Predictive machine learning models based on VASARI features for WHO grading, isocitrate dehydrogenase mutation, and 1p19q co-deletion status: a multicenter study.

The objective of our study was to develop predictive models using Visually Accessible Rembrandt Images (VASARI) magnetic resonance imaging (MRI) features combined with machine learning techniques to predict the World Health Organization (WHO) grade, isocitrate dehydrogenase (IDH) mutation status, and 1p19q co-deletion status of high-grade gliomas. To achieve this, we retrospectively included 485 patients with high-grade glioma from the First Affiliated Hospital of Xinjiang Medical University, of which 312 patients were randomly divided into a training set (n=218) and a test set (n=94) in a 7:3 ratio. Twenty-five VASARI MRI features were selected from an initial set of 30, and three machine learning models - Multilayer Perceptron (MP), Bernoulli Naive Bayes (BNB), and Logistic Regression (LR) - were trained using the training set. The most informative features were identified using recursive feature elimination. Model performance was assessed using the test set and an independent validation set of 173 patients from Beijing Tiantan Hospital. The results indicated that the MP model exhibited the highest predictive accuracy on the training set, achieving an area under the curve (AUC) close to 1, indicating perfect discrimination. However, its performance decreased in the test and validation sets; particularly for predicting the 1p19q co-deletion status, the AUC was only 0.703, suggesting potential overfitting. On the other hand, the BNB model demonstrated robust generalization on the test and validation sets, with AUC values of 0.8292 and 0.8106, respectively, for predicting IDH mutation status and 1p19q co-deletion status, indicating high accuracy, sensitivity, and specificity. The LR model also showed good performance with AUCs of 0.7845 and 0.8674 on the test and validation sets, respectively, for predicting IDH mutation status, although it was slightly inferior to the BNB model for the 1p19q co-deletion status. In conclusion, integrating VASARI MRI features with machine learning techniques shows promise for the non-invasive prediction of glioma molecular markers, which could guide treatment strategies and improve prognosis in glioma patients. Nonetheless, further model optimization and validation are necessary to enhance its clinical utility.

A deep learning radiomics model based on CT images for predicting the biological activity of hepatic cystic echinococcosis.

Introduction: Hepatic cystic echinococcosis (HCE) is a widely seen parasitic infection. Biological activity is crucial for treatment planning. This work aims to explore the potential applications of a deep learning radiomics (DLR) model, based on CT images, in predicting the biological activity grading of hepatic cystic echinococcosis. Methods: A retrospective analysis of 160 patients with hepatic echinococcosis was performed (127 and 33 in training and validation sets). Volume of interests (VOIs) were drawn, and radiomics features and deep neural network features were extracted. Feature selection was performed on the training set, and radiomics score (Rad Score) and deep learning score (Deep Score) were calculated. Seven diagnostics models (based on logistic regression algorithm) for the biological activity grading were constructed using the selected radiomics features and two deep model features respectively. All models were evaluated using the receiver operating characteristic curve, and the area under the curve (AUC) was calculated. A nomogram was constructed using the combined model, and its calibration, discriminatory ability, and clinical utility were assessed. Results: 12, 6 and 10 optimal radiomics features, deep learning features were selected from two deep learning network (DLN) features, respectively. For biological activity grading of hepatic cystic echinococcosis, the combined model demonstrated strong diagnostic performance, with an AUC value of 0.888 (95% CI: 0.837-0.936) in the training set and 0.876 (0.761-0.964) in the validation set. The clinical decision analysis curve indicated promising results, while the calibration curve revealed that the nomogram's prediction result was highly compatible with the actual result. Conclusion: The DLR model can be used for predicting the biological activity grading of hepatic echinococcosis.

Tumor suppressor FRMD3 controls mammary epithelial cell fate determination via notch signaling pathway.

