Spleen Segmentation Research Articles

Multi-scale dual-channel feature embedding decoder for biomedical image segmentation

Background and Objective:Attaining global context along with local dependencies is of paramount importance for achieving highly accurate segmentation of objects from image frames and is challenging while developing deep learning-based biomedical image segmentation. Several transformer-based models have been proposed to handle this issue in biomedical image segmentation. Despite this, segmentation accuracy remains an ongoing challenge, as these models often fall short of the target range due to their limited capacity to capture critical local and global contexts. However, the quadratic computational complexity is the main limitation of these models. Moreover, a large dataset is required to train those models. Methods:In this paper, we propose a novel multi-scale dual-channel decoder to mitigate this issue. The complete segmentation model uses two parallel encoders and a dual-channel decoder. The encoders are based on convolutional networks, which capture the features of the input images at multiple levels and scales. The decoder comprises a hierarchy of Attention-gated Swin Transformers with a fine-tuning strategy. The hierarchical Attention-gated Swin Transformers implements a multi-scale, multi-level feature embedding strategy that captures short and long-range dependencies and leverages the necessary features without increasing computational load. At the final stage of the decoder, a fine-tuning strategy is implemented that refines the features to keep the rich features and reduce the possibility of over-segmentation. Results:The proposed model is evaluated on publicly available LiTS, 3DIRCADb, and spleen datasets obtained from Medical Segmentation Decathlon. The model is also evaluated on a private dataset from Medical College Kolkata, India. We observe that the proposed model outperforms the state-of-the-art models in liver tumor and spleen segmentation in terms of evaluation metrics at a comparative computational cost. Conclusion:The novel dual-channel decoder embeds multi-scale features and creates a representation of both short and long-range contexts efficiently. It also refines the features at the final stage to select only necessary features. As a result, we achieve better segmentation performance than the state-of-the-art models.

UNet-based multi-organ segmentation in photon counting CT using virtual monoenergetic images.

Multi-organ segmentation aids in disease diagnosis, treatment, and radiotherapy. The recently emerged photon counting detector-based CT (PCCT) provides spectral information of the organs and the background tissue and may improve segmentationperformance. We propose UNet-based multi-organ segmentation in PCCT using virtual monoenergetic images (VMI) to exploit spectral informationeffectively. The proposed method consists of the following steps: Noise reduction in bin-wise images, image-based material decomposition, generating VMIs, and deep learning-based segmentation. VMIs are synthesized for various x-ray energies using basis images. The UNet-based networks (3D UNet, Swin UNETR) were used for segmentation, and dice similarity coefficients (DSC) and 3D visualization of the segmented result were evaluation indicators. We validated the proposed method for the liver, pancreas, and spleen segmentation using abdominal phantoms from 55 subjects for dual- and quad-energy bins. We compared it to the conventional PCCT-based segmentation, which uses only the (noise-reduced) bin-wise images. The experiments were conducted on two cases by adjusting the doselevels. The proposed method improved the training stability for most cases. With the proposed method, the average DSC for the three organs slightly increased from 0.933 to 0.95, and the standard deviation decreased from 0.066 to 0.047, for example, in the low dose case (using VMIs v.s. bin-wise images from dual-energy bins; 3D UNet). The proposed method using VMIs improves training stability for multi-organ segmentation in PCCT, particularly when the number of energy bins issmall.

Anatomy-constrained synthesis for spleen segmentation improvement in unpaired mouse micro-CT scans with 3D CycleGAN

