Radiology Research Articles

Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images

Laryngeal cancer exhibits a notable global health burden, with later-stage detection contributing to a low mortality rate. Laryngeal cancer diagnosis on throat region images is a pivotal application of computer vision (CV) and medical image diagnoses in the medical sector. It includes detecting and analysing abnormal or cancerous tissue from the larynx, an integral part of the vocal and respiratory systems. The computer-aided system makes use of artificial intelligence (AI) through deep learning (DL) and machine learning (ML) models, including convolution neural networks (CNN), for automated disease diagnoses and detection. Various DL and ML approaches are executed to categorize the extraction feature as healthy and cancerous tissues. This article introduces an automated Laryngeal Cancer Diagnosis using the Dandelion Optimizer Algorithm with Ensemble Learning (LCD-DOAEL) method on Biomedical Throat Region Image. The LCD-DOAEL method aims to investigate the images of the throat region for the presence of laryngeal cancer. In the LCD-DOAEL method, the Gaussian filtering (GF) approach is applied to eliminate the noise in the biomedical images. Besides, the complex and intrinsic feature patterns can be extracted by the MobileNetv2 model. Meanwhile, the DOA model carries out the hyperparameter selection of MobileNetV2 architecture. Finally, the ensemble of three classifiers such as bidirectional long short-term memory (BiLSTM), regularized extreme learning machine (ELM), and backpropagation neural network (BPNN) models, are utilized for the classification process. A comprehensive set of simulations is conducted on the biomedical image dataset to highlight the efficient performance of the LCD-DOAEL technique. The comparison analysis of the LCD-DOAEL method exhibited a superior accuracy outcome of 97.54% over other existing techniques.

Deep Learning With Ultrasound Images Enhance the Diagnosis of Nonalcoholic Fatty Liver

ObjectiveThis research aimed to improve diagnosis of non-alcoholic fatty liver disease (NAFLD) by deep learning with ultrasound Images and reduce the impact of the professional competence and personal bias of the diagnostician. MethodThree convolutional neural network models were used to classify and identify the ultrasound images to obtain the best network. Then, the features in the ultrasound images were extracted and a new convolutional neural network was created based on the best network. Finally, the accuracy of several networks was compared and the best network was evaluated using AUC. ResultsModels of VGG16, ResNet50, and Inception-v3 were individually applied to classify and identify 710 ultrasound images containing NAFLD, demonstrating accuracies of 66.2%, 58.5%, and 59.2%, respectively. To further improve the classification accuracy, two features are presented: the ultrasound echo attenuation coefficient (θ), derived from fitting brightness values within sliding region of interest (ROIs), and the ratio of Doppler effect (ROD), identified through analyzing spots exhibiting the Doppler effect. Then, a multi-input deep learning network framework based on the VGG16 model is established, where the VGG16 model processes ultrasound image, while the fully connected layers handle θ and ROD. Ultimately, these components are combined to jointly generate predictions, demonstrating robust diagnostic capabilities for moderate to severe fatty liver (AUC = 0.95). Moreover, the average accuracy is increased from 64.8% to 77.5%, attributed to the introduction of two advanced features with domain knowledge. ConclusionThis research holds significant potential in aiding doctors for more precise and efficient diagnosis of ultrasound images related to NAFLD.

Root canal configuration of human permanent anterior teeth: A cross-sectional study using cone-beam computed tomography in the Pakistani population.

