RESUMEN
PURPOSE: Attenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images. METHODS: Non-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center). RESULTS: In terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21-14.81%) and FL-PL (CI:11.82-13.84%) models demonstrated excellent agreement with the centralized framework (CI:10.32-12.00%), while FL-based algorithms improved model performance by over 11% compared to CB training strategy (CI: 22.34-26.10%). Furthermore, the Mann-Whitney test between different strategies revealed no significant differences between CZ and FL-based algorithms (p-value > 0.05) in center-categorized mode. At the same time, a significant difference was observed between the different training approaches on the overall dataset (p-value < 0.05). In addition, voxel-wise comparison, with respect to reference CT-ASC, exhibited similar performance for images predicted by CZ (R2 = 0.94), FL-SQ (R2 = 0.93), and FL-PL (R2 = 0.92), while CB model achieved a far lower coefficient of determination (R2 = 0.74). Despite the strong correlations between CZ and FL-based methods compared to reference CT-ASC, a slight underestimation of predicted voxel values was observed. CONCLUSION: Deep learning-based models provide promising results toward quantitative PET image reconstruction. Specifically, we developed two FL models and compared their performance with center-based and centralized models. The proposed FL-based models achieved higher performance compared to center-based models, comparable with centralized models. Our work provided strong empirical evidence that the FL framework can fully benefit from the generalizability and robustness of DL models used for AC/SC in PET, while obviating the need for the direct sharing of datasets between clinical imaging centers.
Asunto(s)
Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía Computarizada por Tomografía de Emisión de Positrones , Tomografía de Emisión de Positrones/métodos , Imagen por Resonancia Magnética/métodosRESUMEN
In this study, the ability of radiomics features extracted from myocardial perfusion imaging with SPECT (MPI-SPECT) was investigated for the prediction of ejection fraction (EF) post-percutaneous coronary intervention (PCI) treatment. A total of 52 patients who had undergone pre-PCI MPI-SPECT were enrolled in this study. After normalization of the images, features were extracted from the left ventricle, initially automatically segmented by k-means and active contour methods, and finally edited and approved by an expert radiologist. More than 1700 2D and 3D radiomics features were extracted from each patient's scan. A cross-combination of three feature selections and seven classifier methods was implemented. Three classes of no or dis-improvement (class 1), improved EF from 0 to 5% (class 2), and improved EF over 5% (class 3) were predicted by using tenfold cross-validation. Lastly, the models were evaluated based on accuracy, AUC, sensitivity, specificity, precision, and F-score. Neighborhood component analysis (NCA) selected the most predictive feature signatures, including Gabor, first-order, and NGTDM features. Among the classifiers, the best performance was achieved by the fine KNN classifier, which yielded mean accuracy, AUC, sensitivity, specificity, precision, and F-score of 0.84, 0.83, 0.75, 0.87, 0.78, and 0.76, respectively, in 100 iterations of classification, within the 52 patients with 10-fold cross-validation. The MPI-SPECT-based radiomic features are well suited for predicting post-revascularization EF and therefore provide a helpful approach for deciding on the most appropriate treatment.
