RESUMO
Aggressive systemic mastocytosis (ASM) is an advanced subtype of systemic mastocytosis characterized by organ involvement. In this article, we report a case with ASM in a 54-year-old woman with characteristic findings on computed tomography (CT) and fluorine-18-fluorodeoxyglucose positron emission tomography (18F-FDG PET)/CT. Contrast-enhanced CT on admission revealed hepatosplenomegaly, generalized osteosclerosis, colonic edema, edematous thickening of the wall in the ascending colon and edema in the surrounding regions of these organs and mesentery, ileus, subcutaneous edema, periportal collar sign, and multiple mesenteric lymphadenopathies. There was no 18F-FDG uptake in the lesions other than mild 18F-FDG uptake in the vertebrae, making the possibility of differential diagnoses such as metastasis, lymphoma, and extramedullary leukemia lower. Based on bone marrow biopsy results and clinical findings, the diagnosis of ASM was established. ASM can be a potentially fatal disease with a poor prognosis, and understanding its distinctive clinical course and imaging findings is crucial for early therapeutic intervention.
RESUMO
PURPOSE: The diagnostic performance of large language artificial intelligence (AI) models when utilizing radiological images has yet to be investigated. We employed Claude 3 Opus (released on March 4, 2024) and Claude 3.5 Sonnet (released on June 21, 2024) to investigate their diagnostic performances in response to the Radiology's Diagnosis Please quiz questions. MATERIALS AND METHODS: In this study, the AI models were tasked with listing the primary diagnosis and two differential diagnoses for 322 quiz questions from Radiology's "Diagnosis Please" cases, which included cases 1 to 322, published from 1998 to 2023. The analyses were performed under the following conditions: (1) Condition 1: submitter-provided clinical history (text) alone. (2) Condition 2: submitter-provided clinical history and imaging findings (text). (3) Condition 3: clinical history (text) and key images (PNG file). We applied McNemar's test to evaluate differences in the correct response rates for the overall accuracy under Conditions 1, 2, and 3 for each model and between the models. RESULTS: The correct diagnosis rates were 58/322 (18.0%) and 69/322 (21.4%), 201/322 (62.4%) and 209/322 (64.9%), and 80/322 (24.8%) and 97/322 (30.1%) for Conditions 1, 2, and 3 for Claude 3 Opus and Claude 3.5 Sonnet, respectively. The models provided the correct answer as a differential diagnosis in up to 26/322 (8.1%) for Opus and 23/322 (7.1%) for Sonnet. Statistically significant differences were observed in the correct response rates among all combinations of Conditions 1, 2, and 3 for each model (p < 0.01). Claude 3.5 Sonnet outperformed in all conditions, but a statistically significant difference was observed only in the comparison for Condition 3 (30.1% vs. 24.8%, p = 0.028). CONCLUSION: Two AI models demonstrated a significantly improved diagnostic performance when inputting both key images and clinical history. The models' ability to identify important differential diagnoses under these conditions was also confirmed.
RESUMO
PURPOSE: Large language models (LLMs) are rapidly advancing and demonstrating high performance in understanding textual information, suggesting potential applications in interpreting patient histories and documented imaging findings. As LLMs continue to improve, their diagnostic abilities are expected to be enhanced further. However, there is a lack of comprehensive comparisons between LLMs from different manufacturers. In this study, we aimed to test the diagnostic performance of the three latest major LLMs (GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro) using Radiology Diagnosis Please Cases, a monthly diagnostic quiz series for radiology experts. MATERIALS AND METHODS: Clinical history and imaging findings, provided textually by the case submitters, were extracted from 324 quiz questions originating from Radiology Diagnosis Please cases published between 1998 and 2023. The top three differential diagnoses were generated by GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro, using their respective application programming interfaces. A comparative analysis of diagnostic performance among these three LLMs was conducted using Cochrane's Q and post hoc McNemar's tests. RESULTS: The respective diagnostic accuracies of GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro for primary diagnosis were 41.0%, 54.0%, and 33.9%, which further improved to 49.4%, 62.0%, and 41.0%, when considering the accuracy of any of the top three differential diagnoses. Significant differences in the diagnostic performance were observed among all pairs of models. CONCLUSION: Claude 3 Opus outperformed GPT-4o and Gemini 1.5 Pro in solving radiology quiz cases. These models appear capable of assisting radiologists when supplied with accurate evaluations and worded descriptions of imaging findings.
