RESUMO
BACKGROUND: Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies. MATERIALS AND METHODS: This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients. RESULTS: A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively. CONCLUSION: Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.
Assuntos
Neoplasias da Mama , Aprendizado Profundo , Mamografia , Humanos , Feminino , Mamografia/métodos , Neoplasias da Mama/patologia , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico , Pessoa de Meia-Idade , Estudos Retrospectivos , Biópsia , Idoso , Adulto , Carcinoma Intraductal não Infiltrante/diagnóstico por imagem , Carcinoma Intraductal não Infiltrante/patologia , Carcinoma Intraductal não Infiltrante/diagnóstico , Procedimentos Desnecessários/estatística & dados numéricos , Mama/patologia , Mama/diagnóstico por imagemRESUMO
Background Background parenchymal enhancement (BPE) at dynamic contrast-enhanced (DCE) MRI of cancer-free breasts increases the risk of developing breast cancer; implications of quantitative BPE in ipsilateral breasts with breast cancer are largely unexplored. Purpose To determine whether quantitative BPE measurements in one or both breasts could be used to predict recurrence risk in women with breast cancer, using the Oncotype DX recurrence score as the reference standard. Materials and Methods This HIPAA-compliant retrospective single-institution study included women diagnosed with breast cancer between January 2007 and January 2012 (development set) and between January 2012 and January 2017 (internal test set). Quantitative BPE was automatically computed using an in-house-developed computer algorithm in both breasts. Univariable logistic regression was used to examine the association of BPE with Oncotype DX recurrence score binarized into high-risk (recurrence score >25) and low- or intermediate-risk (recurrence score ≤25) categories. Models including BPE measures were assessed for their ability to distinguish patients with high risk versus those with low or intermediate risk and the actual recurrence outcome. Results The development set included 127 women (mean age, 58 years ± 10.2 [SD]; 33 with high risk and 94 with low or intermediate risk) with an actual local or distant recurrence rate of 15.7% (20 of 127) at a minimum 10 years of follow-up. The test set included 60 women (mean age, 57.8 years ± 11.6; 16 with high risk and 44 with low or intermediate risk). BPE measurements quantified in both breasts were associated with increased odds of a high-risk Oncotype DX recurrence score (odds ratio range, 1.27-1.66 [95% CI: 1.02, 2.56]; P < .001 to P = .04). Measures of BPE combined with tumor radiomics helped distinguish patients with a high-risk Oncotype DX recurrence score from those with a low- or intermediate-risk score, with an area under the receiver operating characteristic curve of 0.94 in the development set and 0.79 in the test set. For the combined models, the negative predictive values were 0.97 and 0.93 in predicting actual distant recurrence and local recurrence, respectively. Conclusion Ipsilateral and contralateral DCE MRI measures of BPE quantified in patients with breast cancer can help distinguish patients with high recurrence risk from those with low or intermediate recurrence risk, similar to Oncotype DX recurrence score. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Zhou and Rahbar in this issue.
Assuntos
Neoplasias da Mama , Humanos , Feminino , Pessoa de Meia-Idade , Neoplasias da Mama/diagnóstico por imagem , Estudos Retrospectivos , Mama/diagnóstico por imagem , Fatores de Risco , Imageamento por Ressonância MagnéticaRESUMO
PURPOSE OF REVIEW: Plant-derived foods are one of the most common causative sources of food allergy in China, with a significant relationship to pollinosis. This review aims to provide a comprehensive overview of this food-pollen allergy syndrome and its molecular allergen diagnosis to better understand the cross-reactive basis. RECENT FINDINGS: Food-pollen cross-reactivity has been mainly reported in Northern China, Artemisia pollen is the major related inhalant source, followed by tree pollen (Betula), while grass pollen plays a minor role. Pollen allergy is relatively low in Southern China, with allergies to grass pollen being more important than weed and tree pollens. Rosaceae fruits and legume seeds stand out as major related allergenic foods. Non-specific lipid transfer protein (nsLTP) has been found to be the most clinically relevant cross-reacting allergenic component, able to induce severe reactions. PR-10, profilin, defensin, chitinase, and gibberellin-regulated proteins are other important cross-reactive allergen molecules. Artemisia pollen can induce allergenic cross-reactions with a wide range of plant-derived foods in China, and spring tree pollens (Betula) are also important. nsLTP found in both pollen and plant-derived food is considered the most significant allergen in food pollen cross-reactivity. Component-resolved diagnosis with potential allergenic proteins is recommended to improve diagnostic accuracy and predict the potential risk of causing allergic symptoms.
