Abdominal Segmentation Research Articles

Association Between Body Composition Measured by Artificial Intelligence and Long-Term Sequelae After Acute Pancreatitis.

The clinical utility of body composition in the development of complications of acute pancreatitis (AP) remains unclear. We aimed to describe the associations between body composition and the recurrence of AP. We performed a retrospective study of patients hospitalized with AP at three tertiary care centers. Patients with computer tomography (CT) imaging of the abdomen at admission were included. A previously validated and fully automated abdominal segmentation algorithm was used for body composition analysis. Hospitalization for a recurrent episode of AP was the primary endpoint. Secondary endpoints included the development of chronic pancreatitis (CP) or diabetes mellitus (DM) in patients who were evaluated. Cox Proportional Hazards regression was used. From a total of 347 patients, 89 (25.6%) were hospitalized for recurrent AP (median time: 219days). Thirty-four of 112 patients (30.4%) developed CP (median time: 311days) and 22 of 88 (25.0%) developed DM (median time: 1104days). After adjusting for age, male sex, first episode of AP, BUN, and severity of AP, we found that obesity, body mass index, alcohol pancreatitis, and gallstone pancreatitis were significantly associated with a recurrent episode of AP. Body composition was not associated with recurrent AP. In unadjusted analysis, subcutaneous adipose tissue (SAT) (HR 0.87 per 10 cm2, p = 0.002) was associated with CP. Skeletal muscle (SM) mass approached significance for CP (p = 0.0546). Intermuscular adipose tissue (IMAT) (HR 1.45 per 5 cm2, p = 0.0264) was associated with DM. Body composition was not associated with having a recurrent AP. At follow-up, 30% and 25% of evaluated patients developed CP and DM, respectively. A higher SAT and IMAT were associated with a lower incidence of CP and higher incidence of DM, respectively.

Widespread regulation of the maternal transcriptome by Nanos in Drosophila.

The translational repressor Nanos (Nos) regulates a single target, maternal hunchback (hb) mRNA, to govern abdominal segmentation in the early Drosophila embryo. Nos is recruited to sites in the 3' UTR of hb mRNA in collaboration with the sequence-specific RNA-binding protein Pumilio (Pum); on its own, Nos has no binding specificity. Nos is expressed at other stages of development, but very few mRNA targets that might mediate its action at these stages have been described. Nor has it been clear whether Nos is targeted to other mRNAs in concert with Pum or via other mechanisms. In this report, we identify mRNAs targeted by Nos via 2 approaches. First, we identify mRNAs depleted upon expression of a chimera bearing Nos fused to the nonsense mediated decay (NMD) factor Upf1. We find that, in addition to hb, Upf1-Nos depletes approximately 2,600 mRNAs from the maternal transcriptome in early embryos. Virtually all of these appear to be targeted in a canonical, hb-like manner in concert with Pum. In a second, more conventional approach, we identify mRNAs that are stabilized during the maternal zygotic transition (MZT) in embryos from nos- females. Most (86%) of the 1,185 mRNAs regulated by Nos are also targeted by Upf1-Nos, validating use of the chimera. Previous work has shown that 60% of the maternal transcriptome is degraded in early embryos. We find that maternal mRNAs targeted by Upf1-Nos are hypoadenylated and inefficiently translated at the ovary-embryo transition; they are subsequently degraded in the early embryo, accounting for 59% of all destabilized maternal mRNAs. We suggest that the late ovarian burst of Nos represses a large fraction of the maternal transcriptome, priming it for later degradation by other factors in the embryo.

Automated abdominal organ segmentation algorithms for non-enhanced CT for volumetry and 3D radiomics analysis