RESUMO
Peliosis hepatis (PH) is a rare benign vascular condition characterized by sinusoidal dilatation and the presence of blood-filled spaces within the liver. PH is often clinically asymptomatic and is discovered incidentally. It presents a clinical challenge as its imaging findings frequently mimic other pathologies, including primary or secondary malignancies and abscesses. In this article, we present a case of a 73-year-old woman with a history of recurrent tongue cancer treated by surgery and chemoradiotherapy, and concurrent multiple myeloma, in whom PH was incidentally discovered. Based on computed tomography, magnetic resonance imaging, and 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) imaging findings prior to biopsy, PH was diagnosed, and pathologically confirmed. Follow-up computed tomography five months after the discontinuation of raloxifene hydrochloride, a selective estrogen receptor modulator and a suspected drug causing PH, the regression of PH lesions was observed.
RESUMO
INTRODUCTION: The Amplatzer Vascular Plug (AVP) series enables precise positioning and high migration resistance, allowing embolization in short segments; however, inadequate embolization or recanalization may occasionally occur. We hypothesized that leaks may occur when AVPs are implanted in vessels with irregular lumen due to insufficient adherence to the vessel. This hypothesis was tested by experiments with a vascular model. We employed a coil packing technique between the AVP lobes to embolize internal iliac arteries with an irregular lumen. METHODS: Saline was injected through the Y-shaped glass tubes of the stenotic and the smooth model (without stenotic lesion), and the amount of leakage was measured when the AVP was deployed. The feasibility and effectiveness of filling coils between the lobes of AVP II were evaluated. A total of 11 cases were retrospectively reviewed using this technique for internal iliac artery embolization prior to endovascular aortic repair. RESULTS: The amount of leakage was significantly higher in the presence of stenotic lesions. Insertion of a 2.2 F microcatheter from the side of the proximal lobe of AVP II and filling of coils was achieved in all 11 cases. Follow-up contrast-enhanced CT showed no recanalization, leakage, or other obvious complications. CONCLUSION: Coil packing technique around Amplatzer Vascular Plugs could be an effective method and a reliable option for arterial embolization, especially in vessels with irregular lumens.
RESUMO
RATIONALE AND OBJECTIVES: To determine if super-resolution deep learning reconstruction (SR-DLR) improves the depiction of cranial nerves and interobserver agreement when assessing neurovascular conflict in 3D fast asymmetric spin echo (3D FASE) brain MR images, as compared to deep learning reconstruction (DLR). MATERIALS AND METHODS: This retrospective study involved reconstructing 3D FASE MR images of the brain for 37 patients using SR-DLR and DLR. Three blinded readers conducted qualitative image analyses, evaluating the degree of neurovascular conflict, structure depiction, sharpness, noise, and diagnostic acceptability. Quantitative analyses included measuring edge rise distance (ERD), edge rise slope (ERS), and full width at half maximum (FWHM) using the signal intensity profile along a linear region of interest across the center of the basilar artery. RESULTS: Interobserver agreement on the degree of neurovascular conflict of the facial nerve was generally higher with SR-DLR (0.429-0.923) compared to DLR (0.175-0.689). SR-DLR exhibited increased subjective image noise compared to DLR (p ≥ 0.008). However, all three readers found SR-DLR significantly superior in terms of sharpness (p < 0.001); cranial nerve depiction, particularly of facial and acoustic nerves, as well as the osseous spiral lamina (p < 0.001); and diagnostic acceptability (p ≤ 0.002). The FWHM (mm)/ERD (mm)/ERS (mm-1) for SR-DLR and DLR was 3.1-4.3/0.9-1.1/8795.5-10,703.5 and 3.3-4.8/1.4-2.1/5157.9-7705.8, respectively, with SR-DLR's image sharpness being significantly superior (p ≤ 0.001). CONCLUSION: SR-DLR enhances image sharpness, leading to improved cranial nerve depiction and a tendency for greater interobserver agreement regarding facial nerve neurovascular conflict.