The luminal-to-basal transition in mammary epithelial cells (MECs) is accompanied by changes in epithelial cell lineage plasticity; however, the underlying mechanism remains elusive. Here, we report that deficiency of Frmd3 inhibits mammary gland lineage development and induces stemness of MECs, subsequently leading to the occurrence of triple-negative breast cancer. Loss of Frmd3 in PyMT mice results in a luminal-to-basal transition phenotype. Single-cell RNA sequencing of MECs indicated that knockout of Frmd3 inhibits the Notch signaling pathway. Mechanistically, FERM domain-containing protein 3 (FRMD3) promotes the degradation of Disheveled-2 by disrupting its interaction with deubiquitinase USP9x. FRMD3 also interrupts the interaction of Disheveled-2 with CK1, FOXK1/2, and NICD and decreases Disheveled-2 phosphorylation and nuclear localization, thereby impairing Notch-dependent luminal epithelial lineage plasticity in MECs. A low level of FRMD3 predicts poor outcomes for breast cancer patients. Together, we demonstrated that FRMD3 is a tumor suppressor that functions as an endogenous activator of the Notch signaling pathway, facilitating the basal-to-luminal transformation in MECs.

Rapid detection of the irinotecan-related UGT1A1 & 5-fluorouracil related DPYD polymorphism by asymmetric polymerase chain reaction melting curve analysis.

BACKGROUND: Determination of DPYD and UGT1A1 polymorphisms prior to 5-fluorouracil and irinotecan therapy is crucial for avoiding severe adverse drug effects. Hence, there is a pressing need for accurate and reliable genotyping methods for the most common DPYD and UGT1A1 polymorphisms. In this study, we introduce a novel polymerase chain reaction (PCR) melting curve analysis method for discriminating DPYD c.1236G > A, c.1679 T > G, c.2846A > T, IVS14 + 1G > A and UGT1A1*1, *28, *6 (G71R) genotypes. METHODS: Following protocol optimization, this technique was employed to genotype 28 patients, recruited between March 2023 and October 2023, at the First Affiliated Hospital of Xiamen University. These patients included 20 with UGT1A1 *1/*1, 8 with UGT1A1 *1/*28, 4 with UGT1A1 *28/*28, 22 with UGT1A1*6 G/G, 6 with UGT1A1*6 G/A, 4 with UGT1A1*6 A/A, 27 with DPYD(c.1236) G/G, 3 with DPYD(c.1236) G/A, 2 with DPYD(c.1236) A/A, 27 with DPYD(c.1679) T/T, 2 with DPYD(c.1679) T/G, 3 with DPYD(c.1679) G/G, 28 with DPYD(c.2846A/T) A/A, 2 with DPYD(c.2846A/T) A/T, 2 with DPYD(c.2846A/T) T/T, 28 with DPYD(c.IVS14 + 1) G/G, 2 with DPYD(c.IVS14 + 1) G/G, and 2 with DPYD(c.IVS14 + 1) G/G, as well as 3 plasmid standards. Method accuracy was assessed by comparing results with those from Sanger sequencing or Multiplex quantitative PCR(qPCR). Intra- and inter-run precision of melting temperatures (Tms) were calculated to evaluate reliability, and sensitivity was assessed through limit of detection examination. RESULTS: The new method accurately identified all genotypes and exhibited higher accuracy than Multiplex qPCR. Intra- and inter-run coefficients of variation for Tms were both ≤1.97 %, with standard deviations ≤0.95 °C. The limit of detection was 0.09 ng/µL of input genomic DNA. CONCLUSION: Our developed PCR melting curve analysis offers accurate, reliable, rapid, simple, and cost-effective detection of DPYD and UGT1A1 polymorphisms. Its application can be easily extended to clinical laboratories equipped with a fluorescent PCR platform.

Calibrating ultrasonic sensor measurements of crop canopy heights: a case study of maize and wheat.

