Imaging Reporting Research Articles

Extraordinary Presentation of Chronic Pyelonephritis as Retroperitoneal Mass: An Image Report

AbstractHere we are presenting a unique presentation of chronic pyelonephritis as retroperitoneal mass. It produced a diagnostic dilemma, and final diagnosis was confirmed after histopathology report.

Fetal Brain MRI Abnormalities in Pyruvate Dehydrogenase Complex Deficiency.

Pyruvate dehydrogenase complex deficiency (PDCD) is a disorder of mitochondrial metabolism that is caused by pathogenic variants in multiple genes, including PDHA1. Typical neonatal brain imaging findings have been described, with a focus on malformative and encephaloclastic features. Fetal brain MRI in PDCD has not been comprehensively described. The aims of this study were (1) to further characterize the fetal brain MRI findings in PDCD using comprehensive fetal imaging and genetic testing and (2) to determine whether markers of diagnosis of PDCD could be identified on prenatal imaging. Fetuses with a diagnosis of PDCD related to a genetic etiology that had undergone fetal MRI were included. Fetuses were identified retrospectively from local databases of 4 fetal diagnostic clinics within tertiary pediatric health care centers. Electronic medical records were reviewed retrospectively: demographics, maternal and pregnancy history, fetal outcomes, and neonatal outcomes (if available) were reviewed and recorded. Fetal and neonatal imaging reports were reviewed; source fetal and neonatal brain MRI scans were reviewed by a single pediatric neuroradiologist (J.W.S.) for consistency. Genetic testing strategies and results including variant type, zygosity, inheritance pattern, and pathogenicity were recorded. Deidentified data were combined and reported descriptively. A total of 10 fetuses with a diagnosis of PDCD were included. 8 fetuses had corpus callosum dysgenesis, 6 had an abnormal gyration pattern, 10 had reduced brain volumes, and 9 had cystic lesions. 1 fetus had intraventricular hemorrhages. 1 fetus had a midbrain malformation with aqueductal stenosis and severe hydrocephalus. 6 fetuses imaged in the second trimester had cystic lesions involving the ganglionic eminences (GEs) while GE cysts were not present in the 4 fetuses imaged in the third trimester. Fetuses with PDCD have similar brain MRI findings to neonates described in the literature, although some of these findings are subtle early in pregnancy. Additional features, such as cystic lesions of the GEs, are noted in the second trimester in fetuses with PDCD. These may represent an early diagnostic marker of PDCD, although more data are needed to validate this association. Early diagnosis of PDCD using fetal MRI may inform genetic counseling, pregnancy decision making, and neonatal care planning.

Serum trace elements show association with thyroperoxidase autoantibodies in Thyroid Imaging Reporting and Data System (TI-RADS) 4 nodules

Thyroid nodule (TN) has been becoming a great concern worldwide due to its high incidence. Although some studies have reported associations between trace elements exposure and the risk of TNs, the linkage was not inconclusive. The present study aimed to identify the association of selected serum trace elements (Ca, Mg, V, Fe, Co, Cu, Zn, Se, Mn and Mo) with TNs among general adults. A cross-sectional study was conducted in January 2021 in Chengdu, China. 1282 subjects completed the questionnaire and gave at least one human biological material after an overnight fast, venous blood, and urine, including 377 TN participants defined through ultrasound. Various trace elements in serum specimens were determined by inductively coupled plasma mass spectrometry. Thyroid functions were tested by chemiluminescent microparticle immunoassay (CMIA). The associations between trace elements levels and the risk of TNs were examined by restricted cubic splines (RCS) regression and bayesian kernel machine regression (BKMR) models. TNs were more common in females (P < 0.001) and in the elderly (P < 0.001) and that they were also frequently associated with fertility, marital status, annual household income, drinking, anxiety, vitamin supplement, tea consumption, hypertension and hyperlipidemia. After adjusting for confounders by a propensity score matching model, the association between trace elements concentrations and TNs risk was found to be statistically insignificant in the RCS (P for nonlinear > 0.05) and BKMR models. FT3 or T4 (total or free) increased significantly with increasing total trace elements mixture levels. In TI-RADS-4 TN subjects, TPO-Ab level increased significantly with increasing total trace elements mixture levels in the high-dose range. Ca, Zn, Mo at their 75th percentile showed positive individual effects on TPO-Ab, which was examined to be interactive. The detection of trace elements for TNs in general adults may be of no significance, but once individuals classified as TI-RADS-4 TNs are detected with abnormal TPO-Ab, Ca, Zn and Mo level are recommended to measure. The substantive association on it still needs to be continuously explored in the future.

