Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 112
Filtrar
1.
Ann Surg Oncol ; 31(3): 1536-1545, 2024 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-37957504

RESUMO

BACKGROUND: Sublobar resection is strongly associated with poor prognosis in early-stage lung adenocarcinoma, with the presence of tumor spread through air spaces (STAS). Thus, preoperative prediction of STAS is important for surgical planning. This study aimed to develop a STAS deep-learning (STAS-DL) prediction model in lung adenocarcinoma with tumor smaller than 3 cm and a consolidation-to-tumor (C/T) ratio less than 0.5. METHODS: The study retrospectively enrolled of 581 patients from two institutions between 2015 and 2019. The STAS-DL model was developed to extract the feature of solid components through solid components gated (SCG) for predicting STAS. The STAS-DL model was assessed with external validation in the testing sets and compared with the deep-learning model without SCG (STAS-DLwoSCG), the radiomics-based model, the C/T ratio, and five thoracic surgeons. The performance of the models was evaluated using area under the curve (AUC), accuracy and standardized net benefit of the decision curve analysis. RESULTS: The study evaluated 458 patients (institute 1) in the training set and 123 patients (institute 2) in the testing set. The proposed STAS-DL yielded the best performance compared with the other methods in the testing set, with an AUC of 0.82 and an accuracy of 74%, outperformed the STAS-DLwoSCG with an accuracy of 70%, and was superior to the physicians with an AUC of 0.68. Moreover, STAS-DL achieved the highest standardized net benefit compared with the other methods. CONCLUSION: The proposed STAS-DL model has great potential for the preoperative prediction of STAS and may support decision-making for surgical planning in early-stage, ground glass-predominant lung adenocarcinoma.


Assuntos
Adenocarcinoma de Pulmão , Aprendizado Profundo , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/patologia , Estudos Retrospectivos , Invasividade Neoplásica/patologia , Adenocarcinoma de Pulmão/patologia , Tomografia Computadorizada por Raios X/métodos , Estadiamento de Neoplasias , Prognóstico
2.
Pediatr Res ; 2023 Dec 05.
Artigo em Inglês | MEDLINE | ID: mdl-38049649

RESUMO

BACKGROUND: The study aimed to analyze the effect of uteroplacental insufficiency (UPI) on leptin expression and lung development of intrauterine growth restriction (IUGR) rats. METHODS: On day 17 of pregnancy, time-dated Sprague-Dawley rats were randomly divided into either an IUGR group or a control group. Uteroplacental insufficiency surgery (IUGR) and sham surgery (control) were conducted. Offspring rats were spontaneously delivered on day 22 of pregnancy. On postnatal days 0 and 7, rats' pups were selected at random from the control and IUGR groups. Blood was withdrawn from the heart to determine leptin levels. The right lung was obtained for leptin and leptin receptor levels, immunohistochemistry, proliferating cell nuclear antigen (PCNA), western blot, and metabolomic analyses. RESULTS: UPI-induced IUGR decreased leptin expression and impaired lung development, causing decreased surface area and volume in offspring. This results in lower body weight, decreased serum leptin levels, lung leptin and leptin receptor levels, alveolar space, PCNA, and increased alveolar wall volume fraction in IUGR offspring rats. The IUGR group found significant relationships between serum leptin, radial alveolar count, von Willebrand Factor, and metabolites. CONCLUSION: Leptin may contribute to UPI-induced lung development during the postnatal period, suggesting supplementation as a potential treatment. IMPACT: The neonatal rats with intrauterine growth restriction (IUGR) caused by uteroplacental insufficiency (UPI) showed decreased leptin expression and impaired lung development. UPI-induced IUGR significantly decreased surface area and volume in lung offspring. This is a novel study that investigates leptin expression and lung development in neonatal rats with IUGR caused by UPI. If our findings translate to IUGR infants, leptin may contribute to UPI-induced lung development during the postnatal period, suggesting supplementation as a potential treatment.

