Radiomic analysis for predicting prognosis of colorectal cancer from preoperative 18F-FDG PET/CT.

BACKGROUND: To develop and validate a survival model with clinico-biological features and 18F- FDG PET/CT radiomic features via machine learning, and for predicting the prognosis from the primary tumor of colorectal cancer. METHODS: A total of 196 pathologically confirmed patients with colorectal cancer (stage I to stage IV) were included. Preoperative clinical factors, serum tumor markers, and PET/CT radiomic features were included for the recurrence-free survival analysis. For the modeling and validation, patients were randomly divided into the training (n = 137) and validation (n = 59) set, while the 78 stage III patients [training (n = 55), and validation (n = 23)] was divided for the further experiment. After selecting features by the log-rank test and variable-hunting methods, random survival forest (RSF) models were built on the training set to analyze the prognostic value of selected features. The performance of models was measured by C-index and was tested on the validation set with bootstrapping. Feature importance and the Pearson correlation were also analyzed. RESULTS: Radiomics signature (containing four PET/CT features and four clinical factors) achieved the best result for prognostic prediction of 196 patients (C-index 0.780, 95% CI 0.634-0.877). Moreover, four features (including two clinical features and two radiomics features) were selected for prognostic prediction of the 78 stage III patients (C-index was 0.820, 95% CI 0.676-0.900). K-M curves of both models significantly stratified low-risk and high-risk groups (P < 0.0001). Pearson correlation analysis demonstrated that selected radiomics features were correlated with tumor metabolic factors, such as SUVmean, SUVmax. CONCLUSION: This study presents integrated clinico-biological-radiological models that can accurately predict the prognosis in colorectal cancer using the preoperative 18F-FDG PET/CT radiomics in colorectal cancer. It is of potential value in assisting the management and decision making for precision treatment in colorectal cancer. Trial registration The retrospectively registered study was approved by the Ethics Committee of Fudan University Shanghai Cancer Center (No. 1909207-14-1910) and the data were analyzed anonymously.

Co-fermented cow milk protein by Lactobacillus helveticus KLDS 1.8701 and Lactobacillus plantarum KLDS 1.0386 attenuates its allergic immune response in Balb/c mice.

Milk protein is one of the major food allergens. As an effective processing method, fermentation may reduce the potential allergenicity of allergens. This study aimed to evaluate the therapeutic potential of co-fermented milk protein using Lactobacillus helveticus KLDS 1.8701 and Lactobacillus plantarum KLDS 1.0386 in cow milk protein allergy (CMPA) management. This study determined the secondary and tertiary structures of the fermented versus unfermented proteins by Fourier-transform infrared spectroscopy and surface hydrophobicity to evaluate its conformational changes. Our results showed that different fermentation methods have significantly altered the conformational structures of the cow milk protein, especially the tertiary structure. Further, the potential allergenicity of the fermented cow milk protein was assessed in Balb/c mice, and mice treated with the unfermented milk and phosphate-buffered saline were used as a control. We observed a significant reduction in allergenicity via the results of the spleen index, serum total IgE, specific IgE, histamine, and mouse mast cell protease 1 in the mice treated with the co-fermented milk protein. In addition, we analyzed the cytokines and transcription factors expression levels of spleen and jejunum and confirmed that co-fermentation could effectively reduce the sensitization of cow milk protein by regulating the imbalance of T helper (Th1/Th2 and Treg/Th17). This study suggested that changes of conformational structure could reduce the potential sensitization of cow milk protein; thus, fermentation may be a promising strategy for developing a method of hypoallergenic dairy products.

Multi-parametric MRI phenotype with trustworthy machine learning for differentiating CNS demyelinating diseases.

