RESUMO
OBJECTIVES: We sought to identify the impact of transcatheter aortic valve implantation (TAVI) on changes of fractional flow reserve computed tomography (FFRCT) values and the associated clinical impact. METHODS: A retrospective analysis was done with CT obtained pre-TAVI, prior to hospital discharge and at 1-year follow-up, which provided imaging sources for the calculation of FFRCT values based on an online platform. RESULTS: A total of 190 patients were enrolled. Patients with pre-procedural FFRCT value > 0.80 (i.e., negative) and ≤ 0.80 (i.e., positive) demonstrated a significantly opposite change in the value after TAVI (0.8798 vs. 0.8718, p < 0.001 and 0.7634 vs. 0.8222, p < 0.001, respectively). The history of coronary artery disease (CAD) was identified as an independent predictor for FFRCT changing from negative to positive after TAVI (odds ratio [OR] 2.927, 95% confidence interval [CI] 1.130-7.587, p = 0.027), with lesions more severely stenosed (OR 1.039, 95% CI 1.003-1.076, p = 0.034) and in left anterior descending coronary artery (LAD) (OR 3.939, 95% CI 1.060-14.637, p = 0.041) being prone to change. CONCLUSIONS: TAVI directly brings improvement in FFRCT values in patients with compromised coronary flow. Patients with a history of CAD, especially with lesions more severely stenosed and in LAD, were under risk of FFRCT changing from negative to positive after TAVI. KEY POINTS: â¢The effect of TAVI on coronary hemodynamics might be influenced by different ischemic severity and coronary territories reflected by FFRCT values. â¢As different FFRCT variations did not impact outcomes of TAVI patients, AS, but not coronary issues, may be the primary problem to affect, which needs further validation.
Assuntos
Doença da Artéria Coronariana , Estenose Coronária , Reserva Fracionada de Fluxo Miocárdico , Substituição da Valva Aórtica Transcateter , Angiografia por Tomografia Computadorizada , Angiografia Coronária , Doença da Artéria Coronariana/diagnóstico por imagem , Doença da Artéria Coronariana/cirurgia , Vasos Coronários/diagnóstico por imagem , Hemodinâmica , Humanos , Valor Preditivo dos Testes , Estudos Retrospectivos , Índice de Gravidade de Doença , Tomografia Computadorizada por Raios XRESUMO
Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.
Assuntos
Inteligência Artificial , Betacoronavirus , Infecções por Coronavirus/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Adulto , Idoso , COVID-19 , Teste para COVID-19 , Técnicas de Laboratório Clínico/métodos , Infecções Comunitárias Adquiridas/diagnóstico por imagem , Infecções por Coronavirus/diagnóstico , Aprendizado Profundo , Diagnóstico Diferencial , Feminino , Humanos , Imageamento Tridimensional/métodos , Masculino , Pessoa de Meia-Idade , Pandemias , Curva ROC , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Estudos Retrospectivos , SARS-CoV-2 , Sensibilidade e Especificidade , Tomografia Computadorizada por Raios X/métodosRESUMO
BACKGROUND: We aimed to compare the performance of FFRCT and FFRQCA in assessing the functional significance of coronary artery stenosis in patients suffering from coronary artery disease with stable angina. METHOD: A total of 101 stable coronary heart disease (CAD) patients with 181 lesions were recruited. FFRCT and FFRQCA were compared using invasive fractional flow reserve (FFR) as a reference standard. Comparisons between FFRCT and FFRQCA were conducted based on strategies of the geometric reconstruction, boundary conditions, and geometric characteristics. The performance of FFRCT and FFRQCA in detecting hemodynamic significance was also investigated. RESULTS: The performance of FFRCT and FFRQCA in discriminating hemodynamically significant lesions was compared. Good correlation and agreement with invasive FFR was found using FFRCT and FFRQCA (r = 0.809, p < 0.001 and r = 0.755, p < 0.001). A significant difference was observed in the complex coronary artery tree, in which relatively better prediction was observed using FFRCT than FFRQCA when analyzing the stenosis distributed in the middle segment of a stenotic branch (p = 0.036). Moreover, FFRCT was found to be better at predicting hemodynamically insignificant stenosis than FFRQCA (p = 0.007), while the performance of the two parameters was similar in discriminating functional significant lesions using an FFR threshold of ≤ 0.8 as a reference standard. CONCLUSION: FFRCT and FFRQCA could both accurately rule out functional insignificant lesions in stable CAD patients. FFRCT was found to be better for the noninvasive screening of CAD patients with stable angina than FFRQCA. KEY POINTS: ⢠FFR CT and FFR QCA were both in good correlation and agreement with invasive FFR measurements. ⢠FFR CT is superior in accuracy and consistency compared to FFR QCA in patients with stenoses distributed in left coronary artery. ⢠The noninvasive nature of FFR CT could provide potential benefit for stable CAD patients on disease management.