RESUMO
Citrobacter sp. XT1-2-2, a functional microorganism with potential utilization, has the ability to immobilize soil cadmium. In this study, the regulatory gene cysH, as a rate-limiting enzyme in the sulfur metabolic pathway, was selected for functional analysis affecting cadmium immobilization in soil. To verify the effect of APS reductase on CdS formation, the ΔAPS and ΔAPS-com strains were constructed by conjugation transfer. Through TEM analysis, it was found that the adsorption of Cd2+ was affected by the absence of APS reductase in XT1-2-2 strain. The difference analysis of biofilm formation indicated that APS reductase was necessary for cell aggregation and biofilm formation. The p-XRD, XPS and FT-IR analysis revealed that APS reductase played an important role in the cadmium immobilization process of XT1-2-2 strain and promoting the formation of CdS. According to the pot experiments, the cadmium concentration of roots, culms, leaves and grains inoculated with ΔAPS strain was significantly higher than that of wild-type and ΔAPS-com strains, and the cadmium removal ability of ΔAPS strain was significantly lower than that of wild-type strain. The study provided insights into the exploration of new bacterial assisted technique for the remediation and safe production of rice in cadmium-contaminated paddy soils.
RESUMO
In recent years, allergic diseases have occurred frequently, affecting more than 20% of the global population. The current first-line treatment of anti-allergic drugs mainly includes topical corticosteroids, as well as adjuvant treatment of antihistamine drugs, which have adverse side effects and drug resistance after long-term use. Therefore, it is essential to find alternative anti-allergic agents from natural products. High pressure, low temperature, and low/lack of light lead to highly functionalized and diverse functional natural products in the marine environment. This review summarizes the information on anti-allergic secondary metabolites with a variety of chemical structures such as polyphenols, alkaloids, terpenoids, steroids, and peptides, obtained mainly from fungi, bacteria, macroalgae, sponges, mollusks, and fish. Molecular docking simulation is applied by MOE to further reveal the potential mechanism for some representative marine anti-allergic natural products to target the H1 receptor. This review may not only provide insight into information about the structures and anti-allergic activities of natural products from marine organisms but also provides a valuable reference for marine natural products with immunomodulatory activities.
Assuntos
Antialérgicos , Produtos Biológicos , Animais , Organismos Aquáticos/química , Antialérgicos/farmacologia , Produtos Biológicos/química , Simulação de Acoplamento Molecular , Fungos/químicaRESUMO
OBJECTIVE: An estimated 1.5 million people die every year worldwide from traumatic brain injury (TBI). Physicians are relatively poor at predicting long-term outcomes early in patients with severe TBI. Machine learning (ML) has shown promise at improving prediction models across a variety of neurological diseases. The authors sought to explore the following: 1) how various ML models performed compared to standard logistic regression techniques, and 2) if properly calibrated ML models could accurately predict outcomes up to 2 years posttrauma. METHODS: A secondary analysis of a prospectively collected database of patients with severe TBI treated at a single level 1 trauma center between November 2002 and December 2018 was performed. Neurological outcomes were assessed at 3, 6, 12, and 24 months postinjury with the Glasgow Outcome Scale. The authors used ML models including support vector machine, neural network, decision tree, and naïve Bayes models to predict outcome across all 4 time points by using clinical information available on admission, and they compared performance to a logistic regression model. The authors attempted to predict unfavorable versus favorable outcomes (Glasgow Outcome Scale scores of 1-3 vs 4-5), as well as mortality. Models' performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) with 95% confidence interval and balanced accuracy. RESULTS: Of the 599 patients in the database, the authors included 501, 537, 469, and 395 at 3, 6, 12, and 24 months posttrauma. Across all time points, the AUCs ranged from 0.71 to 0.85 for mortality and from 0.62 to 0.82 for unfavorable outcomes with various modeling strategies. Decision tree models performed worse than all other modeling approaches for multiple time points regarding both unfavorable outcomes and mortality. There were no statistically significant differences between any other models. After proper calibration, the models had little variation (0.02-0.05) across various time points. CONCLUSIONS: The ML models tested herein performed with equivalent success compared with logistic regression techniques for prognostication in TBI. The TBI prognostication models could predict outcomes beyond 6 months, out to 2 years postinjury.