To analyse and document internal root morphological variations in permanent anterior teeth using conebeam computed tomography. The cross-sectional, retrospective study was conducted from January 21 to June 19, 2021, at Jinnah Magnetic Resonance Imaging and Body Scan, and comprised data from July to December 2020 related to all the patients who had been referred to the centre for dental cone-beam computed tomography scan. The scans were evaluated at the Radiology Department of the School of Dentistry at Shaheed Zulfiqar Ali Bhutto Medical University, Islamabad, Pakistan. The morphology of the roots and root canals in all permanent anterior teeth was examined. Root canal configuration was categorised using Vertucci's classification. Data was analysed using SPSS 20. Of the 211 patients, 116(55%) were females and 95(45%) were males. The overall mean age was 39.9±1.02 years (range: 15-65 years). All the permanent anterior teeth exhibited a single root, with the exception 2(0.9%) mandibular right and 4(1.9%) left canines which had double roots. Type I root canals were observed in all 211 (100%) maxillary right central incisors, maxillary left central incisors and maxillary left canines. Among maxillary right canines, 208(98.6%) had type-I root canals, and the corresponding value for maxillary right lateral incisors was 209(99.1%), and for maxillary left lateral incisors, the value was 210(99.5%). Root canal polymorphism had no significant association with gender (p>0.05). The presence of type-I root canal was common in permanent anterior teeth, and there was significant association of root canal polymorphism with gender.

Evaluation of volume measurements of neuroanatomical structures related to speech in multiple sclerosis patients.

Individuals with multiple sclerosis (MS) may experience various speech-related issues, including decreased speech rate, increased pauses, and changes in speech rhythms. The purpose of this study was to compare the volumes of speech-related neuroanatomical structures in MS patients with those in a control group. The research was conducted in the Neurology and Radiology Departments of Malatya Training and Research Hospital. The records of patients who presented to the Neurology Department between 2019 and 2022 were examined. The study included the magnetic resonance imaging (MRI) findings of 100 individuals, with 50 in the control group and 50 patients with MS, who had applied to the hospital in the specified years. VolBrain is a free system that works automatically over the internet (http://volbrain.upv.es/), enabling the measurement of brain volumes without human interaction. The acquired images were analyzed using the VolBrain program. As a result of our research, a significant decrease was found in the volume of 18 of 26 speech-related regions in MS patients. It was determined that whole brain volumes decreased in the MS group compared to the control group. In our study, volume measurements of more speech-related areas were performed, unlike the few related studies previously conducted. We observed significant atrophy findings in the speech-related areas of the frontal, temporal, and parietal lobes of MS patients.

Mapping and Deep Analysis of Hospital Radiology Department to Identify Workflow Challenges and Their Potential Digital Solutions

Mapping and Deep Analysis of Hospital Radiology Department to Identify Workflow Challenges and Their Potential Digital Solutions

MRI T2w Radiomics-Based Machine Learning Models in Imaging Simulated Biopsy Add Diagnostic Value to PI-RADS in Predicting Prostate Cancer: A Retrospective Diagnostic Study.

Currently, prostate cancer (PCa) prebiopsy medical image diagnosis mainly relies on mpMRI and PI-RADS scores. However, PI-RADS has its limitations, such as inter- and intra-radiologist variability and the potential for imperceptible features. The primary objective of this study is to evaluate the effectiveness of a machine learning model based on radiomics analysis of MRI T2-weighted (T2w) images for predicting PCa in prebiopsy cases. A retrospective analysis was conducted using 820 lesions (363 cases, 457 controls) from The Cancer Imaging Archive (TCIA) Database for model development and validation. An additional 83 lesions (30 cases, 53 controls) from Hong Kong Queen Mary Hospital were used for independent external validation. The MRI T2w images were preprocessed, and radiomic features were extracted. Feature selection was performed using Cross Validation Least Angle Regression (CV-LARS). Using three different machine learning algorithms, a total of 18 prediction models and 3 shape control models were developed. The performance of the models, including the area under the curve (AUC) and diagnostic values such as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were compared to the PI-RADS scoring system for both internal and external validation. All the models showed significant differences compared to the shape control model (all p < 0.001, except SVM model PI-RADS+2 Features p = 0.004, SVM model PI-RADS+3 Features p = 0.002). In internal validation, the best model, based on the LR algorithm, incorporated 3 radiomic features (AUC = 0.838, sensitivity = 76.85%, specificity = 77.36%). In external validation, the LR (3 features) model outperformed PI-RADS in predictive value with AUC 0.870 vs. 0.658, sensitivity 56.67% vs. 46.67%, specificity 92.45% vs. 84.91%, PPV 80.95% vs. 63.64%, and NPV 79.03% vs. 73.77%. The machine learning model based on radiomics analysis of MRI T2w images, along with simulated biopsy, provides additional diagnostic value to the PI-RADS scoring system in predicting PCa.