4.
Nutr Metab (Lond) ; 20(1): 50, 2023 Nov 21.
Artigo em Inglês | MEDLINE | ID: mdl-37990266

RESUMO

BACKGROUND: This study investigated the effect of uteroplacental insufficiency (UPI) on renal development by detecting metabolic alterations in the kidneys of rats with intrauterine growth restriction (IUGR). METHODS: On gestational day 17, pregnant Sprague Dawley rats were selected and allocated randomly to either the IUGR group or the control group. The IUGR group received a protocol involving the closure of bilateral uterine vessels, while the control group underwent a sham surgery. The rat pups were delivered on gestational day 22 by natural means. Pups were randomly recruited from both the control and IUGR groups on the seventh day after birth. The kidneys were surgically removed to conduct Western blot and metabolomic analyses. RESULTS: IUGR was produced by UPI, as evidenced by the significantly lower body weights of the pups with IUGR compared to the control pups on postnatal day 7. UPI significantly increased the levels of cleaved caspase-3 (p < 0.05) and BAX/Bcl-2 (p < 0.01) in the pups with IUGR. Ten metabolites exhibited statistically significant differences between the groups (q < 0.05). Metabolic pathway enrichment analysis demonstrated statistically significant variations between the groups in the metabolism related to fructose and mannose, amino and nucleotide sugars, and inositol phosphate. CONCLUSIONS: UPI alters kidney metabolism in growth-restricted newborn rats and induces renal apoptosis. The results of our study have the potential to provide new insights into biomarkers and metabolic pathways that are involved in the kidney changes generated by IUGR.

5.
Phys Med Biol ; 68(24)2023 Dec 13.
Artigo em Inglês | MEDLINE | ID: mdl-37832565

RESUMO

The automated marker-free longitudinal Infrared (IR) breast image registration overcomes several challenges like no anatomic fiducial markers on the body surface, blurry boundaries, heat pattern variation by environmental and physiological factors, nonrigid deformation, etc, has the ability of quantitative pixel-wise analysis with the heat energy and patterns change in a time course study. To achieve the goal, scale-invariant feature transform, Harris corner, and Hessian matrix were employed to generate the feature points as anatomic fiducial markers, and hybrid genetic algorithm and particle swarm optimization minimizing the matching errors was used to find the appropriate corresponding pairs between the 1st IR image and thenth IR image. Moreover, the mechanism of the IR spectrogram hardware system has a high level of reproducibility. The performance of the proposed longitudinal image registration system was evaluated by the simulated experiments and the clinical trial. In the simulated experiments, the mean difference of our system is 1.64 mm, which increases 57.58% accuracy than manual determination and makes a 17.4% improvement than the previous study. In the clinical trial, 80 patients were captured several times of IR breast images during chemotherapy. Most of them were well aligned in the spatiotemporal domain. In the few cases with evident heat pattern dissipation and spatial deviation, it still provided a reliable comparison of vascular variation. Therefore, the proposed system is accurate and robust, which could be considered as a reliable tool for longitudinal approaches to breast cancer diagnosis.


Assuntos
Algoritmos , Neoplasias da Mama , Humanos , Feminino , Reprodutibilidade dos Testes , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagem , Marcadores Fiduciais
6.
J Biomed Sci ; 30(1): 57, 2023 Jul 31.
Artigo em Inglês | MEDLINE | ID: mdl-37517995