Assuntos
Angina Estável/diagnóstico , Angiografia por Tomografia Computadorizada/métodos , Angiografia Coronária/métodos , Reserva Fracionada de Fluxo Miocárdico/fisiologia , Idoso , Angina Estável/fisiopatologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , Índice de Gravidade de DoençaRESUMO
OBJECTIVES: To evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for the detection of intracranial hemorrhage (ICH) and its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, and subarachnoid) in non-contrast head CT. METHODS: A total of 2836 subjects (ICH/normal, 1836/1000) from three institutions were included in this ethically approved retrospective study, with a total of 76,621 slices from non-contrast head CT scans. ICH and its five subtypes were annotated by three independent experienced radiologists, with majority voting as reference standard for both the subject level and the slice level. Ninety percent of data was used for training and validation, and the rest 10% for final evaluation. A joint CNN-RNN classification framework was proposed, with the flexibility to train when subject-level or slice-level labels are available. The predictions were compared with the interpretations from three junior radiology trainees and an additional senior radiologist. RESULTS: It took our algorithm less than 30 s on average to process a 3D CT scan. For the two-type classification task (predicting bleeding or not), our algorithm achieved excellent values (≥ 0.98) across all reporting metrics on the subject level. For the five-type classification task (predicting five subtypes), our algorithm achieved > 0.8 AUC across all subtypes. The performance of our algorithm was generally superior to the average performance of the junior radiology trainees for both two-type and five-type classification tasks. CONCLUSIONS: The proposed method was able to accurately detect ICH and its subtypes with fast speed, suggesting its potential for assisting radiologists and physicians in their clinical diagnosis workflow. KEY POINTS: ⢠A 3D joint CNN-RNN deep learning framework was developed for ICH detection and subtype classification, which has the flexibility to train with either subject-level labels or slice-level labels. ⢠This deep learning framework is fast and accurate at detecting ICH and its subtypes. ⢠The performance of the automated algorithm was superior to the average performance of three junior radiology trainees in this work, suggesting its potential to reduce initial misinterpretations.
Assuntos
Algoritmos , Aprendizado Profundo , Imageamento Tridimensional/métodos , Hemorragias Intracranianas/diagnóstico , Tomografia Computadorizada por Raios X/métodos , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Criança , Pré-Escolar , Feminino , Humanos , Lactente , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Estudos Retrospectivos , Adulto JovemRESUMO
BACKGROUND: The invasive fractional flow reserve has been considered the gold standard for identifying ischaemia-related stenosis in patients with suspected coronary artery disease. Determining non-invasive FFR based on coronary computed tomographic angiography datasets using computational fluid dynamics tends to be a demanding process. Therefore, the diagnostic performance of a simplified method for the calculation of FFRCTA requires further evaluation. OBJECTIVES: The aim of this study was to investigate the diagnostic performance of FFRCTA calculated based on a simplified method by referring to the invasive FFR in patient-specific coronary arteries and clinical decision-making. METHODS: Twenty-nine subjects included in this study underwent CCTA before undergoing clinically indicated invasive coronary angiography for suspected coronary artery disease. Pulsatile flow simulation and a novel boundary condition were used to obtain FFRCTA based on the CCTA datasets. The Pearson correlation, Bland-Altman plots and the diagnostic performance of FFRCTA and CCTA stenosis were analyzed by comparison to the invasive FFR reference standard. Ischaemia was defined as an FFR or FFRCTA ≤0.80, and anatomically obstructive CAD was defined as a CCTA stenosis >50%. RESULTS: FFRCTA and invasive FFR were well correlated (r = 0.742, P = 0.001). Slight systematic underestimation was found in FFRCTA (mean difference 0.03, standard deviation 0.05, P = 0.001). The area under the receiver-operating characteristic curve was 0.93 for FFRCTA and 0.75 for CCTA on a per-vessel basis. Per-patient accuracy, sensitivity and specificity were 79.3, 93.7 and 61.5%, respectively, for FFRCTA and 62.1, 87.5 and 30.7%, respectively, for CCTA. Per-vessel accuracy, sensitivity and specificity were 80.6, 94.1 and 68.4%, respectively, for FFRCTA and 61.6, 88.2 and 36.8%, respectively, for CCTA. CONCLUSIONS: FFRCTA derived from pulsatile simulation with a simplified novel boundary condition was in good agreement with invasive FFR and showed better diagnostic performance compared to CCTA, suggesting that the simplified method has the potential to be an alternative and accurate way to assess the haemodynamic characteristics for coronary stenosis.
