Automated pancreas segmentation from computed tomography and magnetic resonance images: A systematic review

Deep-learning based automated pancreas segmentation on CT scans of chronic pancreatitis patients

OBJECTIVES

This study aimed to develop an artificial intelligence (AI)-based segmentation model for accurate delineation of the complex pancreas in patients with chronic pancreatitis (CP) using computer tomography (CT) scans obtained during routine clinical work-up. Validation was performed with internal and external test datasets. A secondary objective was to evaluate the impact of visceral fat area (at the third lumbar level), pancreas volume, and CT parameters on model performance.

METHODS

This multicenter study included 550 retrospectively collected CT scans from Aalborg (n = 373; 224 CP, 150 healthy subjects) and Bergen Hospitals (n = 97 CP), and an online dataset from the National Institutes of Health (NIH) (n = 80, healthy subjects). The Aalborg dataset was divided into a training cohort (n = 326) and an internal test set (n = 47), while the Bergen and NIH datasets served as external test sets. The AI model employed the nnU-Net architecture, with performance evaluated using the Sørensen-Dice index. Correlations with visceral fat, pancreas volume, and CT parameters were assessed.

RESULTS

The pancreas segmentation AI model achieved a Dice score of 0.85 ± 0.08 on the Aalborg test set, 0.79 ± 0.19 on the Bergen dataset, and 0.79 ± 0.18 on the NIH dataset. Visceral fat and pancreas volume positively correlated with Dice scores (r = 0.45 and r = 0.53, both p < 0.0001), while CT parameters had no significant impact (all p-values > 0.07).

CONCLUSION

The AI model demonstrated high accuracy and robustness in pancreas segmentation of both CP patients and healthy subjects, and across diverse sites and scanners, suggesting its potential for clinical application.

Intra-Pancreatic Fat Deposition and Pancreatitis: Insights from the COSMOS Program

The global burden of pancreatitis is substantial, bedevilled by the lack of pathogenesis-based treatments for acute pancreatitis and chronic pancreatitis. The integrated PANDORA (PANcreatic Diseases Originating from intRa-pancreatic fAt) hypothesis "moved the needle" on thinking why pancreatitis develops by bringing fat in the pancreas to the fore. A total of 20 original clinical studies exploring an uncharted territory of fat in the pancreas and pancreatitis were published between 2019 and 2024 as part of the COSMOS (Clinical and epidemiOlogical inveStigations in Metabolism, nutritiOn, and pancreatic diseaseS) program. This review concisely summarises the novel insights into the relationship of intra-pancreatic fat deposition with endocrine and exocrine pancreatic functions, behavioural and nutritional factors, as well as various biomarkers. Tapping into the wealth of knowledge derived from the COSMOS program can unlock new perspectives on the treatment of acute pancreatitis and chronic pancreatitis.

Enhanced accuracy and stability in automated intra-pancreatic fat deposition monitoring of type 2 diabetes mellitus using Dixon MRI and deep learning

PURPOSE

Intra-pancreatic fat deposition (IPFD) is closely associated with the onset and progression of type 2 diabetes mellitus (T2DM). We aimed to develop an accurate and automated method for assessing IPFD on multi-echo Dixon MRI.

MATERIALS AND METHODS

In this retrospective study, 534 patients from two centers who underwent upper abdomen MRI and completed multi-echo and double-echo Dixon MRI were included. A pancreatic segmentation model was trained on double-echo Dixon water images using nnU-Net. Predicted masks were registered to the proton density fat fraction (PDFF) maps of the multi-echo Dixon sequence. Deep semantic segmentation feature-based radiomics (DSFR) and radiomics features were separately extracted on the PDFF maps and modeled using the support vector machine method with 5-fold cross-validation. The first deep learning radiomics (DLR) model was constructed to distinguish T2DM from non-diabetes and pre-diabetes by averaging the output scores of the DSFR and radiomics models. The second DLR model was then developed to distinguish pre-diabetes from non-diabetes. Two radiologist models were constructed based on the mean PDFF of three pancreatic regions of interest.

RESULTS

The mean Dice similarity coefficient for pancreas segmentation was 0.958 in the total test cohort. The AUCs of the DLR and two radiologist models in distinguishing T2DM from non-diabetes and pre-diabetes were 0.868, 0.760, and 0.782 in the training cohort, and 0.741, 0.724, and 0.653 in the external test cohort, respectively. For distinguishing pre-diabetes from non-diabetes, the AUCs were 0.881, 0.688, and 0.688 in the training cohort, which included data combined from both centers. Testing was not conducted due to limited pre-diabetic patients. Intraclass correlation coefficients between radiologists' pancreatic PDFF measurements were 0.800 and 0.699 at two centers, suggesting good and moderate reproducibility, respectively.

CONCLUSION

The DLR model demonstrated superior performance over radiologists, providing a more efficient, accurate and stable method for monitoring IPFD and predicting the risk of T2DM and pre-diabetes. This enables IPFD assessment to potentially serve as an early biomarker for T2DM, providing richer clinical information for disease progression and management.

AI-powered innovations in pancreatitis imaging: a comprehensive literature synthesis

Early identification of pancreatitis remains a significant clinical diagnostic challenge that impacts patient outcomes. The evolution of quantitative imaging followed by deep learning models has shown great promise in the non-invasive diagnosis of pancreatitis and its complications. We provide an overview of advancements in diagnostic imaging and quantitative imaging methods along with the evolution of artificial intelligence (AI). In this article, we review the current and future states of methodology and limitations of AI in improving clinical support in the context of early detection and management of pancreatitis.