Asunto(s)
Imagen de Perfusión Miocárdica , Intervención Coronaria Percutánea , Humanos , Volumen Sistólico , Tomografía Computarizada de Emisión de Fotón Único , Aprendizaje Automático , PerfusiónRESUMEN
A U-shaped contraction pattern was shown to be associated with a better Cardiac resynchronization therapy (CRT) response. The main goal of this study is to automatically recognize left ventricular contractile patterns using machine learning algorithms trained on conventional quantitative features (ConQuaFea) and radiomic features extracted from Gated single-photon emission computed tomography myocardial perfusion imaging (GSPECT MPI). Among 98 patients with standard resting GSPECT MPI included in this study, 29 received CRT therapy and 69 did not (also had CRT inclusion criteria but did not receive treatment yet at the time of data collection, or refused treatment). A total of 69 non-CRT patients were employed for training, and the 29 were employed for testing. The models were built utilizing features from three distinct feature sets (ConQuaFea, radiomics, and ConQuaFea + radiomics (combined)), which were chosen using Recursive feature elimination (RFE) feature selection (FS), and then trained using seven different machine learning (ML) classifiers. In addition, CRT outcome prediction was assessed by different treatment inclusion criteria as the study's final phase. The MLP classifier had the highest performance among ConQuaFea models (AUC, SEN, SPE = 0.80, 0.85, 0.76). RF achieved the best performance in terms of AUC, SEN, and SPE with values of 0.65, 0.62, and 0.68, respectively, among radiomic models. GB and RF approaches achieved the best AUC, SEN, and SPE values of 0.78, 0.92, and 0.63 and 0.74, 0.93, and 0.56, respectively, among the combined models. A promising outcome was obtained when using radiomic and ConQuaFea from GSPECT MPI to detect left ventricular contractile patterns by machine learning.
Asunto(s)
Imagen de Perfusión Miocárdica , Humanos , Tomografía Computarizada de Emisión de Fotón Único , Aprendizaje Automático , Algoritmos , PerfusiónRESUMEN
The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images in patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 patients who had visible scars on short-axis LGE-CMR images and were candidates for CABG surgery were selected and enrolled in this study. MR imaging was performed preoperatively using a 1.5-T MRI scanner. All images were segmented by two expert radiologists (in consensus). Prior to extraction of radiomics features, all MR images were resampled to an isotropic voxel size of 1.8 × 1.8 × 1.8 mm3. Subsequently, intensities were quantized to 64 discretized gray levels and a total of 93 features were extracted. The applied algorithms included a smoothly clipped absolute deviation (SCAD)-penalized support vector machine (SVM) and the recursive partitioning (RP) algorithm as a robust classifier for binary classification in this high-dimensional and non-sparse data. All models were validated with repeated fivefold cross-validation and 10,000 bootstrapping resamples. Ten and seven features were selected with SCAD-penalized SVM and RP algorithm, respectively, for CABG responder/non-responder classification. Considering univariate analysis, the GLSZM gray-level non-uniformity-normalized feature achieved the best performance (AUC: 0.62, 95% CI: 0.53-0.76) with SCAD-penalized SVM. Regarding multivariable modeling, SCAD-penalized SVM obtained an AUC of 0.784 (95% CI: 0.64-0.92), whereas the RP algorithm achieved an AUC of 0.654 (95% CI: 0.50-0.82). In conclusion, different radiomics texture features alone or combined in multivariate analysis using machine learning algorithms provide prognostic information regarding myocardial function in patients after CABG.
Asunto(s)
Algoritmos , Aprendizaje Automático , Humanos , Imagen por Resonancia Magnética/métodos , Máquina de Vectores de Soporte , Puente de Arteria Coronaria , Estudios RetrospectivosRESUMEN
INTRODUCTION: Placenta is a complex organ that plays a significant role in the maintenance of pregnancy health. It is a dynamic organ that undergoes dramatic changes in growth and development at different stages of gestation. In the first-trimester, the conceptus develops in a low oxygen environment that favors organogenesis in the embryo and cell proliferation and angiogenesis in the placenta; later in pregnancy, higher oxygen concentration is required to support the rapid growth of the fetus. This oxygen transition, which appears unique to the human placenta, must be finely tuned through successive rounds of protein signature alterations. This study compares placental proteome in normal first-trimester (FT) and term human placentas (TP). METHODS: Normal human first-trimester and term placental samples were collected and differentially expressed proteins were identified using two-dimensional liquid chromatography-tandem mass spectrometry. RESULTS: Despite the overall similarities, 120 proteins were differently expressed in first and term placentas. Out of these, 72 were up-regulated and 48 were down-regulated in the first when compared with the full term placentas. Twenty out of 120 differently expressed proteins were sequenced, among them seven showed increased (GRP78, PDIA3, ENOA, ECH1, PRDX4, ERP29, ECHM), eleven decreased (TRFE, ALBU, K2C1, ACTG, CSH2, PRDX2, FABP5, HBG1, FABP4, K2C8, K1C9) expression in first-trimester compared to the full-term placentas and two proteins exclusively expressed in first-trimester placentas (MESD, MYDGF). CONCLUSION: According to Reactome and PANTHER softwares, these proteins were mostly involved in response to chemical stimulus and stress, regulation of biological quality, programmed cell death, hemostatic and catabolic processes, protein folding, cellular oxidant detoxification, coagulation and retina homeostasis. Elucidation of alteration in protein signature during placental development would provide researchers with a better understanding of the critical biological processes of placentogenesis and delineate proteins involved in regulation of placental function during development.