Assuntos
Lesões Encefálicas Traumáticas , Lesões Encefálicas , Humanos , Teorema de Bayes , Lesões Encefálicas Traumáticas/diagnóstico , Lesões Encefálicas Traumáticas/terapia , Modelos Logísticos , Aprendizado de Máquina , PrognósticoRESUMO
BACKGROUND: In our previous study, Citrobacter sp. XT1-2-2 was isolated from high cadmium-contaminated soils, and demonstrated an excellent ability to decrease the bioavailability of cadmium in the soil and inhibit cadmium uptake in rice. In addition, the strain XT1-2-2 could significantly promote rice growth and increase rice biomass. Therefore, the strain XT1-2-2 shows great potential for remediation of cadmium -contaminated soils. However, the genome sequence of this organism has not been reported so far. RESULTS: Here the basic characteristics and genetic diversity of the strain XT1-2-2 were described, together with the draft genome and comparative genomic results. The strain XT1-2-2 is 5040459 bp long with an average G + C content of 52.09%, and contains a total of 4801 genes. Putative genomic islands were predicted in the genome of Citrobacter sp. XT1-2-2. All genes of a complete set of sulfate reduction pathway and various putative heavy metal resistance genes in the genome were identified and analyzed. CONCLUSIONS: These analytical results provide insights into the genomic basis of microbial immobilization of heavy metals.
Assuntos
Metais Pesados , Oryza , Poluentes do Solo , Cádmio/metabolismo , Citrobacter , Poluentes do Solo/metabolismo , Solo , Oryza/metabolismo , GenômicaRESUMO
Background After severe traumatic brain injury (sTBI), physicians use long-term prognostication to guide acute clinical care yet struggle to predict outcomes in comatose patients. Purpose To develop and evaluate a prognostic model combining deep learning of head CT scans and clinical information to predict long-term outcomes after sTBI. Materials and Methods This was a retrospective analysis of two prospectively collected databases. The model-building set included 537 patients (mean age, 40 years ± 17 [SD]; 422 men) from one institution from November 2002 to December 2018. Transfer learning and curriculum learning were applied to a convolutional neural network using admission head CT to predict mortality and unfavorable outcomes (Glasgow Outcomes Scale scores 1-3) at 6 months. This was combined with clinical input for a holistic fusion model. The models were evaluated using an independent internal test set and an external cohort of 220 patients with sTBI (mean age, 39 years ± 17; 166 men) from 18 institutions in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) study from February 2014 to April 2018. The models were compared with the International Mission on Prognosis and Analysis of Clinical Trials in TBI (IMPACT) model and the predictions of three neurosurgeons. Area under the receiver operating characteristic curve (AUC) was used as the main model performance metric. Results The fusion model had higher AUCs than did the IMPACT model in the prediction of mortality (AUC, 0.92 [95% CI: 0.86, 0.97] vs 0.80 [95% CI: 0.71, 0.88]; P < .001) and unfavorable outcomes (AUC, 0.88 [95% CI: 0.82, 0.94] vs 0.82 [95% CI: 0.75, 0.90]; P = .04) on the internal data set. For external TRACK-TBI testing, there was no evidence of a significant difference in the performance of any models compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.90) in the prediction of mortality. The Imaging model (AUC, 0.73; 95% CI: 0.66-0.81; P = .02) and the fusion model (AUC, 0.68; 95% CI: 0.60, 0.76; P = .02) underperformed as compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.89) in the prediction of unfavorable outcomes. The fusion model outperformed the predictions of the neurosurgeons. Conclusion A deep learning model of head CT and clinical information can be used to predict 6-month outcomes after severe traumatic brain injury. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Haller in this issue.