RESUMO
Germinomas frequently cause hydrocephalus, and ventriculoperitoneal shunts (VPS) have been commonly used for their management. Although VPS can potentially serve as a route for peritoneal dissemination of germinomas, the abdominal imaging characteristics of this rare yet important complication remain unknown. In this article, we report the computed tomography imaging findings of diffuse peritoneal dissemination of intracranial germinoma.
RESUMO
Cytokines are small secreted proteins that have specific effects on cellular interactions and are crucial for functioning of the immune system. Cytokines are involved in almost all diseases, but as microscopic chemical compounds they cannot be visualized at imaging for obvious reasons. Several imaging manifestations have been well recognized owing to the development of cytokine therapies such as those with bevacizumab (antibody against vascular endothelial growth factor) and chimeric antigen receptor (CAR) T cells and the establishment of new disease concepts such as interferonopathy and cytokine release syndrome. For example, immune effector cell-associated neurotoxicity is the second most common form of toxicity after CAR T-cell therapy toxicity, and imaging is recommended to evaluate the severity. The emergence of COVID-19, which causes a cytokine storm, has profoundly impacted neuroimaging. The central nervous system is one of the systems that is most susceptible to cytokine storms, which are induced by the positive feedback of inflammatory cytokines. Cytokine storms cause several neurologic complications, including acute infarction, acute leukoencephalopathy, and catastrophic hemorrhage, leading to devastating neurologic outcomes. Imaging can be used to detect these abnormalities and describe their severity, and it may help distinguish mimics such as metabolic encephalopathy and cerebrovascular disease. Familiarity with the neuroimaging abnormalities caused by cytokine storms is beneficial for diagnosing such diseases and subsequently planning and initiating early treatment strategies. The authors outline the neuroimaging features of cytokine-related diseases, focusing on cytokine storms, neuroinflammatory and neurodegenerative diseases, cytokine-related tumors, and cytokine-related therapies, and describe an approach to diagnosing cytokine-related disease processes and their differentials. ©RSNA, 2024 Supplemental material is available for this article.
Assuntos
Síndrome da Liberação de Citocina , Neuroimagem , Humanos , COVID-19/diagnóstico por imagem , Síndrome da Liberação de Citocina/diagnóstico por imagem , Síndrome da Liberação de Citocina/etiologia , Citocinas , SARS-CoV-2RESUMO
This systematic review article aims to investigate the clinical and radiological imaging characteristics of adrenal abnormalities in patients with thrombocytopenia, anasarca, fever, reticulin fibrosis, renal dysfunction, and organomegaly (TAFRO) syndrome. We searched the literature in PubMed, the Cochrane Library, and the Web of Science Core Collection. Ultimately, we analyzed 11 studies with 22 patients plus our 1 patient, totaling 23 patients. The mean age was 47.0 ± 12.6 years. There were 20 male and 3 female patients, respectively. The histopathological analysis of lymph nodes was conducted in 15 patients (65.2%), and the diagnosis was consistent with TAFRO syndrome in all 15 patients. Among the 23 patients, 11 patients (18 adrenal glands) showed adrenal ischemia/infarction, 9 patients (13 adrenal glands) showed adrenal hemorrhage, and 4 patients (7 adrenal glands) showed adrenomegaly without evidence of concurrent ischemia/infarction or hemorrhage. One patient demonstrated unilateral adrenal hemorrhage and contralateral adrenomegaly. In patients with adrenal ischemia/infarction, the adrenal glands displayed poor enhancement through contrast-enhanced computed tomography (CT). In patients with adrenal hemorrhage, the adrenal glands revealed high attenuation through non-enhanced CT and hematoma through magnetic resonance imaging. Adrenomegaly, with or without adrenal ischemia/infarction or hemorrhage, was observed in all patients (23/23, 100%). The subsequent calcification of the affected adrenal glands was frequently observed (9/14, 64.3%) when a follow-up CT was performed. Abdominal pain was frequent (15/23, 65.2%), all of which occurred after the disease's onset, suggesting the importance of considering TAFRO syndrome as a cause of acute abdomen. Given the absence of evidence of adrenal abnormalities in non-TAFRO-idiopathic multicentric Castleman disease (iMCD), they may serve as diagnostic clues for differentiating TAFRO syndrome from non-TAFRO-iMCD.