Abstract Purpose To develop fully-automated abdominal organ segmentation algorithms from non-enhanced abdominal CT and low-dose chest CT and assess their feasibility for automated CT volumetry and 3D radiomics analysis of abdominal solid organs. Methods Fully-automated nnU-Net-based models were developed to segment the liver, spleen, and both kidneys in non-enhanced abdominal CT, and the liver and spleen in low-dose chest CT. 105 abdominal CTs and 60 low-dose chest CTs were used for model development, and 55 abdominal CTs and 10 low-dose chest CTs for external testing. The segmentation performance for each organ was assessed using the Dice similarity coefficients, with manual segmentation results serving as the ground truth. Agreements between ground-truth measurements and model estimates of organ volume and 3D radiomics features were assessed using the Bland–Altman analysis and intraclass correlation coefficients (ICC). Results The models accurately segmented the liver, spleen, right kidney, and left kidney in abdominal CT and the liver and spleen in low-dose chest CT, showing mean Dice similarity coefficients in the external dataset of 0.968, 0.960, 0.952, and 0.958, respectively, in abdominal CT, and 0.969 and 0.960, respectively, in low-dose chest CT. The model-estimated and ground truth volumes of these organs exhibited mean differences between − 0.7% and 2.2%, with excellent agreements. The automatically extracted mean and median Hounsfield units (ICCs, 0.970–0.999 and 0.994–0.999, respectively), uniformity (ICCs, 0.985–0.998), entropy (ICCs, 0.931–0.993), elongation (ICCs, 0.978–0.992), and flatness (ICCs, 0.973–0.997) showed excellent agreement with ground truth measurements for each organ; however, skewness (ICCs, 0.210–0.831), kurtosis (ICCs, 0.053–0.933), and sphericity (ICCs, 0.368–0.819) displayed relatively low and inconsistent agreement. Conclusion Our nnU-Net-based models accurately segmented abdominal solid organs in non-enhanced abdominal and low-dose chest CT, enabling reliable automated measurements of organ volume and specific 3D radiomics features.

Skeleton-guided 3D convolutional neural network for tubular structure segmentation.

Accurate segmentation of tubular structures is crucial for clinical diagnosis and treatment but is challenging due to their complex branching structures and volume imbalance. The purpose of this study is to propose a 3D deep learning network that incorporates skeleton information to enhance segmentation accuracy in these tubular structures. Our approach employs a 3D convolutional network to extract 3D tubular structures from medical images such as CT volumetric images. We introduce a skeleton-guided module that operates on extracted features to capture and preserve the skeleton information in the segmentation results. Additionally, to effectively train our deep model in leveraging skeleton information, we propose a sigmoid-adaptive Tversky loss function which is specifically designed for skeleton segmentation. We conducted experiments on two distinct 3D medical image datasets. The first dataset consisted of 90 cases of chest CT volumetric images, while the second dataset comprised 35 cases of abdominal CT volumetric images. Comparative analysis with previous segmentation approaches demonstrated the superior performance of our method. For the airway segmentation task, our method achieved an average tree length rate of 93.0%, a branch detection rate of 91.5%, and a precision rate of 90.0%. In the case of abdominal artery segmentation, our method attained an average precision rate of 97.7%, a recall rate of 91.7%, and an F-measure of 94.6%. We present a skeleton-guided 3D convolutional network to segment tubular structures from 3D medical images. Our skeleton-guided 3D convolutional network could effectively segment small tubular structures, outperforming previous methods.

Semi-supervised abdominal multi-organ segmentation by object-redrawing.