RESUMEN
The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients' overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.
Asunto(s)
Carcinoma de Células Renales , Neoplasias Renales , Carcinoma de Células Renales/diagnóstico por imagen , Humanos , Neoplasias Renales/diagnóstico por imagen , Estudios Retrospectivos , Tomografía Computarizada por Rayos XRESUMEN
Male factor infertility is involved in almost half of all infertile couples. Lack of the ejaculated sperm owing to testicular malfunction has been reported in 6-10% of infertile men, a condition named nonobstructive azoospermia (NOA). In this study, we investigated untargeted metabolomic profiling of the seminal plasma in NOA men using gas chromatography-mass spectrometry and advance chemometrics. In this regard, the seminal plasma fluids of 11 NOA men with TESE-negative, nine NOA men with TESE-positive and 10 fertile healthy men (as a control group) were collected. Quadratic discriminate analysis (QDA) technique was implemented on total ion chromatograms (TICs) for identification of discriminatory retention times. We developed multivariate classification models using the QDA technique. Our results revealed that the developed QDA models could predict the classes of samples using their TIC data. The receiver operating characteristic curves for these models were >0.88. After recognition of discriminatory retention time's asymmetric penalized least square, evolving factor analysis, correlation optimized warping and alternating least squares strategies were applied for preprocessing and deconvolution of the overlapped chromatographic peaks. We could identify 36 discriminatory metabolites. These metabolites may be considered discriminatory biomarkers for different groups in NOA.
Asunto(s)
Azoospermia/metabolismo , Metaboloma , Semen/metabolismo , Espermatogénesis , Azoospermia/diagnóstico , Azoospermia/fisiopatología , Análisis Discriminante , Cromatografía de Gases y Espectrometría de Masas/métodos , Humanos , Masculino , Metabolómica/métodosRESUMEN
BACKGROUND: This study compares the effectiveness of three treating methods including behavioral mother training (BMT), Verbal self-instruction to the children (VSI), and pharmacotherapy in children with attention deficit-hyperactivity disorder (ADHD) using the continuous performance test (CPT). SUBJECTS AND METHODS: In this semi-experimental study, 51 elementary students were identified in a boys' school in Shiraz (age 8-10) with attention deficit-hyperactivity disorder in a pilot study (among 1760 students). They were randomly divided into three groups; BMT, VSI, and control group. Moreover, 22 students were selected with ADHD among the clients in Hafez hospital. They were chosen by the availability method and they were put into the Pharmacotherapy group. Data collection tools were the Child Symptoms Inventory (CSI-4) and the continuous performance test. All of the groups were evaluated after the intervention and in post-test and also 2 months later in follow up. RESULTS: The treatment type (group) showed statistically significant difference in the result of CPT on severity of attention-deficit and in the number of correct responses (P=0.01), yet on the hyperactivity symptoms, there was no significant difference between the different treatment groups (P=0.08). The time factor shows a significant difference among the different groups (p<0.001). CONCLUSIONS: Comparison of the various treatments of ADHD indicates that pharmacotherapy can improve the severity of attention deficit and the number of correct answers of children with ADHD.