Assuntos
Lesões Encefálicas Traumáticas , Aprendizado Profundo , Adulto , Lesões Encefálicas Traumáticas/diagnóstico por imagem , Lesões Encefálicas Traumáticas/cirurgia , Escala de Coma de Glasgow , Humanos , Masculino , Prognóstico , Estudos Retrospectivos , Tomografia Computadorizada por Raios XRESUMO
Information in digital mammogram images has been shown to be associated with the risk of developing breast cancer. Longitudinal breast cancer screening mammogram examinations may carry spatiotemporal information that can enhance breast cancer risk prediction. No deep learning models have been designed to capture such spatiotemporal information over multiple examinations to predict the risk. In this study, we propose a novel deep learning structure, LRP-NET, to capture the spatiotemporal changes of breast tissue over multiple negative/benign screening mammogram examinations to predict near-term breast cancer risk in a case-control setting. Specifically, LRP-NET is designed based on clinical knowledge to capture the imaging changes of bilateral breast tissue over four sequential mammogram examinations. We evaluate our proposed model with two ablation studies and compare it to three models/settings, including 1) a "loose" model without explicitly capturing the spatiotemporal changes over longitudinal examinations, 2) LRP-NET but using a varying number (i.e., 1 and 3) of sequential examinations, and 3) a previous model that uses only a single mammogram examination. On a case-control cohort of 200 patients, each with four examinations, our experiments on a total of 3200 images show that the LRP-NET model outperforms the compared models/settings.
RESUMO
BACKGROUND: The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. METHODS: We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. "high" vs "low") prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models' performance was measured via area under the receiver operating characteristic curve (AUC). RESULTS: Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. CONCLUSIONS: On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor's microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Aprendizado de Máquina/normas , Feminino , Humanos , Pessoa de Meia-Idade , Invasividade Neoplásica , Fenótipo , Estudos Retrospectivos , Microambiente TumoralRESUMO
BACKGROUND: Surgical risk calculators (SRCs) have been developed for estimation of postoperative complications but do not directly inform decision-making. Decision curve analysis (DCA) is a method for evaluating prediction models, measuring their utility in guiding decisions. We aimed to analyze the utility of SRCs to guide both preoperative and postoperative management of patients undergoing hepatopancreaticobiliary surgery by using DCA. METHODS: A single-institution, retrospective review of patients undergoing hepatopancreaticobiliary operations between 2015 and 2017 was performed. Estimation of postoperative complications was conducted using the American College of Surgeons SRC [ACS-SRC] and the Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) calculator; risks were compared with observed outcomes. DCA was used to model optimal patient selection for risk prevention strategies and to compare the relative performance of the ACS-SRC and POTTER calculators. RESULTS: A total of 994 patients were included in the analysis. C-statistics for the ACS-SRC prediction of 12 postoperative complications ranged from 0.546 to 0.782. DCA revealed that an ACS-SRC-guided readmission prevention intervention, when compared with an all-or-none approach, yielded a superior net benefit for patients with estimated risk between 5% and 20%. Comparison of SRCs for venous thromboembolism intervention demonstrated superiority of the ACS-SRC for thresholds for intervention between 2% and 4% with the POTTER calculator performing superiorly between 4% and 8% estimated risk. CONCLUSIONS: SRCs can be used not only to predict complication risk but also to guide risk prevention strategies. This methodology should be incorporated into external validations of future risk calculators and can be applied for institution-specific quality improvement initiatives to improve patient outcomes.