Analysis Hybrid Approach for Multi-Objective Optimization-based segmentation of fuzzy contours in mammogram using artificial plant optimization algorithm

It is observed that importance is given to the identification of tumor in case of medical image diagnosis. It has been found that in women breast cancer is increasing and due to which it has an impact in the death rate also. In medical domain radiologist generally uses the computer aided detection methods (CAD ). Medical image often contains the noise and some fuzziness in the picture border so the identification of the tumor is having problem and it becomes challenging task. by Owing to the noise and fuzziness of the picture border, identifying tumors on mammograms is challenging. Even though Active contour is an effective method for the segmentation but It is having problem related to local minima. The proposed method is a hybrid which is consist of multi objective optimization and Gravitational search algorithm (GSA) used for segmentation after that results are given to an Artificial plant optimization algorithm (APOA). The operations involve in this process includes some subprocesses primarily contour initialization is done for ROI followed by segmentation through GSA and multi-objective optimization and then APOA is applied. To evaluate the results two different databases are used mini-MIAS and DDSM databases. Results are also compared with other research work carried out earlier. It is observed that our proposed method gives better output then other.

Emergency Radiology in the First 24 h of Two Major Earthquakes on the Same Day and Radiologic Evaluation of Trauma Cases.

On 6 February 2023, two major earthquakes occurred in Turkey on the same day. More than 50,000 people died, and more than 100,000 people were injured in these earthquakes. The aim of this study is to contribute to disaster management plans by evaluating the functioning of a radiology department and the imaging examinations performed after this disaster. The functioning of the radiology clinic at Malatya Training and Research Hospital in the first 24 h after the earthquake was evaluated. The images of 596 patients who were admitted to Malatya Training and Research Hospital for earthquake-related trauma between 6 February 2023, at 4:17 a.m. and 7 February 2023, at 4:17 a.m., and who underwent radiography and computed tomography (CT) were retrospectively reviewed. The mean age of the patients was 37.3 ± 20.1 years. A total of 313 (52.5%) patients were male. The most frequently performed imaging test was a CT scan. In total, 437 (73.3%) of 596 patients underwent a CT scan. At least one body part was affected in 160 patients (26.8%). The most commonly affected regions were the thorax, vertebrae, and extremities. Thoracic findings were observed in 52 patients (32.5%), vertebral findings in 52 patients (32.5%), and extremity findings in 46 patients (28.7%). Fractures were the most common finding in our study. Of the 160 patients with pathologic findings, 139 (86.9%) had evidence of fractures. The role of radiology in disasters is important. When disaster preparedness plans are made, radiology departments should be actively involved in these plans. This will ensure the quick and efficient functioning of radiology departments.

Precise determination of human serum albumin levels in blood serum by a D-π-A based near-infrared fluorescent probe via TICT mechanism

Human serum albumin (HSA) levels in the body are crucial for the accurate diagnosis of various health issues, necessitating continuous monitoring and novel detection methods. This study focused on the development and synthesis of two novel D-π-A small molecule near-infrared fluorescent probes, PTPA-B and CPTPA-B. The probes demonstrated selective detection of HSA with a rapid response time of 1 min and high sensitivity, featuring limits of detection (LOD) of 0.102 μM and 1.702 μM. Under physiological conditions, the intrinsic fluorescence of these probes is minimal due to intramolecular charge transfer (TICT). Upon entering the hydrophobic cavity of HSA, the probes exhibit red fluorescence by inhibiting the TICT process. Additionally, the probes exhibited enhanced biocompatibility in living cells and enabled fluorescence imaging of L-02 live cells. Therefore, the PTPA-B fluorescent probe serves as an effective tool for serum detection, revealing its potential applications in live cell imaging and precise clinical diagnosis.

