Search

To automate the segmentation of whole liver parenchyma on multi-echo chemical shift encoded (MECSE) MR examinations using convolutional neural networks (CNNs) to seamlessly quantify precise organ-related imaging biomarkers such as the fat fraction and iron load. A retrospective multicenter collection of 183 MECSE liver MR examinations was conducted. An encoder-decoder CNN was trained (107 studies) following a 5-fold cross-validation strategy to improve the model performance and ensure lack of overfitting. Proton density fat fraction (PDFF) and R2* were quantified on both manual and CNN segmentation masks. Different metrics were used to evaluate the CNN performance over both unseen internal (46 studies) and external (29 studies) validation datasets to analyze reproducibility. The internal test showed excellent results for the automatic segmentation with a dice coefficient (DC) of 0.93 ± 0.03 and high correlation between the quantification done with the predicted mask and the manual segmentation (rPDFF = 1 and rR2* = 1; p values < 0.001). The external validation was also excellent with a different vendor but the same magnetic field strength, proving the generalization of the model to other manufacturers with DC of 0.94 ± 0.02. Results were lower for the 1.5-T MR same vendor scanner with DC of 0.87 ± 0.06. Both external validations showed high correlation in the quantification (rPDFF = 1 and rR2* = 1; p values < 0.001). In both internal and external validation datasets, the relative error for the PDFF and R2* quantification was below 4% and 1% respectively. Liver parenchyma can be accurately segmented with CNN in a vendor-neutral virtual approach, allowing to obtain reproducible automatic whole organ virtual biopsies. • Whole liver parenchyma can be automatically segmented using convolutional neural networks. • Deep learning allows the creation of automatic pipelines for the precise quantification of liver-related imaging biomarkers such as PDFF and R2*. • MR “virtual biopsy” can become a fast and automatic procedure for the assessment of chronic diffuse liver diseases in clinical practice.

Resumen Objetivo Comparar la esteatosis pancreatica y hepatica mediante la determinacion de la fraccion de grasa por densidad protonica (FGDP) por resonancia magnetica (RM) en pacientes con enfermedad hepatica cronica. Material y metodos Estudio transversal de 46 pacientes adultos con biopsia hepatica por hepatitis viral cronica (n = 19) o por enfermedad hepatica cronica no alcoholica (EHNA) (n = 27). La biopsia de higado se utilizo como referencia para la gradacion de la esteatosis hepatica. Todos los pacientes se sometieron a valoracion clinica y estudio de RM con una secuencia eco de gradiente codificado por desplazamiento quimico con multiples ecos (MECSE) para la cuantificacion de la FGDP en higado y pancreas. Se utilizo el coeficiente de correlacion de Spearman para calcular el grado de asociacion entre la FGDP hepatica y los grados de esteatosis por biopsia, y entre la FGDP pancreatica y la afectacion hepatica (grados de esteatosis y FGDP). El T-test se realizo para comparar variables continuas/ordinales en los grupos de hepatitis viral cronica y EHNA. Las variables categoricas se evaluaron mediante la prueba de χ. Resultados Se observo una correlacion significativa entre la FGDP hepatica y los grados de esteatosis (Rs = 0,875, p Conclusion El deposito de grasa pancreatica se correlaciona con la esteatosis hepatica en pacientes con EHNA cronica. Esta relacion se pierde en los pacientes con hepatitis viral cronica.