RESUMO

BACKGROUND: Supplemental oxygen impairs lung development in newborn infants with respiratory distress. Lactobacillus johnsonii supplementation attenuates respiratory viral infection in mice and exhibits anti-inflammatory effects. This study investigated the protective effects of intranasal administration of L. johnsonii on lung development in hyperoxia-exposed neonatal mice. METHODS: Neonatal C57BL/6N mice were reared in either room air (RA) or hyperoxia condition (85% O2). From postnatal days 0 to 6, they were administered intranasal 10 µL L. johnsonii at a dose of 1 × 105 colony-forming units. Control mice received an equal volume of normal saline (NS). We evaluated the following four study groups: RA + NS, RA + probiotic, O2 + NS, and O2 + probiotic. On postnatal day 7, lung and intestinal microbiota were sampled from the left lung and lower gastrointestinal tract, respectively. The right lung of each mouse was harvested for Western blot, cytokine, and histology analyses. RESULTS: The O2 + NS group exhibited significantly lower body weight and vascular density and significantly higher mean linear intercept (MLI) and lung cytokine levels compared with the RA + NS and RA + probiotic groups. At the genus level of the gut microbiota, the O2 + NS group exhibited significantly higher Staphylococcus and Enterobacter abundance and significantly lower Lactobacillus abundance compared with the RA + NS and RA + probiotic groups. Intranasal L. johnsonii treatment increased the vascular density, decreased the MLI and cytokine levels, and restored the gut microbiota in hyperoxia-exposed neonatal mice. CONCLUSIONS: Intranasal administration of L. johnsonii protects against hyperoxia-induced lung injury and modulates the gut microbiota.


Assuntos
Microbioma Gastrointestinal , Hiperóxia , Lactobacillus johnsonii , Lesão Pulmonar , Ratos , Animais , Camundongos , Hiperóxia/complicações , Hiperóxia/patologia , Animais Recém-Nascidos , Lesão Pulmonar/prevenção & controle , Lesão Pulmonar/patologia , Ratos Sprague-Dawley , Administração Intranasal , Camundongos Endogâmicos C57BL , Pulmão/patologia , Citocinas
7.
Mol Med ; 29(1): 16, 2023 01 30.
Artigo em Inglês | MEDLINE | ID: mdl-36717779

RESUMO

BACKGROUND: Chorioamnionitis is a common cause of preterm birth and leads to serious complications in newborns. The objective of this study was to investigate the role of the Hippo signaling pathway in lung branching morphogenesis under a lipopolysaccharide (LPS)-induced inflammation model. MATERIALS AND METHODS: IMR-90 cells and ex vivo fetal lungs were treated with 0, 10, 30, or 50 µg/ml LPS for 24 and 72 h. Supernatant levels of lactate dehydrogenase (LDH), interleukin (IL)-6, IL-8, Chemokine (C-X-C motif) ligand 1(CXCL1), branching and the surface area ratio, Yes-associated protein (YAP), transcription coactivator with PDZ-binding motif (TAZ), fibroblast growth factor 10 (FGF10), fibroblast growth factor receptor II (FGFR2), SRY-box transcription factor 2 (SOX2), SOX9, and sirtuin 1 (SIRT1) levels were examined. Differentially expressed genes in fetal lungs after LPS treatment were identified by RNA-sequencing. RESULTS: LPS at 50 µg/ml increased IL-6 and IL-8 in IMR-90 cells and increased IL-6, CXCL1 and LDH in fetal lungs. The branching ratio significantly increased by LPS at 30 µg/ml compared to the control but the increased level had decreased by 50 µg/ml LPS exposure. Exposure to 50 µg/ml LPS increased phosphorylated (p)-YAP, p-YAP/YAP, and p-TAZ/TAZ in IMR-90 cells, whereas 50 µg/ml LPS decreased FGF10 and SOX2. Consistently, p-YAP/YAP and p-TAZ/TAZ were increased in fibronectin+ cells of fetal lungs. Moreover, results of RNA-sequencing in fetal lungs showed that SMAD, FGF, IκB phosphorylation, tissue remodeling and homeostasis was involved in branching morphogenesis following exposure to 50 µg/ml LPS. The p-SIRT1/SIRT1 ratio increased in IMR-90 cells by LPS treatment. CONCLUSIONS: This study showed that regulation of the Hippo pathway in fibroblasts of fetal lungs was involved in branching morphogenesis under an inflammatory disease such as chorioamnionitis.