Pancreatic atrophy is a predictor for exocrine pancreatic dysfunction: Data from a large cohort of patients with chronic pancreatitis

OBJECTIVES

Pancreatic atrophy is commonly observed in end-stage chronic pancreatitis (CP). Diagnostic standards for pancreatic atrophy not well established. The present cross-sectional observation study explored two-point pancreatic size measurements in a large CP cohort from the Scandinavian Baltic Pancreatic Club (SBPC) database to validate clinically relevant cutoffs for pancreatic atrophy and explore associations to etiological factors and disease outcomes.

METHODS

Patients with CP according to M-ANNHEIM diagnostic criteria were included. We measured maximal axial dimension of the pancreatic head and body and recorded presence of calcifications and pancreatic duct changes on cross-sectional imaging. We calculated cutoffs for clinically relevant atrophy related to exocrine pancreatic dysfunction (EPD) defined as fecal elastase (FE) < 200. Associations between pancreatic atrophy and smoke, alcohol, sex, body size and disease outcomes were analysed using multivariate logistic regression.

RESULTS

We included 539 CP patients (356 male) from four centres in the SBPC study group. Small pancreatic size represented by sum of two-point maximal axial dimension less than 31 mm for females and 37.5 mm for males predicted EPD with good specificity (males: 0.89 (95 % CI, 0.81, 0.95), females: 0.96 (95 % CI, 0.85, 0.99)) but poor sensitivity (males: 0.38 (95 % CI, 0.31, 0.45), females 0.25 (95 % CI, 0.18, 0.35). Male sex, increasing age and long duration of CP were clearly associated with pancreatic atrophy. Corrected for other factors reducing exocrine capacity, pancreatic atrophy was still strongly associated to EPD.

CONCLUSION

We conclude that following the suggested cutoffs, pancreatic atrophy in CP is independently associated with EPD.

Reinforcement learning-based anatomical maps for pancreas subregion and duct segmentation

BACKGROUND

The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application.

PURPOSE

In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images.

METHODS

A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results.

RESULTS

To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets.

CONCLUSIONS

The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures.

nnU-Net-Based Pancreas Segmentation and Volume Measurement on CT Imaging in Patients with Pancreatic Cancer

RATIONALE AND OBJECTIVES

To develop and validate a deep learning (DL)-based method for pancreas segmentation on CT and automatic measurement of pancreatic volume in pancreatic cancer.

MATERIALS AND METHODS

This retrospective study used 3D nnU-net architecture for fully automated pancreatic segmentation in patients with pancreatic cancer. The study used 851 portal venous phase CT images (499 pancreatic cancer and 352 normal pancreas). This dataset was divided into training (n = 506), internal validation (n = 126), and external test set (n = 219). For the external test set, the pancreas was manually segmented by two abdominal radiologists (R1 and R2) to obtain the ground truth. In addition, the consensus segmentation was obtained using Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm. Segmentation performance was assessed using the Dice similarity coefficient (DSC). Next, the pancreatic volumes determined by automatic segmentation were compared to those determined by manual segmentation by two radiologists.

RESULTS

The DL-based model for pancreatic segmentation showed a mean DSC of 0.764 in the internal validation dataset and DSC of 0.807, 0.805, and 0.803 using R1, R2, and STAPLE as references in the external test dataset. The pancreas parenchymal volume measured by automatic and manual segmentations were similar (DL-based model: 65.5 ± 19.3 cm3 and STAPLE: 65.1 ± 21.4 cm3; p = 0.486). The pancreatic parenchymal volume difference between the DL-based model predictions and the manual segmentation by STAPLE was 0.5 cm3, with correlation coefficients of 0.88.

CONCLUSION

The DL-based model efficiently generates automatic segmentation of the pancreas and measures the pancreatic volume in patients with pancreatic cancer.

Clinical impact of artificial intelligence-based solutions on imaging of the pancreas and liver

Artificial intelligence (AI) has experienced substantial progress over the last ten years in many fields of application, including healthcare. In hepatology and pancreatology, major attention to date has been paid to its application to the assisted or even automated interpretation of radiological images, where AI can generate accurate and reproducible imaging diagnosis, reducing the physicians’ workload. AI can provide automatic or semi-automatic segmentation and registration of the liver and pancreatic glands and lesions. Furthermore, using radiomics, AI can introduce new quantitative information which is not visible to the human eye to radiological reports. AI has been applied in the detection and characterization of focal lesions and diffuse diseases of the liver and pancreas, such as neoplasms, chronic hepatic disease, or acute or chronic pancreatitis, among others. These solutions have been applied to different imaging techniques commonly used to diagnose liver and pancreatic diseases, such as ultrasound, endoscopic ultrasonography, computerized tomography (CT), magnetic resonance imaging, and positron emission tomography/CT. However, AI is also applied in this context to many other relevant steps involved in a comprehensive clinical scenario to manage a gastroenterological patient. AI can also be applied to choose the most convenient test prescription, to improve image quality or accelerate its acquisition, and to predict patient prognosis and treatment response. In this review, we summarize the current evidence on the application of AI to hepatic and pancreatic radiology, not only in regard to the interpretation of images, but also to all the steps involved in the radiological workflow in a broader sense. Lastly, we discuss the challenges and future directions of the clinical application of AI methods.