Objective. Auto-segmentation in mouse micro-CT enhances the efficiency and consistency of preclinical experiments but often struggles with low-native-contrast and morphologically complex organs, such as the spleen, resulting in poor segmentation performance. While CT contrast agents can improve organ conspicuity, their use complicates experimental protocols and reduces feasibility. We developed a 3D Cycle Generative Adversarial Network (CycleGAN) incorporating anatomy-constrained U-Net models to leverage contrast-enhanced CT (CECT) insights to improve unenhanced native CT (NACT) segmentation. Approach. We employed a standard CycleGAN with an anatomical loss function to synthesize virtual CECT images from unpaired NACT scans at two different resolutions. Prior to training, two U-Nets were trained to automatically segment six major organs in NACT and CECT datasets, respectively. These pretrained 3D U-Nets were integrated during the CycleGAN training, segmenting synthetic images, and comparing them against ground truth annotations. The compound loss within the CycleGAN maintained anatomical fidelity. Full image processing was achieved for low-resolution datasets, while high-resolution datasets employed a patch-based method due to GPU memory constraints. Automated segmentation was applied to original NACT and synthetic CECT scans to evaluate CycleGAN performance using the Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95p). Main results. High-resolution scans showed improved auto-segmentation, with an average DSC increase from 0.728 to 0.773 and a reduced HD95p from 1.19 mm to 0.94 mm. Low-resolution scans benefited more from synthetic contrast, showing a DSC increase from 0.586 to 0.682 and an HD95p reduction from 3.46 mm to 1.24 mm. Significance. Implementing CycleGAN to synthesize CECT scans substantially improved the visibility of the mouse spleen, leading to more precise auto-segmentation. This approach shows the potential in preclinical imaging studies where contrast agent use is impractical.

Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT.

We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly. We retrospectively analyzed CT studies from 139 patients (age range 26-93 years, 43% female) between 2011 and 2019 with histopathological diagnosis of the spleen (19 lymphoma, 120 benign) and divided them into developing (n = 79) and testing (n = 60) datasets. The volumetric radiomic features were extracted from manual segmentation of the whole spleen on venous-phase CT imaging using PyRadiomics package. LASSO regression was applied for feature selection and development of the radiomic signature, which was interrogated with the complete blood cell count and differential count. All p values < 0.05 were considered to be significant. Seven features were selected for constructing the radiomic signature after feature selection, including first-order statistics (10th percentile and Robust Mean Absolute Deviation), shape-based (Surface Area), and texture features (Correlation, MCC, Small Area Low Gray-level Emphasis and Low Gray-level Zone Emphasis). The radiomic signature achieved an excellent diagnostic accuracy of 97%, sensitivity of 89%, and specificity of 98%, distinguishing lymphoma versus benign splenomegaly in the testing dataset. The radiomic signature significantly correlated with the platelet and segmented neutrophil percentage. CT-based radiomics signature can be useful in distinguishing lymphoma versus benign splenomegaly and can reflect the changes in underlying blood profiles.

Artificial Intelligence for Improved Hepatosplenomegaly Diagnosis.

Hepatosplenomegaly is commonly diagnosed by radiologists based on single dimension measurements and heuristic cut-offs. Volumetric measurements may be more accurate for diagnosing organ enlargement. Artificial intelligence techniques may be able to automatically calculate liver and spleen volume and facilitate more accurate diagnosis. After IRB approval, 2 convolutional neural networks (CNN) were developed to automatically segment the liver and spleen on a training dataset comprised of 500 single-phase, contrast-enhanced CT abdomen and pelvis examinations. A separate dataset of ten thousand sequential examinations at a single institution was segmented with these CNNs. Performance was evaluated on a 1% subset and compared with manual segmentations using Sorensen-Dice coefficients and Pearson correlation coefficients. Radiologist reports were reviewed for diagnosis of hepatomegaly and splenomegaly and compared with calculated volumes. Abnormal enlargement was defined as greater than 2 standard deviations above the mean. Median Dice coefficients for liver and spleen segmentation were 0.988 and 0.981, respectively. Pearson correlation coefficients of CNN-derived estimates of organ volume against the gold-standard manual annotation were 0.999 for the liver and spleen (P < 0.001). Average liver volume was 1556.8 ± 498.7 cc and average spleen volume was 194.6 ± 123.0 cc. There were significant differences in average liver and spleen volumes between male and female patients. Thus, the volume thresholds for ground-truth determination of hepatomegaly and splenomegaly were determined separately for each sex. Radiologist classification of hepatomegaly was 65% sensitive, 91% specific, with a positive predictive value (PPV) of 23% and an negative predictive value (NPV) of 98%. Radiologist classification of splenomegaly was 68% sensitive, 97% specific, with a positive predictive value (PPV) of 50% and a negative predictive value (NPV) of 99%. Convolutional neural networks can accurately segment the liver and spleen and may be helpful to improve radiologist accuracy in the diagnosis of hepatomegaly and splenomegaly.

