Liver Segments Research Articles

Indocyanine green fluorescence perfusion testing in robot-assisted hepatic arterial infusion pump placement

BackgroundHepatic arterial infusion pump (HAIP) treatment is a technique used to treat liver localized malignancy with intra-arterial chemotherapy. Methylene blue is generally administered to verify hepatic perfusion and exclude inadvertent extrahepatic perfusion. The use of indocyanine green dye (ICG) combined with near-infrared (NIR) fluorescence imaging during robot-assisted HAIP placement may be an attractive alternative by providing high contrast without blue discoloration of the operative field.MethodsData was collected retrospectively from 2 centers in the Netherlands. Intraoperative perfusion of the liver segments and extrahepatic perfusion were assessed using ICG/NIR as well as methylene blue on video imaging and correlated to postoperative 99 m-Tc perfusion scintigraphy.Results13 patients underwent robot-assisted surgery for HAIP placement; median length of stay was 4 days, complications occurred in 4 patients. Hepatic perfusion showed identical patterns when ICG was compared with methylene blue. In 1 patient, additional extrahepatic perfusion was found using ICG, leading to further vessel ligation. Intraoperative ICG perfusion was concordant with 99 m-Tc perfusion scintigraphy.DiscussionLiver and extrahepatic perfusion determined by ICG fluorescence imaging is concordant with blue dye perfusion and 99 m-Tc perfusion scintigraphy. Therefore, ICG fluorescence imaging is deemed a safe and reliable technique for perfusion testing during robot-assisted HAIP placement.Graphical abstract

Lobar and Segmental Atrophy of the Liver: Differential Diagnoses and Treatments

Segmental or lobar liver atrophy is a common but not well-understood clinical condition. Hepatic atrophy can be classified into hepatic atrophy secondary to other pathologies and primary segmental hepatic atrophy, which is a benign intrahepatic lesion (pseudotumor) not associated with any other pathology. The pathophysiological mechanisms underlying atrophy can be divided into three main situations: obstruction of biliary outflow, obstruction of the systemic venous outflow, and obstruction of incoming portal venous flow. For what may concern secondary hepatic atrophy, there are many pathologies that could underlie this condition, ranging from benign to intrahepatic malignancies, with particular reference to particularly hepatocellular carcinoma and biliary duct carcinoma. An accurate and prompt differential diagnosis between the various forms and causes of atrophy is important for early identification and adequate treatment of underlying pathologies. A comprehensive review of the literature on the etiology and the radiological and histological characteristics of different types of hepatic atrophy is currently unavailable. Therefore, the aim of this review is to summarize the primary and secondary causes of segmental or lobar liver atrophy (excluding forms involving the entire liver parenchyma) and to provide practical tools for clinical and radiological differential diagnosis.

Indocyanine Green Fluorescence-Guided Laparoscopic Anatomical Segmentectomy of Liver Segment 6: Surgical Strategy and Technical Details.

Because of the complex anatomy of the right posterior hepatic pedicle, there have been few reports on standardized laparoscopic portal territory staining-guided anatomical resection of liver segment 6 (LPTAR-S6). This study aimed to elucidate the indocyanine green (ICG) fluorescence staining methods for LPTAR-S6. LPTAR-S6 can be performed using positive and negative fluorescence staining approaches. We implemented these two approaches for patients with hepatocellular carcinoma. Descriptions of the surgical strategy and technical details are presented. Two patients safely underwent LPTAR-S6 using a preoperative three-dimensional reconstruction plan. The intraoperative ICG fluorescence staining effect was satisfactory, and the anatomical landmarks were fully exposed. A detailed preoperative three-dimensional reconstruction plan, complete intraoperative application of real-time laparoscopic ultrasound guidance, and ICG fluorescence staining can result in accurate transection of the liver parenchyma during LPTAR-S6.

Myxoinflammatory fibroblastic sarcoma of the liver: Case report and literature review.