Assuntos
Corioamnionite , Nascimento Prematuro , Feminino , Humanos , Recém-Nascido , Proteínas de Ciclo Celular/metabolismo , Fibroblastos/metabolismo , Inflamação/metabolismo , Interleucina-6/metabolismo , Interleucina-8/metabolismo , Lipopolissacarídeos , Pulmão/metabolismo , Morfogênese , Nascimento Prematuro/metabolismo , RNA/metabolismo , Sirtuína 1/metabolismo , Transativadores/genética , Gravidez
8.
J Dev Orig Health Dis ; 14(2): 272-278, 2023 04.
Artigo em Inglês | MEDLINE | ID: mdl-36239256

RESUMO

Fetal growth restriction (FGR) is associated with reduced cardiac function in neonates. Uteroplacental insufficiency (UPI) is the most common cause of FGR. The mechanisms underlying these alterations remain unknown. We hypothesized that UPI would influence cardiac development in offspring rats. Through this study, we evaluated the effects of UPI during pregnancy on heart histology and pulmonary hypertension in growth-restricted newborn rats. On gestation Day 18, either UPI was induced through bilateral uterine vessel ligation (FGR group) or sham surgery (control group) was performed. The right middle lobe of the lung and the heart were harvested for histological and immunohistochemical evaluation on postnatal days 0 and 7. The FGR group exhibited significantly lower body weight, hypertrophy and degeneration of cardiomyocytes, increased intercellular spaces between the cardiomyocytes and collagen deposition, and decreased glycogen deposition and HNK-1 expression compared with the control group on postnatal days 0 and 7. These results suggest that neonates with FGR may have inadequate myocardial reserves, which may cause subsequent cardiovascular compromise in future life. Further studies are required to evaluate the hemodynamic changes in these growth-restricted neonates.


Assuntos
Insuficiência Placentária , Gravidez , Humanos , Feminino , Ratos , Animais , Animais Recém-Nascidos , Retardo do Crescimento Fetal/etiologia , Retardo do Crescimento Fetal/metabolismo , Pulmão , Coração
9.
Cancers (Basel) ; 14(23)2022 Nov 29.
Artigo em Inglês | MEDLINE | ID: mdl-36497379

RESUMO

It remains a challenge to preoperatively forecast whether lung pure ground-glass nodules (pGGNs) have invasive components. We aimed to construct a radiomic model using tumor characteristics to predict the histologic subtype associated with pGGNs. We retrospectively reviewed clinicopathologic features of pGGNs resected in 338 patients with lung adenocarcinoma between 2011-2016 at a single institution. A radiomic prediction model based on forward sequential selection and logistic regression was constructed to differentiate adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma. The study cohort included 133 (39.4%), 128 (37.9%), and 77 (22.8%) patients with AIS, MIA, and invasive adenocarcinoma (acinar 55.8%, lepidic 33.8%, papillary 10.4%), respectively. The majority (83.7%) underwent sublobar resection. There were no nodal metastases or tumor recurrence during a mean follow-up period of 78 months. Three radiomic features-cluster shade, homogeneity, and run-length variance-were identified as predictors of histologic subtype and were selected to construct a prediction model to classify the AIS/MIA and invasive adenocarcinoma groups. The model achieved accuracy, sensitivity, specificity, and AUC of 70.6%, 75.0%, 70.0%, and 0.7676, respectively. Applying the developed radiomic feature model to predict the histologic subtypes of pGGNs observed on CT scans can help clinically in the treatment selection process.

10.
Front Oncol ; 12: 1027036, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36387180

RESUMO

Background: Preoperative two-dimensional manual measurement of pulmonary artery diameter in a single-cut axial view computed tomography (CT) image is a commonly used non-invasive prediction method for pulmonary hypertension. However, the accuracy may be unreliable. Thus, this study aimed to evaluate the correlation of short-term surgical outcomes and pulmonary artery/aorta (PA/Ao) diameter ratio measured by automated three-dimensional (3D) segmentation in lung cancer patients who underwent thoracoscopic lobectomy. Materials and methods: We included 383 consecutive lung cancer patients with thin-slice CT images who underwent lobectomy at a single institute between January 1, 2011 and December 31, 2019. Automated 3D segmentation models were used for 3D vascular reconstruction and measurement of the average diameters of Ao and PA. Propensity-score matching incorporating age, Charlson comorbidity index, and lobectomy performed by uniportal VATS was used to compare clinical outcomes in patients with PA/Ao ratio ≥1 and those <1. Results: Our segmentation method measured 29 (7.57%) patients with a PA/Ao ratio ≥1. After propensity-score matching, a higher overall postoperative complication classified by the Clavien-Dindo classification (p = 0.016) were noted in patients with 3D PA/Ao diameter ratio ≥1 than those of <1. By multivariate logistic regression, patients with a 3D PA/Ao ratio ≥ 1 (p = 0.013) and tumor diameter > 3 cm (p = 0.002) both significantly predict the incidence of postoperative complications. Conclusions: Pulmonary artery/aorta diameter ratio ≥ 1 measured by automated 3D segmentation may predict postoperative complications in lung cancer patients who underwent lobectomy.