Abdominal organ segmentation via deep diffeomorphic mesh deformations

Abdominal organ segmentation from CT and MRI is an essential prerequisite for surgical planning and computer-aided navigation systems. It is challenging due to the high variability in the shape, size, and position of abdominal organs. Three-dimensional numeric representations of abdominal shapes with point-wise correspondence to a template are further important for quantitative and statistical analyses thereof. Recently, template-based surface extraction methods have shown promising advances for direct mesh reconstruction from volumetric scans. However, the generalization of these deep learning-based approaches to different organs and datasets, a crucial property for deployment in clinical environments, has not yet been assessed. We close this gap and employ template-based mesh reconstruction methods for joint liver, kidney, pancreas, and spleen segmentation. Our experiments on manually annotated CT and MRI data reveal limited generalization capabilities of previous methods to organs of different geometry and weak performance on small datasets. We alleviate these issues with a novel deep diffeomorphic mesh-deformation architecture and an improved training scheme. The resulting method, UNetFlow, generalizes well to all four organs and can be easily fine-tuned on new data. Moreover, we propose a simple registration-based post-processing that aligns voxel and mesh outputs to boost segmentation accuracy.

Automated Deep Learning Artificial Intelligence Tool for Spleen Segmentation on CT: Defining Volume-Based Thresholds for Splenomegaly.

BACKGROUND: Splenomegaly has historically been assessed on imaging using potentially inaccurate linear measurements. Prior work tested a deep-learning artificial intelligence (AI) tool that automatically segments the spleen to determine splenic volume. OBJECTIVE: To apply the deep-learning AI tool in a large screening population to establish volume-based splenomegaly thresholds. METHODS: This retrospective study included a primary (screening) sample of 8901 patients (mean age, 56±10 years; 4235 men, 4666 women) who underwent CT colonoscopy (n=7736) or renal-donor CT (n=1165) from April 2004 to January 2017, and a secondary sample of 104 patients (mean age, 56±8 years; 62 men, 42 women) with end-stage liver disease (ESLD) who underwent pre-liver transplant CT from January 2011 to May 2013. The automated deep-learning AI tool was used for spleen segmentation, to determine splenic volumes. Two radiologists independently reviewed a subset of segmentations. Weight-based volume thresholds for splenomegaly were derived using regression analysis. Performance of linear measurements was assessed. Frequency of splenomegaly using weight-based volumetric thresholds in the secondary sample was determined. RESULTS: In the primary sample, both observers confirmed splenectomy in 20 patients with automated splenic volume of zero; confirmed incomplete splenic coverage in 28 patients with a tool output error; and confirmed adequate segmentation in 21 patients with low (<50 cc) volume, 49 patients with high (>600 cc) volume, and 200 additional randomly selected patients. In 8853 patients included in analysis of splenic volumes (i.e., excluding zero or error values), the mean automated splenic volume was 216±100 ml. Weight-based volumetric threshold (in milliliters) for splenomegaly was defined as 3.0*(weight[kg])+127; for weight >125 kg, splenomegaly threshold was constant (503 ml). Sensitivity and specificity for volume-defined splenomegaly were 13% and 100% at true-craniocaudal length of 13 cm, and 78% and 88% for maximum-3D length of 13 cm. In the secondary sample, both observers identified segmentation failure in one patient. Mean automated splenic volume in the 103 remaining patients was 796±457 ml; 84% (87/103) of patients met the weight-based volume-defined splenomegaly threshold. CONCLUSION: We derived a weight-based volumetric threshold for splenomegaly using an automated AI-based tool. CLINICAL IMPACT: The AI tool could facilitate large-scale opportunistic screening for splenomegaly.