Strategies for minimizing repeated exposures in diagnostic radiography

Advancements in diagnostic radiography have significantly improved medical imaging, yet the associated radiation exposure poses health risks, particularly with repeated examinations. Technological innovations, including the transition from analog to digital radiography, have led to substantial reductions in radiation doses while enhancing image quality. Digital systems, coupled with automatic exposure control (AEC), dynamically adjust radiation levels based on patient size and diagnostic requirements, minimizing unnecessary exposure. Iterative reconstruction algorithms in CT imaging further reduce radiation doses by efficiently processing images and reducing noise. Hardware improvements, such as high-efficiency detectors, capture high-quality images with lower radiation levels, contributing to dose reduction. Standardizing radiographic protocols across healthcare settings ensures consistent practices, reducing variability in radiation doses. Techniques such as beam collimation and appropriate shielding protect surrounding tissues and enhance image quality, while continuous education for technologists maintains proficiency in dose-reduction strategies. Patient education is crucial for minimizing repeated exposures. Informing patients about the risks of ionizing radiation and the importance of adhering to follow-up schedules can reduce unnecessary examinations. Electronic health records (EHRs) facilitate the tracking of cumulative radiation doses, enabling informed decision-making regarding additional imaging studies. Adherence to the ALARA principle (As low as reasonably achievable) in clinical practice ensures that radiation exposure is minimized while achieving diagnostic goals. Special considerations for vulnerable populations, such as children and pregnant women, further enhance safety. Implementing radiation safety measures and maintaining a commitment to ongoing professional development for healthcare providers fosters a culture of safety within radiology departments. By integrating these strategies, healthcare providers can balance the diagnostic benefits of radiography with the imperative to protect patients from unnecessary radiation exposure, ultimately enhancing patient safety and improving diagnostic outcomes. This comprehensive approach ensures that radiographic procedures remain both effective and safe, optimizing patient care in medical imaging.

Consensus guidelines on the diagnosis and treatment of pancreatic pseudocyst and walled-off necrosis from a Chinese multiple disciplinary team expert panel.

To prepare a set of practice guidelines to standardize the entire process, from diagnosis to treatment and follow-up, for pancreatic pseudocysts and walled-off necrosis. Thirty-six experts in the fields of digestive endoscopy, pancreatic surgery, interventional radiology, and others presented their opinions via discussions in online conferences by referring to the patient, intervention, comparison, and outcomes principles and then reviewed the evidence and statements using the Delphi method to reach a consensus. The consensus of >80% was finally achieved for the items. The experts discussed and reached a consensus on 29 statements including 10 categories: (1) definition and classification, (2) imaging and endoscopic diagnosis, (3) therapeutic implications, (4) surgical therapy, (5) percutaneous catheter drainage, (6) endoscopic retrograde cholangiopancreatography, (7) EUS-guided drainage, (8) stent selection for EUS-guided drainage, (9) complication related to stents for cyst drainage, and (10) drug treatment and follow-up. This consensus based on the clinical experience of experts in various fields and international evidence-based medicine further standardizes the multidisciplinary diagnosis and treatment processes for pancreatic pseudocysts and walled-off necrosis.

A Comparison of Pre- and Post-Treatment Cranial MRI Characteristics in Patients with Pediatric Epilepsy Receiving Levetiracetam.

