0.82), and TTA obtaining the highest score (Dice = 0.94). Our outcomes highlight the importance of quantifying the segmentation uncertainty and that decision-makers can choose the approach most in line with the risk propensity degree required by the application and theirpolicy.

Gaining Insight into Updated MR Imaging for Quantitative Assessment of Cartilage Injury in Knee Osteoarthritis.

Knee Osteoarthritis (KOA) entails progressive cartilage degradation, reviewed via MRI for morphology, biochemical composition, and microtissue alterations, discussing clinical advantages, limitations, and research applicability. Compositional MRI, like T2/T2* mapping, T1rho mapping, gagCEST, dGEMRIC, sodium imaging, diffusion-weighted imaging, and diffusion-tensor imaging, provide insights into cartilage injury in KOA. These methods quantitatively measure collagen, glycosaminoglycans, and water content, revealing important information about biochemical compositional and microstructural alterations. Innovative techniques like hybrid multi-dimensional MRI and diffusion-relaxation correlation spectrum imaging show potential in depicting initial cartilage changes at a sub-voxel level. Integration of automated image analysis tools addressed limitations in manual cartilage segmentation, ensuring robust and reproducible assessments of KOA cartilage. Compositional MRI techniques reveal microstructural changes in cartilage. Multi-dimensional MR imaging assesses biochemical alterations in KOA-afflicted cartilage, aiding early degeneration identification. Integrating artificial intelligence enhances cartilage analysis, optimal diagnostic accuracy for early KOA detection and monitoring.

MRI-based Deep Learning Models for Preoperative Breast Volume and Density Assessment Assisting Breast Reconstruction.

The volume of the implant is the most critical element of breast reconstruction, so it is necessary to accurately assess the preoperative volume of the healthy and affected breasts and select the appropriate implant for placement. Accurate and automated methods for quantitative assessment of breast volume can optimize breast reconstruction surgery and assist physicians in clinical decision making. The aim of this study was to develop an artificial intelligence model for automated segmentation of the breast and measurement of volume. A total of 249 subjects undergoing breast reconstruction surgery were enrolled in this study. Subjects underwent preoperative breast MRI, and the breast region manually outlined by the imaging physician served as the gold standard for volume measurement by the automated segmentation model. In this study, we developed three automated algorithms for automatic segmentation of breast regions, including a simple alignment model, an alignment dynamic encoding model, and a deep learning model. The volumetric agreement between the three automated segmentation algorithms and the breast regions manually segmented by imaging physicians was evaluated by calculating the mean square error (MSE) and intragroup correlation coefficient (ICC), and the reproducibility of the automated segmentation of the breast regions was assessed by the test-retest step. The three breast automated segmentation models developed in this study (simple registration model, dynamic programming model, and deep learning model) showed strong ICC with manual segmentation of the breast region, with MSEs of 1.124, 0.693, and 0.781, and ICCs of 0.975 (95% CI, 0.869-0.991), 0.986 (95% CI, 0.967-0.996), and 0.983 (95% CI, 0.961-0.992), respectively. Regarding the test-retest results of breast volume, the dynamic programming model performed the best with an MSE of 0.370 and an ICC of 0.993 (95% CI, 0.982-0.997), followed by the deep learning algorithm with an MSE of 0.741 and an ICC of 0.983 (95% CI, 0.956-0.993), and the simple registration algorithm with an MSE of 0.763 and an ICC of 0.982 (95% CI, 0.949-0.993). The reproducibility of the breast region segmented by the three automated algorithms was higher than that of manual segmentation by different radiologists. The three automated breast segmentation algorithms developed in this study generate accurate and reliable breast regions, enable highly reproducible breast region segmentation and automated volume measurements, and provide a valuable tool for surgical selection of appropriate prostheses. This journal requires that authors assign a level of evidence to each submission to which Evidence-Based Medicine rankings are applicable. This excludes Review Articles, Book Reviews, and manuscripts that concern Basic Science, Animal Studies, Cadaver Studies, and Experimental Studies. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Probability maps for deep learning-based head and neck tumor segmentation: Graphical User Interface design and test