BACKGROUND: Misdiagnosis of multiple sclerosis (MS) and neuromyelitis optica (NMO) may delay the treatment, resulting in poor prognosis. However, the precise identification of these two diseases is still challenging in clinical practice. We aimed to evaluate the value of quantitative radiomic features extracted from the brain white matter lesions for differential diagnosis of MS and NMO. METHODS: We recruited 116 CNS demyelinating patients including 78 MS, and 38 NMO. Three neuroradiologists performed visual differential diagnosis based on brain MRI for comparison purpose. A multi-level scheme was designed to harness the selection of discriminative and stable radiomics features extracted from brain while mater lesions in T1-MPRAGE, T2 sequences and clinical factors. Based on the imaging phenotype composed of the selected radiomic and clinical features, Multi-parametric Multivariate Random Forest (MM-RF) model was constructed and verified with both 10-fold cross-validation and independent testing. Result interpretation was provided to build trust in diagnostic decisions. RESULTS: Eighty-six patients were randomly selected to form the training set while the rest 30 patients for independent testing. On the training set, our MM-RF model achieved accuracy 0.849 and AUC 0.826 in 10-fold cross-validation, which were significantly higher than clinical visual analysis (0.709 and 0.683, p < 0.05). In the independent testing, the MM-RF model achieved AUC 0.902, accuracy 0.871, sensitivity 0.873, specificity 0.869, respectively. Furthermore, age, sex and EDSS were found mildly correlated with the radiomic features (p of all < 0.05). CONCLUSIONS: Multi-parametric radiomic features have potential as practical quantitative imaging biomarkers for differentiating MS from NMO.

Automatic identification of myopic maculopathy related imaging features in optic disc region via machine learning methods.

BACKGROUND: Myopic maculopathy (MM) is the most serious and irreversible complication of pathologic myopia, which is a major cause of visual impairment and blindness. Clinic proposed limited number of factors related to MM. To explore additional features strongly related with MM from optic disc region, we employ a machine learning based radiomics analysis method, which could explore and quantify more hidden or imperceptible MM-related features to the naked eyes and contribute to a more comprehensive understanding of MM and therefore may assist to distinguish the high-risk population in an early stage. METHODS: A total of 457 eyes (313 patients) were enrolled and were divided into severe MM group and without severe MM group. Radiomics analysis was applied to depict features significantly correlated with severe MM from optic disc region. Receiver Operating Characteristic were used to evaluate these features' performance of classifying severe MM. RESULTS: Eight new MM-related image features were discovered from the optic disc region, which described the shapes, textural patterns and intensity distributions of optic disc region. Compared with clinically reported MM-related features, these newly discovered features exhibited better abilities on severe MM classification. And the mean values of most features were markedly changed between patients with peripapillary diffuse chorioretinal atrophy (PDCA) and macular diffuse chorioretinal atrophy (MDCA). CONCLUSIONS: Machine learning and radiomics method are useful tools for mining more MM-related features from the optic disc region, by which complex or even hidden MM-related features can be discovered and decoded. In this paper, eight new MM-related image features were found, which would be useful for further quantitative study of MM-progression. As a nontrivial byproduct, marked changes between PDCA and MDCA was discovered by both new image features and clinic features.

Integrative nomogram of CT imaging, clinical, and hematological features for survival prediction of patients with locally advanced non-small cell lung cancer.