Change in Splenic Volume as a Surrogate Marker for Immunotherapy Response in Patients with Advanced Urothelial and Renal Cell Carcinoma-Evaluation of a Novel Approach of Fully Automated Artificial Intelligence Based Splenic Segmentation.

In the treatment of advanced urothelial (aUC) and renal cell carcinoma (aRCC), biomarkers such as PD-1 and PD-L1 are not robust prognostic markers for immunotherapy (IO) response. Previously, a significant association between IO and a change in splenic volume (SV) was described for several tumour entities. To the best of our knowledge, this study presents the first correlation of SV to IO in aUC and aRCC. All patients with aUC (05/2017-10/2021) and aRCC (01/2012-05/2022) treated with IO at our academic centre were included. SV was measured at baseline, 3 and 9 months after initiation of IO using an in-house developed convolutional neural network-based spleen segmentation method. Uni- and multivariate Cox regression models for overall survival (OS) and progression-free survival (PFS) were used. In total, 35 patients with aUC and 30 patients with aRCC were included in the analysis. Lower SV at the three-month follow-up was significantly associated with improved OS in the aRCC group. We describe a new, innovative artificial intelligence-based approach of a radiological surrogate marker for IO response in aUC and aRCC which presents a promising new predictive imaging marker. The data presented implicate improved OS with lower follow-up SV in patients with aRCC.

A Deep-Learning Approach to Spleen Volume Estimation in Patients with Gaucher Disease.

The enlargement of the liver and spleen (hepatosplenomegaly) is a common manifestation of Gaucher disease (GD). An accurate estimation of the liver and spleen volumes in patients with GD, using imaging tools such as magnetic resonance imaging (MRI), is crucial for the baseline assessment and monitoring of the response to treatment. A commonly used method in clinical practice to estimate the spleen volume is the employment of a formula that uses the measurements of the craniocaudal length, diameter, and thickness of the spleen in MRI. However, the inaccuracy of this formula is significant, which, in turn, emphasizes the need for a more precise and reliable alternative. To this end, we employed deep-learning techniques, to achieve a more accurate spleen segmentation and, subsequently, calculate the resulting spleen volume with higher accuracy on a testing set cohort of 20 patients with GD. Our results indicate that the mean error obtained using the deep-learning approach to spleen volume estimation is 3.6 ± 2.7%, which is significantly lower than the common formula approach, which resulted in a mean error of 13.9 ± 9.6%. These findings suggest that the integration of deep-learning methods into the clinical routine practice for spleen volume calculation could lead to improved diagnostic and monitoring outcomes.

A novel role of the splenic volume in Crohn's disease: evaluating the efficacy of infliximab.

Background: A number of patients with Crohn's disease (CD) suffer from loss of response to infliximab (IFX) therapy. Splenic volume is reported to be enlarged in patients with CD compared to normal individuals. The association between splenic volume and IFX efficacy in CD remains unclear. Methods: We performed a retrospective study of patients with CD who received regular IFX treatment at Zhongshan Hospital, Fudan University, between August 2015 and December 2021. We collected baseline characteristics and clinical features from medical records in the CD database of Zhongshan Hospital. We accurately measured the splenic volume using semi-auto spleen segmentation software, followed by the analysis of splenic volume and IFX efficacy. Results: We included 49 patients with CD receiving IFX treatment, of whom 41 responded to IFX and 8 failed to respond to IFX. Splenic volume, as well as volume adjusted for body mass index (SV/BMI) and body weight (SV/W), was significantly decreased after IFX treatment in responders but increased in non-responders compared to the volume before the treatment. Accordingly, the levels of leukocyte count, platelet count, C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR) were decreased after IFX treatment in responders. Contrarily, the levels of hemoglobin, albumin, and tumor necrosis factor (TNF)-α were elevated in responders. Moreover, both CRP and TNF-α levels were significantly positively correlated with SV/BMI in all patients. Conclusion: Splenic volume, especially SV/BMI and SV/W, was reduced after IFX treatment in CD patients responsive to IFX. SV/BMI was positively correlated with disease activity. Splenic volume is a promising indicator to evaluate IFX efficacy in CD.