Myxoinflammatory fibroblastic sarcoma (MIFS) is a rare low-grade malignant soft tissue sarcoma that primarily affects the distal extremities in adults, with the highest incidence in patients in their 40s and 50s. It has a high local recurrence rate and a low metastasis rate. Although MIFSs have been documented in other sites, an MIFS in the liver is highly unusual. Herein, we present a case of a patient with hepatic MIFS. The patient was a 58-year-old Chinese man with abdominal pain as the primary symptom. Abdominal computed tomography and magnetic resonance imaging revealed a mass in the right posterior lobe of the liver. The patient underwent surgical excision, and the excised specimen was identified as MIFS. Three years later, the patient returned to our hospital for abdominal pain. Computed tomography and magnetic resonance imaging revealed a mass in liver segments 2/3/4. Postoperative pathological examination of the tumor revealed the recurrence of MIFS. The patient underwent surgical resection of the MIFS. The patient received multiple pirarubicin-based chemotherapy treatments and an ALK inhibitor (anlotinib) within 6 months after surgery, but the tumor recurred. MIFS can not only occur in the proximal limbs, trunk, head, and neck but can also affect the abdominal organs. Surgical resection remains the primary treatment option for MIFS in the absence of any contraindications. Because the recurrence rate of MIFS is high, meticulous long-term monitoring is required.

Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework

The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder–decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality’s conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.

Exploring Generalizable Distillation for Efficient Medical Image Segmentation.

Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks (i.e., teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks.

LIVER CANCER IMAGE PREPROCESSING AND FEATURE SELECTION USING A HYBRID DEEP LEARNING NETWORK

A liver's primary duties include producing bile, which is necessary for the breakdown of fats, filtering and changing potentially harmful compounds in the blood, and storing vitamins and nutrients. The diagnosis of malignant liver lesions can be made using a variety of techniques, including magnetic resonance imaging (MRI) and/or CT scanning with multiphase contrast agent injection. focuses on the methods for creating tumor and liver segmentation with the IVGG19-UNeT hybrid deep learning network. The suggested model's deep learning network scheme structure is made up of preprocessing, feature extraction, classification, and segmentation. With over 98% accuracy in tumor categorization, the suggested method accurately identifies the greatest number of tumor regions.

Recent trends and new developments in liver transplantation.

Liver transplantation (LT) has been an established treatment for end-staged liver disease for acute, chronic, metabolic diseases and liver cancer. Advanced surgical techniques, refined indications and contraindications for LT, improvements of donor selection, prognostic scorings system and immunosuppressive regimens have contributed to the improved outcomes of liver transplantation. The etiologies of cirrhosis have been shifting from viral hepatitis to metabolic associated fatty liver disease. New indications include peripheral or mass forming bile duct cancer, metastases from bowel cancers or neuroendocrine tumors. Resection and partial liver segments 2-3 transplantation with delayed total hepatectomy has been performed to the limited cases, which was the explored technique of auxiliary partial orthotopic LT. Minimally invasive donor hepatectomy (laparoscopic or robotic) has been increasingly done. In this review are described the recent pressing topics in LT.

Transformer Skip‐Fusion Based SwinUNet for Liver Segmentation From CT Images

ABSTRACTLiver segmentation is a crucial step in medical image analysis and is essential for diagnosing and treating liver diseases. However, manual segmentation is time‐consuming and subject to variability among observers. To address these challenges, a novel liver segmentation approach, SwinUNet with transformer skip‐fusion is proposed. This method harnesses the Swin Transformer's capacity to model long‐range dependencies efficiently, the U‐Net's ability to preserve fine spatial details, and the transformer skip‐fusion's effectiveness in enabling the decoder to learn intricate features from encoder feature maps. In experiments using the 3DIRCADb and CHAOS datasets, this technique outperformed traditional CNN‐based methods, achieving a mean DICE coefficient of 0.988% and a mean Jaccard coefficient of 0.973% by aggregating the results obtained from each dataset, signifying outstanding agreement with ground truth. This remarkable accuracy in liver segmentation holds significant promise for improving liver disease diagnosis and enhancing healthcare outcomes for patients with liver conditions.

A Case Series and Literature Review of Alveolar Echinococcosis in Kashmir, India: An Emerging Endemic Zone for Echinococcus multilocularis.