Multi-organ segmentation is a critical task in medical imaging, with wide-ranging applications in both clinical practice and research. Accurate delineation of organs from high-resolution 3D medical images, such as CT scans, is essential for radiation therapy planning, enhancing treatment outcomes, and minimizing radiation toxicity risks. Additionally, it plays a pivotal role in quantitative image analysis, supporting various medical research studies. Despite its significance, manual segmentation of multiple organs from 3D images is labor-intensive and prone to low reproducibility due to high interoperator variability. Recent advancements in deep learning have led to several automated segmentation methods, yet many rely heavily on labeled data and human anatomy expertise. In this study, our primary objective is to address the limitations of existing semi-supervised learning (SSL) methods for abdominal multi-organ segmentation. We aim to introduce a novel SSL approach that leverages unlabeled data to enhance the performance of deep neural networks in segmenting abdominal organs. Specifically, we propose a method that incorporates a redrawing network into the segmentation process to correct errors and improve accuracy. Our proposed method comprises three interconnected neural networks: a segmentation network for image segmentation, a teacher network for consistency regularization, and a redrawing network for object redrawing. During training, the segmentation network undergoes two rounds of optimization: basic training and readjustment. We adopt the Mean-Teacher model as our baseline SSL approach, utilizing labeled and unlabeled data. However, recognizing significant errors in abdominal multi-organ segmentation using this method alone, we introduce the redrawing network to generate redrawn images based on CT scans, preserving original anatomical information. Our approach is grounded in the generative process hypothesis, encompassing segmentation, drawing, and assembling stages. Correct segmentation is crucial for generating accurate images. In the basic training phase, the segmentation network is trained using both labeled and unlabeled data, incorporating consistency learning to ensure consistent predictions before and after perturbations. The readjustment phase focuses on reducing segmentation errors by optimizing the segmentation network parameters based on the differences between redrawn and original CT images. We evaluated our method using two publicly available datasets: the beyond the cranial vault (BTCV) segmentation dataset (training: 44, validation: 6) and the abdominal multi-organ segmentation (AMOS) challenge 2022 dataset (training:138, validation:16). Our results were compared with state-of-the-art SSL methods, including MT and dual-task consistency (DTC), using the Dice similarity coefficient (DSC) as an accuracy metric. On both datasets, our proposed SSL method consistently outperformed other methods, including supervised learning, achieving superior segmentation performance for various abdominal organs. These findings demonstrate the effectiveness of our approach, even with a limited number of labeled data. Our novel semi-supervised learning approach for abdominal multi-organ segmentation addresses the challenges associated with this task. By integrating a redrawing network and leveraging unlabeled data, we achieve remarkable improvements in accuracy. Our method demonstrates superior performance compared to existing SSL and supervised learning methods. This approach holds great promise in enhancing the precision and efficiency of multi-organ segmentation in medical imaging applications.

Deep Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and Heterogeneous Public Datasets.

BACKGROUND. Deep learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. OBJECTIVE. The purpose of this article is to develop and validate deep learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. METHODS. This retrospective study developed and validated deep learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤ 18 years) datasets (n = 483) and three public datasets comprising pediatric and adult examinations with various pathologies (n = 1248). Three deep learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for Artificial Intelligence (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pretraining on public datasets. For comparison, TotalSegmentator, a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. RESULTS. For internal pediatric data, the DSC for TotalSegmentator, NT models, and TL models for normal liver was 0.953, 0.964-0.965, and 0.965-0.966, respectively; for normal spleen, 0.914, 0.942-0.945, and 0.937-0.945; for normal pancreas, 0.733, 0.774-0.785, and 0.775-0.786; and for pancreas with pancreatitis, 0.703, 0.590-0.640, and 0.667-0.711. For public pediatric data, the DSC for TotalSegmentator, NT models, and TL models for liver was 0.952, 0.871-0.908, and 0.941-0.946, respectively; for spleen, 0.905, 0.771-0.827, and 0.897-0.926; and for pancreas, 0.700, 0.577-0.648, and 0.693-0.736. For public primarily adult data, the DSC for TotalSegmentator, NT models, and TL models for liver was 0.991, 0.633-0.750, and 0.926-0.952, respectively; for spleen, 0.983, 0.569-0.604, and 0.923-0.947; and for pancreas, 0.909, 0.148-0.241, and 0.699-0.775. The DynUNet TL model was selected as the best-performing NT or TL model considering DSC values across organs and test datasets and was made available as an open-source MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). CONCLUSION. TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and Total-Segmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. CLINICAL IMPACT. The selected model may be used for various volumetry applications in pediatric imaging.

PheoSeg: A 3D transfer learning framework for accurate abdominal CT pheochromocytoma segmentation and surgical grade prediction