OBJECTIVES: To determine the integrative value of clinical, hematological, and computed tomography (CT) radiomic features in survival prediction for locally advanced non-small cell lung cancer (LA-NSCLC) patients. METHODS: Radiomic features and clinical and hematological features of 118 LA-NSCLC cases were firstly extracted and analyzed in this study. Then, stable and prognostic radiomic features were automatically selected using the consensus clustering method with either Cox proportional hazard (CPH) model or random survival forest (RSF) analysis. Predictive radiomic, clinical, and hematological parameters were subsequently fitted into a final prognostic model using both the CPH model and the RSF model. A multimodality nomogram was then established from the fitting model and was cross-validated. Finally, calibration curves were generated with the predicted versus actual survival status. RESULTS: Radiomic features selected by clustering combined with CPH were found to be more predictive, with a C-index of 0.699 in comparison to 0.648 by clustering combined with RSF. Based on multivariate CPH model, our integrative nomogram achieved a C-index of 0.792 and retained 0.743 in the cross-validation analysis, outperforming radiomic, clinical, or hematological model alone. The calibration curve showed agreement between predicted and actual values for the 1-year and 2-year survival prediction. Interestingly, the selected important radiomic features were significantly correlated with levels of platelet, platelet/lymphocyte ratio (PLR), and lymphocyte/monocyte ratio (LMR) (p values all < 0.05). CONCLUSIONS: The integrative nomogram incorporated CT radiomic, clinical, and hematological features improved survival prediction in LA-NSCLC patients, which would offer a feasible and practical reference for individualized management of these patients. KEY POINTS: • An integrative nomogram incorporated CT radiomic, clinical, and hematological features was constructed and cross-validated to predict prognosis of LA-NSCLC patients. • The integrative nomogram outperformed radiomic, clinical, or hematological model alone. • This nomogram has value to permit non-invasive, comprehensive, and dynamical evaluation of the phenotypes of LA-NSCLC and can provide a feasible and practical reference for individualized management of LA-NSCLC patients.

Preoperative 18F-FDG PET/CT radiomics analysis for predicting HER2 expression and prognosis in gastric cancer.

Background: We aimed to establish and validate 2 machine learning models using 18F-flurodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomic features to predict human epidermal growth factor receptor 2 (HER2) expression and prognosis in gastric cancer (GC) patients. Methods: We retrospectively enrolled 90 patients diagnosed with GC, including their clinical information and the 18F-FDG PET/CT images. Patients were allocated to a training cohort of 72 patients and an independent validation cohort (IVC) of 18 patients. There were 2,100 radiomic features extracted from the 18F-FDG PET/CT scans. A sequential combination of multivariate and univariate feature selection was applied, including sequential forward selection and a redundancy-based analysis. The justification of the model performance was conducted by cross-validation analysis on the training set and an independent validation analysis. Results: The machine learning models were developed using a balanced bagging approach for HER2 expression prediction and prognosis prediction, which differentiated HER2 positive expression from negative expression in the IVC with an area under the receiver operating characteristic curve (AUC) of 0.72, sensitivity of 0.85, and specificity of 0.80. The IVC for prognosis prediction achieved an AUC of 0.75, sensitivity of 0.82, and specificity of 0.71. We also conducted a reasonable interpretation for the selected features in each classification task from multiple aspects, including normalized feature importance analysis and statistical correlation analysis with the clinical features that were defaulted to be effective. Conclusions: 18F-FDG PET/CT radiomics analysis with a machine learning model provides a quantitative, efficient, and objective mechanism for predicting HER2 expression and prognosis in GC patients.

SARS-COV-2 protein NSP9 promotes cytokine production by targeting TBK1.

SARS-COV-2 infection-induced excessive or uncontrolled cytokine storm may cause injury of host tissue or even death. However, the mechanism by which SARS-COV-2 causes the cytokine storm is unknown. Here, we demonstrated that SARS-COV-2 protein NSP9 promoted cytokine production by interacting with and activating TANK-binding kinase-1 (TBK1). With an rVSV-NSP9 virus infection model, we discovered that an NSP9-induced cytokine storm exacerbated tissue damage and death in mice. Mechanistically, NSP9 promoted the K63-linked ubiquitination and phosphorylation of TBK1, which induced the activation and translocation of IRF3, thereby increasing downstream cytokine production. Moreover, the E3 ubiquitin ligase Midline 1 (MID1) facilitated the K48-linked ubiquitination and degradation of NSP9, whereas virus infection inhibited the interaction between MID1 and NSP9, thereby inhibiting NSP9 degradation. Additionally, we identified Lys59 of NSP9 as a critical ubiquitin site involved in the degradation. These findings elucidate a previously unknown mechanism by which a SARS-COV-2 protein promotes cytokine storm and identifies a novel target for COVID-19 treatment.