Asunto(s)
Trastorno por Déficit de Atención con Hiperactividad/terapia , Terapia Conductista/métodos , Estimulantes del Sistema Nervioso Central/farmacología , Metilfenidato/farmacología , Pruebas Neuropsicológicas , Trastorno por Déficit de Atención con Hiperactividad/tratamiento farmacológico , Trastorno por Déficit de Atención con Hiperactividad/fisiopatología , Estimulantes del Sistema Nervioso Central/administración & dosificación , Niño , Humanos , Masculino , Metilfenidato/administración & dosificación , Proyectos Piloto , Índice de Severidad de la Enfermedad , Resultado del TratamientoRESUMEN
We focus on reviewing state-of-the-art developments of dedicated PET scanners with irregular geometries and the potential of different aspects of multifunctional PET imaging. First, we discuss advances in non-conventional PET detector geometries. Then, we present innovative designs of organ-specific dedicated PET scanners for breast, brain, prostate, and cardiac imaging. We will also review challenges and possible artifacts by image reconstruction algorithms for PET scanners with irregular geometries, such as non-cylindrical and partial angular coverage geometries and how they can be addressed. Then, we attempt to address some open issues about cost/benefits analysis of dedicated PET scanners, how far are the theoretical conceptual designs from the market/clinic, and strategies to reduce fabrication cost without compromising performance.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Tomografía de Emisión de Positrones , Humanos , Fantasmas de Imagen , Tomografía de Emisión de Positrones/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Encéfalo , AlgoritmosRESUMEN
BACKGROUND: This study aimed to investigate the value of clinical, radiomic features extracted from gross tumor volumes (GTVs) delineated on CT images, dose distributions (Dosiomics), and fusion of CT and dose distributions to predict outcomes in head and neck cancer (HNC) patients. METHODS: A cohort of 240 HNC patients from five different centers was obtained from The Cancer Imaging Archive. Seven strategies, including four non-fusion (Clinical, CT, Dose, DualCT-Dose), and three fusion algorithms (latent low-rank representation referred (LLRR),Wavelet, weighted least square (WLS)) were applied. The fusion algorithms were used to fuse the pre-treatment CT images and 3-dimensional dose maps. Overall, 215 radiomics and Dosiomics features were extracted from the GTVs, alongside with seven clinical features incorporated. Five feature selection (FS) methods in combination with six machine learning (ML) models were implemented. The performance of the models was quantified using the concordance index (CI) in one-center-leave-out 5-fold cross-validation for overall survival (OS) prediction considering the time-to-event. RESULTS: The mean CI and Kaplan-Meier curves were used for further comparisons. The CoxBoost ML model using the Minimal Depth (MD) FS method and the glmnet model using the Variable hunting (VH) FS method showed the best performance with CI = 0.73 ± 0.15 for features extracted from LLRR fused images. In addition, both glmnet-Cindex and Coxph-Cindex classifiers achieved a CI of 0.72 ± 0.14 by employing the dose images (+ incorporated clinical features) only. CONCLUSION: Our results demonstrated that clinical features, Dosiomics and fusion of dose and CT images by specific ML-FS models could predict the overall survival of HNC patients with acceptable accuracy. Besides, the performance of ML methods among the three different strategies was almost comparable.