Pheochromocytoma is a rare urological disease. Accurate segmentation of pheochromocytoma and its surrounding abdominal organs is crucial for surgical planning and preoperative diagnosis. However, current clinical datasets typically include tumor labels but lack comprehensive multi-organ abdominal labels, and detailed descriptions of the spatial relationships between the tumor and adjacent organs are insufficient. To address the challenge of automatic multi-organ segmentation in the abdomen without comprehensive labels around pheochromocytoma, we propose a novel method for automatic multi-source migration segmentation and preoperative diagnostic grading of pheochromocytoma and its surrounding organs. This method utilizes nnUNet to extract data fingerprint information from the target domain (Clinical Pheochromocytoma dataset of Peking Union Medical College Hospital, PPGL) as prior knowledge, which is then transferred to two source domains (FLARE2022 and AMOS2022). We trained 10 models and incorporated them into a "Model Bank". Additionally, we employed an improved CC-FV method to screen the models in the "Model Bank," identifying the model with the highest mobility (class consistency and feature diversity). This selected model served as a pre-trained model for abdominal multi-organ segmentation and was subsequently adapted for tumor segmentation. To address the issue of limited clinical data, we introduced a data enhancement technique for 3D medical images. The enhanced dataset was used to fine-tune the pre-trained model, resulting in a model capable of segmenting multiple organs and tumors in the abdomen. From the segmentation results, we extracted the spatial relationships between the tumor and surrounding abdominal organs and constructed a radiomic model to predict and analyze the surgical grading. Experimental results demonstrate that our proposed method achieves a Dice coefficient that is, on average, 10.18 % higher on FLARE2022 and AMOS2022 datasets compared to segmentation frameworks such as Swin-Unet, UNETR, CoTr, nnformer, and nnUNetv2. For the PPGL dataset, the Dice coefficient for pheochromocytoma and surrounding organs was 87.27 %. In summary, our method effectively realizes efficient and automatic segmentation of pheochromocytoma and surrounding organs, as well as preoperative diagnostic classification.

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique.

Abdominal multi-organ segmentation is one of the most important topics in the field of medical image analysis, and it plays an important role in supporting clinical workflows such as disease diagnosis and treatment planning. In this study, an efficient multi-organ segmentation method called Swin-PSAxialNet based on the nnU-Net architecture is proposed. It was designed specifically for the precise segmentation of 11 abdominal organs in CT images. The proposed network has made the following improvements compared to nnU-Net. Firstly, Space-to-depth (SPD) modules and parameter-shared axial attention (PSAA) feature extraction blocks were introduced, enhancing the capability of 3D image feature extraction. Secondly, a multi-scale image fusion approach was employed to capture detailed information and spatial features, improving the capability of extracting subtle features and edge features. Lastly, a parameter-sharing method was introduced to reduce the model's computational cost and training speed. The proposed network achieves an average Dice coefficient of 0.93342 for the segmentation task involving 11 organs. Experimental results indicate the notable superiority of Swin-PSAxialNet over previous mainstream segmentation methods. The method shows excellent accuracy and low computational costs in segmenting major abdominal organs.

Functional Characterization of Abdominal-A in the Pine Caterpillar Moth, Dendrolimus punctatus

Hox genes, specifically the bithorax complex (ubx, abdominal-a, and abdominal-b), play a crucial role in specifying posterior abdominal development and serve as key regulators of germline gene development in insects. However, the function of the bithorax complex in the pine caterpillar moth, Dendrolimus punctatus, a major pine tree defoliator in China, remains largely unknown. Specifically, Abdominal-A (Abd-a) controls regional variation in abdominal segmentation in model insects such as Drosophila and Tribolium; however, its role in D. Punctatus remains unexplored. In this study, CRISPR/Cas9 was used to functionally characterize Abd-a in D. punctatus. Two target sites were selected, and the genotypes and phenotypes of the G0 and G1 generations were evaluated. Our findings indicate that knocking out Abd-a led to an abnormality in the posterior segments A2–A7, as well as the loss of appendages, mainly prolegs, and affected the thoracic T3 segmentation as well as wing development. Moreover, mutation in Abd-a also impacted anal and reproductive development. Taken together, these results demonstrate that DpAbd-a is essential for embryonic and reproductive development in D. punctatus and could be a promising target for genetic control of this devastating conifer defoliator.