Assuntos
Angiografia por Tomografia Computadorizada , Angiografia Coronária , Doença da Artéria Coronariana/diagnóstico por imagem , Doença da Artéria Coronariana/fisiopatologia , Reserva Fracionada de Fluxo Miocárdico , Idoso , Idoso de 80 Anos ou mais , Doença da Artéria Coronariana/complicações , Estenose Coronária/complicações , Estenose Coronária/diagnóstico por imagem , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Masculino , Pessoa de Meia-Idade , Isquemia Miocárdica/complicações , Isquemia Miocárdica/diagnóstico , Medicina de PrecisãoRESUMO
Two heme-dependent catalase genes were amplified from genomic DNA of Lactobacillus plantarum WCFS1 (KatE1) and Lactobacillus brevis ATCC 367 (KatE2), respectively, and a manganese-containing superoxide dismutase from Lactobacillus casei MCJΔ1 (MnSOD) were cloned into plasmid pELX1, yielding pELX1-KatE1, pELX1-KatE2 and pELX1-MnSOD, then the recombinant plasmids were transferred into L. casei MCJΔ1. The strains of L. casei MCJΔ1/pELX1-KatE1 and L. casei MCJΔ1/pELX1-KatE2 were tolerant at 2 mM H2O2. The survival rates of L. casei MCJΔ1/pELX1-KatE1 and L. casei MCJΔ1/pELX1-KatE2 were 270-fold and 300-fold higher than that of the control strain on a short-term H2O2 exposure, and in aerated condition, the survival cells counts were 146- and 190-fold higher than that of the control strain after 96 h of incubation. Furthermore, L. casei MCJΔ1/pELX1-MnSOD was the best in three recombinants which was superior in the living cell viability during storage when co-storage with Lactobacillus delbrueckii subsp. lactis LBCH-1.
Assuntos
Catalase/genética , Catalase/metabolismo , Lacticaseibacillus casei/genética , Lacticaseibacillus casei/metabolismo , Viabilidade Microbiana , Superóxido Dismutase/genética , Superóxido Dismutase/metabolismo , Catalase/biossíntese , Peróxido de Hidrogênio/metabolismo , Peróxido de Hidrogênio/farmacologia , Lacticaseibacillus casei/efeitos dos fármacos , Lacticaseibacillus casei/enzimologia , Viabilidade Microbiana/efeitos dos fármacos , Oxirredução/efeitos dos fármacos , Superóxido Dismutase/biossíntese , Transformação BacterianaRESUMO
OBJECTIVES: Fat radiomic profile (FRP) was a promising imaging biomarker for identifying increased cardiac risk. We hypothesize FRP can be extended to fat regions around pulmonary veins (PV), left atrium (LA), and left atrial appendage (LAA) to investigate their usefulness in identifying atrial fibrillation (AF) and the risk of AF recurrence. METHODS: We analysed 300 individuals and grouped patients according to the occurrence and types of AF. We used receiver operating characteristic and survival curves analyses to evaluate the value of imaging biomarkers, including fat attenuation index (FAI) and FRP, in distinguishing AF from sinus rhythm and predicting post-ablation recurrence. RESULTS: FRPs from AF-relevant fat regions showed significant performance in distinguishing AF and non-AF with higher AUC values than FAI (peri-PV: FRP = 0.961 vs FAI = 0.579, peri-LA: FRP = 0.923 vs FAI = 0.575, peri-LAA: FRP = 0.900 vs FAI = 0.665). FRPs from peri-PV, peri-LA, and peri-LAA were able to differentiate persistent and paroxysmal AF with AUC values of 0.804, 0.819, and 0.694. FRP from these regions improved AF recurrence prediction with an AUC of 0.929, 0.732, and 0.794. Patients with FRP cut-off values of ≥0.16, 0.38, and 0.26 had a 7.22-, 5.15-, and 4.25-fold higher risk of post-procedure recurrence, respectively. CONCLUSIONS: FRP demonstrated potential in identifying AF, distinguishing AF types, and predicting AF recurrence risk after ablation. FRP from peri-PV fat depot exhibited a strong correlation with AF. Therefore, evaluating epicardial fat using FRP was a promising approach to enhance AF clinical management. ADVANCES IN KNOWLEDGE: The role of epicardial adipose tissue (EAT) in AF had been confirmed, we focussed on the relationship between EAT around pulmonary arteries and LAA in AF which was still unknown. Meanwhile, we used the FRP to excavate more information of EAT in AF.