Pneumatosis cystoides intestinalis is an uncommon disease with unknown etiology characterized by the presence of multiple gas-filled cysts within the submucosa or subserosa of the intestinal wall. Pneumoperitoneum and/or intestinal perforation are complications that may be associated with pneumatosis cystoides intestinalis. The patients are often prone to misdiagnosis or mistreatment.We are presenting a case of pneumatosis cystoides intestinalis in a 42 year-old woman affected by peritoneal free air and numerous, diffuse, bubble-like intramural gas collections into the jejunum and ileum, showed in CT-enterography images. The woman had a carcinoid tumor located in jejunum two years ago, treated with enterectomy. Recent complaints of nonspecific symptoms of abdominal discomfort and diarrhea motivated the realization of CT scan, serum chromogranin and urine 5-hidroxindolacetic acid for hypothesis of tumor carcinoid recurrence withdraw. The only change found was the presence of pneumatosis cystoides intestinalis in CT-enterography images without intestinal necrosis, bleeding or evident obstruction. For that reason no surgical procedure was realized and the patient stayed on surveillance. Actually, the patient complaints are sporadic abdominal discomfort, without pneumatosis cystoides intestinalis clinical evidence. Conclusion: The treatment plan of patient with PCI depends on underlying cause and clinical condition severity. When conservative treatment is adopted the clinical evolution of pneumatosis cystoides intestinalis is unpredictable and can even disappear in an indeterminate number of patients. Resumo: A pneumatose cistoide intestinal é uma doença incomum, de etiologia desconhecida, caracterizada pela presença de múltiplos cistos preenchidos com gás na submucosa ou subserosa da parede intestinal. O pneumoperitoneu e/ou a perfuração intestinal são complicações que podem estar associadas à pneumatose cistoide intestinal. Os pacientes geralmente estão sujeitos a erros de diagnóstico ou de tratamento.Apresentamos um caso de pneumatose cistoide intestinal em paciente do sexo feminino, 42 anos de idade, com ar livre peritoneal e numerosas coleções gasosas intramurais, difusas e semelhantes a bolhas no jejuno e íleo, visualizados em imagens de enterografia por tomografia computadorizada (TC). Há dois anos, a paciente teve um tumor carcinoide localizado no jejuno que foi tratado com enterectomia. As queixas recentes de sintomas inespecíficos, desconforto abdominal e diarreia motivaram a realização da TC e exame de cromogranina sérica e ácido 5-hidroxindolacético na urina para excluir a hipótese de recorrência do tumor carcinoide. A única alteração encontrada foi a presença de pneumatose cistoide intestinal em imagens de enterografia por TC sem necrose intestinal, sangramento ou obstrução evidente. Por esse motivo, nenhum procedimento cirúrgico foi realizado, e a paciente permaneceu em observação. Atualmente, a queixa da paciente é de desconforto abdominal esporádico, sem evidência clínica de pneumatose cistoide intestinal. Conclusão: O plano de tratamento de pacientes com PCI depende da causa subjacente e da gravidade da condição clínica. Quando o tratamento conservador é adotado, a evolução clínica da pneumatose cistoide intestinal é imprevisível e pode até desaparecer em alguns pacientes. Keywords: Pneumatosis cystoides intestinalis, Pneumoperitoneum, Bowel dilatation, Intestinal cysts, Extra-luminal gas, Palavras-chave: Pneumatose cistoide intestinal, Pneumoperitoneu, Dilatação intestinal, Cistos intestinais, Gás extraluminal

Abstract Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. Key Points • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

Purpose: This work aims to develop a computer-aided diagnosis (CAD) to quantify the extent of pulmonary involvement (PI) in COVID-19 as well as the radiological patterns referred to as lung opacities in chest computer tomography (CT). Methods: One hundred thirty subjects with COVID-19 pneumonia who underwent chest CT at hospital admission were retrospectively studied (141 sets of CT scan images). Eighty-eight healthy individuals without radiological evidence of acute lung disease served as controls. Two radiologists selected up to four regions of interest (ROI) per patient (totaling 1,475 ROIs) visually regarded as well-aerated regions (472), ground-glass opacity (GGO, 413), crazy paving and linear opacities (CP/LO, 340), and consolidation (250). After balancing with 250 ROIs for each class, the density quantiles (2.5, 25, 50, 75, and 97.5%) of 1,000 ROIs were used to train (700), validate (150), and test (150 ROIs) an artificial neural network (ANN) classifier (60 neurons in a single-hidden-layer architecture). Pulmonary involvement was defined as the sum of GGO, CP/LO, and consolidation volumes divided by total lung volume (TLV), and the cutoff of normality between controls and COVID-19 patients was determined with a receiver operator characteristic (ROC) curve. The severity of pulmonary involvement in COVID-19 patients was also assessed by calculating Z scores relative to the average volume of parenchymal opacities in controls. Thus, COVID-19 cases were classified as mild (