Canopy height serves as an important dynamic indicator of crop growth in the decision-making process of field management. Compared with other commonly used canopy height measurement techniques, ultrasonic sensors are inexpensive and can be exposed in fields for long periods of time to obtain easy-to-process data. However, the acoustic wave characteristics and crop canopy structure affect the measurement accuracy. To improve the ultrasonic sensor measurement accuracy, a four-year (2018-2021) field experiment was conducted on maize and wheat, and a measurement platform was developed. A series of single-factor experiments were conducted to investigate the significant factors affecting measurements, including the observation angle (0-60°), observation height (0.5-2.5 m), observation period (8:00-18:00), platform moving speed with respect to the crop (0-2.0 m min-1), planting density (0.2-1 time of standard planting density), and growth stage (maize from three-leaf to harvest period and wheat from regreening to maturity period). The results indicated that both the observation angle and planting density significantly affected the results of ultrasonic measurements (p-value< 0.05), whereas the effects of other factors on measurement accuracy were negligible (p-value > 0.05). Moreover, a double-input factor calibration model was constructed to assess canopy height under different years by utilizing the normalized difference vegetation index and ultrasonic measurements. The model was developed by employing the least-squares method, and ultrasonic measurement accuracy was significantly improved when integrating the measured value of canopy heights and the normalized difference vegetation index (NDVI). The maize measurement accuracy had a root mean squared error (RMSE) ranging from 81.4 mm to 93.6 mm, while the wheat measurement accuracy had an RMSE from 37.1 mm to 47.2 mm. The research results effectively combine stable and low-cost commercial sensors with ground-based agricultural machinery platforms, enabling efficient and non-destructive acquisition of crop height information.

Role of long non-coding RNA TCONS_02443383 in regulating cell adhesion and peroxisome proliferator-activated receptor (PPAR) signaling genes in atherosclerosis: A New Zealand white rabbit model study.

OBJECTIVE: In this study, we performed RNA sequencing (RNA-seq) on the abdominal aorta tissue of New Zealand rabbits and investigated the potential association of lncRNA TCONS_02443383 with the development of AS through bioinformatics analysis of the sequencing data. The obtained results were further validated using quantitative real-time polymerase chain reaction (qRT-PCR). METHOD: We induced an AS model in New Zealand rabbits by causing balloon injury to the abdominal aorta vascular wall and administering a high-fat diet. We then upregulated the expression level of the lncRNA TCONS_02443383 by injecting lentiviral plasmids through the ear vein. RNA sequencing (RNA-seq) was performed on the abdominal aorta tissues. We conducted Kyoto Encyclopedia of Genes and Genomes (KEGG) signaling pathway and Gene Ontology (GO) analyses. RESULT: The overexpression of the lncRNA TCONS_02443383 led to an upregulation of peroxisome proliferator-activated receptor (PPAR) signaling pathways as well as genes related to cell adhesion. CONCLUSION: The overexpression of the lncRNA TCONS_02443383 can inhibit the occurrence and development of AS by upregulating peroxisome proliferator-activated receptor (PPAR) signaling pathways and genes related to cell adhesion.

MR-based radiomics predictive modelling of EGFR mutation and HER2 overexpression in metastatic brain adenocarcinoma: a two-centre study.

OBJECTIVES: Magnetic resonance (MR)-based radiomics features of brain metastases are utilised to predict epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) overexpression in adenocarcinoma, with the aim to identify the most predictive MR sequence. METHODS: A retrospective inclusion of 268 individuals with brain metastases from adenocarcinoma across two institutions was conducted. Utilising T1-weighted imaging (T1 contrast-enhanced [T1-CE]) and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequences, 1,409 radiomics features were extracted. These sequences were randomly divided into training and test sets at a 7:3 ratio. The selection of relevant features was done using the least absolute shrinkage selection operator, and the training cohort's support vector classifier model was employed to generate the predictive model. The performance of the radiomics features was evaluated using a separate test set. RESULTS: For contrast-enhanced T1-CE cohorts, the radiomics features based on 19 selected characteristics exhibited excellent discrimination. No significant differences in age, sex, and time to metastasis were observed between the groups with EGFR mutations or HER2 + and those with wild-type EGFR or HER2 (p > 0.05). Radiomics feature analysis for T1-CE revealed an area under the curve (AUC) of 0.98, classification accuracy of 0.93, sensitivity of 0.92, and specificity of 0.93 in the training cohort. In the test set, the AUC was 0.82. The 19 radiomics features for the T2-FLAIR sequence showed AUCs of 0.86 in the training set and 0.70 in the test set. CONCLUSIONS: This study developed a T1-CE signature that could serve as a non-invasive adjunctive tool to determine the presence of EGFR mutations and HER2 + status in adenocarcinoma, aiding in the direction of treatment plans. CLINICAL RELEVANCE STATEMENT: We propose radiomics features based on T1-CE brain MR sequences that are both evidence-based and non-invasive. These can be employed to guide clinical treatment planning in patients with brain metastases from adenocarcinoma.