Assuntos
Fibrilação Atrial , Ablação por Cateter , Humanos , Fibrilação Atrial/diagnóstico por imagem , Fibrilação Atrial/cirurgia , Angiografia por Tomografia Computadorizada , Tecido Adiposo Epicárdico , Radiômica , Átrios do Coração/diagnóstico por imagem , Recidiva , Ablação por Cateter/métodosRESUMO
Myocardial ischemia diagnosis with CT perfusion imaging (CTP) is important in coronary artery disease management. Traditional analysis procedure is time-consuming and error-prone due to the semi-manual and operator-dependent nature. To improve the diagnostic performance, a deep learning-based, fully automatic, and clinical-ready framework was developed. Two collaborating deep learning networks including a 3D U-Net for left ventricle segmentation and a CNN for anatomical landmarks detection were trained on 276 subjects. With our processing framework, the 17-segment left ventricular model was automatically generated conformed to the clinical standard. Myocardial blood flow computed by commercial software was extracted within each segment and visualized against the bull's eye plot. The performance was validated on another 45 subjects. Coronary angiography and invasive fractional flow reserve measurements were also performed in these patients to serve as the gold standard for myocardial ischemia diagnosis. As a result, the diagnostic accuracy for our method was 81.08%, much higher than that for commercially available CTP analysis software (56.75%), and our method demonstrated a higher consistency (Kappa coefficient 0.759 vs. 0.585). Besides, the average processing time of our method was much lower (30 ± 10.5 s/subject vs. over 30 min/subject). In conclusion, the proposed deep learning-based framework could be a promising tool for assisting CTP analysis.
Assuntos
Doença da Artéria Coronariana , Estenose Coronária , Aprendizado Profundo , Reserva Fracionada de Fluxo Miocárdico , Isquemia Miocárdica , Imagem de Perfusão do Miocárdio , Humanos , Doença da Artéria Coronariana/diagnóstico por imagem , Angiografia por Tomografia Computadorizada/métodos , Valor Preditivo dos Testes , Isquemia Miocárdica/diagnóstico por imagem , Angiografia Coronária/métodos , Imagem de Perfusão do Miocárdio/métodosRESUMO
Establishing a patient-specific and non-invasive technique to derive blood flow as well as coronary structural information from one single cardiac CT imaging modality. 336 patients with chest pain or ST segment depression on electrocardiogram were retrospectively enrolled. All patients underwent adenosine-stressed dynamic CT myocardial perfusion imaging (CT-MPI) and coronary computed tomography angiography (CCTA) in sequence. Relationship between myocardial mass (M) and blood flow (Q), defined as log(Q) = b · log(M) + log(Q0), was explored based on the general allometric scaling law. We used 267 patients to obtain the regression results and found strong linear relationship between M (gram) and Q (mL/min) (b = 0.786, log(Q0) = 0.546, r = 0.704; p < 0.001). We Also found this correlation was applicable for patients with either normal or abnormal myocardial perfusion (p < 0.001). Datasets from the other 69 patients were used to validate this M-Q correlation and found the patient-specific blood flow could be accurately estimated from CCTA compared to that measured from CT-MPI (146.480 ± 39.607 vs 137.967 ± 36.227, r = 0.816, and 146.480 ± 39.607 vs 137.967 ± 36.227, r = 0.817, for the left ventricle region and LAD-subtended region, respectively, all unit in mL/min). In conclusion, we established a technique to provide general and patient-specific myocardial mass-blood flow correlation obeyed to allometric scaling law. Blood flow information could be directly derived from structural information acquired from CCTA.
Assuntos
Doença da Artéria Coronariana , Estenose Coronária , Humanos , Angiografia Coronária/métodos , Estudos Retrospectivos , Angiografia por Tomografia Computadorizada/métodos , Tomografia Computadorizada por Raios X/métodos , Coração , Valor Preditivo dos TestesRESUMO
PURPOSE: Lung function depends on lung expansion and contraction during the respiratory cycle. Respiratory-gated CT imaging and 3D image registration can be used to locally estimate lung tissue expansion and contraction (regional lung volume change) by computing the determinant of the Jacobian matrix of the image registration deformation field. In this study, the authors examine the reproducibility of Jacobian-based measures of lung tissue expansion in two repeat 4DCT acquisitions of mechanically ventilated sheep and free-breathing humans. METHODS: 4DCT image data from three white sheep and nine human subjects were used for this analysis. In each case, two 4DCT studies were acquired for each subject within a short time interval. The animal subjects were anesthetized and mechanically ventilated, while the humans were awake and spontaneously breathing based on respiratory pacing audio cues. From each 4DCT data set, an image pair consisting of a volume reconstructed near end inspiration and a volume reconstructed near end exhalation was selected. The end inspiration and end exhalation images were registered using a tissue volume preserving deformable registration algorithm and the Jacobian of the registration deformation field was used to measure regional lung expansion. The Jacobian map from the baseline data set was compared to the Jacobian map from the followup data by measuring the voxel-by-voxel Jacobian ratio. RESULTS: In the animal subjects, the mean Jacobian ratio (baseline scan Jacobian divided by followup scan Jacobian, voxel-by-voxel) was 0.9984±0.021 (mean ± standard deviation, averaged over the entire lung region). The mean Jacobian ratio was 1.0224±0.058 in the human subjects. The reproducibility of the Jacobian values was found to be strongly dependent on the reproducibility of the subject's respiratory effort and breathing pattern. CONCLUSIONS: Lung expansion, a surrogate for lung function, can be assessed using two or more respiratory-gated CT image acquisitions. The results show that good reproducibility can be obtained in anesthetized, mechanically ventilated animals, but variations in respiratory effort and breathing patterns reduce reproducibility in spontaneously-breathing humans. The global linear normalization can globally compensate for breathing effort differences, but a homogeneous scaling does not account for differences in regional lung expansion rates. Additional work is needed to develop compensation procedures or normalization schemes that can account for local variations in lung expansion during respiration.