May Patients with Recurrent Venous Disease Benefit from Sequential Treatment More than Those without Previous Intervention? A Single-Center Retrospective Study on the Safety and Efficacy of Abdominal and Pelvic Veins Embolization in Sequential Approach.

Background/Objective: The endovenous embolization of insufficient abdominal/pelvic veins is the preferred method of treatment. Also, it seems to be crucial in the treatment of lower limb vein insufficiency, particularly in recurrent disease. This study aimed to evaluate of pelvic vein embolization safety and its impact on the short-term outcome in the sequential treatment of venous disease. Methods: A retrospective analysis involved data from 506 female patients with venous disease involving abdominal and pelvic veins. All records were extracted from the medical database and included patient history, imaging reports as well as pre- and post-operative surveys. Results: Among the patients analyzed, 37.2% underwent some venous intervention in the past, with significant differences in symptom severity between groups. The embolization procedure revealed a high safety profile, with no serious complications. Pain during and after the procedure was generally low, with significantly lower pain scores in patients with recurrence. In patients who required left renal vein venoplasty a 1.7-fold increased risk of lumbar pain after embolization and venoplasty procedure was observed. Overall, 66.6% of patients reported improvement in pelvic symptoms and 72.1% experienced improvement in leg symptoms. The full sequential treatment protocol (abdominal, pelvic, and leg compartment) demonstrated superior outcomes in leg symptom improvement compared to embolization alone. Conclusions: Pelvic vein embolization is a safe and effective method of treatment, significantly improving both pelvic and leg symptoms, particularly in patients with a history of previous interventions in lower limb veins. Further studies are warranted to validate our findings and further refine treatment protocols.

Imaging in pelvic exenteration-a multidisciplinary practice guide from the ESGAR-SAR-ESUR-PelvEx collaborative group.

Pelvic exenteration (PE) is a radical surgical approach designed for the curative treatment of advanced pelvic malignancies, requiring en-bloc resection of multiple pelvic organs. While the procedure is radical, it has shown promise in enhancing long-term survival and is now comparable in surgical mortality to elective resections for primary pelvic cancers. Imaging plays a crucial role in preoperative planning, with MRI, CT, and PET/CT being pivotal in assessing the extent of cancer and formulating a surgical roadmap. This paper presents clinical practice guidelines for imaging in the context of PE, developed jointly by ESGAR, SAR, ESUR, and the PelvEx Collaborative. These guidelines aim to standardize imaging protocols and reporting to improve the preoperative assessment and facilitate decision-making in the multidisciplinary treatment of pelvic cancers. Our recommendations underscore the importance of a multidisciplinary approach and the need for clear and precise imaging reports to optimize patient care. CLINICAL RELEVANCE STATEMENT: Our recommendations underscore the importance of a multidisciplinary approach and the need for clear and precise imaging reports to optimize patient care. KEY POINTS: MRI is mandatory for local staging in pelvic exenteration. Structured reporting (using the template provided in this guide) is recommended. Multidisciplinary review of imaging is critical for surgical planning.

MeFD-Net: multi-expert fusion diagnostic network for generating radiology image reports

MeFD-Net: multi-expert fusion diagnostic network for generating radiology image reports

Monitoring of Nanodrug Accumulation in Murine Breast Cancer Metastases.