Assuntos
Técnicas de Apoio para a Decisão , Procedimentos Cirúrgicos do Sistema Digestório/estatística & dados numéricos , Complicações Pós-Operatórias/epidemiologia , Idoso , Idoso de 80 Anos ou mais , Procedimentos Cirúrgicos do Sistema Digestório/efeitos adversos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pennsylvania/epidemiologia , Complicações Pós-Operatórias/etiologia , Estudos Retrospectivos , Medição de RiscoRESUMO
BACKGROUND: Diffusion-weighted imaging (DWI) in MRI plays an increasingly important role in diagnostic applications and developing imaging biomarkers. Automated whole-breast segmentation is an important yet challenging step for quantitative breast imaging analysis. While methods have been developed on dynamic contrast-enhanced (DCE) MRI, automatic whole-breast segmentation in breast DWI MRI is still underdeveloped. PURPOSE: To develop a deep/transfer learning-based segmentation approach for DWI MRI scans and conduct an extensive study assessment on four imaging datasets from both internal and external sources. STUDY TYPE: Retrospective. SUBJECTS: In all, 98 patients (144 MRI scans; 11,035 slices) of four different breast MRI datasets from two different institutions. FIELD STRENGTH/SEQUENCES: 1.5T scanners with DCE sequence (Dataset 1 and Dataset 2) and DWI sequence. A 3.0T scanner with one external DWI sequence. ASSESSMENT: Deep learning models (UNet and SegNet) and transfer learning were used as segmentation approaches. The main DCE Dataset (4,251 2D slices from 39 patients) was used for pre-training and internal validation, and an unseen DCE Dataset (431 2D slices from 20 patients) was used as an independent test dataset for evaluating the pre-trained DCE models. The main DWI Dataset (6,343 2D slices from 75 MRI scans of 29 patients) was used for transfer learning and internal validation, and an unseen DWI Dataset (10 2D slices from 10 patients) was used for independent evaluation to the fine-tuned models for DWI segmentation. Manual segmentations by three radiologists (>10-year experience) were used to establish the ground truth for assessment. The segmentation performance was measured using the Dice Coefficient (DC) for the agreement between manual expert radiologist's segmentation and algorithm-generated segmentation. STATISTICAL TESTS: The mean value and standard deviation of the DCs were calculated to compare segmentation results from different deep learning models. RESULTS: For the segmentation on the DCE MRI, the average DC of the UNet was 0.92 (cross-validation on the main DCE dataset) and 0.87 (external evaluation on the unseen DCE dataset), both higher than the performance of the SegNet. When segmenting the DWI images by the fine-tuned models, the average DC of the UNet was 0.85 (cross-validation on the main DWI dataset) and 0.72 (external evaluation on the unseen DWI dataset), both outperforming the SegNet on the same datasets. DATA CONCLUSION: The internal and independent tests show that the deep/transfer learning models can achieve promising segmentation effects validated on DWI data from different institutions and scanner types. Our proposed approach may provide an automated toolkit to help computer-aided quantitative analyses of breast DWI images. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:635-643.
Assuntos
Aprendizado Profundo , Mama/diagnóstico por imagem , Imagem de Difusão por Ressonância Magnética , Humanos , Imageamento por Ressonância Magnética , Estudos RetrospectivosRESUMO
OBJECTIVES: To investigate the association of chest CT findings with mortality in clinical management of older patients. METHODS: From January 21 to February 14, 2020, 98 older patients (≥ 60 years) who had undergone chest CT scans ("initial CT") on admission were enrolled. Manifestation and CT score were compared between the death group and the survival group. In each group, patients were sub-grouped based on the time interval between symptom onset and the "initial CT" scan: subgroup1 (interval ≤ 5 days), subgroup2 (interval between 6 and 10 days), and subgroup3 (interval > 10 days). Adjusted ROC curve after adjustment for age and gender was applied. RESULTS: Consolidations on CT images were more common in the death group (n = 46) than in the survival group (n = 52) (53.2% vs 32.0%, p < 0.001). For subgroup1 and subgroup2, a higher mean CT score was found for the death group (33.0 ± 17.1 vs 12.9 ± 8.7, p < 0.001; 38.8 ± 12.3 vs 24.3 ± 11.9, p = 0.002, respectively) and no significant difference of CT score was identified with respect to subgroup3 (p = 0.144). In subgroup1, CT score of 14.5 with a sensitivity of 83.3% and a specificity of 77.3% for the prediction of mortality was an optimal cutoff value, with an adjusted AUC of 0.881. In subgroup2, CT score of 27.5 with a sensitivity of 87.5% and a specificity of 70.6% for the prediction of mortality was an optimal cutoff value, with an adjusted AUC of 0.895. CONCLUSIONS: "Initial CT" scores may be useful to speculate prognosis and stratify patients. Severe manifestation on CT at an early stage may indicate poor prognosis for older patients with COVID-19. KEY POINTS: ⢠Severe manifestation on CT at an early stage may indicate poor prognosis for older patients with COVID-19. ⢠Radiologists should pay attention to the time interval between symptom onsets and CT scans of patients with COVID-19. ⢠Consolidations on CT images were more common in death patients than in survival patients.