Glutamylation of an HIV-1 protein inhibits the immune response by hijacking STING.

Cyclic GMP-AMP synthase (cGAS) recognizes Y-form cDNA of human immunodeficiency virus type 1 (HIV-1) and initiates antiviral immune response through cGAS-stimulator of interferon genes (STING)-TBK1-IRF3-type I interferon (IFN-I) signalingcascade. Here, we report that the HIV-1 p6 protein suppresses HIV-1-stimulated expression of IFN-I and promotes immune evasion. Mechanistically, the glutamylated p6 at residue Glu6 inhibits the interaction between STING and tripartite motif protein 32 (TRIM32) or autocrine motility factor receptor (AMFR). This subsequently suppresses the K27- and K63-linked polyubiquitination of STING at K337, therefore inhibiting STING activation, whereas mutation of the Glu6 residue partially reverses the inhibitory effect. However, CoCl2, an agonist of cytosolic carboxypeptidases (CCPs), counteracts the glutamylation of p6 at the Glu6 residue and inhibits HIV-1 immune evasion. These findings reveal a mechanism through which an HIV-1 protein mediates immune evasion and provides a therapeutic drug candidate to treat HIV-1 infection.

Dynamic topology analysis for spatial patterns of multifocal lesions on MRI.

Quantitatively analysing the spatial patterns of multifocal lesions on clinical MRI is an important step towards a better understanding of the disease and for precision medicine, which is yet to be properly explored by feature engineering and deep learning methods. Network science addresses this issue by explicitly modeling the inter-lesion topology. However, the construction of the informative graph with optimal edge sparsity and quantification of community graph structures are the current challenges in network science. In this paper, we address these challenges with a novel Dynamic Topology Analysis framework on the basis of persistent homology, aiming to investigate the predictive values of global geometry and local clusters of multifocal lesions. Firstly, Dynamic Hierarchical Network is proposed to construct informative global and community-level topology over multi-scale networks from sparse to dense. Multi-scale global topology is constructed with a nested sequence of Rips complexes, from which a new K-simplex Filtration is designed to generate a higher-level topological abstraction for community identification based on the connectivity of k-simplices in the Rips Complex. Secondly, to quantify multi-scale community structures, we design a new Decomposed Community Persistence algorithm to track the dynamic evolution of communities, and then summarise the evolutionary communities incorporated with a customisable descriptor. The quantified community features are encapsulated with global geometric invariants for topological pattern analysis. The proposed framework was evaluated on both diagnostic differentiation and prognostic prediction for multiple sclerosis that is a typical multifocal disease, and achieved ROC_AUC 0.875 and 0.767, respectively, outperforming seven state-of-the-art persistent homology methods and the reported performance of six feature engineering and deep learning methods.

18F-FDG PET/CT radiomic analysis for classifying and predicting microvascular invasion in hepatocellular carcinoma and intrahepatic cholangiocarcinoma.

Background: Microvascular invasion (MVI) is a critical risk factor for early recurrence of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). The aim of this study was to explore the contribution of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomic features for the preoperative prediction of HCC and ICC classification and MVI. Methods: In this retrospective study, 127 (HCC: ICC =76:51) patients with suspected MVI accompanied by either HCC or ICC were included (In HCC group, MVI positive: negative =46:30 in ICC group, MVI positive: negative =31:20). Results-driven feature engineering workflow was used to select the most predictive feature combinations. The prediction model was based on supervised machine learning classifier. Ten-fold cross validation on training cohort and independent test cohort were constructed to ensure stability and generalization ability of models. Results: For HCC and ICC classification, radiomics predictors composed of two PET and one CT feature achieved area under the curve (AUC) of 0.86 (accuracy, sensitivity, specificity was 0.82, 0.78, 0.88, respectively) on test cohort. For MVI prediction, in HCC group, our MVI prediction model achieved AUC of 0.88 (accuracy, sensitivity, specificity was 0.78, 0.88, 0.60 respectively) with three PET features associated with tumor stage on test cohort. In ICC group, the phenotype composed of two PET features and carbohydrate antigen 19-9 (CA19-9) achieved AUC of 0.90 (accuracy, sensitivity, specificity was 0.77, 0.75, 0.80, respectively). Conclusions: 18F-FDG PET/CT radiomic features integrating clinical factors have potential in HCC and ICC classification and MVI prediction, while PET features have dominant predictive power in model performance. The prediction model has value in providing a non-invasive biomarker for an earlier indication and comprehensive quantification of primary liver cancers.