BackgroundThe different tumor appearance of head and neck cancer across imaging modalities, scanners, and acquisition parameters accounts for the highly subjective nature of the manual tumor segmentation task. The variability of the manual contours is one of the causes of the lack of generalizability and the suboptimal performance of deep learning (DL) based tumor auto-segmentation models. Therefore, a DL-based method was developed that outputs predicted tumor probabilities for each PET-CT voxel in the form of a probability map instead of one fixed contour. The aim of this study was to show that DL-generated probability maps for tumor segmentation are clinically relevant, intuitive, and a more suitable solution to assist radiation oncologists in gross tumor volume segmentation on PET-CT images of head and neck cancer patients. MethodA graphical user interface (GUI) was designed, and a prototype was developed to allow the user to interact with tumor probability maps. Furthermore, a user study was conducted where nine experts in tumor delineation interacted with the interface prototype and its functionality. The participants’ experience was assessed qualitatively and quantitatively. ResultsThe interviews with radiation oncologists revealed their preference for using a rainbow colormap to visualize tumor probability maps during contouring, which they found intuitive. They also appreciated the slider feature, which facilitated interaction by allowing the selection of threshold values to create single contours for editing and use as a starting point. Feedback on the prototype highlighted its excellent usability and positive integration into clinical workflows. ConclusionsThis study shows that DL-generated tumor probability maps are explainable, transparent, intuitive and a better alternative to the single output of tumor segmentation models.

Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images

ObjectivesThis study aims to develop an innovative, deep model for thymoma risk stratification using preoperative CT images. Current algorithms predominantly focus on radiomic features or 2D deep features and require manual tumor segmentation by radiologists, limiting their practical applicability.MethodsThe deep model was trained and tested on a dataset comprising CT images from 147 patients (82 female; mean age, 54 years ± 10) who underwent surgical resection and received subsequent pathological confirmation. The eligible participants were divided into a training cohort (117 patients) and a testing cohort (30 patients) based on the CT scan time. The model consists of two stages: 3D tumor segmentation and risk stratification. The radiomic model and deep model (2D) were constructed for comparative analysis. Model performance was evaluated through dice coefficient, area under the curve (AUC), and accuracy.ResultsIn both the training and testing cohorts, the deep model demonstrated better performance in differentiating thymoma risk, boasting AUCs of 0.998 and 0.893 respectively. This was compared to the radiomic model (AUCs of 0.773 and 0.769) and deep model (2D) (AUCs of 0.981 and 0.760). Notably, the deep model was capable of simultaneously identifying lesions, segmenting the region of interest (ROI), and differentiating the risk of thymoma on arterial phase CT images. Its diagnostic prowess outperformed that of the baseline model.ConclusionsThe deep model has the potential to serve as an innovative decision-making tool, assisting on clinical prognosis evaluation and the discernment of suitable treatments for different thymoma pathological subtypes.Key Points• This study incorporated both tumor segmentation and risk stratification.• The deep model, using clinical and 3D deep features, effectively predicted thymoma risk.• The deep model improved AUCs by 16.1pt and 17.5pt compared to radiomic model and deep model (2D) respectively.

Validation of a 3D-printed model of cryptoglandular perianal fistulas.

Visualising the course of a complex perianal fistula on imaging can be difficult. It has been postulated that three-dimensional (3D) models of perianal fistulas improve understanding of the perianal pathology, contribute to surgical decision-making and might even improve future outcomes of surgical treatment. The aim of the current study is to investigate the accuracy of 3D-printed models of perianal fistulas compared with magnetic resonance imaging (MRI). MRI scans of 15 patients with transsphincteric and intersphincteric fistulas were selected and then assessed by an experienced abdominal and colorectal radiologist. A standardised method of creating a 3D-printed anatomical model of cryptoglandular perianal fistula was developed by a technical medical physicist and a surgeon in training with special interest in 3D printing. Manual segmentation of the fistula and external sphincter was performed by a trained technical medical physicist. The anatomical models were 3D printed in a 1:1 ratio and assessed by two colorectal surgeons. The 3D-printed models were then scanned with a 3D scanner. Volume of the 3D-printed model was compared with manual segmentation. Inter-rater reliability statistics were calculated for consistency between the radiologist who assessed the MRI scans and the surgeons who assessed the 3D-printed models. The assessment of the MRI was considered the 'gold standard'. Agreement between the two surgeons who assessed the 3D printed models was also determined. Consistency between the radiologist and the surgeons was almost perfect for classification (κ = 0.87, κ = 0.87), substantial for complexity (κ = 0.73, κ = 0.74) and location of the internal orifice (κ = 0.73, κ = 0.73) and moderate for the percentage of involved external anal sphincter in transsphincteric fistulas (ICC 0.63, ICC 0.52). Agreement between the two surgeons was substantial for classification (κ = 0.73), complexity (κ = 0.74), location of the internal orifice (κ = 0.75) and percentage of involved external anal sphincter in transsphincteric fistulas (ICC 0.77). Our 3D-printed anatomical models of perianal fistulas are an accurate reflection of the MRI. Further research is needed to determine the added value of 3D-printed anatomical models in preoperative planning and education.