Assuntos
Tomografia Computadorizada Quadridimensional/métodos , Pulmão/anatomia & histologia , Pulmão/diagnóstico por imagem , Adulto , Idoso , Animais , Feminino , Humanos , Pulmão/citologia , Pulmão/fisiologia , Masculino , Pessoa de Meia-Idade , Tamanho do Órgão , Reprodutibilidade dos Testes , Respiração , Respiração Artificial , OvinosRESUMO
PURPOSE: Regional lung volume change as a function of lung inflation serves as an index of parenchymal and airway status as well as an index of regional ventilation and can be used to detect pathologic changes over time. In this paper, the authors propose a new regional measure of lung mechanics-the specific air volume change by corrected Jacobian. The authors compare this new measure, along with two existing registration based measures of lung ventilation, to a regional ventilation measurement derived from xenon-CT (Xe-CT) imaging. METHODS: 4DCT and Xe-CT datasets from four adult sheep are used in this study. Nonlinear, 3D image registration is applied to register an image acquired near end inspiration to an image acquired near end expiration. Approximately 200 annotated anatomical points are used as landmarks to evaluate registration accuracy. Three different registration based measures of regional lung mechanics are derived and compared: the specific air volume change calculated from the Jacobian (SAJ); the specific air volume change calculated by the corrected Jacobian (SACJ); and the specific air volume change by intensity change (SAI). The authors show that the commonly used SAI measure can be derived from the direct SAJ measure by using the air-tissue mixture model and assuming there is no tissue volume change between the end inspiration and end expiration datasets. All three ventilation measures are evaluated by comparing to Xe-CT estimates of regional ventilation. RESULTS: After registration, the mean registration error is on the order of 1 mm. For cubical regions of interest (ROIs) in cubes with size 20 mm × 20 mm × 20 mm, the SAJ and SACJ measures show significantly higher correlation (linear regression, average r(2) = 0.75 and r(2) = 0.82) with the Xe-CT based measure of specific ventilation (sV) than the SAI measure. For ROIs in slabs along the ventral-dorsal vertical direction with size of 150 mm × 8 mm × 40 mm, the SAJ, SACJ, and SAI all show high correlation (linear regression, average r(2) = 0.88, r(2) = 0.92, and r(2) = 0.87) with the Xe-CT based sV without significant differences when comparing between the three methods. The authors demonstrate a linear relationship between the difference of specific air volume change and difference of tissue volume in all four animals (linear regression, average r(2) = 0.86). CONCLUSIONS: Given a deformation field by an image registration algorithm, significant differences between the SAJ, SACJ, and SAI measures were found at a regional level compared to the Xe-CT sV in four sheep that were studied. The SACJ introduced here, provides better correlations with Xe-CT based sV than the SAJ and SAI measures, thus providing an improved surrogate for regional ventilation.
Assuntos
Tomografia Computadorizada Quadridimensional/métodos , Processamento de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Pulmão/patologia , Tomografia Computadorizada Espiral/métodos , Xenônio/química , Algoritmos , Animais , Desenho de Equipamento , Imageamento Tridimensional/métodos , Masculino , Modelos Estatísticos , Ventilação Pulmonar , Reprodutibilidade dos Testes , Ovinos , SoftwareRESUMO
OBJECTIVES: We aim to evaluate a deep learning (DL) model and radiomic model for preoperative differentiation of nodular cryptococcosis from solitary lung cancer in patients with malignant features on CT images. MATERIALS AND METHODS: We retrospectively recruited 319 patients with solitary pulmonary nodules and suspicious signs of malignancy from three hospitals. All lung nodules were resected, and one by one radiologic-pathologic correlation was performed. A three-dimensional DL model was used for tumor segmentation and extraction of three-dimensional radiomic features. We used the Max-Relevance and Min-Redundancy algorithm and the eXtreme Gradient Boosting algorithm to select the nodular radiomics features. We proposed a DL local-global model, a DL local model and radiomic model to preoperatively differentiate nodular cryptococcosis from solitary lung cancer. The DL local-global model includes information of both nodules and the whole lung, while the DL local model only includes information of solitary lung nodules. Five-fold cross-validation was used to select and validate these models. The prediction performance of the model was evaluated using receiver operating characteristic curve (ROC) and calibration curve. A new loss function was applied in our deep learning framework to optimize the area under the ROC curve (AUC) directly. RESULTS: 295 patients were enrolled and they were non-symptomatic, with negative tumor markers and fungus markers in blood tests. These patients have not been diagnosed by the combination of CT imaging, laboratory results and clinical data. The lung volume was slightly larger in patients with lung cancers than that in patients with cryptococcosis (3552.8 ± 1184.6 ml vs 3491.9 ± 1017.8 ml). The DL local-global model achieved the best performance in differentiating between nodular cryptococcosis and lung cancer (area under the curve [AUC] = 0.88), which was higher than that of the DL local model (AUC = 0.84) and radiomic (AUC = 0.79) model. CONCLUSION: The DL local-global model is a non-invasive diagnostic tool to differentiate between nodular cryptococcosis and lung cancer nodules which are hard to be diagnosed by the combination of CT imaging, laboratory results and clinical data, and overtreatment may be avoided.
