A Novel Immune Classification for Predicting Immunotherapy Responsiveness in Patients With Adamantinomatous Craniopharyngioma

Adamantinomatous craniopharyngioma (ACP) is the most common tumor of the sellar region in children. The aggressive behavior of ACP challenges the treatment for it. However, immunotherapy is rarely studied in ACP. In this research, we performed unsupervised cluster analysis on the 725 immune-related genes and arrays of 39 patients with ACP patients in GSE60815 and GSE94349 databases. Two novel immune subtypes were identified, namely immune resistance (IR) subtype and immunogenic (IG) subtype. Interestingly, we found that the ACPs with IG subtype (34.78%, 8/23) were more likely to respond to immunotherapy than the ACPs with IR subtype (6.25%, 1/16) via tumor immune dysfunction and exclusion (TIDE) method. Simultaneously, the enrichment analysis indicated that the differentially expressed genes (DEGs) (p < 0.01, FDR < 0.01) of the IG subtype were chiefly involved in inflammatory and immune responses. However, the DEGs of the IR subtype were mainly involved in RNA processing. Next, immune infiltration analysis revealed a higher proportion of M2 macrophage in the IG subtype than that in the IR subtype. Compared with the IR subtype, the expression levels of immune checkpoint molecules (PD1, PDL1, PDL2, TIM3, CTLA4, Galectin9, LAG3, and CD86) were significantly upregulated in the IG subtype. The ssGSEA results demonstrated that the biofunction of carcinogenesis in the IG subtype was significantly enriched, such as lymphocyte infiltration, mesenchymal phenotype, stemness maintenance, and tumorigenic cytokines, compared with the IR subtype. Finally, a WDR89 (the DEG between IG and IR subtype)-based nomogram model was constructed to predict the immune classification of ACPs with excellent performance. This predictive model provided a reliable classification assessment tool for clinicians and aids treatment decision-making in the clinic.

Metabolomic Profile at Birth, Bronchiolitis and Recurrent Wheezing: A 3-Year Prospective Study

There is growing interest for studying how early-life influences the development of respiratory diseases. Our aim was to apply metabolomic analysis to urine collected at birth, to evaluate whether there is any early metabolic signatures capable to distinguish children who will develop acute bronchiolitis and/or recurrent wheezing. Urine was collected at birth in healthy term newborns. Children were followed up to the age of 3 years and evaluated for the development of acute bronchiolitis and recurrent wheezing (≥3 episodes). Urine were analyzed through a liquid-chromatography mass-spectrometry based untargeted approach. Metabolomic data were investigated applying univariate and multivariate techniques. 205 children were included: 35 had bronchiolitis, 11 of whom had recurrent wheezing. Moreover, 13 children had recurrent wheezing not preceded by bronchiolitis. Multivariate data analysis didn’t lead to reliable classification models capable to distinguish children with and without bronchiolitis or with recurrent wheezing preceded by bronchiolitis neither by PLS for classification (PLS2C) nor by Random Forest (RF). However, a reliable signature was discovered to distinguish children who later develop recurrent wheezing not preceded by bronchiolitis, from those who do not (MCCoob = 0.45 for PLS2C and MCCoob = 0.48 for RF). In this unselected birth cohort, a well-established untargeted metabolomic approach found no biochemical-metabolic dysregulation at birth associated with the subsequent development of acute bronchiolitis or recurrent wheezing post-bronchiolitis, not supporting the hypothesis of an underlying predisposing background. On the other hand, a metabolic signature was discovered that characterizes children who develop wheezing not preceded by bronchiolitis.

Inter- and intraobserver reliability of morphological Mutch classification for greater tuberosity fractures of the proximal humerus: A comparison of x-ray, two-, and three-dimensional CT imaging