Inter- and intra-observer variability of computed tomography-based parenchymal- and ductal diameters in chronic pancreatitis: a multi-observer international study

PURPOSE

The need for incorporation of quantitative imaging biomarkers of pancreatic parenchymal and ductal structures has been highlighted in recent proposals for new scoring systems in chronic pancreatitis (CP). To quantify inter- and intra-observer variability in CT-based measurements of ductal- and gland diameters in CP patients.

MATERIALS AND METHODS

Prospectively acquired pancreatic CT examinations from 50 CP patients were reviewed by 12 radiologists and four pancreatologists from 10 institutions. Assessment entailed measuring maximum diameter in the axial plane of four structures: (1) pancreatic head (PDhead), (2) pancreatic body (PDbody), (3) main pancreatic duct in the pancreatic head (MPDhead), and (4) body (MPDbody). Agreement was assessed by the 95% limits of agreement with the mean (LOAM), representing how much a single measurement for a specific subject may plausibly deviate from the mean of all measurements on the specific subject. Bland-Altman limits of agreement (LoA) were generated for intra-observer pairs.

RESULTS

The 16 observers completed 6400 caliper placements comprising a first and second measurement session. The widest inter-observer LOAM was seen with PDhead (± 9.1 mm), followed by PDbody (± 5.1 mm), MPDhead (± 3.2 mm), and MPDbody (± 2.6 mm), whereas the mean intra-observer LoA width was ± 7.3, ± 5.1, ± 3.7, and ± 2.4 mm, respectively.

CONCLUSION

Substantial intra- and inter-observer variability was observed in pancreatic two-point measurements. This was especially pronounced for parenchymal and duct diameters of the pancreatic head. These findings challenge the implementation of two-point measurements as the foundation for quantitative imaging scoring systems in CP.

Artificial intelligence in adrenal imaging: A critical review of current applications

In the elective field of adrenal imaging, artificial intelligence (AI) can be used for adrenal lesion detection, characterization, hypersecreting syndrome management and patient follow-up. Although a perfect AI tool that includes all required steps from detection to analysis does not exist yet, multiple AI algorithms have been developed and tested with encouraging results. However, AI in this setting is still at an early stage. In this regard, most published studies about AI in adrenal gland imaging report preliminary results that do not have yet daily applications in clinical practice. In this review, recent developments and current results of AI in the field of adrenal imaging are presented. Limitations and future perspectives of AI are discussed.

A fat fraction phantom for establishing new convolutional neural network to determine the pancreatic fat deposition

The determination of fat fraction based on Magnetic Resonance Imaging (MRI) requires extremely accurate data reconstruction for the assessment of pancreatic fat accumulation in medical diagnostics and biological research. In this study, the signal model of the oil and water emulsion was created with a 3.0 T field strength. We examined the quantification of the fat fraction from phantom and the intrapancreatic fat fraction using the techniques of magnetic resonance spectroscopy (MRS) and Iterative Decomposition with Echo Asymmetry and Least-Squares estimate (IDEAL) in magnetic resonance imaging (MRI). Additionally, we contrasted expert manual pancreatic fat assessment with MRS and IDEAL pancreatic fat fraction quantification. There was a strong connection between the true fat volume fraction and the fat fraction from IDEAL and MRS (R² = 0.99 and 0.99, respectively). For both phantom and in vivo measurements, Pearson's correlation and linear regression analysis were used. The findings of the in vivo assessment revealed a variable correlation between the pancreatic fat fraction MRI readings. We also used MR-opsy for manual pancreatic fat fraction segmentation since it read pancreatic fat fractions more accurately than IDEAL and MRS, which aided in the development of machine learning's ability to assess pancreatic fat automatically.

Volumetric Pancreas Segmentation on Computed Tomography: Accuracy and Efficiency of a Convolutional Neural Network Versus Manual Segmentation in 3D Slicer in the Context of Interreader Variability of Expert Radiologists

PURPOSE

This study aimed to compare accuracy and efficiency of a convolutional neural network (CNN)-enhanced workflow for pancreas segmentation versus radiologists in the context of interreader reliability.

METHODS

Volumetric pancreas segmentations on a data set of 294 portal venous computed tomographies were performed by 3 radiologists (R1, R2, and R3) and by a CNN. Convolutional neural network segmentations were reviewed and, if needed, corrected ("corrected CNN [c-CNN]" segmentations) by radiologists. Ground truth was obtained from radiologists' manual segmentations using simultaneous truth and performance level estimation algorithm. Interreader reliability and model's accuracy were evaluated with Dice-Sorenson coefficient (DSC) and Jaccard coefficient (JC). Equivalence was determined using a two 1-sided test. Convolutional neural network segmentations below the 25th percentile DSC were reviewed to evaluate segmentation errors. Time for manual segmentation and c-CNN was compared.

RESULTS

Pancreas volumes from 3 sets of segmentations (manual, CNN, and c-CNN) were noninferior to simultaneous truth and performance level estimation-derived volumes [76.6 cm 3 (20.2 cm 3 ), P < 0.05]. Interreader reliability was high (mean [SD] DSC between R2-R1, 0.87 [0.04]; R3-R1, 0.90 [0.05]; R2-R3, 0.87 [0.04]). Convolutional neural network segmentations were highly accurate (DSC, 0.88 [0.05]; JC, 0.79 [0.07]) and required minimal-to-no corrections (c-CNN: DSC, 0.89 [0.04]; JC, 0.81 [0.06]; equivalence, P < 0.05). Undersegmentation (n = 47 [64%]) was common in the 73 CNN segmentations below 25th percentile DSC, but there were no major errors. Total inference time (minutes) for CNN was 1.2 (0.3). Average time (minutes) taken by radiologists for c-CNN (0.6 [0.97]) was substantially lower compared with manual segmentation (3.37 [1.47]; savings of 77.9%-87% [ P < 0.0001]).