Assuntos
Criptococose , Aprendizado Profundo , Neoplasias Pulmonares , Nódulo Pulmonar Solitário , Criptococose/diagnóstico por imagem , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Estudos Retrospectivos , Nódulo Pulmonar Solitário/patologia , Tomografia Computadorizada por Raios X/métodosRESUMO
Multimodal image registration is a vital initial step in several medical image applications for providing complementary information from different data modalities. Since images with different modalities do not exhibit the same characteristics, finding their accurate correspondences remains a challenge. For convolutional multimodal registration methods, two components are quite significant: descriptive image feature as well as the suited similarity metric. However, these two components are often custom-designed and are infeasible to the high diversity of tissue appearance across modalities. In this paper, we translate image registration into a decision-making problem, where registration is achieved via an artificial agent trained by asynchronous reinforcement learning. More specifically, convolutional long-short-term-memory is incorporated after stacked convolutional layers in this method to extract spatial-temporal image features and learn the similarity metric implicitly. A customized reward function driven by landmark error is advocated to guide the agent to the correct registration direction. A Monte Carlo rollout strategy is also leveraged to perform as a look-ahead inference in the testing stage, to increase registration accuracy further. Experiments on paired CT and MR images of patients diagnosed as nasopharyngeal carcinoma demonstrate that our method achieves state-of-the-art performance in medical image registration.
Assuntos
Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , HumanosRESUMO
Extensive research has been devoted to the segmentation of the coronary artery. However, owing to its complex anatomical structure, it is extremely challenging to automatically segment the coronary artery from 3D coronary computed tomography angiography (CCTA). Inspired by recent ideas to use tree-structured long short-term memory (LSTM) to model the underlying tree structures for NLP tasks, we propose a novel tree-structured convolutional gated recurrent unit (ConvGRU) model to learn the anatomical structure of the coronary artery. However, unlike tree-structured LSTM proposed for semantic relatedness as well as sentiment classification in natural language processing, our tree-structured ConvGRU model considers the local spatial correlations in the input data as the convolutions are used for input-to-state as well as state-to-state transitions, thus more suitable for image analysis. To conduct voxel-wise segmentation, a tree-structured segmentation framework is presented. It consists of a fully convolutional network (FCN) for multi-scale discriminative feature extraction and the final prediction, and a tree-structured ConvGRU layer for anatomical structure modeling. The proposed framework is extensively evaluated on four large-scale 3D CCTA dataset (the largest to the best of our knowledge), and experiments show that our method is more accurate as well as efficient, compared with other coronary artery segmentation approaches.
Assuntos
Angiografia por Tomografia Computadorizada , Angiografia Coronária , Vasos Coronários/diagnóstico por imagem , Aprendizado Profundo , Interpretação de Imagem Assistida por Computador/métodos , Imageamento Tridimensional , Vasos Coronários/anatomia & histologia , HumanosRESUMO
PURPOSE: Automated anatomical labeling facilitates the diagnostic process for physicians and radiologists. One of the challenges in automated anatomical labeling problems is the robustness to handle the large individual variability inherited in human anatomy. A novel deep neural network framework, referred to Tree Labeling Network (TreeLab-Net), is proposed to resolve this problem in this work. METHODS: A multi-layer perceptron (MLP) encoder network and a bidirectional tree-structural long short-term memory (Bi-TreeLSTM) are combined to construct the TreeLab-Net. Vessel spatial locations and directions are selected as features, where a spherical coordinate transform is utilized to normalize vessel spatial variations. The dataset includes 436 coronary computed tomography angiography images. Tenfold cross-validation is performed for evaluation. RESULTS: The precision-recall curve of TreeLab-Net shows that the four main branch classes, LM, LAD, LCX and RCA, have the area under the curve (AUC) higher than 97%. Other major side branch classes, D, OM, and R-PLB, also have AUC higher than 90%. Comparing with four other methods (i.e., AdaBoost, MLP, Up-to-Down and Down-to-Up TreeLSTM), the TreeLab-Net achieves higher F1 scores with less topological errors. CONCLUSION: The TreeLab-Net is able to capture the characteristics of tree structures by learning the spatial and topological dependencies of blood vessels effectively. The results demonstrate that TreeLab-Net is able to yield competitive performances on a large dataset with great variance among subjects.