Radiomics of Intrahepatic Cholangiocarcinoma and Peritumoral Tissue Predicts Postoperative Survival: Development of a CT-Based Clinical-Radiomic Model.

For many tumors, radiomics provided a relevant prognostic contribution. This study tested whether the computed tomography (CT)-based textural features of intrahepatic cholangiocarcinoma (ICC) and peritumoral tissue improve the prediction of survival after resection compared with the standard clinical indices. All consecutive patients affected by ICC who underwent hepatectomy at six high-volume centers (2009-2019) were considered for the study. The arterial and portal phases of CT performed fewer than 60days before surgery were analyzed. A manual segmentation of the tumor was performed (Tumor-VOI). A 5-mm volume expansion then was applied to identify the peritumoral tissue (Margin-VOI). The study enrolled 215 patients. After a median follow-up period of 28months, the overall survival (OS) rate was 57.0%, and the progression-free survival (PFS) rate was 34.9% at 3years. The clinical predictive model of OS had a C-index of 0.681. The addition of radiomic features led to a progressive improvement of performances (C-index of 0.71, including the portal Tumor-VOI, C-index of 0.752 including the portal Tumor- and Margin-VOI, C-index of 0.764, including all VOIs of the portal and arterial phases). The latter model combined clinical variables (CA19-9 and tumor pattern), tumor indices (density, homogeneity), margin data (kurtosis, compacity, shape), and GLRLM indices. The model had performance equivalent to that of the postoperative clinical model including the pathology data (C-index of 0.765). The same results were observed for PFS. The radiomics of ICC and peritumoral tissue extracted from preoperative CT improves the prediction of survival. Both the portal and arterial phases should be considered. Radiomic and clinical data are complementary and achieve a preoperative estimation of prognosis equivalent to that achieved in the postoperative setting.

Single-shot simplified cardioneuroablation

Abstract Introduction Cardioneuroablation (CNA) is a promising therapy of a spectrum of arrhythmias dependent on increased activity of parasympathetic tone. The right anterior ganglionated plexus (RAGP), localized paraseptally between right atrium and right superior pulmonary vein, is frequently a primary target for CNA. Methods are sought to determine exact locations of RAGP to minimize ablation lesion set during CNA. Immediate and accurate intraprocedural visualization of RAGP area in patients undergoing CNA is desirable. Methods Consecutive patients who underwent right-atrial CNA for reflex syncope, symptomatic bradycardia or vagal atrial fibrillation were included into the study. After venous contrast injection a 3-dimensional rotational atrial scan (3DRAS) was used to obtain digital images. Next, manual segmentation (MS) of hypodense areas between the right atrium (RA) and the right superior pulmonary vein (RSPV) was performed to reconstruct RAGP. Using 3-dimensional mapping system such created 3D RAGP area visualisation was automatically synchronized with fluoroscopy and these sites were targeted for CNA. Heart rate (HR) acceleration ≥30% and ultra-short-term deceleration capacity (UST-DC) were used for determination of acute CNA outcomes. Results Five patients (3 males, age 37±17) underwent 3DRAS and MS of RAGP area during CNA. A single radiofrequency lesion was delivered in each patient (mean RF time - 33±15s, power - 25W). The mean procedure time was 40±13 minutes. Targeted HR acceleration was achieved in all patients (baseline HR vs post-CNA HR, 57±8bpm vs 93±11bpm; p=0.0007; mean HR acceleration 65±15%). UST-DC significantly decreased after CNA (pre-CNA UST-DC vs post-CNA UST-DC, 13.6ms vs 3.2ms, p=0.00096). There were no complications. Conclusions Single-shot simplified CNA is feasible. Visualization of RAGP area using 3DRAS and MS is safe, effective and can very rapidly delineate CNA target.Figure

P.079 Relationships between anatomical features and outcome after stereotactic laser amygdalohippocampotomy