A prospective study on 110 patients with echinococcosis at Dr. Khuroo's Medical Clinic, Srinagar, Kashmir, India, from March 2019 to April 2024 identified 12 cases (4 males, 8 females; mean age of 46.58 ± 11.97 years) of Alveolar echinococcosis (AE). Two patients were detected through ultrasound examinations carried out for unrelated causes; one presented with features of liver abscess, and nine had pain in the right upper quadrant for a mean period of 2.2 ± 1.79 years. All had the liver as the primary organ involved, with 15 tumor masses of a mean maximum diameter of 9.22 ± 3.21 cm and volume of 426 ± 374.61 cm3. Tumors placed centrally had invaded vessels and the biliary tract in eight patients, and those placed peripherally had invaded the liver capsule and adjacent organs in nine patients. Histologic examination of liver biopsies or resected organs revealed necrotic lesions, calcifications, and granulomatous inflammation with slender, thin-walled vesicles of bizarre configuration that stained strongly eosinophilic with periodic acid Schiff. Two patients had segmental liver resections; one was treated with liver aspiration, while the other nine with advanced disease received chemotherapy with albendazole along with praziquantel. Patients showed clinical improvement on a median follow-up of 12 months (range 1 to 60 months); however, MRI T2-weighted images and 18F-FDG-PET-CECT scans in two patients showed active disease on follow-up at one and five years, respectively. A systematic review detected 146 cases of AE in India from 1980 to April 2024. Twenty cases were from foreign countries, mostly from Central Asian republics, and 118 (93.65%) of the remaining 126 Indian patients were permanent residents of Kashmir Valley. The disease affected a population of 79,197 residing in 22 villages from 5 border districts of the valley. These villages were either high in or adjacent to the Himalayan mountain range. Disease prevalence in the affected population was 146.47/105 (males 131.53/105 and females 163.18/105) and the incidence was 12.41/105/year (males 11.16/105/year and females 13.81/105/year). Possible causes of the emergence of AE are discussed, and future directions for research to face this challenge arebeen identified.

Evaluation of Various Methods of Liver Measurement in Comparison to Volumetric Segmentation Based on Computed Tomography.

Background: A reliable assessment of liver volume, necessary before transplantation, remains a challenge. Our work aimed to assess the differences in the evaluation and measurements of the liver between independent observers and compare different formulas calculating its volume in relation to volumetric segmentation. Methods: Eight researchers measured standard liver dimensions based on 105 abdominal computed tomography (CT) scans. Based on the results obtained, the volume of the liver was calculated using twelve different methods. An independent observer performed a volumetric segmentation of the livers based on the same CT examinations. Results: Significant differences were found between the formulas and in relation to volumetric segmentation, with the closest results obtained for the Heinemann et al. method. The measurements of individual observers differed significantly from one another. The observers also rated different numbers of livers as enlarged. Conclusions: Due to significant differences, despite its time-consuming nature, the use of volumetric liver segmentation in the daily assessment of liver volume seems to be the most accurate method.

G-MBRMD: Lightweight liver segmentation model based on guided teaching with multi-head boundary reconstruction mapping distillation

Background and Objectives:Liver segmentation is pivotal for the quantitative analysis of liver cancer. Although current deep learning methods have garnered remarkable achievements for medical image segmentation, they come with high computational costs, significantly limiting their practical application in the medical field. Therefore, the development of an efficient and lightweight liver segmentation model becomes particularly important. Methods:In our paper, we propose a real-time, lightweight liver segmentation model named G-MBRMD. Specifically, we employ a Transformer-based complex model as the teacher and a convolution-based lightweight model as the student. By introducing proposed multi-head mapping and boundary reconstruction strategies during the knowledge distillation process, Our method effectively guides the student model to gradually comprehend and master the global boundary processing capabilities of the complex teacher model, significantly enhancing the student model’s segmentation performance without adding any computational complexity. Results:On the LITS dataset, we conducted rigorous comparative and ablation experiments, four key metrics were used for evaluation, including model size, inference speed, Dice coefficient, and HD95. Compared to other methods, our proposed model achieved an average Dice coefficient of 90.14±16.78%, with only 0.6 MB memory and 0.095 s inference speed for a single image on a standard CPU. Importantly, this approach improved the average Dice coefficient of the baseline student model by 1.64% without increasing computational complexity. Conclusion:The results demonstrate that our method successfully realizes the unification of segmentation precision and lightness, and greatly enhances its potential for widespread application in practical settings.

Automatic liver segmentation from CT volumes based on multi-view information fusion and condition random fields

Liver segmentation from CT images is a fundamental and essential step for many clinical applications, such as disease diagnosis, surgery navigator, and radiation therapy. Due to the limited computing resources, automatic and accurate liver segmentation from 3D CT volume is still a challenge task. In this paper, we propose an automatic liver segmentation method by fusing multi-view information. First, a 2D network combined with Dual Self-Attention (DSA) is proposed and applied on multi-sectional 2D slices reconstructed from axial, coronal, and sagittal directions. Then, to generate 3D segmentation results, a lightweight 3D network is designed to fuse the segmentation results from different viewing. Finally, a full connection condition random field is used to refine the 3D results. The proposed method is evaluated on four public datasets, including 3DIRCADb, CHAOS, Sliver07, and LiTS. The experimental results show that the proposed method can accurately segment the liver region for the datasets with large or small cases, as well as healthy or lesion livers. The dice values obtained by the proposed method on four datasets are 0.952, 0.969, 0.958, and 0.964, respectively, which are better than those obtained by many existing ones.