Background and Objectives: This study was performed for the purpose of assessing whether antiepileptic levetiracetam treatment produces a change in brain volumes in children with epilepsy. To that end, we compared the volumes of the basal ganglia (caudate nucleus, putamen, globus, hip-pocampus, and thalamus) at magnetic resonance imaging (MRI) before and after treatment (months 18-24) in pediatric epilepsy patients using levetiracetam. Materials and Methods: This retrospective study involved a volumetric comparison of patients presenting to the Balikesir University Medical Faculty pediatric neurology clinic between 01.08.2019 and 01.11.2023 and diagnosed with epilepsy, and who underwent cranial MRI before and 18-24 months after treatment at the radiology department. The demographic and clinical characteristics (age, sex, family history of epilepsy, type of epilepsy, and EEG features (normal, abnormal, epileptiform)) of the patients included in the study were recorded. Results: The comparison of basal ganglia volumes at cranial MRI before and at months 18-24 of treatment revealed significant differences in the left caudate nucleus, right putamen, left putamen, left globus pallidus, right thalamus, left thalamus, and right hippocampal regions. Conclusions: In conclusion, differing findings are encountered at cranial imaging in patients with epilepsy, depending on the seizure frequency, activity, and the type of antiepileptic drugs used. This study compared basal ganglia volumes on cranial MRIs taken before and 18-24 months after treatment in pediatric epilepsy patients using levetiracetam. A significant increase was observed in the volumes of basal ganglia (caudate nucleus, putamen, globus pallidus, hippocampus, and thalamus) on the MRIs of pediatric epilepsy patients using levetiracetam.

Current status and new advancements in molecular imaging of liver cancer

Early-stage diagnosis of liver cancer is challenging, with an overall poor prognosis. The tumor microenvironment of primary liver cancer is complex, exhibiting significant heterogeneity both interpersonally and intratumorally. Therefore, it is of paramount importance to dynamically analyze biological markers in the tumor microenvironment of primary liver cancer in vivo. In recent years, significant progress has been made in the imaging diagnosis and treatment of liver cancer with the development of molecular imaging. Molecular imaging techniques utilize specific nano-imaging probes to evaluate pathological changes of liver cancer at the molecular and cellular levels in real-time. These techniques enable precise imaging to reveal key molecular biomarkers involved in the occurrence and progression of liver cancer, exploring their associations with cancer progression and outcomes. This article focuses on molecular imaging, emphasizing the current research status and latest advancements in the field of liver cancer diagnosis and therapy using techniques such as CT, MRI, optical imaging, PET imaging, and multimodal imaging. It also identifies important future directions and significant challenges for further development.

Research progress and prospects of the application of radiographic imaging in the precise diagnosis and treatment of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a highly heterogeneous kind of malignant tumor with a high recurrence rate and low five-year survival rate, which has become one of the major public health issues in China. Currently, HCC is the only solid tumor that can be solely diagnosed based on epidemiological history and typical imaging features without preoperative pathological confirmation. The paradigm for HCC imaging diagnosis has shifted in recent years from anatomy to function, from macroscopic to microscopic, and from diagnosis to prediction in the context of precision medicine, making it possible to study the microscopic processes such as HCC genes and their metabolic laws from the perspective of qualitative and quantitative imaging, thereby providing more accurate biological and imaging information for elucidating the occurrence, development, and clinical treatment decisions of HCC.This paper reviews the research progress of HCC imaging in recent years, demonstrating the rapid horizontal development and enormous potential of imaging in the vertical follow-up of HCC precision diagnosis and treatment. Simultaneously, it also puts forward the shortcomings of current HCC imaging research and looks forward to future development directions in order to be more accurately used in clinical decision support systems.

Non-invasive imaging diagnosis of a mediastinal paraganglioma: a case report.

Non-invasive imaging diagnosis of a mediastinal paraganglioma: a case report.