I[formula omitted]U-Net: A dual-path U-Net with rich information interaction for medical image segmentation

Although the U-shape networks have achieved remarkable performances in many medical image segmentation tasks, they rarely model the sequential relationship of hierarchical layers. This weakness makes it difficult for the current layer to effectively utilize the historical information of the previous layer, leading to unsatisfactory segmentation results for lesions with blurred boundaries and irregular shapes. To solve this problem, we propose a novel dual-path U-Net, dubbed I2U-Net. The newly proposed network encourages historical information re-usage and re-exploration through rich information interaction among the dual paths, allowing deep layers to learn more comprehensive features that contain both low-level detail description and high-level semantic abstraction. Specifically, we introduce a multi-functional information interaction module (MFII), which can model cross-path, cross-layer, and cross-path-and-layer information interactions via a unified design, making the proposed I2U-Net behave similarly to an unfolded RNN and enjoying its advantage of modeling time sequence information. Besides, to further selectively and sensitively integrate the information extracted by the encoder of the dual paths, we propose a holistic information fusion and augmentation module (HIFA), which can efficiently bridge the encoder and the decoder. Extensive experiments on four challenging tasks, including skin lesion, polyp, brain tumor, and abdominal multi-organ segmentation, consistently show that the proposed I2U-Net has superior performance and generalization ability over other state-of-the-art methods. The code is available at https://github.com/duweidai/I2U-Net.

Adjusting U-Net for the aortic abdominal aneurysm CT segmentation case

Adjusting U-Net for the aortic abdominal aneurysm CT segmentation case

Impact of Fat Distribution and Metabolic Diseases on Cerebral Microcirculation: A Multimodal Study on Type 2 Diabetic and Obese Patients.

Background: Since metabolic diseases and atherosclerotic vascular events are firmly associated, herein we investigate changes in central microcirculation and atherosclerosis-related body fat distribution in patients with type 2 diabetes mellitus and obesity. Methods: Resting brain perfusion single-photon emission computed tomography (SPECT) imaging with Technetium-99m hexamethylpropylene amine oxime ([99mTc]Tc-HMPAO SPECT) was performed, and the breath-holding index (BHI) and carotid intima-media thickness (cIMT) were measured to characterise central microcirculation. Besides CT-based abdominal fat tissue segmentation, C-peptide level, glycaemic and anthropometric parameters were registered to search for correlations with cerebral blood flow and vasoreactivity. Results: Although no significant difference was found between the resting cerebral perfusion of the two patient cohorts, a greater blood flow increase was experienced in the obese after the breath-holding test than in the diabetics (p < 0.05). A significant positive correlation was encountered between resting and provocation-triggered brain perfusion and C-peptide levels (p < 0.005). BMI and cIMT were negatively correlated (rho = -0.27 and -0.23 for maximum and mean cIMT, respectively), while BMI and BHI showed a positive association (rho = 0.31 and rho = 0.29 for maximum and mean BHI, respectively), which could be explained by BMI-dependent changes in fat tissue distribution. cIMT demonstrated a disproportional relationship with increasing age, and higher cIMT values were observed for the men. Conclusions: Overall, C-peptide levels and circulatory parameters seem to be strong applicants to predict brain microvascular alterations and related cognitive decline in such patient populations.

View adaptive unified self-supervised technique for abdominal organ segmentation

Automatic abdominal organ segmentation is an essential prerequisite for accurate volumetric analysis, disease diagnosis, and tracking by medical practitioners. However, the deformable shapes, variable locations, overlapping with nearby organs, and similar contrast make the segmentation challenging. Moreover, the requirement of a large manually labeled dataset makes it harder. Hence, a semi-supervised contrastive learning approach is utilized to perform the automatic abdominal organ segmentation. Existing 3D deep learning models based on contrastive learning are not able to capture the 3D context of medical volumetric data along three planes/views: axial, sagittal, and coronal views. In this work, a semi-supervised view-adaptive unified model (VAU-model) is proposed to make the 3D deep learning model as view-adaptive to learn 3D context along each view in a unified manner. This method utilizes the novel optimization function that assists the 3D model to learn the 3D context of volumetric medical data along each view in a single model. The effectiveness of the proposed approach is validated on the three types of datasets: BTCV, NIH, and MSD quantitatively and qualitatively. The results demonstrate that the VAU model achieves an average Dice score of 81.61% which is a 3.89% improvement compared to the previous best results for pancreas segmentation in multi-organ dataset BTCV. It also achieves an average Dice score of 77.76% and 76.76% for the pancreas under the single organ non-pathological NIH dataset, and pathological MSD dataset.