Robust and efficient abdominal CT segmentation using shape constrained multi-scale attention network

PurposeAlthough many deep learning-based abdominal multi-organ segmentation networks have been proposed, the various intensity distributions and organ shapes of the CT images from multi-center, multi-phase with various diseases introduce new challenges for robust abdominal CT segmentation. To achieve robust and efficient abdominal multi-organ segmentation, a new two-stage method is presented in this study. MethodsA binary segmentation network is used for coarse localization, followed by a multi-scale attention network for the fine segmentation of liver, kidney, spleen, and pancreas. To constrain the organ shapes produced by the fine segmentation network, an additional network is pre-trained to learn the shape features of the organs with serious diseases and then employed to constrain the training of the fine segmentation network. ResultsThe performance of the presented segmentation method was extensively evaluated on the multi-center data set from the Fast and Low GPU Memory Abdominal oRgan sEgmentation (FLARE) challenge, which was held in conjunction with International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021. Dice Similarity Coefficient (DSC) and Normalized Surface Dice (NSD) were calculated to quantitatively evaluate the segmentation accuracy and efficiency. An average DSC and NSD of 83.7% and 64.4% were achieved, and our method finally won the second place among more than 90 participating teams. ConclusionsThe evaluation results on the public challenge demonstrate that our method shows promising performance in robustness and efficiency, which may promote the clinical application of the automatic abdominal multi-organ segmentation.

3D Medical image segmentation using parallel transformers

Most recent 3D medical image segmentation methods adopt convolutional neural networks (CNNs) that rely on deep feature representation and achieve adequate performance. However, due to the convolutional architectures having limited receptive fields, they cannot explicitly model the long-range dependencies in the medical image. Recently, Transformer can benefit from global dependencies using self-attention mechanisms and learn highly expressive representations. Some works were designed based on the Transformers, but the existing Transformers suffer from extreme computational and memories, and they cannot take full advantage of the powerful feature representations in 3D medical image segmentation. In this paper, we aim to connect the different resolution streams in parallel and propose a novel network, named Transformer based High Resolution Network (TransHRNet), with an Effective Transformer (EffTrans) block, which has sufficient feature representation even at high feature resolutions. Given a 3D image, the encoder first utilizes CNN to extract the feature representations to capture the local information, and then the different feature maps are reshaped elaborately for tokens that are fed into each Transformer stream in parallel to learn the global information and repeatedly exchange the information across streams. Unfortunately, the proposed framework based on the standard Transformer needs a huge amount of computation, thus we introduce a deep and effective Transformer to deliver better performance with fewer parameters. The proposed TransHRNet is evaluated on the Multi-Atlas Labeling Beyond the Cranial Vault (BCV) dataset that consists of 11 major human organs and the Medical Segmentation Decathlon (MSD) dataset for brain tumor and spleen segmentation tasks. Experimental results show that it performs better than the convolutional and other related Transformer-based methods on the 3D multi-organ segmentation tasks. Code is available at https://github.com/duweidai/TransHRNet.

Spleen Tissue Segmentation Algorithm for Cryo-Imaging Data.