Bifidobacterium animalis subsp. lactis XLTG11 improves antibiotic-related diarrhea by alleviating inflammation, enhancing intestinal barrier function and regulating intestinal flora.

Antibiotic-associated diarrhea (AAD) is a common side effect during antibiotic treatment. In this study, we evaluated the regulatory effect of Bifidobacterium animalis subsp. lactis XLTG11 on mouse diarrhea caused by antibiotic-induced intestinal flora disturbance. Then, two strains of Bifidobacterium animalis subsp. lactis XLTG11 and Bifidobacterium animalis subsp. lactis BB-12 were administered to AAD mice. We found that the recovery effect of using B. lactis XLTG11 was better than that of B. lactis BB-12. B. lactis XLTG11 reduced the pathological characteristics of the intestinal tract, and significantly reduced the levels of lipopolysaccharide (LPS), D-lactic acid (D-LA) and diamine oxidase (DAO) to decrease intestinal permeability. In addition, these two strains significantly increased the expression of aquaporin and tight junction proteins, and inhibited toll-like receptor 4 (TLR4)/activation of the nuclear factor-κB (NF-κB) signaling pathway, significantly increased the levels of anti-inflammatory cytokines and decreased levels of pro-inflammatory cytokines. Moreover, after treatment with B. lactis XLTG11, the contents of acetic acid, propionic acid, butyric acid and total short-chain fatty acids were significantly increased. Compared with the MC group, B. lactis XLTG11 increased the abundance and diversity of the intestinal flora and changed the composition of the intestinal flora. We found that B. lactis XLTG11 can promote the recovery of intestinal flora and mucosal barrier function, thereby effectively improving AAD-related symptoms, providing a scientific basis for future clinical applications.

18F-FDG PET/CT Radiomics for Preoperative Prediction of Lymph Node Metastases and Nodal Staging in Gastric Cancer.

OBJECTIVES: The accurate assessment of lymph node metastases (LNMs) and the preoperative nodal (N) stage are critical for the precise treatment of patients with gastric cancer (GC). The diagnostic performance, however, of current imaging procedures used for this assessment is sub-optimal. Our aim was to investigate the value of preoperative 18F-FDG PET/CT radiomic features to predict LNMs and the N stage. METHODS: We retrospectively collected clinical and 18F-FDG PET/CT imaging data of 185 patients with GC who underwent total or partial radical gastrectomy. Patients were allocated to training and validation sets using the stratified method at a fixed ratio (8:2). There were 2,100 radiomic features extracted from the 18F-FDG PET/CT scans. After selecting radiomic features by the random forest, relevancy-based, and sequential forward selection methods, the BalancedBagging ensemble classifier was established for the preoperative prediction of LNMs, and the OneVsRest classifier for the N stage. The performance of the models was primarily evaluated by the AUC and accuracy, and validated by the independent validation methods. Analysis of the feature importance and the correlation were also conducted. We also compared the predictive performance of our radiomic models to that with the contrast-enhanced CT (CECT) and 18F-FDG PET/CT. RESULTS: There were 185 patients-127 men, 58 women, with the median age of 62, and an age range of 22-86 years. One CT feature and one PET feature were selected to predict LNMs and achieved the best performance (AUC: 82.2%, accuracy: 85.2%). This radiomic model also detected some LNMs that were missed in CECT (19.6%) and 18F-FDG PET/CT (35.7%). For predicting the N stage, four CT features and one PET feature were selected (AUC: 73.7%, accuracy: 62.3%). Of note, a proportion of patients in the validation set whose LNMs were incorrectly staged by CECT (57.4%) and 18F-FDG PET/CT (55%) were diagnosed correctly by our radiomic model. CONCLUSION: We developed and validated two machine learning models based on the preoperative 18F-FDG PET/CT images that have a predictive value for LNMs and the N stage in GC. These predictive models show a promise to offer a potentially useful adjunct to current staging approaches for patients with GC.

