RESUMEN
PURPOSE: To systematically review the use of artificial intelligence (AI) in musculoskeletal (MSK) ultrasound (US) with an emphasis on AI algorithm categories and validation strategies. MATERIAL AND METHODS: An electronic literature search was conducted for articles published up to January 2024. Inclusion criteria were the use of AI in MSK US, involvement of humans, English language, and ethics committee approval. RESULTS: Out of 269 identified papers, 16 studies published between 2020 and 2023 were included. The research was aimed at predicting diagnosis and/or segmentation in a total of 11 (69%) out of 16 studies. A total of 11 (69%) studies used deep learning (DL)-based algorithms, three (19%) studies employed conventional machine learning (ML)-based algorithms, and two (12%) studies employed both conventional ML- and DL-based algorithms. Six (38%) studies used cross-validation techniques with K-fold cross-validation being the most frequently employed (n = 4, 25%). Clinical validation with separate internal test datasets was reported in nine (56%) papers. No external clinical validation was reported. CONCLUSION: AI is a topic of increasing interest in MSK US research. In future studies, attention should be paid to the use of validation strategies, particularly regarding independent clinical validation performed on external datasets.
RESUMEN
Pulmonary vasculitis identifies a heterogeneous group of diseases characterized by inflammation, damage and necrosis of the wall of pulmonary vessels. The most common approach to classify vasculitis is according to etiology, therefore dividing them into primary and secondary, with a further sub-classification of primary vasculitis based on the size of the affected vessels (large, medium, and small). Pulmonary involvement is frequently observed in patients with systemic vasculitis and radiological presentation is not pathognomonic, but may vary between diseases. The main findings using high-resolution computed tomography (HRCT) include small vessel wall thickening, nodular lesions, cavitary lesions, reticular opacities, ground-glass opacities (GGO), consolidations, interlobular septal thickening, tracheobronchial stenosis, and aneurysmal dilatation of pulmonary arteries, with or without pleural effusion. Radiological diagnosis alone is difficult since signs and symptoms of lung vessel involvement are often non-specific and might overlap with other conditions such as infections, connective tissue diseases and neoplasms. Therefore, the aim of this review is to describe the most common radiological features of lung involvement in pulmonary vasculitis so that, alongside detailed clinical history and laboratory tests, a prompt diagnosis can be performed.
RESUMEN
Broncho-alveolar lavage (BAL) is indicated in cases of uncertain diagnosis but high suspicion of Sars-Cov-2 infection allowing to collect material for microbiological culture to define the presence of coinfection or super-infection. This prospective study investigated the correlation between chest computed tomography (CT) findings, Covid-19 Reporting and Data System score, and clinical outcomes in Coronavirus disease 2019 (Covid-19) patients who underwent BAL with the aim of predicting outcomes such as lung coinfection, respiratory failure, and hospitalization length based on chest CT abnormalities. Study population included 34 patients (range 38-90 years old; 20 males, 14 females) with a positive nucleic acid amplification test for Covid-19 infection, suitable BAL examination, and good quality chest CT scan in the absence of lung cancer history. Pulmonary coinfections were found in 20.6% of patients, predominantly caused by bacteria. Specific correlations were found between right middle lobe involvement and pulmonary co-infections. Severe lung injury (PaO2/FiO2 ratio of 100-200) was associated with substantial involvement of right middle, right upper, and left lower lobes. No significant correlation was found between chest CT findings and inflammatory markers (C-reactive protein, procalcitonin) or hospitalization length of stay. Specific chest CT patterns, especially in right middle lobe, could serve as indicators for the presence of co-infections and disease severity in noncritically ill Covid-19 patients, aiding clinicians in timely interventions and personalized treatment strategies.