Metastatic breast cancer is a devastating disease with very limited therapeutic options, calling for new therapeutic strategies. Oncogenic miRNAs have been shown to be associated with the metastatic potential of breast cancer and are implicated in tumor cell migration, invasion, and viability. However, it can be difficult to deliver an inhibitory RNA molecule to the tissue of interest. To overcome this challenge and deliver active antisense oligonucleotides to tumors, we utilized magnetic iron oxide nanoparticles as a delivery platform. These nanoparticles target tissues with increased vascular permeability, such as sites of inflammation or cancer. Delivery of these nanoparticles can be monitored in vivo by magnetic resonance imaging (MRI) due to their magnetic properties. Translation of this therapeutic approach into the clinic will be more accessible because of its compatibility with this relevant imaging modality. They can also be labeled with other imaging reporters such as a Cy5.5 near-infrared optical dye for correlative optical imaging and fluorescence microscopy. Here, we demonstrate that nanoparticles labeled with Cy5.5 and conjugated to therapeutic oligomers targeting oncogenic miRNA-10b (termed MN-anti-miR10b, or "nanodrug") administered intravenously accumulate in metastatic sites, opening a possibility for therapeutic intervention of metastatic breast cancer.

Preliminary clinical practice of radical prostatectomy without preoperative biopsy.

At present, biopsy is essential for the diagnosis of prostate cancer (PCa) before radical prostatectomy (RP). However, with the development of prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) and multiparametric magnetic resonance imaging (mpMRI), it might be feasible to avoid biopsy before RP. Herein, we aimed to explore the feasibility of avoiding biopsy before RP in patients highly suspected of having PCa after assessment of PSMA PET/CT and mpMRI. Between December 2017 and April 2022, 56 patients with maximum standardized uptake value (SUVmax) of ≥4 and Prostate Imaging Reporting and Data System (PI-RADS) ≥4 lesions who received RP without preoperative biopsy were enrolled from two tertiary hospitals. The consistency between clinical and pathological diagnoses was evaluated. Preoperative characteristics were compared among patients with different pathological types, T stages, International Society of Urological Pathology (ISUP) grades, and European Association of Urology (EAU) risk groups. Fifty-five (98%) patients were confirmed with PCa by pathology, including 49 (89%) with clinically significant prostate cancer (csPCa, defined as ISUP grade ≥2 malignancy). One patient was diagnosed with high-grade prostatic intraepithelial neoplasia (HGPIN). CsPCa patients, compared with clinically insignificant prostate cancer (cisPCa)andHGPIN patients, were associated with a higher level of prostate-specific antigen (22.9ng/mL vs. 10.0ng/mL, P=0.032), a lower median prostate volume (32.2mL vs. 65.0mL, P=0.001), and a higher median SUVmax (13.3 vs. 5.6, P<0.001). It might be feasible to avoid biopsy before RP for patients with a high probability of PCa based on PSMA PET/CT and mpMRI. However, the diagnostic efficacy of csPCa with PI-RADS ≥4 and SUVmax of ≥4 is inadequate for performing a procedure such as RP. Further prospective multicenter studies with larger sample sizes are necessary to confirm our perspectives and establish predictive models with PSMA PET/CT and mpMRI.

Automatic Classification of Conclusions from Multi-Tracer Reports of PET Brain Imaging in Cognitive Impairment.

The goal of this paper is to build an automatic way to interpret conclusions from brain molecular imaging reports performed for investigation of cognitive disturbances (FDG, Amyloid and Tau PET) by comparing several traditional machine learning (ML) techniques-based text classification methods. Two purposes are defined: to identify positive or negative results in all three modalities, and to extract diagnostic impressions for Alzheimer's Disease (AD), Fronto-Temporal Dementia (FTD), Lewy Bodies Dementia (LBD) based on metabolism of perfusion patterns. A dataset was created by manual parallel annotation of 1668 conclusions of reports from the Nuclear Medicine and Molecular Imaging Division of Geneva University Hospitals. The 6 Machine Learning (ML) algorithms (Support Vector Machine (Linear and Radial Basis function), Naive Bayes, Logistic Regression, Random Forrest, and K-Nearest Neighbors) were trained and evaluated with a 5-fold cross-validation scheme to assess their performance and generalizability. The best classifier was SVM showing the following accuracies: FDG (0.97), Tau (0.94), Amyloid (0.98), Oriented Diagnostic (0.87 for a diagnosis among AD, FTD, LBD, undetermined, other), paving the way for a paradigm shift in the field of data handling in nuclear medicine research.