CONCLUSIONS

Convolutional neural network-enhanced workflow provides high accuracy and efficiency for volumetric pancreas segmentation on computed tomography.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Use of Magnetic Resonance Imaging to Quantify Fat and Steatosis in the Pancreas in Patients after Bariatric Surgery: a Retrospective Study

INTRODUCTION

Pancreatic steatosis (PS) has both metabolic consequences and local effects on the pancreas itself. Magnetic resonance imaging (MRI) is the most reliable non-invasive method for diagnosing PS. We investigated the impact of metabolic syndrome (MS) on the presence of PS, differences in individuals with and without PS, and the metabolic effects of bariatric procedures.

METHODS

Changes in anthropometric and basic biochemistry values and MS occurrence were evaluated in 34 patients with obesity who underwent a bariatric procedure. After the procedure, patients underwent MRI with manual 3D segmentation mask creation to determine the pancreatic fat content (PFC). We compared the differences in the PFC and the presence of PS in individuals with and without MS and compared patients with and without PS.

RESULTS

We found no significant difference in the PFC between the groups with and without MS or in the occurrence of PS. There were significant differences in patients with and without PS, especially in body mass index (BMI), fat mass, visceral adipose tissue (VAT), select adipocytokines, and lipid spectrum with no difference in glycemia levels. Significant metabolic effects of bariatric procedures were observed.

CONCLUSIONS

Bariatric procedures can be considered effective in the treatment of obesity, MS, and some of its components. Measuring PFC using MRI did not show any difference in relation to MS, but patients who lost weight to BMI < 30 did not suffer from PS and had lower overall fat mass and VAT. Glycemia levels did not have an impact on the presence of PS.

Effect of Gray Value Discretization and Image Filtration on Texture Features of the Pancreas Derived from Magnetic Resonance Imaging at 3T

Radiomics of pancreas magnetic resonance (MR) images is positioned well to play an important role in the management of diseases characterized by diffuse involvement of the pancreas. The effect of image pre-processing configurations on these images has been sparsely investigated. Fifteen individuals with definite chronic pancreatitis (an exemplar diffuse disease of the pancreas) and 15 healthy individuals were included in this age- and sex-matched case-control study. MR images of the pancreas were acquired using a single 3T scanner. A total of 93 first-order and second-order texture features of the pancreas were compared between the study groups, by subjecting MR images of the pancreas to 7 image pre-processing configurations related to gray level discretization and image filtration. The studied parameters of intensity discretization did not vary in terms of their effect on the number of significant first-order texture features. The number of statistically significant first-order texture features varied after filtering (7 with the use of logarithm filter and 3 with the use of Laplacian of Gaussian filter with 5 mm σ). Intensity discretization generally affected the number of significant second-order texture features more markedly than filtering. The use of fixed bin number of 16 yielded 42 significant second-order texture features, fixed bin number of 128–38 features, fixed bin width of 6–24 features, and fixed bin width of 42–26 features. The specific parameters of filtration and intensity discretization had differing effects on radiomics signature of the pancreas. Relative discretization with fixed bin number of 16 and use of logarithm filter hold promise as pre-processing configurations of choice in future radiomics studies in diffuse diseases of the pancreas.

Artificial Intelligence Applied to Pancreatic Imaging: A Narrative Review

The diagnosis, evaluation, and treatment planning of pancreatic pathologies usually require the combined use of different imaging modalities, mainly, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). Artificial intelligence (AI) has the potential to transform the clinical practice of medical imaging and has been applied to various radiological techniques for different purposes, such as segmentation, lesion detection, characterization, risk stratification, or prediction of response to treatments. The aim of the present narrative review is to assess the available literature on the role of AI applied to pancreatic imaging. Up to now, the use of computer-aided diagnosis (CAD) and radiomics in pancreatic imaging has proven to be useful for both non-oncological and oncological purposes and represents a promising tool for personalized approaches to patients. Although great developments have occurred in recent years, it is important to address the obstacles that still need to be overcome before these technologies can be implemented into our clinical routine, mainly considering the heterogeneity among studies.

Multiscale unsupervised domain adaptation for automatic pancreas segmentation in CT volumes using adversarial learning

PURPOSE

Computer-aided automatic pancreas segmentation is essential for early diagnosis and treatment of pancreatic diseases. However, the annotation of pancreas images requires professional doctors and considerable expenditure. Due to imaging differences among various institution population, scanning devices and imaging protocols etc., significant degradation in the performance of model inference results is prone to occur when models trained with domain-specific (usually institution-specific) datasets are directly applied to new (other centers/institutions) domain data. In this paper, we propose a novel unsupervised domain adaptation method based on adversarial learning to address pancreas segmentation challenges with the lack of annotations and domain shift interference.

METHODS

A 3D semantic segmentation model with attention module and residual module is designed as the backbone pancreas segmentation model. In both segmentation model and domain adaptation discriminator network, a multiscale progressively weighted structure is introduced to acquire different field of views. Features of labeled data and unlabeled data are fed in pairs into the proposed multiscale discriminator to learn domain-specific characteristics. Then the unlabeled data features with pseudo-domain label are fed to the discriminator to acquire domain-ambiguous information. With this adversarial learning strategy, the performance of the segmentation network is enhanced to segment unseen unlabeled data.