Asunto(s)
COVID-19 , Tomografía Computarizada por Rayos X , Humanos , COVID-19/complicaciones , COVID-19/diagnóstico por imagen , Masculino , Femenino , Persona de Mediana Edad , Anciano , Adulto , Tomografía Computarizada por Rayos X/métodos , Anciano de 80 o más Años , Estudios Prospectivos , Lavado Broncoalveolar/métodos , SARS-CoV-2 , Coinfección , Pulmón/diagnóstico por imagen , Unidades de Cuidados Intensivos/estadística & datos numéricosRESUMEN
Artificial intelligence (AI) has demonstrated great potential in a wide variety of applications in interventional radiology (IR). Support for decision-making and outcome prediction, new functions and improvements in fluoroscopy, ultrasound, computed tomography, and magnetic resonance imaging, specifically in the field of IR, have all been investigated. Furthermore, AI represents a significant boost for fusion imaging and simulated reality, robotics, touchless software interactions, and virtual biopsy. The procedural nature, heterogeneity, and lack of standardisation slow down the process of adoption of AI in IR. Research in AI is in its early stages as current literature is based on pilot or proof of concept studies. The full range of possibilities is yet to be explored.Relevance statement Exploring AI's transformative potential, this article assesses its current applications and challenges in IR, offering insights into decision support and outcome prediction, imaging enhancements, robotics, and touchless interactions, shaping the future of patient care.Key points⢠AI adoption in IR is more complex compared to diagnostic radiology.⢠Current literature about AI in IR is in its early stages.⢠AI has the potential to revolutionise every aspect of IR.
Asunto(s)
Inteligencia Artificial , Radiología Intervencionista , Humanos , Radiología Intervencionista/métodosRESUMEN
Segmentation and image intensity discretization impact on radiomics workflow. The aim of this study is to investigate the influence of interobserver segmentation variability and intensity discretization methods on the reproducibility of MRI-based radiomic features in lipoma and atypical lipomatous tumor (ALT). Thirty patients with lipoma or ALT were retrospectively included. Three readers independently performed manual contour-focused segmentation on T1-weighted and T2-weighted sequences, including the whole tumor volume. Additionally, a marginal erosion was applied to segmentations to evaluate its influence on feature reproducibility. After image pre-processing, with included intensity discretization employing both fixed bin number and width approaches, 1106 radiomic features were extracted from each sequence. Intraclass correlation coefficient (ICC) 95% confidence interval lower bound ≥ 0.75 defined feature stability. In contour-focused vs. margin shrinkage segmentation, the rates of stable features extracted from T1-weighted and T2-weighted images ranged from 92.68 to 95.21% vs. 90.69 to 95.66% after fixed bin number discretization and from 95.75 to 97.65% vs. 95.39 to 96.47% after fixed bin width discretization, respectively, with no difference between the two segmentation approaches (p ≥ 0.175). Higher stable feature rates and higher feature ICC values were found when implementing discretization with fixed bin width compared to fixed bin number, regardless of the segmentation approach (p < 0.001). In conclusion, MRI radiomic features of lipoma and ALT are reproducible regardless of the segmentation approach and intensity discretization method, although a certain degree of interobserver variability highlights the need for a preliminary reliability analysis in future studies.
Asunto(s)
Lipoma , Imagen por Resonancia Magnética , Variaciones Dependientes del Observador , Humanos , Lipoma/diagnóstico por imagen , Lipoma/patología , Imagen por Resonancia Magnética/métodos , Femenino , Masculino , Reproducibilidad de los Resultados , Persona de Mediana Edad , Estudios Retrospectivos , Anciano , Adulto , Procesamiento de Imagen Asistido por Computador/métodos , RadiómicaRESUMEN
BACKGROUND: COVID-19 is a pandemic disease affecting predominantly the respiratory apparatus with clinical manifestations ranging from asymptomatic to respiratory failure. Chest CT is a crucial tool in diagnosing and evaluating the severity of pulmonary involvement through dedicated scoring systems. Nonetheless, many questions regarding the relationship of radiologic and clinical features of the disease have emerged in multidisciplinary meetings. The aim of this retrospective study was to explore such relationship throughout an innovative and alternative approach. MATERIALS AND METHODS: This study included 550 patients (range 25-98 years; 354 males, mean age 66.1; 196 females, mean age 70.9) hospitalized for COVID-19 with available radiological and clinical data between 1 March 2021 and 30 April 2022. Radiological data included CO-RADS, chest CT score, dominant pattern, and typical/atypical findings detected on CT examinations. Clinical data included clinical score and outcome. The relationship between such features was investigated through the development of the main four frequently asked questions summarizing the many issues arisen in multidisciplinary meetings, as follows 1) CO-RADS, chest CT score, clinical score, and outcomes; 2) the involvement of a specific lung lobe and outcomes; 3) dominant pattern/distribution and severity score for the same chest CT score; 4) additional factors and outcomes. RESULTS: 1) If CT was suggestive for COVID, a strong correlation between CT/clinical score and prognosis was found; 2) Middle lobe CT involvement was an unfavorable prognostic criterion; 3) If CT score < 50%, the pattern was not influential, whereas if CT score > 50%, crazy paving as dominant pattern leaded to a 15% increased death rate, stacked up against other patterns, thus almost doubling it; 4) Additional factors usually did not matter, but lymph-nodes and pleural effusion worsened prognosis. CONCLUSIONS: This study outlined those radiological features of COVID-19 most relevant towards disease severity and outcome with an innovative approach.