Quantitative Prediction of Microsatellite Instability in Colorectal Cancer With Preoperative PET/CT-Based Radiomics.

OBJECTIVES: Microsatellite instability (MSI) status is an important hallmark for prognosis prediction and treatment recommendation of colorectal cancer (CRC). To address issues due to the invasiveness of clinical preoperative evaluation of microsatellite status, we investigated the value of preoperative 18F-FDG PET/CT radiomics with machine learning for predicting the microsatellite status of colorectal cancer patients. METHODS: A total of 173 patients that underwent 18F-FDG PET/CT scans before operations were retrospectively analyzed in this study. The microsatellite status for each patient was identified as microsatellite instability-high (MSI-H) or microsatellite stable (MSS), according to the test for mismatch repair gene proteins with immunohistochemical staining methods. There were 2,492 radiomic features in total extracted from 18F-FDG PET/CT imaging. Then, radiomic features were selected through multivariate random forest selection and univariate relevancy tests after handling the imbalanced dataset through the random under-sampling method. Based on the selected features, we constructed a BalancedBagging model based on Adaboost classifiers to identify the MSI status in patients with CRC. The model performance was evaluated by the area under the curve (AUC), sensitivity, specificity, and accuracy on the validation dataset. RESULTS: The ensemble model was constructed based on two radiomic features and achieved an 82.8% AUC for predicting the MSI status of colorectal cancer patients. The sensitivity, specificity, and accuracy were 83.3, 76.3, and 76.8%, respectively. The significant correlation of the selected two radiomic features with multiple effective clinical features was identified (p < 0.05). CONCLUSION: 18F-FDG PET/CT radiomics analysis with the machine learning model provided a quantitative, efficient, and non-invasive mechanism for identifying the microsatellite status of colorectal cancer patients, which optimized the treatment decision support.

Altered Functional Connectivity in White and Gray Matter in Patients With Multiple Sclerosis.

Background: Functional magnetic resonance imaging (fMRI) has been widely used to assess neural activity changes in gray matter (GM) in patients with multiple sclerosis (MS); however, brain function alterations in white matter (WM) relatively remain under-explored. Purpose: This work aims to identify the functional connectivity in both the WM and the GM of patients with MS using fMRI and the correlations between these functional changes and cumulative disability as well as the lesion ratio. Materials and Methods: For this retrospective study, 37 patients with clinically definite MS and 43 age-matched healthy controls were included between 2010 and 2014. Resting-state fMRI was performed. The WFU Pick and JHU Eve atlases were used to define 82 GM and 48 WM regions in common spaces, respectively. The time courses of blood oxygen level-dependent (BOLD) signals were averaged over each GM or WM region. The averaged time courses for each pair of GM and WM regions were correlated. All 82 × 48 correlations for each subject formed a functional correlation matrix. Results: Compared with the healthy controls, the MS patients had a decreased temporal correlation between the WM and the GM regions. Five WM bundles and four GM regions had significantly decreased mean correlation coefficients (CCs). More specifically, the WM functional alterations were negatively correlated with the lesion volume in the bilateral fornix, and the mean GM-averaged CCs of the WM bundles were inversely correlated with the lesion ratio (r = -0.36, P = 0.012). No significant correlation was found between WM functional alterations and the paced auditory serial addition test score, Expanded Disease Severity Scale score, and Multiple Sclerosis Severity Score (MSSS) in MS. Conclusions: These findings highlight current gaps in our knowledge of the WM functional alterations in patients with MS and may link WM function with pathological mechanisms.