11.
Front Pediatr ; 10: 952313, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36160795

RESUMO

Background: Intrauterine growth restriction (IUGR) is among the most challenging problems in antenatal care. Several factors implicated in the pathophysiology of IUGR have been identified. We aimed to investigate the effect of UPI on lung development by identifying metabolic changes during the first seven days of postnatal life. Materials and methods: On gestation day 17, four time-dated pregnant Sprague Dawley rats were randomized to a IUGR group or a control group, which underwent an IUGR protocol comprising bilateral uterine vessel ligation and sham surgery, respectively. On gestation day 22, 39 control and 26 IUGR pups were naturally delivered. The rat pups were randomly selected from the control and IUGR group on postnatal day 7. The pups' lungs were excised for histological, Western blot, and metabolomic analyses. Liquid chromatography mass spectrometry was performed for metabolomic analyses. Results: UPI induced IUGR, as evidenced by the IUGR rat pups having a significantly lower average body weight than the control rat pups on postnatal day 7. The control rats exhibited healthy endothelial cell healthy and vascular development, and the IUGR rats had a significantly lower average radial alveolar count than the control rats. The mean birth weight of the 26 IUGR rats (5.89 ± 0.74 g) was significantly lower than that of the 39 control rats (6.36 ± 0.55 g; p < 0.01). UPI decreased the levels of platelet-derived growth factor-A (PDGF-A) and PDGF-B in the IUGR newborn rats. One-way analysis of variance revealed 345 features in the pathway, 14 of which were significant. Regarding major differential metabolites, 10 of the 65 metabolites examined differed significantly between the groups (p < 0.05). Metabolite pathway enrichment analysis revealed significant between-group differences in the metabolism of glutathione, arginine-proline, thiamine, taurine-hypotaurine, pantothenate, alanine-aspartate-glutamate, cysteine-methionine, glycine-serine-threonine, glycerophospholipid, and purine as well as in the biosynthesis of aminoacyl-tRNA, pantothenate, and CoA. Conclusions: UPI alters lung development and metabolomics in growth-restricted newborn rats. Our findings may elucidate new metabolic mechanisms underlying IUGR-induced altered lung development and serve as a reference for the development of prevention and treatment strategies for IUGR-induced altered lung development.

12.
Artigo em Inglês | MEDLINE | ID: mdl-35966750

RESUMO

Diabetes in children and its complications are on the rise globally, which is accompanied by increasing in diabetes-related complications. Oxidative stress and inflammation induced by elevated blood sugar in diabetic patients are considered risk factors associated with the development of diabetes complications, including chronic kidney disease and its later development to end-stage renal disease. Microvascular changes within the kidneys of DM patients often lead to chronic kidney disease, which aggravates the illness. Sigesbeckia orientalis extract (SOE), reported to have strong antioxidative and excellent anti-inflammatory activities, is used in the modern practice of traditional Chinese medicine. Kidneys from three groups of control mice (CTR), mice with streptozotocin (STZ)-induced diabetes (DM), and mice with STZ-induced DM treated with SOE (DMRx) were excised for morphological analyses and immunohistochemical assessments. Only mice in the DM group exhibited significantly lower body weight, but higher blood sugar was present. The results revealed more obvious renal injury in the DM group than in the other groups, which appeared as greater glomerular damage and tubular injury, sores, and plenty of connective tissues within the mesangium. Not only did the DM group have a higher level of cytokine, tumor necrosis factor, and the oxidative stress marker, 8-hydroxyguanosine expression, but also factors of the nuclear factor pathway and biomarkers of microvascular status had changed. Disturbances to the kidneys in DMRx mice were attenuated compared to the DM group. We concluded that SOE is an effective medicine, with antioxidative and anti-inflammatory abilities, to protect against or attenuate diabetic nephropathy from inflammatory disturbances by oxidative stress and to cure vessel damage in a hyperglycemic situation.