Spleen tissue segmentation is an essential process for analyzing various immunological diseases as observed in the cryo-imaging data. Because manual labeling of the spleen tissue by human experts is not efficient, an automatic segmentation algorithm is needed. In this study, we developed a novel algorithm for automatically segmenting spleen substructures including white pulp and red pulp for the first time. The algorithm is designed for datasets created by a cryo-imaging system. This unique technology can effectively enable cellular tracking anywhere in the whole mouse with single-cell sensitivity. The proposed algorithm consists of four components: initial spleen mask creation, feature extraction, Supervised Patch-based Fuzzy c-Mean (spFCM) classification, and post-processing. The algorithm accurately and efficiently labeled spleen tissues in all experiment settings. The algorithm also improved the spleen segmentation throughput by 90 folds as compared to the manual segmentation. Moreover, we show that our novel spFCM algorithm outperformed traditional fast-learning classifiers as well as the U-Net deep-learning model in many aspects. Two major contributions of this paper are (1) an explainable algorithm for segmenting spleen tissues in cryo-images for the first time and (2) an spFCM algorithm as a new classifier. We also discussed that our work can be beneficial to researchers who work not only in the fields of graft-versus-host disease (GVHD) mouse models, but also in that of other immunological disease models where spleen analysis is essential. Future work building upon our research may lay the foundations for biomedical studies that utilize cryo-imaging technology.

Two-Stage Deep Learning Model for Automated Segmentation and Classification of Splenomegaly.

Splenomegaly is a common cross-sectional imaging finding with a variety of differential diagnoses. This study aimed to evaluate whether a deep learning model could automatically segment the spleen and identify the cause of splenomegaly in patients with cirrhotic portal hypertension versus patients with lymphoma disease. This retrospective study included 149 patients with splenomegaly on computed tomography (CT) images (77 patients with cirrhotic portal hypertension, 72 patients with lymphoma) who underwent a CT scan between October 2020 and July 2021. The dataset was divided into a training (n = 99), a validation (n = 25) and a test cohort (n = 25). In the first stage, the spleen was automatically segmented using a modified U-Net architecture. In the second stage, the CT images were classified into two groups using a 3D DenseNet to discriminate between the causes of splenomegaly, first using the whole abdominal CT, and second using only the spleen segmentation mask. The classification performances were evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Occlusion sensitivity maps were applied to the whole abdominal CT images, to illustrate which regions were important for the prediction. When trained on the whole abdominal CT volume, the DenseNet was able to differentiate between the lymphoma and liver cirrhosis in the test cohort with an AUC of 0.88 and an ACC of 0.88. When the model was trained on the spleen segmentation mask, the performance decreased (AUC = 0.81, ACC = 0.76). Our model was able to accurately segment splenomegaly and recognize the underlying cause. Training on whole abdomen scans outperformed training using the segmentation mask. Nonetheless, considering the performance, a broader and more general application to differentiate other causes for splenomegaly is also conceivable.

Deep-learning-based hepatic fat assessment (DeHFt) on non-contrast chest CT and its association with disease severity in COVID-19 infections: A multi-site retrospective study.

BackgroundHepatic steatosis (HS) identified on CT may provide an integrated cardiometabolic and COVID-19 risk assessment. This study presents a deep-learning-based hepatic fat assessment (DeHFt) pipeline for (a) more standardised measurements and (b) investigating the association between HS (liver-to-spleen attenuation ratio <1 in CT) and COVID-19 infections severity, wherein severity is defined as requiring invasive mechanical ventilation, extracorporeal membrane oxygenation, death.MethodsDeHFt comprises two steps. First, a deep-learning-based segmentation model (3D residual-UNet) is trained (N = 80) to segment the liver and spleen. Second, CT attenuation is estimated using slice-based and volumetric-based methods. DeHFt-based mean liver and liver-to-spleen attenuation are compared with an expert's ROI-based measurements. We further obtained the liver-to-spleen attenuation ratio in a large multi-site cohort of patients with COVID-19 infections (D1, N = 805; D2, N = 1917; D3, N = 169) using the DeHFt pipeline and investigated the association between HS and COVID-19 infections severity.FindingsThe DeHFt pipeline achieved a dice coefficient of 0.95, 95% CI [0.93–0.96] on the independent validation cohort (N = 49). The automated slice-based and volumetric-based liver and liver-to-spleen attenuation estimations strongly correlated with expert's measurement. In the COVID-19 cohorts, severe infections had a higher proportion of patients with HS than non-severe infections (pooled OR = 1.50, 95% CI [1.20–1.88], P < .001).InterpretationThe DeHFt pipeline enabled accurate segmentation of liver and spleen on non-contrast CTs and automated estimation of liver and liver-to-spleen attenuation ratio. In three cohorts of patients with COVID-19 infections (N = 2891), HS was associated with disease severity. Pending validation, DeHFt provides an automated CT-based metabolic risk assessment.FundingFor a full list of funding bodies, please see the Acknowledgements.