Microbiology and Epidemiology of Orbital Cellulitis in Pediatric and Young Adult Patients.

Using data from the large and geographically diverse Military Health System (MHS) beneficiary population, we aimed to characterize and update the epidemiology and microbiology of pediatric orbital cellulitis given previous data are limited to small, single-center studies. Following institutional review board approval, we performed a retrospective analysis using the Military Health System admissions, microbiology, and pharmacy data between June 2009 and September 2019. Patients less than 22 years of age with radiological confirmation of orbital cellulitis were included. Demographic data, presence of sinusitis, advanced imaging reports, blood and wound culture results with antibiotic susceptibilities, and antibiotic prescriptions were collected. Descriptive statistics were used to summarize demographic characteristics. Imaging findings were grouped by Chandler's stage (CS), an imaging-based measure of the progressive severity of orbital involvement. A Cochran-Armitage trend test was used to evaluate the relationship between CS and likelihood of positive confirmatory culture. There was a male predominance (66.9%) and 55.5% of subjects had comorbid sinusitis. Of the 130 subjects included, 33.8% had one or more positive cultures, 30.8% had a positive wound culture, and 4.6% had a positive blood culture. The most identified organism was coagulase-negative staphylococci (23.3%), followed by Staphylococcus aureus (18.9%), Streptococcus intermedius (17.8%), and strict anaerobes as a group (13.3%). Gram-negative organisms were rare. Twenty-five percent of S. aureus were methicillin-resistant. Clindamycin resistance was identified in 9% of all S. aureus, 50% of coagulase-negative staphylococci, and 25% of S. intermedius. Clindamycin plus ceftriaxone was the most prescribed empiric antibiotic regimen (36.2%). Likelihood of a positive culture significantly increased with advancing CS. Orbital cellulitis occurs most frequently in males with sinusitis. Likelihood of positive wound culture is increased with a more advanced CS. Staphylococcus and Streptococcus spp. and anaerobes are the most identified pathogens in orbital cellulitis, while gram-negative organisms are rare. Empiric antibiotic selection should include an anti-methicillin-resistant S. aureus agent combined with a broad-spectrum beta-lactam and anaerobic coverage.

Identifying enthesitis in the sacroiliac joints in patients with axial spondyloarthritis by readers of varying experience: impact of the learning progress

BackgroundThis study aimed to investigate the accuracy of identifying enthesitis along with other inflammatory lesions and structural lesions on the MRI of the sacroiliac joints (SIJ) by readers of varying experience and how training sessions and workshops could help improve the accuracy.MethodsA total of 224 patients with clinical diagnosis of axial spondyloarthritis who underwent SIJ MRI examinations were retrospectively included in this study. Three readers with 5 years, 3 years and 1 year of experience in musculoskeletal imaging were invited to review the SIJ MRI images independently, while the imaging reports of a senior radiologist (> 10 years’ experience) were used as reference. After the first round of image review, a training session and a workshop on the imaging of SIJ in spondyloarthritis were held and the three readers were asked to review the images in the second round. We calculated the accuracy of identifying inflammatory and structural lesions of the three readers as well as the intra-reader agreement.ResultsEnthesitis could be observed in 52.23% of the axial spondyloarthritis patients, while 81.58% of the patients with enthesitis were accompanied with bone marrow edema. All the three readers showed better accuracy at identifying structural lesions than inflammatory lesions. In the first round of image review, the three readers only correctly identified 15.07%, 2.94% and 0.74% of the enthesitis sites. After the training session and workshop, the accuracy rose to 61.03%, 39.34% and 20.22%. The intra-reader agreement of enthesitis calculated as Cohen’s kappa was 0.23, 0.034 and 0.014, respectively.ConclusionReaders with less experience in musculoskeletal imaging showed lower accuracy of identifying inflammatory lesions, notably enthesitis. Training sessions and workshops could help improve the diagnostic accuracy of the junior readers.