A novel score for early prediction of urinary tract infection risk in patients with acute ischemic stroke: a nomogram-based retrospective cohort study.

This study aimed to construct and externally validate a user-friendly nomogram-based scoring model for predicting the risk of urinary tract infections (UTIs) in patients with acute ischemic stroke (AIS). A retrospective real-world cohort study was conducted on 1748 consecutive hospitalized patients with AIS. Out of these patients, a total of 1132 participants were ultimately included in the final analysis, with 817 used for model construction and 315 utilized for external validation. Multivariate regression analysis was applied to develop the model. The discriminative capacity, calibration ability, and clinical effectiveness of the model were evaluated. The overall incidence of UTIs was 8.13% (92/1132), with Escherichia coli being the most prevalent causative pathogen in patients with AIS. After multivariable analysis, advanced age, female gender, National Institute of Health Stroke Scale (NIHSS) score ≥ 5, and use of urinary catheters were identified as independent risk factors for UTIs. A nomogram-based SUNA model was constructed using these four factors (Area under the receiver operating characteristic curve (AUC) = 0.810), which showed good discrimination (AUC = 0.788), calibration, and clinical utility in the external validation cohort. Based on four simple and readily available factors, we derived and externally validated a novel and user-friendly nomogram-based scoring model (SUNA score) to predict the risk of UTIs in patients with AIS. The model has a good predictive value and provides valuable information for timely intervention in patients with AIS to reduce the occurrence of UTIs.

Biobank-wide association scan identifies risk factors for late-onset Alzheimer's disease and endophenotypes.

Rich data from large biobanks, coupled with increasingly accessible association statistics from genome-wide association studies (GWAS), provide great opportunities to dissect the complex relationships among human traits and diseases. We introduce BADGERS, a powerful method to perform polygenic score-based biobank-wide association scans. Compared to traditional approaches, BADGERS uses GWAS summary statistics as input and does not require multiple traits to be measured in the same cohort. We applied BADGERS to two independent datasets for late-onset Alzheimer's disease (AD; n=61,212). Among 1738 traits in the UK biobank, we identified 48 significant associations for AD. Family history, high cholesterol, and numerous traits related to intelligence and education showed strong and independent associations with AD. Furthermore, we identified 41 significant associations for a variety of AD endophenotypes. While family history and high cholesterol were strongly associated with AD subgroups and pathologies, only intelligence and education-related traits predicted pre-clinical cognitive phenotypes. These results provide novel insights into the distinct biological processes underlying various risk factors for AD.

Multiparametric MRI-Based Interpretable Radiomics Machine Learning Model Differentiates Medulloblastoma and Ependymoma in Children: A Two-Center Study.