Assuntos
Betacoronavirus , Infecções por Coronavirus/diagnóstico por imagem , Infecções por Coronavirus/mortalidade , Avaliação Geriátrica/estatística & dados numéricos , Pneumonia Viral/diagnóstico por imagem , Pneumonia Viral/mortalidade , Tomografia Computadorizada por Raios X/métodos , Idoso , Idoso de 80 Anos ou mais , COVID-19 , China/epidemiologia , Feminino , Avaliação Geriátrica/métodos , Humanos , Pulmão/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Pandemias , Prognóstico , Curva ROC , Reprodutibilidade dos Testes , Estudos Retrospectivos , SARS-CoV-2 , Sensibilidade e EspecificidadeRESUMO
Deep learning Convolutional Neural Networks have achieved remarkable performance in a variety of classification tasks. The data-driven nature of deep learning indicates that a model behaves in response to the data used to train the model, and the quality of datasets may lead to substantial influence on the model's performance, especially when dealing with complicated clinical images. In this paper, we propose a simple and novel method to investigate and quantify a deep learning model's response with respect to a given sample, allowing us to detect out-of-distribution samples based on a newly proposed metric, Response Score. The key idea is that samples belonging to different classes may have different degrees of influence on a model. We quantify the resulting consequence of a single sample to a trained-model and relate the quantitative measure of the consequence (by the Response Score) to detect the out-of-distribution samples. The proposed method can find multiple applications such as (1) recognizing abnormal samples, (2) detecting mixed-domain data, and (3) identifying mislabeled data. We present extensive experiments on the three different applications using four biomedical imaging datasets. Experimental results show that our method exhibits remarkable performance and outperforms the compared methods.
Assuntos
Aprendizado Profundo , Redes Neurais de ComputaçãoRESUMO
In this work, we assess how pre-training strategy affects deep learning performance for the task of distinguishing false-recall from malignancy and normal (benign) findings in digital mammography images. A cohort of 1303 breast cancer screening patients (4935 digital mammogram images in total) was retrospectively analyzed as the target dataset for this study. We assessed six different convolutional neural network model structures utilizing four different imaging datasets (total > 1.4 million images (including ImageNet); medical images different in terms of scale, modality, organ, and source) for pre-training on six classification tasks to assess how the performance of CNN models varies based on training strategy. Representative pre-training strategies included transfer learning with medical and non-medical datasets, layer freezing, varied network structure, and multi-view input for both binary and triple-class classification of mammogram images. The area under the receiver operating characteristic curve (AUC) was used as the model performance metric. The best performing model out of all experimental settings was an AlexNet model incrementally pre-trained on ImageNet and a large Breast Density dataset. The AUC for the six classification tasks using this model ranged from 0.68 to 0.77. In the case of distinguishing recalled-benign mammograms from others, four out of five pre-training strategies tested produced significant performance differences from the baseline model. This study suggests that pre-training strategy influences significant performance differences, especially in the case of distinguishing recalled- benign from malignant and benign screening patients.
Assuntos
Neoplasias da Mama , Aprendizado Profundo , Neoplasias da Mama/diagnóstico por imagem , Humanos , Mamografia , Redes Neurais de Computação , Estudos RetrospectivosRESUMO
Microvascular invasion (mVI) is the most significant independent predictor of recurrence for hepatocellular carcinoma (HCC), but its pre-operative assessment is challenging. In this study, we investigate the use of multi-parametric MRI radiomics to predict mVI status before surgery. We retrospectively collected pre-operative multi-parametric liver MRI scans for 99 patients who were diagnosed with HCC. These patients received surgery and pathology-confirmed diagnosis of mVI. We extracted radiomics features from manually segmented HCC regions and built machine learning classifiers to predict mVI status. We compared the performance of such classifiers when built on five MRI sequences used both individually and combined. We investigated the effects of using features extracted from the tumor region only, the peritumoral marginal region only, and the combination of the two. We used the area under the receiver operating characteristic curve (AUC) and accuracy as performance metrics. By combining features extracted from multiple MRI sequences, AUCs are 86.69%, 84.62%, and 84.19% when features are extracted from the tumor only, the peritumoral region only, and the combination of the two, respectively. For tumor-extracted features, the T2 sequence (AUC = 80.84%) and portal venous sequence (AUC = 79.22%) outperform other MRI sequences in single-sequence-based models and their combination yields the highest AUC of 86.69% for mVI status prediction. Our results show promise in predicting mVI from pre-operative liver MRI scans and indicate that information from multi-parametric MRI sequences is complementary in identifying mVI.