Multi-modal transformer architecture for medical image analysis and automated report generation

Medical practitioners examine medical images, such as X-rays, write reports based on the findings, and provide conclusive statements. Manual interpretation of the results and report generation by examiners are time-consuming processes that lead to potential delays in diagnosis. We propose an automated report generation model for medical images leveraging an encoder–decoder architecture. Our model utilizes transformer architectures, including Vision Transformer (ViT) and its variants like Data Efficient Image Transformer (DEiT) and BERT pre-training image transformer (BEiT), as an encoder. These transformers are adapted for processing to extract and gain visual information from medical images. Reports are transformed into text embeddings, and the Generative Pre-trained Transformer (GPT2) model is used as a decoder to generate medical reports. Our model utilizes a cross-attention mechanism between the vision transformer and GPT2, which enables it to create detailed and coherent medical reports based on the visual information extracted by the encoder. In our model, we have extended the report generation with general knowledge, which is independent of the inputs and provides a comprehensive report in a broad sense. We conduct our experiments on the Indiana University X-ray dataset to demonstrate the effectiveness of our models. Generated medical reports from the model are evaluated using word overlap metrics such as Bleu scores, Rouge-L, retrieval augmentation answer correctness, and similarity metrics such as skip thought cs, greedy matching, vector extrema, and RAG answer similarity. Results show that our model is performing better than the recurrent models in terms of report generation, answer similarity, and word overlap metrics. By automating the report generation process and incorporating advanced transformer architectures and general knowledge, our approach has the potential to significantly improve the efficiency and accuracy of medical image analysis and report generation.

DKA-RG: Disease-Knowledge-Enhanced Fine-Grained Image–Text Alignment for Automatic Radiology Report Generation

Automatic radiology report generation is a task that combines artificial intelligence and medical information processing, and it fully relies on computer vision and natural language processing techniques. Nowadays, automatic radiology report generation is still a very challenging task because it requires semantically adequate alignment of data from two modalities: radiology images and text. Existing approaches tend to focus on coarse-grained alignment at the global level and do not take into account the disease characteristics of radiology images at fine-grained semantics, which results in the generated reports potentially omitting key disease diagnostic descriptions. In this work, we propose a new approach, disease-knowledge-enhanced fine-grained image–text alignment for automatic radiology report generation (DKA-RG). The method combines global and disease-level alignment, thus facilitating the extraction of fine-grained disease features by the model. Our approach also introduces a knowledge graph to inject medical domain expertise into the model. Our proposed DKA-RG consists of two training steps: the image–report alignment stage and the image-to-report generation stage. In the alignment stage, we use global contrastive learning to align images and texts from a high level and also augment disease contrastive learning with medical knowledge to enhance the disease detection capability. In the report generation stage, the report text generated from the images is more accurate in describing the disease information thanks to sufficient alignment. Through extensive quantitative and qualitative experiments on two widely used datasets, we validate the effectiveness of our DKA-RG on the task of radiology report generation. Our DKA-RG achieves superior performance on multiple types of metrics (natural language generation and clinical efficacy metrics) compared to existing methods, demonstrating that the method can improve the reliability and accuracy of automatic radiology report generation systems.

Quantitative and Radiological Assessment of Post-cardiac-Arrest Comatose Patients with Diffusion-Weighted Magnetic Resonance Imaging.

Although magnetic resonance imaging, particularly diffusion-weighted imaging, has increasingly been used as part of a multimodal approach to prognostication in patients who are comatose after cardiac arrest, the performance of quantitative analysis of apparent diffusion coefficient (ADC) maps, as compared to standard radiologist impression, has not been well characterized. This retrospective study evaluated quantitative ADC analysis to the identification of anoxic brain injury by diffusion abnormalities on standard clinical magnetic resonance imaging reports. The cohort included 204 previously described comatose patients after cardiac arrest. Clinical outcome was assessed by (1) 3-6 month post-cardiac-arrest cerebral performance category and (2) coma recovery to following commands. Radiological evaluation was obtained from clinical reports and characterized as diffuse, cortex only, deep gray matter structures only, or no anoxic injury. Quantitative analyses of ADC maps were obtained in specific regions of interest (ROIs), whole cortex, and whole brain. A subgroup analysis of 172 was performed after eliminating images with artifacts and preexisting lesions. Radiological assessment outperformed quantitative assessment over all evaluated regions (area under the curve [AUC] 0.80 for radiological interpretation and 0.70 for the occipital region, the best performing ROI, p = 0.011); agreement was substantial for all regions. Radiological assessment still outperformed quantitative analysis in the subgroup analysis, though by smaller margins and with substantial to near-perfect agreement. When assessing for coma recovery only, the difference was no longer significant (AUC 0.83 vs. 0.81 for the occipital region, p = 0.70). Although quantitative analysis eliminates interrater differences in the interpretation of abnormal diffusion imaging and avoids bias from other prediction modalities, clinical radiologist interpretation has a higher predictive value for outcome. Agreement between radiological and quantitative analysis improved when using high-quality scans and when assessing for coma recovery using following commands. Quantitative assessment may thus be more subject to variability in both clinical management and scan quality than radiological assessment.