BackgroundCOVID-19 pneumonia extension is assessed by computed tomography (CT) with the ratio between the volume of abnormal pulmonary opacities (PO) and CT-estimated lung volume (CTLV). CT-estimated lung weight (CTLW) also correlates with pneumonia severity. However, both CTLV and CTLW depend on demographic and anthropometric variables.PurposesTo estimate the extent and severity of COVID-19 pneumonia adjusting the volume and weight of abnormal PO to the predicted CTLV (pCTLV) and CTLW (pCTLW), respectively, and to evaluate their possible association with clinical and radiological outcomes.MethodsChest CT from 103 COVID-19 and 86 healthy subjects were examined retrospectively. In controls, predictive equations for estimating pCTLV and pCTLW were assessed. COVID-19 pneumonia extent and severity were then defined as the ratio between the volume and the weight of abnormal PO expressed as a percentage of the pCTLV and pCTLW, respectively. A ROC analysis was used to test differential diagnosis ability of the proposed method in COVID-19 and controls. The degree of pneumonia extent and severity was assessed with Z-scores relative to the average volume and weight of PO in controls. Accordingly, COVID-19 patients were classified as with limited, moderate and diffuse pneumonia extent and as with mild, moderate and severe pneumonia severity.ResultsIn controls, CTLV could be predicted by sex and height (adjusted R2 = 0.57; P < 0.001) while CTLW by age, sex, and height (adjusted R2 = 0.6; P < 0.001). The cutoff of 20% (AUC = 0.91, 95%CI 0.88–0.93) for pneumonia extent and of 50% (AUC = 0.91, 95%CI 0.89–0.92) for pneumonia severity were obtained. Pneumonia extent were better correlated when expressed as a percentage of the pCTLV and pCTLW (r = 0.85, P < 0.001), respectively. COVID-19 patients with diffuse and severe pneumonia at admission presented significantly higher CRP concentration, intra-hospital mortality, ICU stay and ventilatory support necessity, than those with moderate and limited/mild pneumonia. Moreover, pneumonia severity, but not extent, was positively and moderately correlated with age (r = 0.46) and CRP concentration (r = 0.44).ConclusionThe proposed estimation of COVID-19 pneumonia extent and severity might be useful for clinical and radiological patient stratification.

Hepatic iron overload may be found in several disorders, such as hereditary hemochromatosis, secondary hemochromatosis and chronic liver disease. Because hepatic iron concentration is a surrogate of total body iron stores, assessment and quantification of hepatic iron overload is important to select those patients who will benefit from specific treatments and also to accurately monitor the therapy. Over the last decades, MR imaging has become an important tool for evaluating iron overload disorders and for non-invasively quantifying hepatic iron concentration.

Iron overload is a common clinical problem resulting from hereditary hemochromatosis or secondary hemosiderosis (mainly associated with transfusion therapy), being also associated with chronic liver diseases and metabolic disorders. Excess of iron accumulates in organs like the liver, pancreas and heart. Without treatment, patients with iron overload disorders will develop liver cirrhosis, diabetes and cardiomyopathy. Iron quantification is therefore crucial not only for diagnosis of iron overload but also to monitor iron-reducing therapies. Liver iron concentration is considered the surrogate marker of total body iron stores. Because liver biopsy is invasive and prone to high variability and sampling bias, MR imaging has emerged as a non-invasive method and gained wide acceptance, now being considered the standard of care for assessing iron overload. Nevertheless, there are different MR techniques for iron quantification and there is still no consensus about the best technique or postprocessing tool for hepatic iron quantification, with the choice of imaging technique depending mainly on the local expertise as well on the available equipment and software. Because different methods should not be used interchangeably, it is important to choose one method and use the same one when following up patients over time.