Assuntos
Carcinoma Hepatocelular , Neoplasias Hepáticas , Carcinoma Hepatocelular/diagnóstico por imagem , Feminino , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Imageamento por Ressonância Magnética , Masculino , Pessoa de Meia-Idade , Invasividade Neoplásica/diagnóstico por imagem , Estudos RetrospectivosRESUMO
The grading of glioma has clinical significance in determining a treatment strategy and evaluating prognosis to investigate a novel set of radiomic features extracted from the fractional anisotropy (FA) and mean diffusivity (MD) maps of brain diffusion tensor imaging (DTI) sequences for computer-aided grading of gliomas. This retrospective study included 108 patients who had pathologically confirmed brain gliomas and DTI scanned during 2012-2018. This cohort included 43 low-grade gliomas (LGGs; all grade II) and 65 high-grade gliomas (HGGs; grade III or IV). We extracted a set of radiomic features, including traditional texture, morphological, and novel deep features derived from pre-trained convolutional neural network models, in the manually-delineated tumor regions. We employed support vector machine and these radiomic features for two classification tasks: LGGs vs HGGs, and grade III vs IV. The area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity was reported as the performance metrics using the leave-one-out cross-validation method. When combining FA+MD, AUC = 0.93, accuracy = 0.94, sensitivity = 0.98, and specificity = 0.86 in classifying LGGs from HGGs, while AUC = 0.99, accuracy = 0.98, sensitivity = 0.98, and specificity = 1.00 in classifying grade III from IV. The AUC and accuracy remain close when features were extracted from only the solid tumor or additionally including necrosis, cyst, and peritumoral edema. Still, the effects in terms of sensitivity and specificity are mixed. Deep radiomic features derived from pre-trained convolutional neural networks showed higher prediction ability than the traditional texture and shape features in both classification experiments. Radiomic features extracted on the FA and MD maps of brain DTI images are useful for noninvasively classification/grading of LGGs vs HGGs, and grade III vs IV.
Assuntos
Neoplasias Encefálicas , Glioma , Adolescente , Adulto , Neoplasias Encefálicas/diagnóstico por imagem , Criança , Pré-Escolar , Imagem de Tensor de Difusão , Feminino , Glioma/diagnóstico por imagem , Humanos , Lactente , Recém-Nascido , Masculino , Pessoa de Meia-Idade , Gradação de Tumores , Redes Neurais de Computação , Estudos Retrospectivos , Adulto JovemRESUMO
BACKGROUND: Artemisia pollen allergy is a major cause of asthma in Northern China. Possible associations between IgE responses to Artemisia allergen components and clinical phenotypes have not yet been evaluated. This study was to establish sensitization patterns of four Artemisia allergens and possible associations with demographic characteristics and clinical phenotypes in three areas of China. METHODS: Two hundred and forty patients allergic to Artemisia pollen were examined, 178 from Shanxi and 30 from Shandong Provinces in Northern China, and 32 from Yunnan Province in Southwestern China. Allergic asthma, rhinitis, conjunctivitis, and eczema symptoms were diagnosed. All patients' sera were tested by ImmunoCAP with mugwort pollen extract and the natural components nArt v 1, nArt ar 2, nArt v 3, and nArt an 7. RESULTS: The frequency of sensitization and the IgE levels of the four components in Artemisia allergic patients from Southwestern China were significantly lower than in those from the North. Art v 1 and Art an 7 were the most frequently recognized allergens (84% and 87%, respectively), followed by Art v 3 (66%) and Art ar 2 (48%). Patients from Northern China were more likely to have allergic asthma (50%) than patients from Southwestern China (3%), and being sensitized to more than two allergens increased the risk of allergic asthma, in which co-sensitization to three major allergens Art v 1, Art v 3, and Art an 7 is prominent. CONCLUSIONS: Component-resolved diagnosis of Chinese Artemisia pollen-allergic patients helps assess the potential risk of mugwort-associated allergic asthma.