18F-FDG PET/CT Radiomic Analysis with Machine Learning for Identifying Bone Marrow Involvement in the Patients with Suspected Relapsed Acute Leukemia.

18F-FDG PET / CT is used clinically for the detection of extramedullary lesions in patients with relapsed acute leukemia (AL). However, the visual analysis of 18F-FDG diffuse bone marrow uptake in detecting bone marrow involvement (BMI) in routine clinical practice is still challenging. This study aims to improve the diagnostic performance of 18F-FDG PET/CT in detecting BMI for patients with suspected relapsed AL. Methods: Forty-one patients (35 in training group and 6 in independent validation group) with suspected relapsed AL were retrospectively included in this study. All patients underwent both bone marrow biopsy (BMB) and 18F-FDG PET/CT within one week. The BMB results were used as the gold standard or real "truth" for BMI. The bone marrow 18F-FDG uptake was visually diagnosed as positive and negative by three nuclear medicine physicians. The skeletal volumes of interest were manually drawn on PET/CT images. A total of 781 PET and 1045 CT radiomic features were automatically extracted to provide a more comprehensive understanding of the embedded pattern. To select the most important and predictive features, an unsupervised consensus clustering method was first performed to analyze the feature correlations and then used to guide a random forest supervised machine learning model for feature importance analysis. Cross-validation and independent validation were conducted to justify the performance of our model. Results: The training group involved 16 BMB positive and 19 BMB negative patients. Based on the visual analysis of 18F-FDG PET, 3 patients had focal uptake, 8 patients had normal uptake, and 24 patients had diffuse uptake. The sensitivity, specificity, and accuracy of visual analysis for BMI diagnosis were 62.5%, 73.7%, and 68.6%, respectively. With the cross-validation on the training group, the machine learning model correctly predicted 31 patients in BMI. The sensitivity, specificity, and accuracy of the machine learning model in BMI detection were 87.5%, 89.5%, and 88.6%, respectively, significantly higher than the ones in visual analysis (P < 0.05). The evaluation on the independent validation group showed that the machine learning model could achieve 83.3% accuracy. Conclusions:18F-FDG PET/CT radiomic analysis with machine learning model provided a quantitative, objective and efficient mechanism for identifying BMI in the patients with suspected relapsed AL. It is suggested in particular for the diagnosis of BMI in the patients with 18F-FDG diffuse uptake patterns.

Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations.

Gliomas are the most common primary malignant brain tumors in adults. Accurate grading is crucial as therapeutic strategies are often disparate for different grades and may influence patient prognosis. This study aims to provide an automated glioma grading platform on the basis of machine learning models. In this paper, we investigate contributions of multi-parameters from multimodal data including imaging parameters or features from the Whole Slide images (WSI) and the proliferation marker Ki-67 for automated brain tumor grading. For each WSI, we extract both visual parameters such as morphology parameters and sub-visual parameters including first-order and second-order features. On the basis of machine learning models, our platform classifies gliomas into grades II, III, and IV. Furthermore, we quantitatively interpret and reveal the important parameters contributing to grading with the Local Interpretable Model-Agnostic Explanations (LIME) algorithm. The quantitative analysis and explanation may assist clinicians to better understand the disease and accordingly to choose optimal treatments for improving clinical outcomes. The performance of our grading model was evaluated with cross-validation, which randomly divided the patients into non-overlapping training and testing sets and repeatedly validated the model on the different testing sets. The primary results indicated that this modular platform approach achieved the highest grading accuracy of 0.90 ± 0.04 with support vector machine (SVM) algorithm, with grading accuracies of 0.91 ± 0.08, 0.90 ± 0.08, and 0.90 ± 0.07 for grade II, III, and IV gliomas, respectively.