Assuntos
Angiografia Coronária/métodos , Vasos Coronários/anatomia & histologia , Diagnóstico por Computador/métodos , Tomografia Computadorizada por Raios X/métodos , Adulto , Área Sob a Curva , Aprendizado Profundo , Feminino , Humanos , Masculino , Redes Neurais de ComputaçãoRESUMO
PURPOSE: Segmentation of the left ventricle (LV), right ventricle (RV) cavities and the myocardium (MYO) from cine cardiac magnetic resonance (MR) images is an important step for diagnosis and monitoring cardiac diseases. Spatial context information may be highly beneficial for segmentation performance improvement. To this end, this paper proposes an iterative multi-path fully convolutional network (IMFCN) to effectively leverage spatial context for automatic cardiac segmentation in cine MR images. METHODS: To effectively leverage spatial context information, the proposed IMFCN explicitly models the interslice spatial correlations using a multi-path late fusion strategy. First, the contextual inputs including both the adjacent slices and the already predicted mask of the above adjacent slice are processed by independent feature-extraction paths. Then, an atrous spatial pyramid pooling (ASPP) module is employed at the feature fusion process to combine the extracted high-level contextual features in a more effective way. Finally, deep supervision (DS) and batch-wise class re-weighting mechanism are utilized to enhance the training of the proposed network. RESULTS: The proposed IMFCN was evaluated and analyzed on the MICCAI 2017 automatic cardiac diagnosis challenge (ACDC) dataset. On the held-out training dataset reserved for testing, our method effectively improved its counterparts that without spatial context and that with spatial context but using an early fusion strategy. On the 50 subjects test dataset, our method achieved Dice similarity coefficient of 0.935, 0.920, and 0.905, and Hausdorff distance of 7.66, 12.10, and 8.80 mm for LV, RV, and MYO, respectively, which are comparable or even better than the state-of-the-art methods of ACDC Challenge. In addition, to explore the applicability to other datasets, the proposed IMFCN was retrained on the Sunnybrook dataset for LV segmentation and also produced comparable performance to the state-of-the-art methods. CONCLUSIONS: We have presented an automatic end-to-end fully convolutional architecture for accurate cardiac segmentation. The proposed method provides an effective way to leverage spatial context in a two-dimensional manner and results in precise and consistent segmentation results.
Assuntos
Coração/diagnóstico por imagem , Processamento de Imagem Assistida por Computador/métodos , Imagem Cinética por Ressonância Magnética , Redes Neurais de Computação , Automação , Bases de Dados Factuais , HumanosRESUMO
We have previously developed a robotic ultrasound imaging system for motion monitoring in abdominal radiation therapy. Owing to the slow speed of ultrasound image processing, our previous system could only track abdominal motions under breath-hold. To overcome this limitation, a novel 2D-based image processing method for tracking intra-fraction respiratory motion is proposed. Fifty-seven different anatomical features acquired from 27 sets of 2D ultrasound sequences were used in this study. Three 2D ultrasound sequences were acquired with the robotic ultrasound system from three healthy volunteers. The remaining datasets were provided by the 2015 MICCAI Challenge on Liver Ultrasound Tracking. All datasets were preprocessed to extract the feature point, and a patient-specific motion pattern was extracted by principal component analysis and slow feature analysis (SFA). The tracking finds the most similar frame (or indexed frame) by a k-dimensional-tree-based nearest neighbor search for estimating the tracked object location. A template image was updated dynamically through the indexed frame to perform a fast template matching (TM) within a learned smaller search region on the incoming frame. The mean tracking error between manually annotated landmarks and the location extracted from the indexed training frame is 1.80 ± 1.42 mm. Adding a fast TM procedure within a small search region reduces the mean tracking error to 1.14 ± 1.16 mm. The tracking time per frame is 15 ms, which is well below the frame acquisition time. Furthermore, the anatomical reproducibility was measured by analyzing the location's anatomical landmark relative to the probe; the position-controlled probe has better reproducibility and yields a smaller mean error across all three volunteer cases, compared to the force-controlled probe (2.69 versus 11.20 mm in the superior-inferior direction and 1.19 versus 8.21 mm in the anterior-posterior direction). Our method reduces the processing time for tracking respiratory motion significantly, which can reduce the delivery uncertainty.