RESULTS

Experiments were conducted on two public annotated datasets as source datasets respectively and one private dataset as target dataset, where annotations were not used for the training process but only for evaluation. The 3D segmentation model achieves comparative performance with state-of-the-art pancreas segmentation methods on source domain. After implementing our domain adaptation architecture, the average Dice Similarity Coefficient(DSC) of the segmentation model trained on the NIH-TCIA source dataset increases from 58.79% to 72.73% on the local hospital dataset, while the performance of the target domain segmentation model transferred from the MSD source dataset rises from 62.34% to 71.17%.

CONCLUSIONS

Correlation of features across data domains are utilized to train the pancreas segmentation model on unlabeled data domain, improving the generalization of the model. Our results demonstrate that the proposed method enables the segmentation model to make meaningful segmentation for unseen data of the training set. In the future, the proposed method has the potential to apply segmentation model trained on public dataset to clinical unannotated CT images from local hospital, effectively assisting radiologists in clinical practice. This article is protected by copyright. All rights reserved.

Segmentation of Pancreatic Subregions in Computed Tomography Images

The accurate segmentation of pancreatic subregions (head, body, and tail) in CT images provides an opportunity to examine the local morphological and textural changes in the pancreas. Quantifying such changes aids in understanding the spatial heterogeneity of the pancreas and assists in the diagnosis and treatment planning of pancreatic cancer. Manual outlining of pancreatic subregions is tedious, time-consuming, and prone to subjective inconsistency. This paper presents a multistage anatomy-guided framework for accurate and automatic 3D segmentation of pancreatic subregions in CT images. Using the delineated pancreas, two soft-label maps were estimated for subregional segmentation—one by training a fully supervised naïve Bayes model that considers the length and volumetric proportions of each subregional structure based on their anatomical arrangement, and the other by using the conventional deep learning U-Net architecture for 3D segmentation. The U-Net model then estimates the joint probability of the two maps and performs optimal segmentation of subregions. Model performance was assessed using three datasets of contrast-enhanced abdominal CT scans: one public NIH dataset of the healthy pancreas, and two datasets D₁ and D₂ (one for each of pre-cancerous and cancerous pancreas). The model demonstrated excellent performance during the multifold cross-validation using the NIH dataset, and external validation using D₁ and D₂. To the best of our knowledge, this is the first automated model for the segmentation of pancreatic subregions in CT images. A dataset consisting of reference anatomical labels for subregions in all images of the NIH dataset is also established.

Fully Automated Abdominal CT Biomarkers for Type 2 Diabetes Using Deep Learning

Background CT biomarkers both inside and outside the pancreas can potentially be used to diagnose type 2 diabetes mellitus. Previous studies on this topic have shown significant results but were limited by manual methods and small study samples. Purpose To investigate abdominal CT biomarkers for type 2 diabetes mellitus in a large clinical data set using fully automated deep learning. Materials and Methods For external validation, noncontrast abdominal CT images were retrospectively collected from consecutive patients who underwent routine colorectal cancer screening with CT colonography from 2004 to 2016. The pancreas was segmented using a deep learning method that outputs measurements of interest, including CT attenuation, volume, fat content, and pancreas fractal dimension. Additional biomarkers assessed included visceral fat, atherosclerotic plaque, liver and muscle CT attenuation, and muscle volume. Univariable and multivariable analyses were performed, separating patients into groups based on time between type 2 diabetes diagnosis and CT date and including clinical factors such as sex, age, body mass index (BMI), BMI greater than 30 kg/m², and height. The best set of predictors for type 2 diabetes were determined using multinomial logistic regression. Results A total of 8992 patients (mean age, 57 years ± 8 [SD]; 5009 women) were evaluated in the test set, of whom 572 had type 2 diabetes mellitus. The deep learning model had a mean Dice similarity coefficient for the pancreas of 0.69 ± 0.17, similar to the interobserver Dice similarity coefficient of 0.69 ± 0.09 (P = .92). The univariable analysis showed that patients with diabetes had, on average, lower pancreatic CT attenuation (mean, 18.74 HU ± 16.54 vs 29.99 HU ± 13.41; P < .0001) and greater visceral fat volume (mean, 235.0 mL ± 108.6 vs 130.9 mL ± 96.3; P < .0001) than those without diabetes. Patients with diabetes also showed a progressive decrease in pancreatic attenuation with greater duration of disease. The final multivariable model showed pairwise areas under the receiver operating characteristic curve (AUCs) of 0.81 and 0.85 between patients without and patients with diabetes who were diagnosed 0-2499 days before and after undergoing CT, respectively. In the multivariable analysis, adding clinical data did not improve upon CT-based AUC performance (AUC = 0.67 for the CT-only model vs 0.68 for the CT and clinical model). The best predictors of type 2 diabetes mellitus included intrapancreatic fat percentage, pancreatic fractal dimension, plaque severity between the L1 and L4 vertebra levels, average liver CT attenuation, and BMI. Conclusion The diagnosis of type 2 diabetes mellitus was associated with abdominal CT biomarkers, especially measures of pancreatic CT attenuation and visceral fat. © RSNA, 2022 Online supplemental material is available for this article.