Asunto(s)
Neoplasias de Cabeza y Cuello , Radiómica , Humanos , Pronóstico , Neoplasias de Cabeza y Cuello/diagnóstico por imagen , Neoplasias de Cabeza y Cuello/radioterapia , Aprendizaje Automático , Tomografía Computarizada por Rayos XRESUMEN
PURPOSE: Non-small cell lung cancer is the most common subtype of lung cancer. Patient survival prediction using machine learning (ML) and radiomics analysis proved to provide promising outcomes. However, most studies reported in the literature focused on information extracted from malignant lesions. This study aims to explore the relevance and additional value of information extracted from healthy organs in addition to tumoral tissue using ML algorithms. PATIENTS AND METHODS: This study included PET/CT images of 154 patients collected from available online databases. The gross tumor volume and 33 volumes of interest defined on healthy organs were segmented using nnU-Net deep learning-based segmentation. Subsequently, 107 radiomic features were extracted from PET and CT images (Organomics). Clinical information was combined with PET and CT radiomics from organs and gross tumor volumes considering 19 different combinations of inputs. Finally, different feature selection (FS; 5 methods) and ML (6 algorithms) algorithms were tested in a 3-fold data split cross-validation scheme. The performance of the models was quantified in terms of the concordance index (C-index) metric. RESULTS: For an input combination of all radiomics information, most of the selected features belonged to PET Organomics and CT Organomics. The highest C-index (0.68) was achieved using univariate C-index FS method and random survival forest ML model using CT Organomics + PET Organomics as input as well as minimum depth FS method and CoxPH ML model using PET Organomics as input. Considering all 17 combinations with C-index higher than 0.65, Organomics from PET or CT images were used as input in 16 of them. CONCLUSIONS: The selected features and C-indices demonstrated that the additional information extracted from healthy organs of both PET and CT imaging modalities improved the ML performance. Organomics could be a step toward exploiting the whole information available from multimodality medical images, contributing to the emerging field of digital twins in health care.
RESUMEN
BACKGROUND: PET/CT images combining anatomic and metabolic data provide complementary information that can improve clinical task performance. PET image segmentation algorithms exploiting the multi-modal information available are still lacking. PURPOSE: Our study aimed to assess the performance of PET and CT image fusion for gross tumor volume (GTV) segmentations of head and neck cancers (HNCs) utilizing conventional, deep learning (DL), and output-level voting-based fusions. METHODS: The current study is based on a total of 328 histologically confirmed HNCs from six different centers. The images were automatically cropped to a 200 × 200 head and neck region box, and CT and PET images were normalized for further processing. Eighteen conventional image-level fusions were implemented. In addition, a modified U2-Net architecture as DL fusion model baseline was used. Three different input, layer, and decision-level information fusions were used. Simultaneous truth and performance level estimation (STAPLE) and majority voting to merge different segmentation outputs (from PET and image-level and network-level fusions), that is, output-level information fusion (voting-based fusions) were employed. Different networks were trained in a 2D manner with a batch size of 64. Twenty percent of the dataset with stratification concerning the centers (20% in each center) were used for final result reporting. Different standard segmentation metrics and conventional PET metrics, such as SUV, were calculated. RESULTS: In single modalities, PET had a reasonable performance with a Dice score of 0.77 ± 0.09, while CT did not perform acceptably and reached a Dice score of only 0.38 ± 0.22. Conventional fusion algorithms obtained a Dice score range of [0.76-0.81] with guided-filter-based context enhancement (GFCE) at the low-end, and anisotropic diffusion and Karhunen-Loeve transform fusion (ADF), multi-resolution singular value decomposition (MSVD), and multi-level image decomposition based on latent low-rank representation (MDLatLRR) at the high-end. All DL fusion models achieved Dice scores of 0.80. Output-level voting-based models outperformed all other models, achieving superior results with a Dice score of 0.84 for Majority_ImgFus, Majority_All, and Majority_Fast. A mean error of almost zero was achieved for all fusions using SUVpeak , SUVmean and SUVmedian . CONCLUSION: PET/CT information fusion adds significant value to segmentation tasks, considerably outperforming PET-only and CT-only methods. In addition, both conventional image-level and DL fusions achieve competitive results. Meanwhile, output-level voting-based fusion using majority voting of several algorithms results in statistically significant improvements in the segmentation of HNC.
Asunto(s)
Neoplasias de Cabeza y Cuello , Tomografía Computarizada por Tomografía de Emisión de Positrones , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Algoritmos , Neoplasias de Cabeza y Cuello/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
The treatment of pain is a patient's right. Pain management committees in healthcare institutions organise and promote pain control programmes.The diversity of care services requires caregivers to use new skills, as shown by the example of mental health and the specific case of the teenager. To relieve pain, innovative nursing practices as well as the use of non-drug based methods would seem to open up new perspectives for the future.