Nature of aortic annulus: Influence of annulus dynamic on the aortic valve hemodynamics

Accurate imaging reports of the aortic valve indicate that the diameter of the aortic annulus changes regularly during a cardiac cycle. Most of these studies aim to demonstrate the proper method for estimating the aortic annulus diameter before performing TAVR surgery, revealing that the aortic annulus is dynamic and not constant throughout the cardiac cycle. This raises the question of how fixing the aortic annulus might affect valve function, which is a question that still needs to be addressed. Therefore, the present study seeks to address this question and elucidate the dynamic impact of the aortic annulus on aortic valve hemodynamics.Two computational models based on this hypothesis were created and solved, and then their results were compared. Both models are identical, except for the intrinsic dynamic nature of the aortic annulus. One model consists of the dynamic behavior, and the other simulates a fixed annulus, resembling the effect of a TAVR operation, SAVR, or any phenomenon that eliminates the dynamic nature of the annulus.Our research findings indicate that the dynamic nature of the annulus enhances blood flow (+2.7 %), increases mean velocity (+11.9) and kinetic energy density (+34 %), prolongs momentum retention during systole, stabilizes the flow jet at the end of systole, reduces the required pressure to keep the leaflets open (−40.9 % at 0.3s), and sustains ventricular pressure superiority (+9.4 %) over the aorta for a longer duration (+17.7 % of systole), a crucial factor in preventing backflow during aortic valve closure. Based on these results, more attention should be paid to the dynamic nature of the annulus.

MRI features of breast cancer immunophenotypes with a focus on luminal estrogen receptor low positive invasive carcinomas

To compare the magnetic resonance imaging (MRI) features of different immunophenotypes of breast carcinoma of no special type (NST), with special attention to estrogen receptor (ER)-low-positive breast cancer. This retrospective, single-centre, Institutional Review Board (IRB)-approved study included 398 patients with invasive breast carcinoma. Breast carcinomas were classified as ER-low-positive when there was ER staining in 1–10% of tumour cells. Pretreatment MRI was reviewed to assess the tumour imaging features according to the 5th edition of the Breast Imaging Reporting and Data System (BI-RADS) lexicon. Of the 398 cases, 50 (12.6%) were luminal A, 191 (48.0%) were luminal B, 26 (6.5%) were luminal ER-low positive, 64 (16.1%) were HER2-overexpressing, and 67 (16.8%) were triple negative. Correlation analysis between MRI features and tumour immunophenotype showed statistically significant differences in mass shape, margins, internal enhancement and the delayed phase of the kinetic curve. An oval or round shape and rim enhancement were most frequently observed in triple-negative and luminal ER-low-positive tumours. Spiculated margins were most common in luminal A and luminal B tumours. A persistent kinetic curve was more frequent in luminal A tumours, while a washout curve was more common in the triple-negative, HER2-overexpressing and luminal ER-low-positive immunophenotypes. Multinomial regression analysis showed that luminal ER-low-positive tumours had similar results to triple-negative tumours for almost all variables. Luminal ER-low-positive tumours present with similar MRI findings to triple-negative tumours, which suggests that MRI can play a fundamental role in adequate radiopathological correlation and therapeutic planning in these patients.