Fully Automated and Explainable Liver Segmental Volume Ratio and Spleen Segmentation at CT for Diagnosing Cirrhosis.

To evaluate the performance of a deep learning (DL) model that measures the liver segmental volume ratio (LSVR) (ie, the volumes of Couinaud segments I-III/IV-VIII) and spleen volumes from CT scans to predict cirrhosis and advanced fibrosis. For this Health Insurance Portability and Accountability Act-compliant, retrospective study, two datasets were used. Dataset 1 consisted of patients with hepatitis C who underwent liver biopsy (METAVIR F0-F4, 2000-2016). Dataset 2 consisted of patients who had cirrhosis from other causes who underwent liver biopsy (Ishak 0-6, 2001-2021). Whole liver, LSVR, and spleen volumes were measured with contrast-enhanced CT by radiologists and the DL model. Areas under the receiver operating characteristic curve (AUCs) for diagnosing advanced fibrosis (≥METAVIR F2 or Ishak 3) and cirrhosis (≥METAVIR F4 or Ishak 5) were calculated. Multivariable models were built on dataset 1 and tested on datasets 1 (hold out) and 2. Datasets 1 and 2 consisted of 406 patients (median age, 50 years [IQR, 44-56 years]; 297 men) and 207 patients (median age, 50 years [IQR, 41-57 years]; 147 men), respectively. In dataset 1, the prediction of cirrhosis was similar between the manual versus automated measurements for spleen volume (AUC, 0.86 [95% CI: 0.82, 0.9] vs 0.85 [95% CI: 0.81, 0.89]; significantly noninferior, P < .001) and LSVR (AUC, 0.83 [95% CI: 0.78, 0.87] vs 0.79 [95% CI: 0.74, 0.84]; P < .001). The best performing multivariable model achieved AUCs of 0.94 (95% CI: 0.89, 0.99) and 0.79 (95% CI: 0.71, 0.87) for cirrhosis and 0.8 (95% CI: 0.69, 0.91) and 0.71 (95% CI: 0.64, 0.78) for advanced fibrosis in datasets 1 and 2, respectively. The CT-based DL model performed similarly to radiologists. LSVR and splenic volume were predictive of advanced fibrosis and cirrhosis.Keywords: CT, Liver, Cirrhosis, Computer Applications-Detection/Diagnosis Supplemental material is available for this article. © RSNA, 2022.

Baseline Splenic Volume Outweighs Immuno-Modulated Size Changes with Regard to Survival Outcome in Patients with Hepatocellular Carcinoma under Immunotherapy.