Many birds, one stone: Medical image segmentation with multiple partially labeled datasets

Medical image segmentation is fundamental in the field of medical image analysis and has wide clinical applications in disease diagnosis and surgical planning etc. Current prevalent solution is to train a deep network in a fully supervised way with a large-scale fully labeled dataset. However, due to the high labor cost and requirement on medical expertise, such dataset is always absent. Instead, there are multiple partially labeled datasets which are originally established for specific purposes. To make full use of these partially labeled datasets, we propose a novel partially supervised segmentation network, named PSSNet, which consists of a task-specific feature learning network followed by a cross-task attention module (xTA) to exploit task dependencies to enhance task-specific features. To solve the challenges raised by unlabeled classes and domain shift across datasets, we propose an adversarial self-training strategy. We conduct experiments on two medical image segmentation tasks. One is the fine-grained fundus image segmentation aiming to simultaneously segment four-class lesions, OD and OC, and vessels. Validation on seven datasets demonstrates that our PSSNet performs the best among three baselines and three state-of-the-arts. The other is the multiple abdominal organ segmentation in CT images. Our PSSNet is trained on three partially labeled datasets, i.e., LiTS, KiTS and Spleen. Validation on one fully labeled dataset, i.e., BTCV, demonstrates that our PSSNet achieves better performances than four state-of-the-arts. The code is publicly available at https://github.com/CVIU-CSU/PSSNet.

Efficient multiscale spatial attention 3D abdominal multiorgan segmentation model

AbstractAccurate and efficient 3D medical image segmentation models are critical for clinical applications. However, many models which performed well in recent years have consumed significant computational cost, especially those based on self‐attention. For more efficient and accurate segmentation of medical 3D images, we develop an efficient multiscale spatial attention model for 3D abdominal multiorgan segmentation. We use 1D and 2D kernels in the encoder and decoder modules to simulate 3D kernels to reduce the number of parameters and computational cost. Furthermore, we use the lightweight spatial attention and mixed pooling module to capture cross‐dimensional information, multiscale features, and long‐range contextual information. We achieved a Dice Similarity Coefficient (DSC) of 89.86 and a Normalized Surface Dice (NSD) of 78.2 on the FLARE dataset with only 1183 M GPU memory usage, 9 M parameters, and 193G floating point operations(FLOPs).

Temporal Trends in Body Composition and Metabolic Markers Prior to Diagnosis of Pancreatic Ductal Adenocarcinoma

Changes in body composition and metabolic factors may serve as biomarkers for the early detection of pancreatic ductal adenocarcinoma (PDAC). The aim of this study was to capture the longitudinal changes in body composition and metabolic factors before diagnosis of PDAC. We performed a retrospective cohort study in which all patients (≥18 years) diagnosed with PDAC from 2002 to 2021 were identified. We collected all abdominal computed tomography scans and 10 different blood-based biomarkers up to 36 months before diagnosis. We applied a fully automated abdominal segmentation algorithm previously developed by our group for 3-dimensional quantification of body composition on computed tomography scans. Longitudinal trends of body composition and blood-based biomarkers before PDAC diagnosis were estimated using linear mixed models, compared across different time windows, and visualized using spline regression. We included 1690 patients in body composition analysis, of whom 516 (30.5%) had ≥2 prediagnostic computed tomography scans. For analysis of longitudinal trends of blood-based biomarkers, 3332 individuals were included. As an early manifestation of PDAC, we observed a significant decrease in visceral and subcutaneous adipose tissue (β= -1.94 [95% confidence interval (CI), -2.39 to -1.48] and β= -2.59 [95% CI, -3.17 to -2.02]) in area (cm2)/height (m2) per 6 months closer to diagnosis, accompanied by a decrease in serum lipids (eg, low-density lipoprotein [β= -2.83; 95% CI, -3.31 to -2.34], total cholesterol [β= -2.69; 95% CI, -3.18 to -2.20], and triglycerides [β= -1.86; 95% CI, -2.61 to -1.11]), and an increase in blood glucose levels. Loss of muscle tissue and bone volume was predominantly observed in the last 6 months before diagnosis. This study identified significant alterations in a variety of soft tissue and metabolic markers that occur in the development of PDAC. Early recognition of these metabolic changes may provide an opportunity for early detection.