Assuntos
Antígenos de Plantas/imunologia , Artemisia/efeitos adversos , Pólen/imunologia , Rinite Alérgica Sazonal/epidemiologia , Adolescente , Adulto , Criança , Pré-Escolar , Reações Cruzadas/imunologia , Feminino , Humanos , Imunização , Imunoglobulina E/sangue , Imunoglobulina E/imunologia , Masculino , Pessoa de Meia-Idade , Fenótipo , Rinite Alérgica Sazonal/diagnóstico , Adulto JovemRESUMO
BACKGROUND: Artemisia pollens have a high potential to induce allergic symptoms. Seven allergen components have been identified, but only Art v 7 has been localized in the pollen grain. This study aimed to localize the allergens in the pollen grains of 4 Artemisia spp. METHODS: Pollen extracts from 2 Chinese Artemisia spp., A. argyi and A. annua, were used to immunize BALB/c mice. Recombinant Art v 1 and Art v 3 allergens were used to select specific monoclonal antibodies (mAbs). Three mAbs were used to purify the natural allergens and were then analyzed by mass spectrometry. As reported previously, polyclonal antibodies were obtained from rabbits immunized with 3 synthesized peptides of Art an 7. Using conventional histology procedures with pollens from 4 Artemisia spp. (A. argyi, A. annua, A. capilaris, and A. sieversiana), allergen images were observed and recorded by fluorescence and confocal laser microscopy. RESULTS: We obtained 2 specific mAbs against Art v 1, 1 against Art v 2, and 4 against Art v 3 homologs. The Art v 1 and Art v 3 homologs were mainly located on the pollen walls, and the Art v 7 homologous protein was localized intracellularly around nuclei. The location of the Art v 2 homologous protein varied across species, being intracellular around nuclei for A. annua and A. argyi, and in both the pollen wall and around nuclei for A. capilaris and A. sieversiana. CONCLUSIONS: Four mugwort allergens were localized in the pollen, and the major Art v 1 and Art v 3 allergens were located mainly in the pollen wall.
Assuntos
Alérgenos/imunologia , Anticorpos Monoclonais/imunologia , Antígenos de Plantas/imunologia , Artemisia/imunologia , Pólen/imunologia , Ensaio de Imunoadsorção Enzimática , Imunofluorescência , ImmunoblottingRESUMO
BACKGROUND: The axillary lymph node status is critical for breast cancer staging and individualized treatment planning. PURPOSE: To assess the effect of determining axillary lymph node (ALN) metastasis by breast MRI-derived radiomic signatures, and compare the discriminating abilities of different MR sequences. STUDY TYPE: Retrospective. POPULATION: In all, 120 breast cancer patients, 59 with ALN metastasis and 61 without metastasis, all confirmed by pathology. FIELD STRENGTH/SEQUENCE: 3 .0T scanner with T1 -weighted imaging, T2 -weighted imaging, diffusion-weighted imaging, and dynamic contrast-enhanced (DCE) sequences. ASSESSMENT: Typical morphological and texture features of the segmented tumor were extracted from four sequences, ie, T1 WI, T2 WI, DWI, and the second postcontrast phase (CE2) of the dynamic contrast-enhanced sequences. Additional contrast enhancement kinetic features were extracted from all DCE sequences (one pre- and seven postcontrast phases). Linear discriminant analysis classifiers were built and compared when using features from an individual sequence or the combination of the sequences in differentiating the ALN metastasis status. STATISTICAL TESTS: Mann-Whitney U-test, Fisher's exact test, least absolute shrinkage selection operator (LASSO) regression, and receiver operating characteristic analysis were performed. RESULTS: The accuracy/AUC of the four sequences was 79%/0.87, 77%/0.85, 74%/0.79, and 79%/0.85 for the T1 WI, CE2, T2 WI, and DWI, respectively. When CE2 was augmented by adding kinetic features, the model achieved the highest performance (accuracy = 0.86 and AUC = 0.91). When all features from the four sequences and the kinetics were combined, it did not lead to a further increase in the performance (P = 0.48). DATA CONCLUSION: Breast tumor's radiomic signatures from preoperative breast MRI sequences are associated with the ALN metastasis status, where CE2 phase and the contrast enhancement kinetic features lead to the highest classification effect. Level of Evidence 3 Technical Efficacy Stage 2 J. Magn. Reson. Imaging 2019;50:1125-1132.