Imaging has not only an established role in screening and diagnosis of hepatocellular carcinoma (HCC) in patients with chronic liver inflammatory diseases, but also a crucial importance for patient stratification and treatment allocation, as well as for assessing treatment response. In the setting of increasing therapeutic options for HCC, the Barcelona Clinic Liver Cancer (BCLC) system still remains the most appropriate way to select candidate cohorts for best treatments. This classification takes into account the imaging information on tumor burden and extension, liver function, and cancer-related symptoms, stratifying patients in five risk categories (Stages 0, A, B, C and D) associated with different treatment options. Still now, there are no clear roles for biomarkers use in treatment allocation. The increasing use of locoregional non-surgical therapies in the different stages is highly dependent on reliable evaluation of treatment response, in particular when they are used with curative intention or for downstaging at liver transplantation re-assessment. Moreover, objective response (OR) has emerged as an important imaging biomarker, providing information on tumor biology, which can contribute for further prognostic assessment. Current guidelines for OR assessment recommend only the measurement of viable tumor according to mRECIST criteria, with further classification into complete response, partial response, stable disease or progressive disease. Either computed tomography (CT) or magnetic resonance (MR) imaging can be used for this purpose, and the Liver Imaging Reporting and Data System (LI-RADS) committee has recently provided some guidance for reporting after locoregional therapies. Nevertheless, imaging pitfalls resulting from treatment-related changes can impact with the correct evaluation of treatment response, especially after transarterial radioembolization (TARE). Volume criteria and emerging imaging techniques might also contribute for a better refinement in the assessment of treatment response and monitoring. As the role of imaging deeply expands in the multidisciplinary assessment of HCC, our main objective in this review is to discuss state-of-the-art decision-making aspects for treatment allocation and provide guidance for treatment response evaluation.

Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

Liver MR is a well-established modality with multiparametric capabilities. However, to take advantage of its full capacity, it is mandatory to master the technique and optimize imaging protocols, apply advanced imaging concepts and understand the use of different contrast media. Physiologic artefacts although inherent to upper abdominal studies can be minimized using triggering techniques and new strategies for motion control. For standardization, the liver MR protocol should include motion-resistant T2-w sequences, in-op phase GRE T1 and T2-w fast spin echo sequences with fat suppression. Diffusion-weighted imaging (DWI) is mandatory, especially for detection of sub-centimetre metastases. Contrast-enhanced MR is the cornerstone of liver MR, especially for lesion characterization. Although extracellular agents are the most extensively used contrast agents, hepatobiliary contrast media can provide an extra-layer of functional diagnostic information adding to the diagnostic value of liver MR. The use of high field strength (3T) increases SNR but is more challenging especially concerning artefact control. Quantitative MR belongs to the new and evolving field of radiomics where the use of emerging biomarkers such as perfusion or DWI can derive new information regarding disease detection, prognostication and evaluation of tumour response. This information can overcome some of the limitations of current tests, especially when using vascular disruptive agents for oncologic treatment assessment. MR is, today, a robust, mature, multiparametric imaging modality where clinical applications have greatly expanded from morphology to advanced imaging. This new concept should be acknowledged by all those involved in producing high quality, high-end liver MR studies. info:eu-repo/semantics/publishedVersion

Diffuse liver diseases result from a wide spectrum of etiologies, and, since they can lead to cirrhosis, end-stage liver disease, and hepatocellular carcinoma, they represent an important cause of morbidity, mortality, and healthcare costs worldwide. Regardless of the etiology, liver fat, iron, and combined overload are common pathological features of different diffuse liver diseases. Fat and iron frequently coexist and they act as cofactors in disease progression. Because liver biopsy has several limitations, quantitative imaging biomarkers have been developed for liver fat and iron quantification.