Application of radiographic imaging diagnosis in the treatment and nursing intervention of perioperative infection for kidney transplant recipients

The severity and complexity of infection after renal transplantation have an important impact on the health and survival prognosis of patients. As an important auxiliary tool, the purpose of this study was to investigate the application and effect of radiography diagnosis in perioperative infection treatment and nursing intervention of kidney transplant recipients. Radiographic diagnosis acquires the patient's image data, evaluates the quality of the image, ensures that the image is clear enough to make an accurate diagnosis, and understands the structure shown in the image to accurately locate the patient's abnormalities or lesions. The early location and accurate diagnosis of perioperative infection of kidney transplant recipients were successfully realized by collecting cases of perioperative infection of kidney transplant recipients and using radiographic diagnosis technology. The use of high-grade antibiotics does not significantly reduce the infection rate of patients. The application of radiographic diagnostic technology in perioperative infection treatment and nursing of kidney transplant recipients is helpful to accurately evaluate the infection site, infection degree and infection type, and guide the selection of reasonable treatment and intervention measures. Radiographic diagnostic technology can also detect and evaluate complications in time, and MMF + CsA + hormone immunosuppression regimen is selected both during and after surgery.

Multimodal imaging diagnosis and analysis of prognostic factors in patients with adult-onset Coats disease.

To describe the multimodal imaging features, treatment, and outcomes of patients diagnosed with adult-onset Coats disease. This retrospective study included patients first diagnosed with Coats disease at ≥18 years of age between September 2017 and September 2021. Some patients received anti-vascular endothelial growth factor (VEGF) therapy (conbercept, 0.5 mg) as the initial treatment, which was combined with laser photocoagulation as needed. All the patients underwent best corrected visual acuity (BCVA) and intraocular pressure examinations, fundus color photography, spontaneous fluorescence tests, fundus fluorescein angiography, optical coherence tomography (OCT), OCT angiography, and other examinations. BCVA alterations and multimodal image findings in the affected eyes following treatment were compared and the prognostic factors were analyzed. The study included 15 patients who were aged 24-72 (57.33±12.61)y at presentation. Systemic hypertension was the most common associated systemic condition, occurring in 13 (86.7%) patients. Baseline BCVA ranged from 2.0 to 5.0 (4.0±1.1), which showed improvement following treatment (4.2±1.0). Multimodal imaging revealed retinal telangiectasis in 13 patients (86.7%), patchy hemorrhage in 5 patients (33.3%), and stage 2B disease (Shield's staging criteria) in 11 patients (73.3%). OCT revealed that the baseline central macular thickness (CMT) ranged from 129 to 964 µm (473.0±230.1 µm), with 13 patients (86.7%) exhibiting a baseline CMT exceeding 250 µm. Furthermore, 8 patients (53.3%) presented with an epiretinal membrane at baseline or during follow-up. Hyper-reflective scars were observed on OCT in five patients (33.3%) with poor visual prognosis. Vision deteriorated in one patient who did not receive treatment. Final vision was stable in three patients who received laser treatment, whereas improvement was observed in one of two patients who received anti-VEGF therapy alone. In addition, 8 of 9 patients (88.9%) who received laser treatment and conbercept exhibited stable or improved BCVA. Multimodal imaging can help diagnose adult-onset Coats disease. Anti-VEGF treatment combined with laser therapy can be an option for improving or maintaining BCVA and resolving macular edema. The final visual outcome depends on macular involvement and the disease stage.

Multiple Instance Pathology Image Diagnosis Model based on Channel Attention and Data Augmentation

The application of machine learning in the medical field has resulted in significant advancements in computer-aided pathological diagnosis. Multiple instance learning (MIL) has emerged as a promising approach for pathological image classification, particularly in scenarios where local annotations are lacking. However, current MIL models often overlook the importance of feature weights in the channel dimension and struggle with imbalanced positive and negative data. To address these limitations, an integration of a channel attention (CA) module and an augmented data (AUG) mechanism into the MIL model is proposed, resulting in improved performance. The CA module dynamically assigns weights to example features in the channel dimension, enhancing or suppressing features adaptively. Additionally, the AUG mechanism effectively balances the distribution of positive and negative data, significantly reducing false negatives. Through ablation experiments, the contributions of the CA module and AUG mechanism in enhancing the overall model performance are analyzed. Experimental validations on the CAMELYON16/17 public pathological image datasets demonstrate that the proposed model and method outperform existing approaches, with particular emphasis on reducing false negatives.