A deep neural network-based end-to-end 3D medical abdominal segmentation and reconstruction model

A deep neural network-based end-to-end 3D medical abdominal segmentation and reconstruction model

AI-based fully automatic image analysis: Optimal abdominal and thoracic segmentation volumes for estimating total muscle volume on computed tomography scans

ObjectivesEvaluation of sarcopenia from computed tomography (CT) is often based on measuring skeletal muscle area on a single transverse slice. Automatic segmentation of muscle volume has a lower variance and may be a better proxy for the total muscle volume than single-slice areas. The aim of the study was to determine which abdominal and thoracic anatomical volumes were best at predicting the total muscle volume. MethodsA cloud-based artificial intelligence tool (recomia.org) was used to segment all skeletal muscle of the torso of 994 patients who had performed whole-torso CT 2008–2020 for various clinical indications. Linear regression models for several anatomical volumes and single-slice areas were compared with regard to predicting the total torso muscle volume. ResultsThe muscle volume from the tip of the coccyx and 25 cm cranially was the best of the abdominal volumes and was significantly better than the L3 slice muscle area (R2 0.935 vs 0.830, P < 0.0001). For thoracic volumes, the muscle volume between the top of the sternum to the lower bound of the Th12 vertebra showed the best correlation with the total volume, significantly better than the Th12 slice muscle area (R2 0.892 vs 0.775, P < 0.0001). Adjusting for body height improved the correlation slightly for all measurements but did not significantly change the ordering. ConclusionsWe identified muscle volumes that can be reliably segmented by automated image analysis which is superior to single slice areas in predicting total muscle volume.

Recurrent feature propagation and edge skip-connections for automatic abdominal organ segmentation

Automatic segmentation of abdominal organs in computed tomography (CT) images can support radiation therapy and image-guided surgery workflows. Development of such automatic solutions remains challenging mainly owing to complex organ interactions and blurry boundaries in CT images. To address these issues, we focus on effective spatial context modeling and explicit edge segmentation priors. Accordingly, we propose a 3D network with four main components trained end-to-end including shared encoder, edge detector, decoder with edge skip-connections (ESCs) and recurrent feature propagation head (RFP-Head). To capture wide-range spatial dependencies, the RFP-Head propagates and harvests local features through directed acyclic graphs (DAGs) formulated with recurrent connections in an efficient slice-wise manner, with regard to spatial arrangement of image units. To leverage edge information, the edge detector learns edge prior knowledge specifically tuned for semantic segmentation by exploiting intermediate features from the encoder with the edge supervision. The ESCs then aggregate the edge knowledge with multi-level decoder features to learn a hierarchy of discriminative features explicitly modeling complementarity between organs’ interiors and edges for segmentation. We conduct extensive experiments on challenging abdominal CT datasets with eight annotated organs. Experimental results show that the proposed network outperforms several state-of-the-art models, especially for the segmentation of small and complicated structures (gallbladder, esophagus, stomach, pancreas and duodenum).

A Robust Network for Multi-Label Abdominal Organs Segmentation

The paper proposes a robust and efficient model designed for multi-label abdominal organ segmentation, featuring a substantially reduced number of parameters. The model focuses on the effectiveness of edge guidance in segmentation and leverages a 3D-Unet architecture with deep supervision, incorporating the robust deep thinking gate (DTG) architecture. Our DTG-incorporated model architecture excels in both efficiency and effectiveness, demonstrating notable enhancements in multi-label abdominal organ segmentation performance. A comprehensive evaluation of the model employed on two datasets of MRI scan of BTCV and FLARE 2022, comparing its performance against state-of-the-art counterparts. The outcomes revealed that the proposed model achieved the highest dice score in the esophagus (0.795), gallbladder (0.945), and pancreas (0.87) while maintaining a most significantly reduced parameter count (13.3 million parameters count). This achievement underscores the model’s efficiency and its suitability for seamless integration into real-world applications, offering promising prospects for enhanced medical image analysis.