Asunto(s)
Salud Mental , Manejo del Dolor , Dolor/psicología , Adolescente , Conducta del Adolescente/psicología , HumanosRESUMEN
This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models' evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.
Asunto(s)
Enfermedad de la Arteria Coronaria , Diabetes Mellitus , Imagen de Perfusión Miocárdica , Humanos , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Aprendizaje Automático , Tomografía Computarizada de Emisión de Fotón Único , Masculino , FemeninoRESUMEN
PROPOSE: An electrocardiogram (ECG) has been extensively used to detect rhythm disturbances. We sought to determine the accuracy of different machine learning in distinguishing abnormal ECGs from normal ones in children who were examined using a resting 12-Lead ECG machine, and we also compared the manual and automated measurement using the modular ECG Analysis System (MEANS) algorithm of ECG features. METHODS: Altogether, 10745 ECGs were recorded for students aged 6 to 18. Manual and automatic ECG features were extracted for each participant. Features were normalized using Z-score normalization and went through the student's t-test and chi-squared test to measure their relevance. We applied the Boruta algorithm for feature selection and then implemented eight classifier algorithms. The dataset was split into training (80%) and test (20%) partitions. The performance of the classifiers was evaluated on the test data (unseen data) by 1000 bootstrap, and sensitivity (SEN), specificity (SPE), AUC, and accuracy (ACC) were reported. RESULTS: In univariate analysis, the highest performance was heart rate and RR interval in the manual dataset and heart rate in an automated dataset with AUC of 0.72 and 0.71, respectively. The best classifiers in the manual dataset were random forest (RF) and quadratic-discriminant-analysis (QDA) with AUC, ACC, SEN, and SPE equal to 0.93, 0.98, 0.69, 0.99, and 0.90, 0.95, 0.75, 0.96, respectively. In the automated dataset, QDA (AUC: 0.89, ACC:0.92, SEN:0.71, SPE:0.93) and stack learning (SL) (AUC:0.89, ACC:0.96, SEN:0.61, SPE:0.99) reached best performances. CONCLUSION: This study demonstrated that the manual measurement of 12-Lead ECG features had better performance than the automated measurement (MEANS algorithm), but some classifiers had promising results in discriminating between normal and abnormal cases. Further studies can help us evaluate the applicability and efficacy of machine-learning approaches for distinguishing abnormal ECGs in community-based investigations in both adults and children.
Asunto(s)
Algoritmos , Aprendizaje Automático , Adulto , Niño , Humanos , Adolescente , Estudios de Cohortes , Arritmias Cardíacas/diagnóstico , Electrocardiografía/métodosRESUMEN
BACKGROUND AND OBJECTIVE: Generalizable and trustworthy deep learning models for PET/CT image segmentation necessitates large diverse multi-institutional datasets. However, legal, ethical, and patient privacy issues challenge sharing of datasets between different centers. To overcome these challenges, we developed a federated learning (FL) framework for multi-institutional PET/CT image segmentation. METHODS: A dataset consisting of 328 FL (HN) cancer patients who underwent clinical PET/CT examinations gathered from six different centers was enrolled. A pure transformer network was implemented as fully core segmentation algorithms using dual channel PET/CT images. We evaluated different frameworks (single center-based, centralized baseline, as well as seven different FL algorithms) using 68 PET/CT images (20% of each center data). In particular, the implemented FL algorithms include clipping with the quantile estimator (ClQu), zeroing with the quantile estimator (ZeQu), federated averaging (FedAvg), lossy compression (LoCo), robust aggregation (RoAg), secure aggregation (SeAg), and Gaussian differentially private FedAvg with adaptive quantile clipping (GDP-AQuCl). RESULTS: The Dice coefficient was 0.80±0.11 for both centralized and SeAg FL algorithms. All FL approaches achieved centralized learning model performance with no statistically significant differences. Among the FL algorithms, SeAg and GDP-AQuCl performed better than the other techniques. However, there was no statistically significant difference. All algorithms, except the center-based approach, resulted in relative errors less than 5% for SUVmax and SUVmean for all FL and centralized methods. Centralized and FL algorithms significantly outperformed the single center-based baseline. CONCLUSIONS: The developed FL-based (with centralized method performance) algorithms exhibited promising performance for HN tumor segmentation from PET/CT images.