Asunto(s)
COVID-19 , Masculino , Femenino , Humanos , Anciano , COVID-19/diagnóstico por imagen , SARS-CoV-2 , Estudios Retrospectivos , Pulmón/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodosRESUMEN
Hepatocellular carcinoma (HCC) is the most common liver cancer and is one of the uppermost 2 causes of cancer death. About 70%-90% of HCCs develop within a cirrhotic liver. According to the most recent guidelines, the imaging characteristics of HCC on contrast-enhanced Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) are generally satisfactory to make a diagnosis. Recently, new advanced techniques such as contrast-enhanced ultrasound, CT perfusion, Dynamic Contrast-enhanced MRI, diffusion weighted imaging and radiomics have increased the diagnostic accuracy and characterization of HCC. This review illustrates the state of the art and recent advances in non-invasive imaging evaluation of HCC.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Neoplasias Hepáticas/diagnóstico por imagen , Medios de Contraste , Imagen por Resonancia Magnética/métodos , Sensibilidad y EspecificidadRESUMEN
Lymphoproliferative lung diseases are a heterogeneous group of disorders characterized by primary or secondary involvement of the lung. Primary pulmonary lymphomas are the most common type, representing 0.5-1% of all primary malignancies of the lung. The radiological presentation is often heterogeneous and non-specific: consolidations, masses, and nodules are the most common findings, followed by ground-glass opacities and interstitial involvement, more common in secondary lung lymphomas. These findings usually show a prevalent perilymphatic spread along bronchovascular bundles, without a prevalence in the upper or lower lung lobes. An ancillary sign, such as a "halo sign", "reverse halo sign", air bronchogram, or CT angiogram sign, may be present and can help rule out a differential diagnosis. Since a wide spectrum of pulmonary parenchymal diseases may mimic lymphoma, a correct clinical evaluation and a multidisciplinary approach are mandatory. In this sense, despite High-Resolution Computer Tomography (HRCT) representing the gold standard, a tissue sample is needed for a certain and definitive diagnosis. Cryobiopsy is a relatively new technique that permits the obtaining of a larger amount of tissue without significant artifacts, and is less invasive and more precise than surgical biopsy.
RESUMEN
.
RESUMEN
Behcet's disease (BD) is a chronic systemic inflammatory disorder characterized by underlying chronic vasculitis of both large- and small-caliber vessels. Thoracic involvement in BD can occur with various types of manifestations, which can be detected with contrast-enhanced MSCT scanning. In addition, MR can be useful in diagnosis. Characteristic features are aneurysms of the pulmonary arteries that can cause severe hemoptysis and SVC thrombosis that manifests as SVC syndrome. Other manifestations are aortic and bronchial artery aneurysms, alveolar hemorrhage, pulmonary infarction, and rarely pleural effusion. Achieving the right diagnosis of these manifestations is important for setting the correct therapy and improving the patient's outcome.
RESUMEN
Clinico-radiological presentation of granulomatous prostatitis (GP) is quite similar to cancer, and differential diagnosis can be very challenging. The study aims to highlight GP features based on clinical findings and multiparametric magnetic resonance imaging (mpMRI) characteristics. We retrospectively reviewed eleven patients from a cohort undergoing targeted biopsy between August 2019 and August 2021. Retrospective data including serum prostate-specific antigen (PSA) levels, PSA density and mpMRI findings were collected. Histopathology revealed seven cases of non-specific GP and four cases of specific GP as a result of intravesical Bacillus Calmette-Guérin (BCG) instillation. All lesions showed low signal intensity in T2w images, restricted diffusivity with hyperintensity in Diffusion-Weighted Imaging (DWI) and low Apparent Diffusion Coefficient (ADC) values. In Dynamic Contrast-Enhanced (DCE) imaging, the enhancement was high-peak and persistent in the majority of cases, especially in BCG-GPs. Moreover, almost all those latter lesions showed avascular core and peripheral rim enhancement. All areas identified on mpMRI were assessed with high to very high suspicion to hold prostate cancer (PIRADS v2.1 scores 4-5). Despite recent advances in imaging modalities and serological investigations, it is currently still a challenge to identify granulomatous prostatitis. Histopathology remains the gold standard in disease diagnosis. However, a differential diagnosis should be considered in patients with prior treatment with BCG.