Simple SummarySplenic volume (SV) has been identified as a highly predictive parameter for prognosis in patients with hepatocellular carcinoma (HCC). Moreover, an association between immunotherapy and an increase in SV has been described for various types of cancer. In our cohort of patients with HCC under immunotherapy, SV was a highly predictive factor for overall survival at baseline and initial follow-up. Although a large proportion of patients (76%) showed an SV increase after the initiation of immunotherapy, this additional immuno-modulated SV change was negligible compared to long-standing changes in the splanchnic circulation in our patient cohort.Background: An association between immunotherapy and an increase in splenic volume (SV) has been described for various types of cancer. SV is also highly predictive of overall survival (OS) in patients with hepatocellular carcinoma (HCC). We evaluated SV and its changes with regard to their prognostic influence in patients with HCC undergoing immunotherapy. Methods: All patients with HCC who received immunotherapy in first or subsequent lines at our tertiary care center between 2016 and 2021 were screened for eligibility. SV was assessed at baseline and follow-up using an AI-based tool for spleen segmentation. Patients were dichotomized into high and low SV based on the median value. Results: Fifty patients were included in the analysis. The median SV prior to treatment was 532 mL. The median OS of patients with high and low SV was 5.1 months and 18.1 months, respectively (p = 0.01). An increase in SV between treatment initiation and the first follow-up was observed in 28/37 (75.7%) patients with follow-up imaging available. This increase in itself was not prognostic for median OS (7.0 vs. 8.5 months, p = 0.73). However, patients with high absolute SV at the first follow-up continued to have impaired survival (4.0 months vs. 30.7 months, p = 0.004). Conclusion: High SV prior to and during treatment was a significant prognostic factor for impaired outcome. Although a large proportion of patients showed an SV increase after the initiation of immunotherapy, this additional immuno-modulated SV change was negligible compared to long-standing changes in the splanchnic circulation in patients with HCC.

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease.

Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability.

Data-Driven Deep Supervision for Medical Image Segmentation.

Medical image segmentation plays a vital role in disease diagnosis and analysis. However, data-dependent difficulties such as low image contrast, noisy background, and complicated objects of interest render the segmentation problem challenging. These difficulties diminish dense prediction and make it tough for known approaches to explore data-specific attributes for robust feature extraction. In this paper, we study medical image segmentation by focusing on robust data-specific feature extraction to achieve improved dense prediction. We propose a new deep convolutional neural network (CNN), which exploits specific attributes of input datasets to utilize deep supervision for enhanced feature extraction. In particular, we strategically locate and deploy auxiliary supervision, by matching the object perceptive field (OPF) (which we define and compute) with the layer-wise effective receptive fields (LERF) of the network. This helps the model pay close attention to some distinct input data dependent features, which the network might otherwise 'ignore' during training. Further, to achieve better target localization and refined dense prediction, we propose the densely decoded networks (DDN), by selectively introducing additional network connections (the 'crutch' connections). Using five public datasets (two retinal vessel, melanoma, optic disc/cup, and spleen segmentation) and two in-house datasets (lymph node and fungus segmentation), we verify the effectiveness of our proposed approach in 2D and 3D segmentation.

Deep learning-based quality-controlled spleen assessment from ultrasound images

ObjectiveSplenomegaly (abnormal splenic enlargement) is a potentially life-threatening condition that occurs in a range of clinical scenarios, including in patients suffering from Sickle cell disease (SCD). Therefore, spleen size assessments from ultrasound imaging are commonly performed in SCD clinics, and typically involve measuring the length of the spleen. However, the current workflow is prone to intra- and inter-observer variability and is dependent on the experience of the sonographer. Our objective was to automate the spleen length measurement process. MethodsTwo deep learning-based approaches were investigated to achieve automated spleen length measurement from ultrasound images. One is a segmentation-based approach, where we trained a modified U-Net to obtain a spleen segmentation and then applied post-processing to measure the spleen length from the segmentation. The second approach is based on direct regression of spleen length. We also incorporated a quality control (QC) model to help less experienced sonographers ensure the quality of ultrasound images before measurement. ResultsOur best model (segmentation-based approach) reached a mean percentage length error (MPLE) of 4.58% on good quality images, which is within the range of human expert inter-observer variability (5.78%). After including bad quality images, the incorporation of the QC step resulted in a significant reduction in MPLE (from 5.76% to 4.88%). ConclusionAutomated, quality-controlled spleen length measurement from ultrasound has been achieved with human-level accuracy. SignificanceThis proposed framework has the potential to assist in making robust and accurate assessments of the spleen, especially in settings where there is a lack of experienced sonographers.