RATIONALE AND OBJECTIVES: Medulloblastoma (MB) and Ependymoma (EM) in children, share similarities in age group, tumor location, and clinical presentation. Distinguishing between them through clinical diagnosis is challenging. This study aims to explore the effectiveness of using radiomics and machine learning on multiparametric magnetic resonance imaging (MRI) to differentiate between MB and EM and validate its diagnostic ability with an external set. MATERIALS AND METHODS: Axial T2 weighted image (T2WI) and contrast-enhanced T1weighted image (CE-T1WI) MRI sequences of 135 patients from two centers were collected as train/test sets. Volume of interest (VOI) was manually delineated by an experienced neuroradiologist, supervised by a senior. Feature selection analysis and the least absolute shrinkage and selection operator (LASSO) algorithm identified valuable features, and Shapley additive explanations (SHAP) evaluated their significance. Five machine-learning classifiers-extreme gradient boosting (XGBoost), Bernoulli naive Bayes (Bernoulli NB), Logistic Regression (LR), support vector machine (SVM), linear support vector machine (Linear SVC) classifiers were built based on T2WI (T2 model), CE-T1WI (T1 model), and T1 + T2WI (T1 + T2 model). A human expert diagnosis was developed and corrected by senior radiologists. External validation was performed at Sun Yat-Sen University Cancer Center. RESULTS: 31 valuable features were extracted from T2WI and CE-T1WI. XGBoost demonstrated the highest performance with an area under the curve (AUC) of 0.92 on the test set and maintained an AUC of 0.80 during external validation. For the T1 model, XGBoost achieved the highest AUC of 0.85 on the test set and the highest accuracy of 0.71 on the external validation set. In the T2 model, XGBoost achieved the highest AUC of 0.86 on the test set and the highest accuracy of 0.82 on the external validation set. The human expert diagnosis had an AUC of 0.66 on the test set and 0.69 on the external validation set. The integrated T1 + T2 model achieved an AUC of 0.92 on the test set, 0.80 on the external validation set, achieved the best performance. Overall, XGBoost consistently outperformed in different classification models. CONCLUSION: The combination of radiomics and machine learning on multiparametric MRI effectively distinguishes between MB and EM in childhood, surpassing human expert diagnosis in training and testing sets.

Differentiation between cerebral alveolar echinococcosis and brain metastases with radiomics combined machine learning approach.

BACKGROUND: Cerebral alveolar echinococcosis (CAE) and brain metastases (BM) share similar in locations and imaging appearance. However, they require distinct treatment approaches, with CAE typically treated with chemotherapy and surgery, while BM is managed with radiotherapy and targeted therapy for the primary malignancy. Accurate diagnosis is crucial due to the divergent treatment strategies. PURPOSE: This study aims to evaluate the effectiveness of radiomics and machine learning techniques based on magnetic resonance imaging (MRI) to differentiate between CAE and BM. METHODS: We retrospectively analyzed MRI images of 130 patients (30 CAE and 100 BM) from Xinjiang Medical University First Affiliated Hospital and The First People's Hospital of Kashi Prefecture, between January 2014 and December 2022. The dataset was divided into training (91 cases) and testing (39 cases) sets. Three dimensional tumors were segmented by radiologists from contrast-enhanced T1WI images on open resources software 3D Slicer. Features were extracted on Pyradiomics, further feature reduction was carried out using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator (LASSO). Finally, we built five machine learning models, support vector machine, logistic regression, linear discrimination analysis, k-nearest neighbors classifier, and Gaussian naïve bias and evaluated their performance via several metrics including sensitivity (recall), specificity, positive predictive value (precision), negative predictive value, accuracy and the area under the curve (AUC). RESULTS: The area under curve (AUC) of support vector classifier (SVC), linear discrimination analysis (LDA), k-nearest neighbors (KNN), and gaussian naïve bias (NB) algorithms in training (testing) sets are 0.99 (0.94), 1.00 (0.87), 0.98 (0.92), 0.97 (0.97), and 0.98 (0.93), respectively. Nested cross-validation demonstrated the robustness and generalizability of the models. Additionally, the calibration plot and decision curve analysis demonstrated the practical usefulness of these models in clinical practice, with lower bias toward different subgroups during decision-making. CONCLUSION: The combination of radiomics and machine learning approach based on contrast enhanced T1WI images could well distinguish CAE and BM. This approach holds promise in assisting doctors with accurate diagnosis and clinical decision-making.

MLNAN: Multi-level noise-aware network for low-dose CT imaging implemented with constrained cycle Wasserstein generative adversarial networks.