Comprehensive deep learning-based assessment of living liver donor CT angiography: from vascular segmentation to volumetric analysis.

Precise preoperative assessment of liver vasculature and volume in living donor liver transplantation is essential for donor safety and recipient surgery. Traditional manual segmentation methods are being supplemented by deep learning (DL) models, which may offer more consistent and efficient volumetric evaluations. This study analyzed living liver donors from Samsung Medical Center using preoperative CT angiography data between April 2022 and February 2023. A DL-based 3D residual U-Net model was developed and trained on segmented CT images to calculate the liver volume and segment vasculature, with its performance compared to traditional manual segmentation by surgeons and actual graft weight. The DL model achieved high concordance with manual methods, exhibiting Dice Similarity Coefficients of 0.94±0.01 for the right lobe and 0.91±0.02 for the left lobe. The liver volume estimates by DL model closely matched those of surgeons, with a mean discrepancy of 9.18mL, and correlated more strongly with actual graft weights (R-squared value of 0.76 compared to 0.68 for surgeons). The DL model demonstrates potential as a reliable tool for enhancing preoperative planning in liver transplantation, offering consistency and efficiency in volumetric assessment. Further validation is required to establish its generalizability across various clinical settings and imaging protocols.

Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML).

Deep learning has attained state-of-the-art results in general image segmentation problems; however, it requires a substantial number of annotated images to achieve the desired outcomes. In the medical field, the availability of annotated images is often limited. To address this challenge, few-shot learning techniques have been successfully adapted to rapidly generalize to new tasks with only a few samples, leveraging prior knowledge. In this paper, we employ a gradient-based method known as Model-Agnostic Meta-Learning (MAML) for medical image segmentation. MAML is a meta-learning algorithm that quickly adapts to new tasks by updating a model's parameters based on a limited set of training samples. Additionally, we use an enhanced 3D U-Net as the foundational network for our models. The enhanced 3D U-Net is a convolutional neural network specifically designed for medical image segmentation. We evaluate our approach on the TotalSegmentator dataset, considering a few annotated images for four tasks: liver, spleen, right kidney, and left kidney. The results demonstrate that our approach facilitates rapid adaptation to new tasks using only a few annotated images. In 10-shot settings, our approach achieved mean dice coefficients of 93.70%, 85.98%, 81.20%, and 89.58% for liver, spleen, right kidney, and left kidney segmentation, respectively. In five-shot sittings, the approach attained mean Dice coefficients of 90.27%, 83.89%, 77.53%, and 87.01% for liver, spleen, right kidney, and left kidney segmentation, respectively. Finally, we assess the effectiveness of our proposed approach on a dataset collected from a local hospital. Employing five-shot sittings, we achieve mean Dice coefficients of 90.62%, 79.86%, 79.87%, and 78.21% for liver, spleen, right kidney, and left kidney segmentation, respectively.

A Novel Liver Tumor segmentation of Adverse Propagation Advanced Swin Transformer Network with Mask region-based convolutional neural networks

The diagnosis and treatment of liver diseases from computed tomography (CT) images is an indispensable task for segmentation of Liver & its tumours. Due to the uneven presence, fuzzy borders, diverse densities, shapes and sizes of lesions segmentation of liver & its tumour is a difficult task. At this point we mainly focused on deep learning algorithms for segmenting liver and its tumour from abdominal CT scan images thereafter minimising the time & energy used for a liver diseases diagnosis This study aims to classify and segment liver tumors using a novel deep learning-based model. A Mask region-based convolutional neural network (Mask R-CNN) model is proposed for multiorgan segmentation to aid esophageal radiation treatment. Due to the fact that organ boundaries may be fuzzy and organ shapes are various, original Mask R-CNN works well on natural image segmentation while leaves something to be desired on the multiorgan segmentation task. Addressing it, the advantages of this method are threefold: (1) a ROI (region of interest) generation method is presented in the RPN (region proposal network) which is able to utilize multiscale semantic features. (2) A prebackground classification subnetwork is integrated to the original mask generation branch to improve the precision of multiorgan segmentation. The segmented image is added to the Adverse Propagation Advanced Swin Transformer Network (APESTNet) to prevent overfitting. The proposed model is based on CT volume slices of patients with liver tumors and evaluated on the public 3D dataset IRCADB01.The proposed model dataset is split into training as 60% and testing as 40 % for classification. The proposed model's accuracy and recall are 99.23 % and 98.24 %, respectively.