Automated pancreas segmentation and volumetry using deep neural network on computed tomography

Pancreas segmentation is necessary for observing lesions, analyzing anatomical structures, and predicting patient prognosis. Therefore, various studies have designed segmentation models based on convolutional neural networks for pancreas segmentation. However, the deep learning approach is limited by a lack of data, and studies conducted on a large computed tomography dataset are scarce. Therefore, this study aims to perform deep-learning-based semantic segmentation on 1006 participants and evaluate the automatic segmentation performance of the pancreas via four individual three-dimensional segmentation networks. In this study, we performed internal validation with 1,006 patients and external validation using the cancer imaging archive pancreas dataset. We obtained mean precision, recall, and dice similarity coefficients of 0.869, 0.842, and 0.842, respectively, for internal validation via a relevant approach among the four deep learning networks. Using the external dataset, the deep learning network achieved mean precision, recall, and dice similarity coefficients of 0.779, 0.749, and 0.735, respectively. We expect that generalized deep-learning-based systems can assist clinical decisions by providing accurate pancreatic segmentation and quantitative information of the pancreas for abdominal computed tomography.

Intra-pancreatic fat deposition: bringing hidden fat to the fore

Development of advanced modalities for detection of fat within the pancreas has transformed understanding of the role of intra-pancreatic fat deposition (IPFD) in health and disease. There is now strong evidence for the presence of minimal (but not negligible) IPFD in healthy human pancreas. Diffuse excess IPFD, or fatty pancreas disease (FPD), is more frequent than type 2 diabetes mellitus (T2DM) (the most common disease of the endocrine pancreas) and acute pancreatitis (the most common disease of the exocrine pancreas) combined. FPD is not strictly a function of high BMI; it can result from the excess deposition of fat in the islets of Langerhans, acinar cells, inter-lobular stroma, acinar-to-adipocyte trans-differentiation or replacement of apoptotic acinar cells. This process leads to a wide array of diseases characterized by excess IPFD, including but not limited to acute pancreatitis, chronic pancreatitis, pancreatic cancer, T2DM, diabetes of the exocrine pancreas. There is ample evidence for FPD being potentially reversible. Weight loss-induced decrease of intra-pancreatic fat is tightly associated with remission of T2DM and its re-deposition with recurrence of the disease. Reversing FPD will open up opportunities for preventing or intercepting progression of major diseases of the exocrine pancreas in the future.

TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

The application of artificial intelligence (AI) to various medical subfields has been a popular topic of research in recent years. In particular, deep learning has been widely used and has proven effective in many cases. Topological data analysis (TDA)—a rising field at the intersection of mathematics, statistics, and computer science—offers new insights into data. In this work, we develop a novel deep learning architecture that we call TopoResNet that integrates topological information into the residual neural network architecture. To demonstrate TopoResNet, we apply it to a skin lesion classification problem. We find that TopoResNet improves the accuracy and the stability of the training process.

3D-Printed Replica and Porcine Explants for Pre-Clinical Optimization of Endoscopic Tumor Treatment by Magnetic Targeting

Simple Summary

Animal models are often needed in cancer research but some research questions may be answered with other models, e.g., 3D replicas of patient-specific data, as these mirror the anatomy in more detail. We, therefore, developed a simple eight-step process to fabricate a 3D replica from computer tomography (CT) data using solely open access software and described the method in detail. For evaluation, we performed experiments regarding endoscopic tumor treatment with magnetic nanoparticles by magnetic hyperthermia and local drug release. For this, the magnetic nanoparticles need to be accumulated at the tumor site via a magnetic field trap. Using the developed eight-step process, we printed a replica of a locally advanced pancreatic cancer and used it to find the best position for the magnetic field trap. In addition, we described a method to hold these magnetic field traps stably in place. The results are highly important for the development of endoscopic tumor treatment with magnetic nanoparticles as the handling and the stable positioning of the magnetic field trap at the stomach wall in close proximity to the pancreatic tumor could be defined and practiced. Finally, the detailed description of the workflow and use of open access software allows for a wide range of possible uses.

Abstract

Background: Animal models have limitations in cancer research, especially regarding anatomy-specific questions. An example is the exact endoscopic placement of magnetic field traps for the targeting of therapeutic nanoparticles. Three-dimensional-printed human replicas may be used to overcome these pitfalls. Methods: We developed a transparent method to fabricate a patient-specific replica, allowing for a broad scope of application. As an example, we then additively manufactured the relevant organs of a patient with locally advanced pancreatic ductal adenocarcinoma. We performed experimental design investigations for a magnetic field trap and explored the best fixation methods on an explanted porcine stomach wall. Results: We describe in detail the eight-step development of a 3D replica from CT data. To guide further users in their decisions, a morphologic box was created. Endoscopies were performed on the replica and the resulting magnetic field was investigated. The best fixation method to hold the magnetic field traps stably in place was the fixation of loops at the stomach wall with endoscopic single-use clips. Conclusions: Using only open access software, the developed method may be used for a variety of cancer-related research questions. A detailed description of the workflow allows one to produce a 3D replica for research or training purposes at low costs.

Clinical Artificial Intelligence Applications in Radiology: Chest and Abdomen

Organ segmentation, chest radiograph classification, and lung and liver nodule detections are some of the popular artificial intelligence (AI) tasks in chest and abdominal radiology due to the wide availability of public datasets. AI algorithms have achieved performance comparable to humans in less time for several organ segmentation tasks, and some lesion detection and classification tasks. This article introduces the current published articles of AI applied to chest and abdominal radiology, including organ segmentation, lesion detection, classification, and predicting prognosis.

Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies

PURPOSE

The aims of this study were to train and evaluate deep learning models for automated segmentation of abdominal organs in whole-body magnetic resonance (MR) images from the UK Biobank (UKBB) and German National Cohort (GNC) MR imaging studies and to make these models available to the scientific community for analysis of these data sets.

METHODS

A total of 200 T1-weighted MR image data sets of healthy volunteers each from UKBB and GNC (400 data sets in total) were available in this study. Liver, spleen, left and right kidney, and pancreas were segmented manually on all 400 data sets, providing labeled ground truth data for training of a previously described U-Net-based deep learning framework for automated medical image segmentation (nnU-Net). The trained models were tested on all data sets using a 4-fold cross-validation scheme. Qualitative analysis of automated segmentation results was performed visually; performance metrics between automated and manual segmentation results were computed for quantitative analysis. In addition, interobserver segmentation variability between 2 human readers was assessed on a subset of the data.

RESULTS

Automated abdominal organ segmentation was performed with high qualitative and quantitative accuracy on UKBB and GNC data. In more than 90% of data sets, no or only minor visually detectable qualitative segmentation errors occurred. Mean Dice scores of automated segmentations compared with manual reference segmentations were well higher than 0.9 for the liver, spleen, and kidneys on UKBB and GNC data and around 0.82 and 0.89 for the pancreas on UKBB and GNC data, respectively. Mean average symmetric surface distance was between 0.3 and 1.5 mm for the liver, spleen, and kidneys and between 2 and 2.2 mm for pancreas segmentation. The quantitative accuracy of automated segmentation was comparable with the agreement between 2 human readers for all organs on UKBB and GNC data.

CONCLUSION

Automated segmentation of abdominal organs is possible with high qualitative and quantitative accuracy on whole-body MR imaging data acquired as part of UKBB and GNC. The results obtained and deep learning models trained in this study can be used as a foundation for automated analysis of thousands of MR data sets of UKBB and GNC and thus contribute to tackling topical and original scientific questions.

Artificial intelligence: a critical review of current applications in pancreatic imaging

The applications of artificial intelligence (AI), including machine learning and deep learning, in the field of pancreatic disease imaging are rapidly expanding. AI can be used for the detection of pancreatic ductal adenocarcinoma and other pancreatic tumors but also for pancreatic lesion characterization. In this review, the basic of radiomics, recent developments and current results of AI in the field of pancreatic tumors are presented. Limitations and future perspectives of AI are discussed.

Pancreas image mining: a systematic review of radiomics

OBJECTIVES

To systematically review published studies on the use of radiomics of the pancreas.

METHODS

The search was conducted in the MEDLINE database. Human studies that investigated the applications of radiomics in diseases of the pancreas were included. The radiomics quality score was calculated for each included study.

RESULTS

A total of 72 studies encompassing 8863 participants were included. Of them, 66 investigated focal pancreatic lesions (pancreatic cancer, precancerous lesions, or benign lesions); 4, pancreatitis; and 2, diabetes mellitus. The principal applications of radiomics were differential diagnosis between various types of focal pancreatic lesions (n = 19), classification of pancreatic diseases (n = 23), and prediction of prognosis or treatment response (n = 30). Second-order texture features were most useful for the purpose of differential diagnosis of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature), whereas filtered image features were most useful for the purpose of classification of diseases of the pancreas and prediction of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature). The median radiomics quality score of the included studies was 28%, with the interquartile range of 22% to 36%. The radiomics quality score was significantly correlated with the number of extracted radiomics features (r = 0.52, p < 0.001) and the study sample size (r = 0.34, p = 0.003).

CONCLUSIONS

Radiomics of the pancreas holds promise as a quantitative imaging biomarker of both focal pancreatic lesions and diffuse changes of the pancreas. The usefulness of radiomics features may vary depending on the purpose of their application. Standardisation of image acquisition protocols and image pre-processing is warranted prior to considering the use of radiomics of the pancreas in routine clinical practice.

KEY POINTS

• Methodologically sound studies on radiomics of the pancreas are characterised by a large sample size and a large number of extracted features. • Optimisation of the radiomics pipeline will increase the clinical utility of mineable pancreas imaging data. • Radiomics of the pancreas is a promising personalised medicine tool in diseases of the pancreas.

Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset

PURPOSE

To develop a two-stage three-dimensional (3D) convolutional neural networks (CNNs) for fully automated volumetric segmentation of pancreas on computed tomography (CT) and to further evaluate its performance in the context of intra-reader and inter-reader reliability at full dose and reduced radiation dose CTs on a public dataset.

METHODS

A dataset of 1994 abdomen CT scans (portal venous phase, slice thickness ≤ 3.75-mm, multiple CT vendors) was curated by two radiologists (R1 and R2) to exclude cases with pancreatic pathology, suboptimal image quality, and image artifacts (n = 77). Remaining 1917 CTs were equally allocated between R1 and R2 for volumetric pancreas segmentation [ground truth (GT)]. This internal dataset was randomly divided into training (n = 1380), validation (n = 248), and test (n = 289) sets for the development of a two-stage 3D CNN model based on a modified U-net architecture for automated volumetric pancreas segmentation. Model's performance for pancreas segmentation and the differences in model-predicted pancreatic volumes vs GT volumes were compared on the test set. Subsequently, an external dataset from The Cancer Imaging Archive (TCIA) that had CT scans acquired at standard radiation dose and same scans reconstructed at a simulated 25% radiation dose was curated (n = 41). Volumetric pancreas segmentation was done on this TCIA dataset by R1 and R2 independently on the full dose and then at the reduced radiation dose CT images. Intra-reader and inter-reader reliability, model's segmentation performance, and reliability between model-predicted pancreatic volumes at full vs reduced dose were measured. Finally, model's performance was tested on the benchmarking National Institute of Health (NIH)-Pancreas CT (PCT) dataset.