Asunto(s)
Aprendizaje Profundo , Neoplasias , Humanos , Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias/diagnóstico por imagen , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodosRESUMEN
PURPOSE: Whole-body bone scintigraphy (WBS) is one of the most widely used modalities in diagnosing malignant bone diseases during the early stages. However, the procedure is time-consuming and requires vigour and experience. Moreover, interpretation of WBS scans in the early stages of the disorders might be challenging because the patterns often reflect normal appearance that is prone to subjective interpretation. To simplify the gruelling, subjective, and prone-to-error task of interpreting WBS scans, we developed deep learning (DL) models to automate two major analyses, namely (i) classification of scans into normal and abnormal and (ii) discrimination between malignant and non-neoplastic bone diseases, and compared their performance with human observers. MATERIALS AND METHODS: After applying our exclusion criteria on 7188 patients from three different centers, 3772 and 2248 patients were enrolled for the first and second analyses, respectively. Data were split into two parts, including training and testing, while a fraction of training data were considered for validation. Ten different CNN models were applied to single- and dual-view input (posterior and anterior views) modes to find the optimal model for each analysis. In addition, three different methods, including squeeze-and-excitation (SE), spatial pyramid pooling (SPP), and attention-augmented (AA), were used to aggregate the features for dual-view input models. Model performance was reported through area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity and was compared with the DeLong test applied to ROC curves. The test dataset was evaluated by three nuclear medicine physicians (NMPs) with different levels of experience to compare the performance of AI and human observers. RESULTS: DenseNet121_AA (DensNet121, with dual-view input aggregated by AA) and InceptionResNetV2_SPP achieved the highest performance (AUCâ¯=â¯0.72) for the first and second analyses, respectively. Moreover, on average, in the first analysis, Inception V3 and InceptionResNetV2 CNN models and dual-view input with AA aggregating method had superior performance. In addition, in the second analysis, DenseNet121 and InceptionResNetV2 as CNN methods and dual-view input with AA aggregating method achieved the best results. Conversely, the performance of AI models was significantly higher than human observers for the first analysis, whereas their performance was comparable in the second analysis, although the AI model assessed the scans in a drastically lower time. CONCLUSION: Using the models designed in this study, a positive step can be taken toward improving and optimizing WBS interpretation. By training DL models with larger and more diverse cohorts, AI could potentially be used to assist physicians in the assessment of WBS images.
RESUMEN
OBJECTIVE: To investigate the impact of harmonization on the performance of CT, PET, and fused PET/CT radiomic features toward the prediction of mutations status, for epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma viral oncogene (KRAS) genes in non-small cell lung cancer (NSCLC) patients. METHODS: Radiomic features were extracted from tumors delineated on CT, PET, and wavelet fused PET/CT images obtained from 136 histologically proven NSCLC patients. Univariate and multivariate predictive models were developed using radiomic features before and after ComBat harmonization to predict EGFR and KRAS mutation statuses. Multivariate models were built using minimum redundancy maximum relevance feature selection and random forest classifier. We utilized 70/30% splitting patient datasets for training/testing, respectively, and repeated the procedure 10 times. The area under the receiver operator characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess model performance. The performance of the models (univariate and multivariate), before and after ComBat harmonization was compared using statistical analyses. RESULTS: While the performance of most features in univariate modeling was significantly improved for EGFR prediction, most features did not show any significant difference in performance after harmonization in KRAS prediction. Average AUCs of all multivariate predictive models for both EGFR and KRAS were significantly improved (q-value < 0.05) following ComBat harmonization. The mean ranges of AUCs increased following harmonization from 0.87-0.90 to 0.92-0.94 for EGFR, and from 0.85-0.90 to 0.91-0.94 for KRAS. The highest performance was achieved by harmonized F_R0.66_W0.75 model with AUC of 0.94, and 0.93 for EGFR and KRAS, respectively. CONCLUSION: Our results demonstrated that regarding univariate modelling, while ComBat harmonization had generally a better impact on features for EGFR compared to KRAS status prediction, its effect is feature-dependent. Hence, no systematic effect was observed. Regarding the multivariate models, ComBat harmonization significantly improved the performance of all radiomics models toward more successful prediction of EGFR and KRAS mutation statuses in lung cancer patients. Thus, by eliminating the batch effect in multi-centric radiomic feature sets, harmonization is a promising tool for developing robust and reproducible radiomics using vast and variant datasets.
Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Carcinoma de Pulmón de Células no Pequeñas/diagnóstico por imagen , Carcinoma de Pulmón de Células no Pequeñas/genética , Receptores ErbB/genética , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patología , Mutación/genética , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Proteínas Proto-Oncogénicas p21(ras)/genéticaRESUMEN
AIMS: Despite the promising results achieved by radiomics prognostic models for various clinical applications, multiple challenges still need to be addressed. The two main limitations of radiomics prognostic models include information limitation owing to single imaging modalities and the selection of optimum machine learning and feature selection methods for the considered modality and clinical outcome. In this work, we applied several feature selection and machine learning methods to single-modality positron emission tomography (PET) and computed tomography (CT) and multimodality PET/CT fusion to identify the best combinations for different radiomics modalities towards overall survival prediction in non-small cell lung cancer patients. MATERIALS AND METHODS: A PET/CT dataset from The Cancer Imaging Archive, including subjects from two independent institutions (87 and 95 patients), was used in this study. Each cohort was used once as training and once as a test, followed by averaging of the results. ComBat harmonisation was used to address the centre effect. In our proposed radiomics framework, apart from single-modality PET and CT models, multimodality radiomics models were developed using multilevel (feature and image levels) fusion. Two different methods were considered for the feature-level strategy, including concatenating PET and CT features into a single feature set and alternatively averaging them. For image-level fusion, we used three different fusion methods, namely wavelet fusion, guided filtering-based fusion and latent low-rank representation fusion. In the proposed prognostic modelling framework, combinations of four feature selection and seven machine learning methods were applied to all radiomics modalities (two single and five multimodalities), machine learning hyper-parameters were optimised and finally the models were evaluated in the test cohort with 1000 repetitions via bootstrapping. Feature selection and machine learning methods were selected as popular techniques in the literature, supported by open source software in the public domain and their ability to cope with continuous time-to-event survival data. Multifactor ANOVA was used to carry out variability analysis and the proportion of total variance explained by radiomics modality, feature selection and machine learning methods was calculated by a bias-corrected effect size estimate known as ω2. RESULTS: Optimum feature selection and machine learning methods differed owing to the applied radiomics modality. However, minimum depth (MD) as feature selection and Lasso and Elastic-Net regularized generalized linear model (glmnet) as machine learning method had the highest average results. Results from the ANOVA test indicated that the variability that each factor (radiomics modality, feature selection and machine learning methods) introduces to the performance of models is case specific, i.e. variances differ regarding different radiomics modalities and fusion strategies. Overall, the greatest proportion of variance was explained by machine learning, except for models in feature-level fusion strategy. CONCLUSION: The identification of optimal feature selection and machine learning methods is a crucial step in developing sound and accurate radiomics risk models. Furthermore, optimum methods are case specific, differing due to the radiomics modality and fusion strategy used.
Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Algoritmos , Carcinoma de Pulmón de Células no Pequeñas/diagnóstico por imagen , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Aprendizaje Automático , Imagen Multimodal , Tomografía Computarizada por Tomografía de Emisión de Positrones , PronósticoRESUMEN
PURPOSE: The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach. METHODS: PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations. RESULTS: The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed. CONCLUSION: The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.