CoProLITE: Constrained Proxy Learning for lIver and hepaTic lesion sEgmentation

Liver and hepatic lesion segmentation is an important task in medical image analysis, which plays a crucial role in diagnosis, treatment planning and monitoring of liver diseases. We observed an ordinal layout of the feature space that aligns with CT image characteristics will improve performance on liver and hepatic lesion segmentation task. In order to enforce the samples to conform to a specific layout of the feature space, we propose a novel liver and hepatic lesion segmentation method called CoProLITE, which learns a constrained proxy for each classes. Specifically, We replace the traditional FCN-based segmentation head by a proxy learning-based head to learn feature representations of the images, and introduces constraints during the training process to guide the learning of the proxies. We extensively evaluate CoProLITE on three public datasets and compare it to state-of-the-art methods. The experimental results demonstrate the effectiveness of the proposed method.

Resección hepática en enfermedad de Caroli unilobar

Caroli’s disease is a congenital disorder caused by a defect of the ductal plate. The clinical picture includes intrahepatic duct lithiasis and recurrent cholangitis usually in young people. The imaging tests reveal the presence of multifocal and segmental dilatation of the intrahepatic bile ducts. Cholangiocarcinoma can develop as a long-term complication of chronic bile duct inflammation and should always be considered as a differential diagnosis. We describe a rare case of a 52-year-old woman who presented with bile duct obstruction after laparoscopic cholecystectomy and required resection of liver segments II and III due to Caroli’s disease with a favorable outcome.

Automated segmentation of liver tumors from computed tomographic scans

The precision of liver tumor segmentation heavily depends on the doctor's expertise, hence it is required to produce an algorithm for automatic liver tumor segmentation to reduce the manual intervention in assessing liver disease identification. We propose a CNN-based UNet architecture designed to segment liver tumors from CT images of size 128×128. In this model, modifications were made to the encoder, decoder, and bridge paths to enhance feature extraction efficiency. The performance of the modified UNet was evaluated against an existing segmentation method using the same CT image size. The comparison focused on the Dice similarity coefficient and accuracy. Our proposed method demonstrated a high Dice similarity coefficient of 75.37 % and an accuracy of 99.75 % on the 3Dircadb dataset. These results indicate that our modified UNet achieved superior segmentation metrics compared to state-of-the-art methods, showcasing its effectiveness in liver tumor segmentation.

Applying LASSO logistic regression for the prediction of biliary complications after ex vivo liver resection and autotransplantation in patients with end-stage hepatic alveolar echinococcosis

BackgroundThe purpose of this study was to explore the relevant risk factors associated with biliary complications (BCs) in patients with end-stage hepatic alveolar echinococcosis (HAE) following ex vivo liver resection and autotransplantation (ELRA) and to establish and visualize a nomogram model.MethodsThis study retrospectively analysed patients with end-stage HAE who received ELRA treatment at the First Affiliated Hospital of Xinjiang Medical University between August 1, 2010 and May 10, 2023. The least absolute shrinkage and selection operator (LASSO) regression model was applied to optimize the feature variables for predicting the incidence of BCs following ELRA. Multivariate logistic regression analysis was used to develop a prognostic model by incorporating the selected feature variables from the LASSO regression model. The predictive ability, discrimination, consistency with the actual risk, and clinical utility of the candidate prediction model were evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Internal validation was performed by the bootstrapping method.ResultsThe candidate prediction nomogram included predictors such as age, hepatic bile duct dilation, portal hypertension, and regular resection based on hepatic segments. The model demonstrated good discrimination ability and a satisfactory calibration curve, with an area under the ROC curve (AUC) of 0.818 (95% CI 0.7417–0.8958). According to DCA, this prediction model can predict the risk of BCs occurrence within a probability threshold range of 9% to 85% to achieve clinical net benefit.ConclusionsA prognostic nomogram with good discriminative ability and high accuracy was developed and validated to predict BCs after ELRA in patients with end-stage HAE.