RESULTS

Three-dimensional CNN had mean (SD) Dice similarity coefficient (DSC): 0.91 (0.03) and average Hausdorff distance of 0.15 (0.09) mm on the test set. Model's performance was equivalent between males and females (P = 0.08) and across different CT slice thicknesses (P > 0.05) based on noninferiority statistical testing. There was no difference in model-predicted and GT pancreatic volumes [mean predicted volume 99 cc (31cc); GT volume 101 cc (33 cc), P = 0.33]. Mean pancreatic volume difference was -2.7 cc (percent difference: -2.4% of GT volume) with excellent correlation between model-predicted and GT volumes [concordance correlation coefficient (CCC)=0.97]. In the external TCIA dataset, the model had higher reliability than R1 and R2 on full vs reduced dose CT scans [model mean (SD) DSC: 0.96 (0.02), CCC = 0.995 vs R1 DSC: 0.83 (0.07), CCC = 0.89, and R2 DSC:0.87 (0.04), CCC = 0.97]. The DSC and volume concordance correlations for R1 vs R2 (inter-reader reliability) were 0.85 (0.07), CCC = 0.90 at full dose and 0.83 (0.07), CCC = 0.96 at reduced dose datasets. There was good reliability between model and R1 at both full and reduced dose CT [full dose: DSC: 0.81 (0.07), CCC = 0.83 and reduced dose DSC:0.81 (0.08), CCC = 0.87]. Likewise, there was good reliability between model and R2 at both full and reduced dose CT [full dose: DSC: 0.84 (0.05), CCC = 0.89 and reduced dose DSC:0.83(0.06), CCC = 0.89]. There was no difference in model-predicted and GT pancreatic volume in TCIA dataset (mean predicted volume 96 cc (33); GT pancreatic volume 89 cc (30), p = 0.31). Model had mean (SD) DSC: 0.89 (0.04) (minimum-maximum DSC: 0.79 -0.96) on the NIH-PCT dataset.

CONCLUSION

A 3D CNN developed on the largest dataset of CTs is accurate for fully automated volumetric pancreas segmentation and is generalizable across a wide range of CT slice thicknesses, radiation dose, and patient gender. This 3D CNN offers a scalable tool to leverage biomarkers from pancreas morphometrics and radiomics for pancreatic diseases including for early pancreatic cancer detection.

CT and MRI of pancreatic tumors: an update in the era of radiomics

Radiomics is a relatively new approach for image analysis. As a part of radiomics, texture analysis, which consists in extracting a great amount of quantitative data from original images, can be used to identify specific features that can help determining the actual nature of a pancreatic lesion and providing other information such as resectability, tumor grade, tumor response to neoadjuvant therapy or survival after surgery. In this review, the basic of radiomics, recent developments and the results of texture analysis using computed tomography and magnetic resonance imaging in the field of pancreatic tumors are presented. Future applications of radiomics, such as artificial intelligence, are discussed.

Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net

Combinations of data augmentation methods and deep learning architectures for automatic pancreas segmentation on CT images are proposed and evaluated. Images from a public CT dataset of pancreas segmentation were used to evaluate the models. Baseline U-net and deep U-net were chosen for the deep learning models of pancreas segmentation. Methods of data augmentation included conventional methods, mixup, and random image cropping and patching (RICAP). Ten combinations of the deep learning models and the data augmentation methods were evaluated. Four-fold cross validation was performed to train and evaluate these models with data augmentation methods. The dice similarity coefficient (DSC) was calculated between automatic segmentation results and manually annotated labels and these were visually assessed by two radiologists. The performance of the deep U-net was better than that of the baseline U-net with mean DSC of 0.703–0.789 and 0.686–0.748, respectively. In both baseline U-net and deep U-net, the methods with data augmentation performed better than methods with no data augmentation, and mixup and RICAP were more useful than the conventional method. The best mean DSC was obtained using a combination of deep U-net, mixup, and RICAP, and the two radiologists scored the results from this model as good or perfect in 76 and 74 of the 82 cases.

Deep pancreas segmentation with uncertain regions of shadowed sets

Pancreas segmentation is a challenging task in medical image analysis especially for the patients with pancreatic cancer. First, the images often have poor contrast and blurred boundaries. Second, there exist large variations in gray scale, texture, location, shape and size among pancreas images. It becomes even worse with cases of pancreatic cancer. Besides, as an inevitable phenomenon, some of the slices have disconnected topology in pancreas part. All these problems lead to high segmentation uncertainties and make the results inaccurate. Existing pancreas segmentation methods rarely achieve sufficiently accurate and robust results especially for cancer cases. To tackle these problems, we propose a 2D deep learning-based method which can involve uncertainties in the process of segmentation iteratively. The proposed method describes the uncertain regions of pancreatic MRI images based on shadowed sets theory. The results are further corrected through increasing the weights of uncertain regions in iterative training. We evaluate our approach on a challenging pancreatic cancer MRI images dataset collected from the Changhai Hospital, and also validate our approach on the NIH pancreas segmentation dataset. The experimental results demonstrate that our proposed method outperforms the state-of-the-art methods in terms of the Dice similarity coefficient of 73.88% on cancer MRI dataset and 84.37% on NIH dataset respectively.