Purpose: The purpose of the study was to evaluate the role of intravoxel incoherent motion (IVIM) diffusion model for the assessment of liver fibrosis and inflammation in diffuse liver disorders, also considering the presence of liver steatosis and iron deposits. Methods: Seventy-four patients were included, with liver biopsy and a 3 Tesla abdominal magnetic resonance imaging examination, with an IVIM diffusion-weighted sequence (single-shot spin-echo echo-planar sequence, with gradient reversal fat suppression; 6 b-values: 0, 50, 200, 400, 600, and 800 s/mm2). Histological evaluation comprised the Ishak modified scale, for grading inflammation and fibrosis, plus steatosis and iron loading classification. The liver apparent diffusion coefficient (ADC) and IVIM parameters (D, D*, f) were calculated from the IVIM images. The relationship between IVIM parameters and histopathological scores were evaluated by ANOVA and Spearman correlation tests. A test-retest experiment assessed reproducibility and repeatability in 10 healthy volunteers and 10 randomly selected patient studies. Results: ADC and f values were lower with higher fibrosis stages (p = 0.009, p = 0.006, respectively) and also with higher necro-inflammatory activity grades (p = 0.02, p = 0.017, respectively). Considered together, only fibrosis presented a significant effect on ADC and f measurements (p < 0.05), whereas inflammation had no significant effect (p > 0.05). A mild correlation was found between ADC and f with fibrosis (R S = -0.32 and R S = -0.38; p < 0.05) and inflammation (R S = -0.31 and R S = -0.32, p < 0.05; respectively). The AUROC for ADC and f measurements with the different dichotomizations between fibrosis or inflammation grades were only fair (0.670 to 0.749, p < 0.05). Neither D nor D* values were significantly different between liver fibrosis or inflammation grades. D measurements were significantly different across histologic grades of steatosis (p < 0.001) and iron overload (p < 0.001), whereas f measurements showed significant differences across histologic steatosis grades (p = 0.005). There was an excellent agreement between the different readers for ADC, f, and D. Conclusions: Although fibrosis presented a significant effect on ADC and f, IVIM measurements are not accurate enough to stage liver fibrosis or necro-inflammatory activity in diffuse liver diseases. D values were influenced by steatosis and iron overload. This work was partially funded by a research Grant from the Teaching and Research Department of Centro Hospitalar do Porto (DEFI:309/12(213-DEFI/251-CES)) and from a Spanish Ministry of Health and Carlos III Health Institute funding grant (PI12/01262). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Anomalous pulmonary venous connection is an uncommon congenital anomaly in which all (total form) or some (partial form) pulmonary veins drain into a systemic vein or into the right atrium rather than into the left atrium.The authors present one case of total anomalous pulmonary venous connection and two cases of partial anomalous pulmonary venous connection, one of supracardiac drainage into the brachiocephalic vein, and the other of infracardiac anomalous venous drainage (scimitar syndrome).Through the presentation of these cases, this article aims to review the main pulmonary venous developmental defects, highlighting the role of imaging techniques in the assessment of these anomalies. Resumo: A conexão anómala das veias pulmonares é uma anomalia congénita rara na qual todas as veias pulmonares (forma total) ou algumas (forma parcial) drenam numa veia sistémica ou na aurícula direita, em vez da aurícula esquerda.Os autores apresentam um caso de conexão anómala total das veias pulmonares e dois casos de retorno anómalo parcial das veias pulmonares, uma drenagem supracardíaca ao nivel da veia braquiocefálica e uma infracardíaca (síndrome da cimitarra).Através da apresentação destes casos, este artigo pretende fazer uma revisão dos principais defeitos do desenvolvimento venoso pulmonar e realçar a importância das técnicas de imagem na avaliação destas anomalias. Keywords: Anomalous pulmonary venous connection, Congenital anomaly, Scimitar syndrome, Palavras-chave: Conexão anómala das veias pulmonares, Anomalia congénita, Síndrome de cimitarra