Background: Stereotactic laser amygdalohippocampotomy (SLAH) has recently been shown to be comparable to traditional temporal lobectomy procedures. The ideal extent and volume of laser ablations remains an area of investigation Methods: 65 patients treated with SLAH for MTS were considered in this retrospective study. Manual segmentations of ablations were created using post-procedure T1-MRI scans. Ablations were assessed in relation to whether they crossed the coronal plane of the superior lateral mesencephalic sulcus (LMS), the extent to which ablation crossed this landmark, and extent of ablation of the uncus. Analysis of was done with binary categorization of 12-month Engel classification score. Results: Distance of ablation posterior to the coronal plane of the LMS was not associated with better surgical outcome (Engel class 1: 6.32 ± 4.16 mm; Engel class 2-4: 7.93 ± 3.75mm; (p = 0.099)). Ratio of ablations extending posterior to the LMS was 0.82 (SD = .39) in Engel 1 patients, and 0.90 (SD = 0.3) in Engel 2-4 patients; (p = 0.370). Volume of ablation showed little correlation with outcome (Engel class 1: 6064 ± 2128 mm3; Engel class 2-4: 5828 ± 3031 mm3; (p=0.239)). Ablation of the uncus showed a strong association with better surgical outcome (Engel class 1: 0.71(SD = 0.31); Engel 2-4: 0.37 (SD = 0.36); p <0.001). Conclusions: Contrary to current practice, extension of ablation posterior to the LMS did not demonstrate improved outcome.

Surveying image segmentation approaches in astronomy

Image segmentation plays a critical role in unlocking the mysteries of the universe, providing astronomers with a clearer perspective on celestial objects within complex astronomical images and data cubes. Manual segmentation, while traditional, is not only time-consuming but also susceptible to biases introduced by human intervention. As a result, automated segmentation methods have become essential for achieving robust and consistent results in astronomical studies. This review begins by summarizing traditional and classical segmentation methods widely used in astronomical tasks. Despite the significant improvements these methods have brought to segmentation outcomes, they fail to meet astronomers’ expectations, requiring additional human correction, further intensifying the labor-intensive nature of the segmentation process. The review then focuses on the transformative impact of machine learning, particularly deep learning, on segmentation tasks in astronomy. It introduces state-of-the-art machine learning approaches, highlighting their applications and the remarkable advancements they bring to segmentation accuracy in both astronomical images and data cubes. As the field of machine learning continues to evolve rapidly, it is anticipated that astronomers will increasingly leverage these sophisticated techniques to enhance segmentation tasks in their research projects. In essence, this review serves as a comprehensive guide to the evolution of segmentation methods in astronomy, emphasizing the transition from classical approaches to cutting-edge machine learning methodologies. We encourage astronomers to embrace these advancements, fostering a more streamlined and accurate segmentation process that aligns with the ever-expanding frontiers of astronomical exploration.

3DVascNet: An Automated Software for Segmentation and Quantification of Mouse Vascular Networks in 3D.

Analysis of vascular networks is an essential step to unravel the mechanisms regulating the physiological and pathological organization of blood vessels. So far, most of the analyses are performed using 2-dimensional projections of 3-dimensional (3D) networks, a strategy that has several obvious shortcomings. For instance, it does not capture the true geometry of the vasculature and generates artifacts on vessel connectivity. These limitations are accepted in the field because manual analysis of 3D vascular networks is a laborious and complex process that is often prohibitive for large volumes. To overcome these issues, we developed 3DVascNet, a deep learning-based software for automated segmentation and quantification of 3D retinal vascular networks. 3DVascNet performs segmentation based on a deep learning model, and it quantifies vascular morphometric parameters such as vessel density, branch length, vessel radius, and branching point density. We tested the performance of 3DVascNet using a large data set of 3D microscopy images of mouse retinal blood vessels. We demonstrated that 3DVascNet efficiently segments vascular networks in 3D and that vascular morphometric parameters capture phenotypes detected by using manual segmentation and quantification in 2 dimension. In addition, we showed that, despite being trained on retinal images, 3DVascNet has high generalization capability and successfully segments images originating from other data sets and organs. Overall, we present 3DVascNet, a freely available software that includes a user-friendly graphical interface for researchers with no programming experience, which will greatly facilitate the ability to study vascular networks in 3D in health and disease. Moreover, the source code of 3DVascNet is publicly available, thus it can be easily extended for the analysis of other 3D vascular networks by other users.