15.
Ann Surg Oncol ; 29(12): 7473-7482, 2022 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-35789301

RESUMO

BACKGROUND: High-grade adenocarcinoma subtypes (micropapillary and solid) treated with sublobar resection have an unfavorable prognosis compared with those treated with lobectomy. We investigated the potential of incorporating solid attenuation component masks with deep learning in the prediction of high-grade components to optimize surgical strategy preoperatively. METHODS: A total of 502 patients with pathologically confirmed high-grade adenocarcinomas were retrospectively enrolled between 2016 and 2020. The SACs attention DL model was developed to apply solid-attenuation-component-like subregion masks (tumor area ≥ - 190 HU) to guide the DL model for predicting high-grade subtypes. The SACA-DL was assessed using 5-fold cross-validation and external validation in the training and testing sets, respectively. The performance, which was evaluated using the area under the curve (AUC), was compared between SACA-DL and the DL model without SACs attention (DLwoSACs), the prior radiomics model, or the model based on the consolidation/tumor (C/T) diameter ratio. RESULTS: We classified 313 and 189 patients into training and testing cohorts, respectively. The SACA-DL achieved an AUC of 0.91 for the cross-validation, which was significantly superior to those of the DLwoSACs (AUC = 0.88; P = 0.02), prior radiomics model (AUC = 0.85; P = 0.004), and C/T ratio (AUC = 0.84; P = 0.002). An AUC of 0.93 was achieved for external validation in the SACA-DL and was significantly better than those of the DLwoSACs (AUC = 0.89; P = 0.04), prior radiomics model (AUC = 0.85; P < 0.001), and C/T ratio (AUC = 0.85; P < 0.001). CONCLUSIONS: The combination of solid-attenuation-component-like subregion masks with the DL model is a promising approach for the preoperative prediction of high-grade adenocarcinoma subtypes.


Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Aprendizado Profundo , Neoplasias Pulmonares , Adenocarcinoma/diagnóstico por imagem , Adenocarcinoma/patologia , Adenocarcinoma/cirurgia , Adenocarcinoma de Pulmão/diagnóstico por imagem , Adenocarcinoma de Pulmão/patologia , Adenocarcinoma de Pulmão/cirurgia , Atenção , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/cirurgia , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodos
16.
Antioxidants (Basel) ; 11(4)2022 Mar 26.
Artigo em Inglês | MEDLINE | ID: mdl-35453326

RESUMO

Oxygen is often required to treat newborns with respiratory disorders, and prolonged exposure to high oxygen concentrations impairs lung development. Ferroptosis plays a vital role in the development of many diseases and has become the focus of treatment and prognosis improvement for related diseases, such as neurological diseases, infections, cancers, and ischemia-reperfusion injury. Whether ferroptosis participates in the pathogenesis of hyperoxia-induced lung injury remains unknown. The aims of this study are to determine the effects of hyperoxia on lung ferroptosis and development in neonatal mice. Newborn C57BL/6 mice were reared in either room air (RA) or hyperoxia (85% O2) at postnatal days 1-7. On postnatal days 3 and 7, the lungs were harvested for histological and biochemical analysis. The mice reared in hyperoxia exhibited significantly higher Fe2+, malondialdehyde, and iron deposition and significantly lower glutathione, glutathione peroxidase 4, and vascular density than did those reared in RA on postnatal days 3 and 7. The mice reared in hyperoxia exhibited a comparable mean linear intercept on postnatal day 3 and a significantly higher mean linear intercept than the mice reared in RA on postnatal day 7. These findings demonstrate that ferroptosis was induced at a time point preceding impaired lung development, adding credence to the hypothesis that ferroptosis is involved in the pathogenesis of hyperoxia-induced lung injury and suggest that ferroptosis inhibitors might attenuate hyperoxia-induced lung injury.