Rethinking masked image modelling for medical image representation

Masked Image Modelling (MIM), a form of self-supervised learning, has garnered significant success in computer vision by improving image representations using unannotated data. Traditional MIMs typically employ a strategy of random sampling across the image. However, this random masking technique may not be ideally suited for medical imaging, which possesses distinct characteristics divergent from natural images. In medical imaging, particularly in pathology, disease-related features are often exceedingly sparse and localized, while the remaining regions appear normal and undifferentiated. Additionally, medical images frequently accompany reports, directly pinpointing pathological changes’ location. Inspired by this, we propose Masked medical Image Modelling (MedIM), a novel approach, to our knowledge, the first research that employs radiological reports to guide the masking and restore the informative areas of images, encouraging the network to explore the stronger semantic representations from medical images. We introduce two mutual comprehensive masking strategies, knowledge-driven masking (KDM), and sentence-driven masking (SDM). KDM uses Medical Subject Headings (MeSH) words unique to radiology reports to identify symptom clues mapped to MeSH words (e.g., cardiac, edema, vascular, pulmonary) and guide the mask generation. Recognizing that radiological reports often comprise several sentences detailing varied findings, SDM integrates sentence-level information to identify key regions for masking. MedIM reconstructs images informed by this masking from the KDM and SDM modules, promoting a comprehensive and enriched medical image representation. Our extensive experiments on seven downstream tasks covering multi-label/class image classification, pneumothorax segmentation, and medical image–report analysis, demonstrate that MedIM with report-guided masking achieves competitive performance. Our method substantially outperforms ImageNet pre-training, MIM-based pre-training, and medical image–report pre-training counterparts. Codes are available at https://github.com/YtongXie/MedIM.

Evaluation of combined hepatocellular-cholangiocarcinoma using CEUS LI-RADS: correlation with pathological characteristics.

To explore the factors that influence the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) classification of combined hepatocellular-cholangiocarcinoma (cHCC-ICC). Between September 2014 to July 2020, the CEUS features of 58 patients with pathologically confirmed cHCC-ICC were retrospectively evaluated and assigned according to the CEUS LI-RADS (version 2017). The pathological characteristics of nodules categorizing as different CEUS LI-RADS categories were compared. Multivariate logistic regression analysis was conducted to explore potential factors that may influence the CEUS LI-RADS classification of cHCC-ICC. According to CEUS LI-RADS, 32.8% (19/58), 63.8% (37/58), and 3.4% (2/58) were categorized as LR-5, LR-M, and LR-TIV, respectively. There was significant difference between the LR-M and LR-5 groups with regard to the pathological grade, nodule size, and HCC/ICC-component ratio of cHCC-ICC. Multivariate logistic regression analysis identified tumor size and the relative proportions of hepatocellular carcinomas (HCC) and intrahepatic cholangiocarcinomas (ICC) components as the independent influencing factors. Tumor size and the relative proportion of HCC and ICC components within the nodule had a significant impact on the CEUS LI-RADS classification of cHCC-ICC.

Thyroid nodules: diagnosis and management.

Thyroid nodules, with a prevalence of almost 25% in the general population, are a common occurrence. Their prevalence varies considerably depending on demographics such as age and sex as well as the presence of risk factors. This article provides a comprehensive overview of the prevalence, risk stratification and current management strategies for thyroid nodules, with a particular focus on changes in diagnostic and therapeutic protocols that have occurred over the past 10 years. Several sonography-based stratification systems (such as Thyroid Imaging Reporting and Data Systems (TIRADS)) might help to predict the malignancy risk of nodules, potentially eliminating the need for biopsy in many instances. However, large or suspicious nodules necessitate cytological evaluation following fine-needle aspiration biopsy for accurate classification. In the case of cytology yielding indeterminate results, additional tools, such as molecular testing, can assist in guiding the management plan. Surgery is no longer the only treatment for symptomatic or malignant nodules: active surveillance or local ablative treatments might be beneficial for appropriately selected patients. To enhance clinician-patient interactions and discussions about diagnostic options, shared decision-making tools have been developed. A personalized, risk-based protocol promotes high-quality care while minimizing costs and unnecessary testing.

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.