Low-dose CT techniques attempt to minimize the radiation exposure of patients by estimating the high-resolution normal-dose CT images to reduce the risk of radiation-induced cancer. In recent years, many deep learning methods have been proposed to solve this problem by building a mapping function between low-dose CT images and their high-dose counterparts. However, most of these methods ignore the effect of different radiation doses on the final CT images, which results in large differences in the intensity of the noise observable in CT images. What'more, the noise intensity of low-dose CT images exists significantly differences under different medical devices manufacturers. In this paper, we propose a multi-level noise-aware network (MLNAN) implemented with constrained cycle Wasserstein generative adversarial networks to recovery the low-dose CT images under uncertain noise levels. Particularly, the noise-level classification is predicted and reused as a prior pattern in generator networks. Moreover, the discriminator network introduces noise-level determination. Under two dose-reduction strategies, experiments to evaluate the performance of proposed method are conducted on two datasets, including the simulated clinical AAPM challenge datasets and commercial CT datasets from United Imaging Healthcare (UIH). The experimental results illustrate the effectiveness of our proposed method in terms of noise suppression and structural detail preservation compared with several other deep-learning based methods. Ablation studies validate the effectiveness of the individual components regarding the afforded performance improvement. Further research for practical clinical applications and other medical modalities is required in future works.

Classification of benign and malignant parotid tumors based on CT images combined with stack generalization model.

Parotid tumors are among the most prevalent tumors in otolaryngology, and malignant parotid tumors are one of the main causes of facial paralysis in patients. Currently, the main diagnostic modality for parotid tumors is computed tomography, which relies mainly on the subjective judgment of clinicians and leads to practical problems such as high workloads. Therefore, to assist physicians in solving the preoperative classification problem, a stacked generalization model is proposed for the automated classification of parotid tumor images. A ResNet50 pretrained model is used for feature extraction. The first layer of the adopted stacked generalization model consists of multiple weak learners, and the results of the weak learners are integrated as input data in a meta-classifier in the second layer. The output results of the meta-classifier are the final classification results. The classification accuracy of the stacked generalization model reaches 91%. Comparing the classification results under different classifiers, the stacked generalization model used in this study can identify benign and malignant tumors in the parotid gland effectively, thus relieving physicians of tedious work pressure.

The Value of the Cardiac Magnetic Resonance Intravoxel Incoherent Motion Technique in Evaluating Microcirculatory Dysfunction in Hypertrophic Cardiomyopathy.

Objective: To evaluate the value of the cardiac magnetic resonance intravoxel incoherent motion (IVIM) technique in microcirculatory dysfunction in patients with hypertrophic cardiomyopathy (HCM). Methods: The medical records of 19 patients with HCM in our hospital from January 2020 to May 2021 were collected retrospectively, and 23 healthy people with a similar age and gender distribution to the patients with HCM were included as controls. All the included subjects underwent clinical assessment and cardiac magnetic resonance imaging. The original IVIM images were analysed, and the imaging parameters of each segment were measured. The HCM group was divided into non-hypertrophic myocardium and hypertrophic myocardium groups. The differences in imaging parameters between the normal and HCM groups were compared. A Spearman correlation analysis was used to explore the correlation between end-diastolic thickness (EDTH) and each IVIM parameter. Results: The D∗ and f values in the HCM group were lower than those in the normal group (p < 0.0001 and p = 0.004, respectively). The f, D, D∗, and EDTH values of the hypertrophic segment, non-hypertrophic segment, and normal groups were statistically significant (p < 0.05). The difference in D∗ values among the mild, moderate, severe, and very severe HCM groups was statistically significant (p < 0.05). There was a statistically significant difference in EDTH among the mild, moderate, severe, and very severe groups (p < 0.001). There were significant differences in the values of D, D∗, and f between the non-delayed enhancement group and the delayed enhancement group (p < 0.05). The EDTH values of 304 segments in the HCM group were negatively correlated with f (r = -0.219, p = 0.028) and D∗ values (r = -0.310, p < 0.001). Conclusion: The use of IVIM technology can achieve a non-invasive early quantitative assessment of microvascular disease in HCM without the injection of a contrast agent and provide a reference for the early diagnosis of and intervention in myocardial ischemia in patients with HCM.