17.
Diagnostics (Basel) ; 12(4)2022 Apr 12.
Artigo em Inglês | MEDLINE | ID: mdl-35454015

RESUMO

Pulmonary hypertension should be preoperatively evaluated for optimal surgical planning to reduce surgical risk in lung cancer patients. Preoperative measurement of vascular diameter in computed tomography (CT) images is a noninvasive prediction method for pulmonary hypertension. However, the current estimation method, 2D manual arterial diameter measurement, may yield inaccurate results owing to low tissue contrast in non-contrast-enhanced CT (NECT). Furthermore, it provides an incomplete evaluation by measuring only the diameter of the arteries rather than the volume. To provide a more complete and accurate estimation, this study proposed a novel two-stage deep learning (DL) model for 3D aortic and pulmonary artery segmentation in NECT. In the first stage, a DL model was constructed to enhance the contrast of NECT; in the second stage, two DL models then applied the enhanced images for aorta and pulmonary artery segmentation. Overall, 179 patients were divided into contrast enhancement model (n = 59), segmentation model (n = 120), and testing (n = 20) groups. The performance of the proposed model was evaluated using Dice similarity coefficient (DSC). The proposed model could achieve 0.97 ± 0.66 and 0.93 ± 0.16 DSC for aortic and pulmonary artery segmentation, respectively. The proposed model may provide 3D diameter information of the arteries before surgery, facilitating the estimation of pulmonary hypertension and supporting preoperative surgical method selection based on the predicted surgical risks.

18.
Eur Radiol ; 32(6): 3767-3777, 2022 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-35020016

RESUMO

OBJECTIVES: To propose and evaluate a set of radiomic features, called morphological dynamics features, for pulmonary nodule detection, which were rooted in the dynamic patterns of morphological variation and needless precise lesion segmentation. MATERIALS AND METHODS: Two datasets were involved, namely, university hospital (UH) and LIDC datasets, comprising 72 CT scans (360 nodules) and 888 CT scans (2230 nodules), respectively. Each nodule was annotated by multiple radiologists. Denoted the category of nodules identified by at least k radiologists as ALk. A nodule detection algorithm, called CAD-MD algorithm, was proposed based on the morphological dynamics radiomic features, characterizing a lesion by ten sets of the same features with different values extracted from ten different thresholding results. Each nodule candidate was classified by a two-level classifier, including ten decision trees and a random forest, respectively. The CAD-MD algorithm was compared with a deep learning approach, the N-Net, using the UH dataset. RESULTS: On the AL1 and AL2 of the UH dataset, the AUC of the AFROC curves were 0.777 and 0.851 for the CAD-MD algorithm and 0.478 and 0.472 for the N-Net, respectively. The CAD-MD algorithm achieved the sensitivities of 84.4% and 91.4% with 2.98 and 3.69 FPs/scan and the N-Net 74.4% and 80.7% with 3.90 and 4.49 FPs/scan, respectively. On the LIDC dataset, the CAD-MD algorithm attained the sensitivities of 87.6%, 89.2%, 92.2%, and 95.0% with 4 FPs/scan for AL1-AL4, respectively. CONCLUSION: The morphological dynamics radiomic features might serve as an effective set of radiomic features for lung nodule detection. KEY POINTS: • Texture features varied with such CT system settings as reconstruction kernels of CT images, CT scanner models, and parameter settings, and so on. • Shape and first-order statistics were shown to be the most robust features against variation in CT imaging parameters. • The morphological dynamics radiomic features, which mainly characterized the dynamic patterns of morphological variation, were shown to be effective for lung nodule detection.