RESUMO
PURPOSE: We investigated whether the quality of high-resolution computed tomography (CT) images of the temporal bone improves with deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (HIR). METHODS: This retrospective study enrolled 36 patients (15 men, 21 women; age, 53.9 ± 19.5 years) who had undergone high-resolution CT of the temporal bone. Axial and coronal images were reconstructed using DLR, HIR, and filtered back projection (FBP). In qualitative image analyses, two radiologists independently compared the DLR and HIR images with FBP in terms of depiction of structures, image noise, and overall quality, using a 5-point scale (5 = better than FBP, 1 = poorer than FBP) to evaluate image quality. The other two radiologists placed regions of interest on the tympanic cavity and measured the standard deviation of CT attenuation (i.e., quantitative image noise). Scores from the qualitative and quantitative analyses of the DLR and HIR images were compared using, respectively, the Wilcoxon signed-rank test and the paired t-test. RESULTS: Qualitative and quantitative image noise was significantly reduced in DLR images compared with HIR images (all comparisons, p ≤ 0.016). Depiction of the otic capsule, auditory ossicles, and tympanic membrane was significantly improved in DLR images compared with HIR images (both readers, p ≤ 0.003). Overall image quality was significantly superior in DLR images compared with HIR images (both readers, p < 0.001). CONCLUSION: Compared with HIR, DLR provided significantly better-quality high-resolution CT images of the temporal bone.
Assuntos
Aprendizado Profundo , Interpretação de Imagem Radiográfica Assistida por Computador , Osso Temporal , Tomografia Computadorizada por Raios X , Humanos , Feminino , Masculino , Osso Temporal/diagnóstico por imagem , Pessoa de Meia-Idade , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Adulto , IdosoRESUMO
Chronic lung allograft dysfunction (CLAD) continues to be the leading cause of death in the long term after lung transplantation (LTx). CLAD has the following two main subtypes: bronchiolitis obliterans syndrome (BOS) and restrictive allograft syndrome (RAS). BOS features obstructive lung dysfunction, while RAS features restrictive lung dysfunction. Overall, RAS has a worse prognosis. The pathophysiology of CLAD is not fully understood; however, pulmonary infections can trigger CLAD, including coronavirus disease 2019 (COVID-19) pneumonia. Here, we describe a case of a 55-year-old female who received LTx about seven years ago and developed RAS after COVID-19 pneumonia. RAS was ultimately diagnosed based on the clinical course and imaging findings. Steroid pulse therapy and empirical antimicrobial therapy were initiated, but respiratory failure progressed, and the patient died 139 days after COVID-19 diagnosis, and 83 days after dyspnea progression. Clinicians should be aware of unusual stair-step clinical courses and imaging features in a given setting of pulmonary infection including COVID-19 to suspect CLAD in lung transplant patients.
RESUMO
BACKGROUND: Radiological differentiation between extra-nodal lymphoma and squamous cell carcinoma in the head and neck is often difficult due to their similarities. PURPOSE: To evaluate the diagnostic benefit of apparent diffusion coefficient (ADC) calculated from diffusion-weighted imaging (DWI) in differentiating the two. MATERIAL AND METHODS: A systematic review was performed by searching the MEDLINE, Scopus, and Embase databases in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement. Forest plots and the pooled mean difference of ADC values were calculated to describe the relationship between extra-nodal lymphoma and squamous cell carcinoma in the head and neck. Heterogeneity among studies was evaluated using the Cochrane Q test and I2 statistic. RESULTS: The review identified eight studies with 440 patients (441 lesions) eligible for meta-analysis. Among all studies, the mean ADC values of squamous cell carcinoma was 0.88 × 10-3mm2/s and that of lymphoma was 0.64 × 10-3mm2/s. In the meta-analysis, the ADC value of lymphoma was significantly lower than that of squamous cell carcinoma (pooled mean difference = 0.235, 95% confidence interval [CI] = 0.168-0.302, P <0.0001). The Cochrane Q test (chi-square = 55.7, P <0.0001) and I2 statistic (I2 = 87.4%, 95% CI = 77.4-93.0%) revealed significant heterogeneity. CONCLUSION: This study highlights the value of quantitative assessment of ADC for objective and reliable differentiation between extra-nodal lymphoma and squamous cell carcinoma in the head and neck. Conclusions should be interpreted with caution due to heterogeneity in the study data.