Background The objective of this study was to investigate inter- and intraobserver reliability of the morphological Mutch classification for greater tuberosity (GT) fragments in consecutive proximal humerus fractures (PHF) regardless of the number of parts according to the Codman classification system for three different imaging modalities (plain radiographs, two-dimensional [2-D] computed tomography [CT], and reformatted, three-dimensional [3-D] CT reconstruction). Materials and methods One hundred thirty-eight consecutive PHF with GT involvement were identified between January 2018 and December 2018 in a supraregional Level 1 trauma center. GT morphology was classified by three blinded observers according to the morphological Mutch classification using the picture archiving and communication software Visage 7.1 (Visage Imaging Inc., San Diego, CA, USA). Fleiss’ and Cohens’ kappa were assessed for inter- and intraobserver reliability. Strength of agreement for kappa (k) values was interpreted according to the Landis and Koch benchmark scale. Results In cases of isolated GT fractures (n = 24), the morphological Mutch classification achieved consistently substantial values for interobserver reliability (radiograph: k = 0.63; 2-D CT: k = 0.75; 3-D CT: k = 0.77). Moreover, use of advanced imaging (2-D and 3-D CT) tends to increase reliability. Consistently substantial mean values were found for intraobserver agreement (radiograph: Ø k = 0.72; 2-D CT: Ø k = 0.8; 3-D CT: Ø k = 0.76). In cases of multi-part PHF with GT involvement (n = 114), interobserver agreement was only slight to fair regardless of imaging modality (radiograph: k = 0.3; 2-D CT: k = 0.17; 3-D CT: k = 0.05). Intraobserver agreement achieved fair to moderate mean values (radiograph: Ø k = 0.56; 2-D CT: Ø k = 0.61; 3-D CT: Ø k = 0.33). Conclusion The morphological Mutch classification remains a reliable classification for isolated GT fractures, even with 2-D or 3-D CT imaging. Usage of these advanced imaging modalities tends to increase interobserver reliability. However, its reliability for multi-part fractures with GT involvement is limited. A simple and reliable classification is missing for this fracture entity.

On the Classification of a Greenhouse Environment for a Rose Crop Based on AI-Based Surrogate Models

A precise microclimate control for dynamic climate changes in greenhouses allows the industry and researchers to develop a simple, robust, reliable, and intelligent model. Accordingly, the objective of this investigation was to develop a method that can accurately define the most suitable environment in the greenhouse for an optimal yield of roses. Herein, an optimal and highly accurate BO-DNN surrogate model was developed (based on 300 experimental data points) for a quick and reliable classification of the rose yield environment considering some of the most influential variables including soil humidity, temperature and humidity of air, CO2 concentration, and light intensity (lux) into its architecture. Initially, two BO techniques (GP and GBRT) are used for the tuning process of the hyper-parameters (such as learning rate, batch size, number of dense nodes, number of dense neurons, number of input nodes, activation function, etc.). After that, an optimal and simple combination of the hyper-parameters was selected to develop a DNN algorithm based on 300 data points, which was further used to classify the rose yield environment (the rose yield environments were classified into four classes such as soil without water, correct environment, too hot, and very cold environments). The very high accuracy of the proposed surrogate model (0.98) originated from the introduction of the most vital soil and meteorological parameters as the inputs of the model. The proposed method can help in identifying intelligent greenhouse environments for efficient crop yields.

The West African Stone Age

In terms of artefacts present, West Africa is not short of evidence relating to human occupation during the Quaternary. The problem hitherto has been one of context and dating; there has been some progress in this regard but poor preservation conditions still restrict the presence of organic remains prior to the beginning of the Late Stone Age (LSA). Nonetheless, an excellent climatic record for the last 520 kya has been established on the basis of cores obtained from Lake Bosumtwi. Stratified Acheulean sites have been excavated at Sansandé and Ravin Blanc on the Falémé River in eastern Senegal. The succeeding Sangoan is an entity for which a consistent and reliable classification remains to be achieved. Despite this, excavations at Anyama in the Ivory Coast have produced a sizeable quantity of material, with a terminus post quem thermoluminescence (TL) date of 254 ± 51 kya. Our knowledge of the Middle Stone Age (MSA) has been transformed by the work carried out at Ounjougou in Mali. More than twenty-five distinct archaeological occurrences have been detected, extending from about 75 to 25 kya. The MSA elsewhere is abundant, and at Adrar Bous is in place beneath the Aterian, but much of it lacks a good stratigraphic context. The following dry period, the Ogolian, must have had a dramatic effect on human settlement, and the majority of LSA sites postdate this episode. There is no apparent link between them and the MSA. Nonetheless, the LSA at Shum Lake in Cameroon does have 14C dates in the range 32,700–12,800 BP. The most significant LSA site is Iwo Eleru, notable for the presence of modern human remains with “archaic” characteristics. A parallel situation has been detected at Ishango in the eastern Democratic Republic of Congo both indicating a hitherto unsuspected “deep substructure” in Late Pleistocene African populations.

Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.

On the Effectiveness of Leukocytes Classification Methods in a Real Application Scenario

Automating the analysis of digital microscopic images to identify the cell sub-types or the presence of illness has assumed a great importance since it aids the laborious manual process of review and diagnosis. In this paper, we have focused on the analysis of white blood cells. They are the body’s main defence against infections and diseases and, therefore, their reliable classification is very important. Current systems for leukocyte analysis are mainly dedicated to: counting, sub-types classification, disease detection or classification. Although these tasks seem very different, they share many steps in the analysis process, especially those dedicated to the detection of cells in blood smears. A very accurate detection step gives accurate results in the classification of white blood cells. Conversely, when detection is not accurate, it can adversely affect classification performance. However, it is very common in real-world applications that work on inaccurate or non-accurate regions. Many problems can affect detection results. They can be related to the quality of the blood smear images, e.g., colour and lighting conditions, absence of standards, or even density and presence of overlapping cells. To this end, we performed an in-depth investigation of the above scenario, simulating the regions produced by detection-based systems. We exploit various image descriptors combined with different classifiers, including CNNs, in order to evaluate which is the most suitable in such a scenario, when performing two different tasks: Classification of WBC subtypes and Leukaemia detection. Experimental results have shown that Convolutional Neural Networks are very robust in such a scenario, outperforming common machine learning techniques combined with hand-crafted descriptors. However, when exploiting appropriate images for model training, even simpler approaches can lead to accurate results in both tasks.

CNN-based multi-class multi-label classification of sound scenes in the context of wind turbine sound emission measurements

Within the scope of the interdisciplinary project WEA-Akzeptanz, measurements of the sound emission of wind turbines were carried out at the Leibniz University Hannover. Due to the environment there are interfering components (e. g. traffic, birdsong, wind, rain, ...) in the recorded signals. Depending on the subsequent signal processing and analysis, it may be necessary to identify sections with the raw sound of a wind turbine, recordings with the purest possible background noise or even a specific combination of interfering noises. Due to the amount of data, a manual classification of the audio signals is usually not feasible and an automated classification becomes necessary. In this paper, we extend our previously proposed multi-class single-label classification model to a multi-class multi-label model, which reflects the real-world acoustic conditions around wind turbines more accurately and allows for finer-grained evaluations. We first provide a short overview of the data acquisition and the dataset. We then briefly summarize our previous approach, extend it to a multi-class multi-label formulation, and analyze the trained convolutional neural network regarding different metrics. All in all, the model delivers very reliable classification results with an overall example-based F1-score of about 80 % for a multi-label classification of 12 classes.

Detection of functional and structural brain alterations in female schizophrenia using elastic net logistic regression

Neuroimaging technique is a powerful tool to characterize the abnormality of brain networks in schizophrenia. However, the neurophysiological substrate of schizophrenia is still unclear. Here we investigated the patterns of brain functional and structural changes in female patients with schizophrenia using elastic net logistic regression analysis of resting-state functional magnetic resonance imaging data. Data from 52 participants (25 female schizophrenia patients and 27 healthy controls) were obtained. Using an elastic net penalty, the brain regions most relevant to schizophrenia pathology were defined in the models using the amplitude of low-frequency fluctuations (ALFF) and gray matter, respectively. The receiver operating characteristic analysis showed reliable classification accuracy with 85.7% in ALFF analysis, and 77.1% in gray matter analysis. Notably, our results showed eight common regions between the ALFF and gray matter analyses, including the Frontal-Inf-Orb-R, Rolandic-Oper-R, Olfactory-R, Angular-L, Precuneus-L, Precuenus-R, Heschl-L, and Temporal-Pole-Mid-R. In addition, the severity of symptoms was found positively associated with the ALFF within the Rolandic-Oper-R and Frontal-Inf-Orb-R. Our findings indicated that elastic net logistic regression could be a useful tool to identify the characteristics of schizophrenia -related brain deterioration, which provides novel insights into schizophrenia diagnosis and prediction.