A region-specific modulation of sleep slow waves on interictal epilepsy markers in focal epilepsy.

OBJECTIVE: Sleep strongly activates interictal epileptic activity through an unclear mechanism. We investigated how scalp sleep slow waves (SSWs), whose positive and negative half-waves reflect the fluctuation of neuronal excitability between the up and down states, respectively, modulate interictal epileptic events in focal epilepsy. METHODS: Simultaneous polysomnography was performed in 45 patients with drug-resistant focal epilepsy during intracranial electroencephalographic recording. Scalp SSWs and intracranial spikes and ripples (80-250 Hz) were detected; ripples were classified as type I (co-occurring with spikes) or type II (occurring alone). The Hilbert transform was used to analyze the distributions of spikes and ripples in the phases of SSWs. RESULTS: Thirty patients with discrete seizure-onset zone (SOZ) and discernable sleep architecture were included. Intracranial spikes and ripples accumulated around the negative peaks of SSWs and increased with SSW amplitude. Phase analysis revealed that spikes and both ripple subtypes in SOZ were similarly facilitated by SSWs exclusively during down state. In exclusively irritative zones outside SOZ (EIZ), SSWs facilitated spikes and type I ripples across a wider range of phases and to a greater extent than those in SOZ. The type II and type I ripples in EIZ were modulated by SSWs in different patterns. Ripples in normal zones decreased specifically during the up-to-down transition and then increased after the negative peak of SSW, with a characteristically high post-/pre-negative peak ratio. SIGNIFICANCE: SSWs modulate interictal events in an amplitude-dependent and region-specific pattern. Pathological ripples and spikes were facilitated predominantly during the cortical down state. Coupling analysis of SSWs could improve the discrimination of pathological and physiological ripples and facilitate seizure localization.

CIABNet: Category imbalance attention block network for the classification of multi-differentiated types of esophageal cancer.

BACKGROUND: Esophageal cancer has become one of the important cancers that seriously threaten human life and health, and its incidence and mortality rate are still among the top malignant tumors. Histopathological image analysis is the gold standard for diagnosing different differentiation types of esophageal cancer. PURPOSE: The grading accuracy and interpretability of the auxiliary diagnostic model for esophageal cancer are seriously affected by small interclass differences, imbalanced data distribution, and poor model interpretability. Therefore, we focused on developing the category imbalance attention block network (CIABNet) model to try to solve the previous problems. METHODS: First, the quantitative metrics and model visualization results are integrated to transfer knowledge from the source domain images to better identify the regions of interest (ROI) in the target domain of esophageal cancer. Second, in order to pay attention to the subtle interclass differences, we propose the concatenate fusion attention block, which can focus on the contextual local feature relationships and the changes of channel attention weights among different regions simultaneously. Third, we proposed a category imbalance attention module, which treats each esophageal cancer differentiation class fairly based on aggregating different intensity information at multiple scales and explores more representative regional features for each class, which effectively mitigates the negative impact of category imbalance. Finally, we use feature map visualization to focus on interpreting whether the ROIs are the same or similar between the model and pathologists, thus better improving the interpretability of the model. RESULTS: The experimental results show that the CIABNet model outperforms other state-of-the-art models, which achieves the most advanced results in classifying the differentiation types of esophageal cancer with an average classification accuracy of 92.24%, an average precision of 93.52%, an average recall of 90.31%, an average F1 value of 91.73%, and an average AUC value of 97.43%. In addition, the CIABNet model has essentially similar or identical to the ROI of pathologists in identifying histopathological images of esophageal cancer. CONCLUSIONS: Our experimental results prove that our proposed computer-aided diagnostic algorithm shows great potential in histopathological images of multi-differentiated types of esophageal cancer.