Assuntos
Abdome/diagnóstico por imagem , Abdome/efeitos da radiação , Fracionamento da Dose de Radiação , Aprendizado de Máquina , Movimento , Radioterapia Guiada por Imagem/métodos , Respiração , Voluntários Saudáveis , Humanos , Processamento de Imagem Assistida por Computador , Planejamento da Radioterapia Assistida por Computador , Reprodutibilidade dos Testes , UltrassonografiaRESUMO
GOAL: Rheumatoid arthritis (RA) is characterized by inflammation within the joint space as well as erosion or destruction of the bone surface. We believe that volumetric (3-D) ultrasound imaging of the joints in conjunction with automated image-analysis tools for segmenting and quantifying the regions of interest can lead to improved RA assessment. METHODS: In this paper, we describe our proposed algorithms for segmenting 1) the 3 -D bone surface and 2) the 3-D joint capsule region. We improve and extend previous 2-D bone extraction methods to 3-D and make our algorithm more robust to the intensity loss due to surface normals facing away from incident acoustic beams. The extracted bone surfaces coupled with a joint-specific anatomical model are used to initialize a coarse localization of the joint capsule region. The joint capsule segmentation is refined iteratively utilizing a probabilistic speckle model. RESULTS: We apply our methods on 51 volumes from 8 subjects, and validate segmentation results with expert annotations. We also provide the quantitative comparison of our bone detection with magnetic resonance imaging. These automated methods have achieved average sensitivity/precision rates of 94%/93% for bone surface detection, and 87%/83% for joint capsule segmentation. Segmentations of normal and inflamed joints are compared to demonstrate the potential of using proposed tools to assess RA pathology at the joint level. CONCLUSION: The proposed image-analysis methods showed encouraging results as compared to expert annotations. SIGNIFICANCE: These computer-assisted tools can be used to help visualize 3-D anatomy in joints and help develop quantitative measurements toward RA assessment.
Assuntos
Artrite Reumatoide/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Algoritmos , Articulações dos Dedos/diagnóstico por imagem , Articulações do Pé/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética/métodos , UltrassonografiaRESUMO
The lobes of the lung slide relative to each other during breathing. Quantifying lobar sliding can aid in better understanding lung function, better modeling of lung dynamics, and for studying phenomenon such as pleural adhesion. We propose a novel measure to characterize lobe sliding in the lung based on the displacement field obtained from image registration of CT scans. When two sliding lobes are modeled as a continuum, the discontinuity in the displacement field at the fissure will manifest as elevated maximum shear--the proposed measure--which is capable of capturing both the level and orientation of sliding. Six human lungs were analyzed using scans spanning functional residual capacity to total lung capacity. The lung lobes were segmented and registered on a lobe-by-lobe basis to obtain the displacement field from which the proposed sliding measure was calculated. The sliding measure was found to be insignificant in the parenchyma, as relatively little tissue shear occurs here. On the other hand, it was elevated along the fissures. Thus, a map of the proposed sliding measure of the entire lung clearly delineates and quantifies sliding between lung lobes. Sliding is a key aspect of lung deformation during breathing. The proposed measure may help resolve artifacts introduced by sliding in deformation analysis techniques used for radiotherapy.
Assuntos
Processamento de Imagem Assistida por Computador , Pulmão/diagnóstico por imagem , Pulmão/fisiopatologia , Modelos Biológicos , Tomografia Computadorizada por Raios X/métodos , Humanos , Medidas de Volume Pulmonar/métodos , Pleura/diagnóstico por imagem , Pleura/fisiopatologiaRESUMO
This paper presents a novel method for respiratory motion compensated reconstruction for cone beam computed tomography (CBCT). The reconstruction is based on a time sequence of motion vector fields, which is generated by a dynamic geometrical object shape model. The dynamic model is extracted from the 2D projection images of the CBCT. The process of the motion extraction is converted into an optimal 3D multiple interrelated surface detection problem, which can be solved by computing a maximum flow in a 4D directed graph. The method was tested on 12 mega-voltage (MV) CBCT scans from three patients. Two sets of motion-artifact-free 3D volumes, full exhale (FE) and full inhale (FI) phases, were reconstructed for each daily scan. The reconstruction was compared with three other motion-compensated approaches based on quantification accuracy of motion and size. Contrast-to-noise ratio (CNR) was also quantified for image quality. The proposed approach has the best overall performance, with a relative tumor volume quantification error of 3.39 ± 3.64% and 8.57 ± 8.31% for FE and FI phases, respectively. The CNR near the tumor area is 3.85 ± 0.42 (FE) and 3.58 ± 3.33 (FI). These results show the clinical feasibility to use the proposed method to reconstruct motion-artifact-free MVCBCT volumes.