RESUMEN
Computed Tomography Pulmonary Angiography (CTPA) is considered the gold standard diagnostic technique in patients with suspected acute pulmonary embolism in emergency departments. Several studies have been conducted on the predictive value of CTPA on the outcomes of pulmonary embolism (PE). The purpose of this article is to provide an updated review of the literature reporting imaging parameters and quantitative CT scores to predict the severity of PE.
Asunto(s)
Embolia Pulmonar , Humanos , Angiografía , Angiografía por Tomografía Computarizada/métodos , Pronóstico , Embolia Pulmonar/diagnóstico por imagen , Tomografía Computarizada por Rayos XRESUMEN
Non-neoplastic lesions of central airways are uncommon entities with different etiologies, with either focal or diffuse involvement of the tracheobronchial tree. Clinical symptoms of non-neoplastic tracheobronchial diseases are non-specific, and diagnosis is difficult, especially in the early stages. Three-dimensional computed tomography (3D-CT) is an evaluable tool as it allows to assess and characterize tracheobronchial wall lesions and meanwhile it enables the evaluation of airways surrounding structures. Multiplanar reconstructions (MPR), minimum intensity projections (MinIP), and 3D Volume Rendering (VR) (in particular, virtual bronchoscopy) also provide information on the site and of the length of airway alterations. This review will be discussed about (1) primary airway disorders, such as relapsing polychondritis, tracheobronchophathia osteochondroplastica, and tracheobronchomegaly, (2) airway diseases, related to granulomatosis with polyangiitis, Chron's disease, Behcet's disease, sarcoidosis, amyloidosis, infections, intubation and transplantation, (3) tracheobronchial malacia, and (4) acute tracheobronchial injury. 3D-CT findings, especially with MPR and 3D VR reconstructions, allows us to evaluate tracheobronchial disease morphologically in detail.
Asunto(s)
Enfermedades Bronquiales , Enfermedades de la Tráquea , Bronquios , Enfermedades Bronquiales/diagnóstico por imagen , Broncoscopía , Humanos , Tomografía Computarizada por Rayos X , Tráquea , Enfermedades de la Tráquea/diagnóstico por imagenRESUMEN
Chest pain is a symptom that can be found in life-threatening conditions such as acute coronary syndrome (ACS). Those patients requiring invasive coronary angiography treatment or surgery should be identified. Often the clinical setting and laboratory tests are not sufficient to rule out a coronary or aortic syndrome. Cardiac radiological imaging has evolved in recent years both in magnetic resonance (MR) and in computed tomography (CT). CT, in particular, due to its temporal and spatial resolution, the quickness of the examination, and the availability of scanners, is suitable for the evaluation of these patients. In particular, the latest-generation CT scanners allow the exclusion of diagnoses such as coronary artery disease and aortic pathology, thereby reducing the patient's stay in hospital and safely selecting patients by distinguishing those who do not need further treatment from those who will need more- or less-invasive therapies. CT additionally reduces costs by improving long-term patient outcome. The limitations related to patient characteristics and those related to radiation exposure are weakening with the improvement of CT technology.
Asunto(s)
Síndrome Coronario Agudo , Enfermedad de la Arteria Coronaria , Síndrome Coronario Agudo/diagnóstico por imagen , Dolor en el Pecho/etiología , Angiografía Coronaria , Servicio de Urgencia en Hospital , Humanos , RadiólogosRESUMEN
Thoracic imaging is fundamental in the diagnostic route of Coronavirus disease 2019 (COVID-19) especially in patients admitted to hospitals. In particular, chest computed tomography (CT) has a key role in identifying the typical features of the infection. Ground-glass opacities (GGO) are one of the main CT findings, but their presence is not specific for this viral pneumonia. In fact, GGO is a radiological sign of different pathologies with both acute and subacute/chronic clinical manifestations. In the evaluation of a subject with focal or diffuse GGO, the radiologist has to know the patient's medical history to obtain a valid diagnostic hypothesis. The authors describe the various CT appearance of GGO, related to the onset of symptoms, focusing also on the ancillary signs that can help radiologist to obtain a correct and prompt diagnosis.