Ultrasonographic Evaluation of the Association between the Prostate Volume and Anthropometric Measurements in a Subset of Adult Nigerian Men with Benign Prostatic Hypertrophy

Background: Benign prostatic hypertrophy (BPH), a major cause of men`s morbidity, is positively related to obesity, which is assessed using anthropometric measurements. Despite the scarcity of local literature on this relationship, varying associations between prostate volume (PV), age, and anthropometric parameters have been reported. Objectives: To ascertain the average BPH volume, the predominant age at risk for BPH, and any correlations between PV and anthropometric measurements in our community. Methods: A prospective cross-sectional study conducted on 125 men aged 40–80years, with normal prostatic-specific antigen (PSA) levels, at the Radiology department, Benue State University Teaching Hospital, Makurdi, from May 2023 to May, 2024. PV was calculated by transabdominal ultrasonography. Anthropometric measurements were made using set procedures, from which the body mass index (BMI), waist-to-hip ratio (WHR), and waist-to-height ratio (WHTR) were computed. The data was analyzed using SPSS and Microsoft Excel with P value &lt; 0.05. Results: The mean age and PV of participants was 61.6±9.5years and 74.2±52.5ml, respectively with majority, 41 (32.8%) of men in their seventh decade of life. Age and PV did not statistically significantly correlate (P = 0.159); however, BMI, HC, WC and WHTR did (P = 0.000, 0.002, 0.006, and 0.014). Conclusion: The mean sonographic PV was 74.2±52.5ml, with men in their seventh decade being the most at risk for BPH. PV exhibited a statistically significant correlation with some anthropometric parameters but not with respondents' age. The equations and models generated from this study will benefit future research on prostatic growth and early detection of BPH.

Case series multilocular cystic hemangioma of the liver: Three cases and literature review.

Multilocular cystic hemangioma is a rare benign tumor classified as an atypical hemangioma. Currently, there are limited imaging reports available, and the imaging characteristics can be challenging to distinguish from other malignant multilocular cystic liver diseases such as cystadenocarcinoma, necessitating confirmation through pathological diagnosis. Here, we discuss the imaging features of 3 cases of multilocular cystic hemangiomas. Case 1 was a 24-year-old young female, and Case 2 involved a 60-year-old elderly male. Both patients were asymptomatic and physical examination revealed hepatic space-occupying lesions. Imaging findings revealed multilocular cystic lesions in the left liver with septa, calcification, a high diffusion-weighted magnetic resonance imaging (DWI) signal at the edge of the lesion, and progressive enhancement of the cyst wall and septa. Case 3 involved a 50-year-old male patient with epigastric distending pain for 1 month and sudden severe abdominal pain for 14 hours. Imaging results revealed a multilocular cystic lesion in the left liver with septa and tumor bleeding, a high DWI signal, and an enhanced cyst wall and septa. The pathological diagnosis confirmed a hepatic hemangioma. All 3 patients underwent liver tumor resection. All 3 patients recovered successfully without any intraoperative or postoperative complications during the follow-up periods of 5 years, 6 months, and 5 months. There were no signs of recurrence. Liver imaging revealed multilocular cystic lesions with features, such as compartmentalization, calcification, or bleeding. Multilocular cystic hemangiomas should be considered in imaging diagnosis. Enhancing our understanding of multilocular cystic hemangiomas can aid in improving the differential diagnosis of other malignant multilocular cystic liver diseases, ultimately reducing unnecessary liver resection.