DSBAV-Net: Depthwise Separable Bottleneck Attention V-Shaped Network with Hybrid Convolution for Left Atrium Segmentation

AbstractAccurate and precise segmentation of the left atrium (LA) is crucial in the early diagnosis and treatment of atrial fibrillation (AF), which is the most common heart rhythm disease in cases. The size of fibrotic tissue in patients with AF is based on manual examination of images obtained from the gadolinium-enhanced cardiac magnetic resonance imaging (MRI) technique. However, manual examination of the acquired images is time-consuming and has many difficulties, such as LA thickness between observers and resolution according to MR devices. To overcome the challenges of manual segmentation of images obtained from MRI devices, end-to-end, fully automated deep learning-based segmentation architectures have become extremely important today. In this study, an encoder–decoder-based V-shaped deep learning architecture is proposed for precise segmentation of LA. In the proposed architecture, standard convolution and depthwise separable convolution are used together. Thus, sparsely connected blocks with fewer parameters and deeply separable convolutions learn the feature representations better, increasing the robustness of the model. In addition, the bottleneck attention module has been added to each encoder layer, allowing the network to learn which features to focus on and which features to suppress in images by attention mapping channel and spatially. The proposed architecture obtained 0.915 dice and 0.844 Jaccard scores in the STACOM 2018 challenge dataset. The obtained results draw attention to the robustness of the model.

Development and benchmarking of a Deep Learning-based MRI-guided gross tumor segmentation algorithm for Radiomics analyses in extremity soft tissue sarcomas

BackgroundVolume of interest (VOI) segmentation is a crucial step for Radiomics analyses and radiotherapy (RT) treatment planning. Because it can be time-consuming and subject to inter-observer variability, we developed and tested a Deep Learning-based automatic segmentation (DLBAS) algorithm to reproducibly predict the primary gross tumor as VOI for Radiomics analyses in extremity soft tissue sarcomas (STS). MethodsA DLBAS algorithm was trained on a cohort of 157 patients and externally tested on an independent cohort of 87 patients using contrast-enhanced MRI. Manual tumor delineations by a radiation oncologist served as ground truths (GTs). A benchmark study with 20 cases from the test cohort compared the DLBAS predictions against manual VOI segmentations of two residents (ERs) and clinical delineations of two radiation oncologists (ROs). The ROs rated DLBAS predictions regarding their direct applicability. ResultsThe DLBAS achieved a median dice similarity coefficient (DSC) of 0.88 against the GTs in the entire test cohort (interquartile range (IQR): 0.11) and a median DSC of 0.89 (IQR 0.07) and 0.82 (IQR 0.10) in comparison to ERs and ROs, respectively. Radiomics feature stability was high with a median intraclass correlation coefficient of 0.97, 0.95 and 0.94 for GTs, ERs, and ROs, respectively. DLBAS predictions were deemed clinically suitable by the two ROs in 35% and 20% of cases, respectively. ConclusionThe results demonstrate that the DLBAS algorithm provides reproducible VOI predictions for radiomics feature extraction. Variability remains regarding direct clinical applicability of predictions for RT treatment planning.

Using a new artificial intelligence-aided method to assess body composition CT segmentation in colorectal cancer patients.

This study aimed to evaluate the accuracy of our own artificial intelligence (AI)-generated model to assess automated segmentation and quantification of body composition-derived computed tomography (CT) slices from the lumber (L3) region in colorectal cancer (CRC) patients. A total of 541 axial CT slices at the L3 vertebra were retrospectively collected from 319 patients with CRC diagnosed during 2012-2019 at a single Australian tertiary institution, Western Health in Melbourne. A two-dimensional U-Net convolutional network was trained on 338 slices to segment muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). Manual reading of these same slices of muscle, VAT and SAT was created to serve as ground truth data. The Dice similarity coefficient was used to assess the U-Net-based segmentation performance on both a validation dataset (68 slices) and a test dataset (203 slices). The measurement of cross-sectional area and Hounsfield unit (HU) density of muscle, VAT and SAT were compared between two methods. The segmentation for muscle, VAT and SAT demonstrated excellent performance for both the validation (Dice similarity coefficients >0.98, respectively) and test (Dice similarity coefficients >0.97, respectively) datasets. There was a strong positive correlation between manual and AI segmentation measurements of body composition for both datasets (Spearman's correlation coefficients: 0.944-0.999, P < 0.001). Compared to the gold standard, this fully automated segmentation system exhibited a high accuracy for assessing segmentation and quantification of abdominal muscle and adipose tissues of CT slices at the L3 in CRC patients.