Assuntos
Imagem de Difusão por Ressonância Magnética , Neoplasias de Cabeça e Pescoço , Linfoma , Humanos , Imagem de Difusão por Ressonância Magnética/métodos , Linfoma/diagnóstico por imagem , Diagnóstico Diferencial , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Carcinoma de Células Escamosas de Cabeça e Pescoço/diagnóstico por imagemRESUMO
OBJECTIVE: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. METHODS: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. RESULTS: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. CONCLUSION: Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.
Assuntos
Inteligência Artificial , Imageamento por Ressonância Magnética , Redes Neurais de Computação , Sarcoma , Neoplasias Uterinas , Humanos , Feminino , Imageamento por Ressonância Magnética/métodos , Neoplasias Uterinas/diagnóstico por imagem , Neoplasias Uterinas/patologia , Sarcoma/diagnóstico por imagem , Sarcoma/patologia , Pessoa de Meia-Idade , Adulto , Sensibilidade e EspecificidadeRESUMO
Beta frequency oscillations originating from the primary motor cortex increase in amplitude following the initiation of voluntary movement, a process termed beta rebound. The strength of beta rebound has been reported to predict the recovery of motor function following stroke, suggesting therapeutic applications of beta rebound modulation. The present study examined the effect of 20 Hz transcranial alternating current stimulation (tACS) on the beta rebound induced by self-paced voluntary movement. Electroencephalograms (EEGs) and electromyograms (EMGs) were recorded from 16 healthy adults during voluntary movements performed before and after active or sham tACS. There was no significant change in average beta rebound after active tACS. However, the beta rebound amplitude was significantly enhanced in a subset of participants, and the magnitude of the increase across all participants was negatively correlated with the difference between individual peak beta frequency and tACS frequency. Thus, matching the stimulus frequency of tACS with individual beta frequency may facilitate therapeutic enhancement for motor rehabilitation.
RESUMO
PURPOSE: To comprehensively summarize the clinical data and CT/MRI characteristics of thyroid-like low-grade nasopharyngeal papillary adenocarcinoma (TL-LGNPPA). METHODS: Twenty-seven lesions from 25 study articles identified through a systematic review and three lesions from our institution associated with TL-LGNPPA were evaluated. RESULTS: The mean age of the patients at diagnosis was 35.7 years, and the male-to-female ratio was nearly half. The chief complaint was nasal obstruction, followed by epistaxis. All patients underwent excision. None of the patients had neck nodes or distant metastases. All patients survived with no locoregional/distant recurrence during 3-93 months of follow-up. All lesions were located at the posterior edge of the nasal septum, attached to the nasopharyngeal parietal wall, and showed no laterality. The mean lesion diameter was 1.7 cm. The margins of lesions were well-defined and lobulated, followed by well-defined smooth margins. None of lesions were associated with parapharyngeal space or skull base destruction. All lesions were iso- and low-density on non-contrast CT. Adjacent skull base sclerosis was detected in 63.6% of lesions. High signal intensity on T2-weighted imaging and mostly iso-signal intensity on T1-weighted imaging compared to muscle tissue. Most lesions were heterogeneous and exhibited moderate contrast enhancement. Relatively large lesions (≥1.4 cm) tended to be more lobulated than smooth margins compared to relatively small lesions (<1.4 cm) (p = 0.016). CONCLUSION: We summarized the clinical and radiological features of TL-LGNPPA to facilitate accurate diagnosis and appropriate management.