Assuntos
Neoplasias Pulmonares , Nódulo Pulmonar Solitário , Algoritmos , Humanos , Pulmão/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Nódulo Pulmonar Solitário/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos
19.
Interact Cardiovasc Thorac Surg ; 34(3): 369-377, 2022 02 21.
Artigo em Inglês | MEDLINE | ID: mdl-34648631

RESUMO

OBJECTIVES: Solitary pulmonary capillary haemangioma (SPCH) is a benign lung tumour that presents as ground-glass nodules on computed tomography (CT) images and mimics lepidic-predominant adenocarcinoma. This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from lepidic-predominant adenocarcinoma. METHODS: In the adenocarcinoma group, all tumours were of the lepidic-predominant subtype with high purity (>70%). A classification model was proposed based on a two-level decision tree and 26 radiomic features extracted from each segmented lesion. For comparison, a baseline model was built with the same 26 features using a support vector machine as the classifier. Both models were assessed by the leave-one-out cross-validation method. RESULTS: This study included 13 and 49 patients who underwent complete resection for SPCH and adenocarcinoma, respectively. Two sets of features were identified for discrimination between the 2 different histology types. The first set included 2 principal components corresponding to the 2 largest eigenvalues for the root node of the two-level decision tree. The second set comprised 4 selected radiomic features. The area under the receiver operating characteristic curve, accuracy, sensitivity, specificity were 0.954, 91.9%, 92.3% and 91.8% in the proposed classification model, and were 0.805, 85.5%, 61.5% and 91.8% in the baseline model, respectively. The proposed classification model significantly outperformed the baseline model (P < 0.05). CONCLUSIONS: The proposed model could differentiate the 2 different histology types on CT images, and this may help surgeons to preoperatively discriminate SPCH from adenocarcinoma.


Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Hemangioma Capilar , Neoplasias Pulmonares , Adenocarcinoma/patologia , Adenocarcinoma de Pulmão/diagnóstico por imagem , Adenocarcinoma de Pulmão/patologia , Humanos , Pulmão/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/cirurgia , Estudos Retrospectivos
20.
Ann Thorac Surg ; 114(3): 999-1006, 2022 09.
Artigo em Inglês | MEDLINE | ID: mdl-34454902

RESUMO

BACKGROUND: We aimed to establish a radiomic prediction model for tumor spread through air spaces (STAS) in lung adenocarcinoma using radiomic values from high-grade subtypes (solid and micropapillary). METHODS: We retrospectively reviewed 327 patients with lung adenocarcinoma from 2 institutions (cohort 1: 227 patients; cohort 2: 100 patients) between March 2017 and March 2019. STAS was identified in 113 (34.6%) patients. A high-grade likelihood prediction model was constructed based on a historical cohort of 82 patients with "near-pure" pathologic subtype. The STAS prediction model based on the patch-wise mechanism identified the high-grade likelihood area for each voxel within the internal border of the tumor. STAS presence was indirectly predicted by a volume percentage threshold of the high-grade likelihood area. Performance was evaluated by receiver operating curve analysis with 10-repetition, 3-fold cross-validation in cohort 1, and was individually tested in cohort 2. RESULTS: Overall, 227 patients (STAS-positive: 77 [33.9%]) were enrolled for cross-validation (cohort 1) while 100 (STAS-positive: 36 [36.0%]) underwent individual testing (cohort 2). The gray level cooccurrence matrix (variance) and histogram (75th percentile) features were selected to construct the high-grade likelihood prediction model, which was used as the STAS prediction model. The proposed model achieved good performance in cohort 1 with an area under the curve, sensitivity, and specificity, of 81.44%, 86.75%, and 62.60%, respectively, and correspondingly, in cohort 2, they were 83.16%, 83.33%, and 63.90%, respectively. CONCLUSIONS: The proposed computed tomography-based radiomic prediction model could help guide preoperative prediction of STAS in early-stage lung adenocarcinoma and relevant surgeries.


Assuntos
Adenocarcinoma de Pulmão , Neoplasias Pulmonares , Adenocarcinoma de Pulmão/cirurgia , Humanos , Neoplasias Pulmonares/cirurgia , Invasividade Neoplásica/patologia , Estadiamento de Neoplasias , Prognóstico , Estudos Retrospectivos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA