Explore the vast range of titles available.

IntroductionTranscriptional analyses have identified several distinct molecular subtypes in pancreatic ductal adenocarcinoma (PDAC) that have prognostic and potential therapeutic significance. However, to date, an indepth, clinicomorphological correlation of these molecular subtypes has not been performed. We sought to identify specific morphological patterns to compare with known molecular subtypes, interrogate their biological significance, and furthermore reappraise the current grading system in PDAC.DesignWe first assessed 86 primary, chemotherapy-naive PDAC resection specimens with matched RNA-Seq data for specific, reproducible morphological patterns. Differential expression was applied to the gene expression data using the morphological features. We next compared the differentially expressed gene signatures with previously published molecular subtypes. Overall survival (OS) was correlated with the morphological and molecular subtypes.ResultsWe identified four morphological patterns that segregated into two components (‘gland forming’ and ‘non-gland forming’) based on the presence/absence of well-formed glands. A morphological cut-off (≥40% ‘non-gland forming’) was established using RNA-Seq data, which identified two groups (A and B) with gene signatures that correlated with known molecular subtypes. There was a significant difference in OS between the groups. The morphological groups remained significantly prognostic within cancers that were moderately differentiated and classified as ‘classical’ using RNA-Seq.ConclusionOur study has demonstrated that PDACs can be morphologically classified into distinct and biologically relevant categories which predict known molecular subtypes. These results provide the basis for an improved taxonomy of PDAC, which may lend itself to future treatment strategies and the development of deep learning models.

Infertility has become a common problem in global health, and unsurprisingly, many couples need medical assistance to achieve reproduction. Many human behaviors can lead to infertility, which is none other than unhealthy sperm. The important thing is that assisted reproductive techniques require selecting healthy sperm. Hence, machine learning algorithms are presented as the subject of this research to effectively modernize and make accurate standards and decisions in classifying sperm. In this study, we developed a deep learning fusion architecture called SwinMobile that combines the Shifted Windows Vision Transformer (Swin) and MobileNetV3 into a unified feature space and classifies sperm from impurities in the SVIA Subset-C. Swin Transformer provides long-range feature extraction, while MobileNetV3 is responsible for extracting local features. We also explored incorporating an autoencoder into the architecture for an automatic noise-removing model. Our model was tested on SVIA, HuSHem, and SMIDS. Comparison to the state-of-the-art models was based on F1-score and accuracy. Our deep learning results accurately classified sperm and performed well in direct comparisons with previous approaches despite the datasets’ different characteristics. We compared the model from Xception on the SVIA dataset, the MC-HSH model on the HuSHem dataset, and Ilhan et al.’s model on the SMIDS dataset and the astonishing results given by our model. The proposed model, especially SwinMobile-AE, has strong classification capabilities that enable it to function with high classification results on three different datasets. We propose that our deep learning approach to sperm classification is suitable for modernizing the clinical world. Our work leverages the potential of artificial intelligence technologies to rival humans in terms of accuracy, reliability, and speed of analysis. The SwinMobile-AE method we provide can achieve better results than state-of-the-art, even for three different datasets. Our results were benchmarked by comparisons with three datasets, which included SVIA, HuSHem, and SMIDS, respectively (95.4% vs. 94.9%), (97.6% vs. 95.7%), and (91.7% vs. 90.9%). Thus, the proposed model can realize technological advances in classifying sperm morphology based on the evidential results with three different datasets, each having its characteristics related to data size, number of classes, and color space.

Magnetic resonance imaging (MRI) serves as the clinical gold standard for diagnosing lumbar disc herniation (LDH). This multicenter study was to develop and clinically validate a deep learning (DL) model utilizing axial T2-weighted lumbar MRI sequences to automate LDH detection, following the Michigan State University (MSU) morphological classification criteria. A total of 8428 patients (100000 axial lumbar MRIs) with spinal surgeons annotating the datasets per MSU criteria, which classifies LDH into 11 subtypes based on morphology and neural compression severity, were analyzed. A DL architecture integrating adaptive multi-scale feature fusion titled as AFFM-YOLOv8 was developed. Model performance was validated against radiologists’ annotations using accuracy, precision, recall, F1-score, and Cohen’s κ (95% confidence intervals). The proposed model demonstrated superior diagnostic performance with a 91.01% F1-score (3.05% improvement over baseline) and 3% recall enhancement across all evaluation metrics. For surgical indication prediction, strong inter-rater agreement was achieved with senior surgeons (κ = 0.91, 95% CI 90.6–91.4) and residents (κ = 0.89, 95% CI 88.5–89.4), reaching consensus levels comparable to expert-to-expert agreement (senior surgeons: κ = 0.89; residents: κ = 0.87). This study establishes a DL framework for automated LDH diagnosis using large-scale axial MRI datasets. The model achieves clinician-level accuracy in MUS-compliant classification, addressing key limitations of prior binary classification systems. By providing granular spatial and morphological insights, this tool holds promise for standardizing LDH assessment and reducing diagnostic delays in resource-constrained settings.

Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA , as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

Optical microscopy is the gold standard technique used to confirm the diagnosis of scabies. Multiple diagnostic features of the pathogen Sarcoptes scabiei var. hominis (S. scabiei) can be identified under a microscope and classified into 3 categories: mites, eggs and fecal pellets. However, mite and eggshell fragments can also be observed, which have been ignored in the 2020 International Alliance for the Control of Scabies (IACS) Criteria and by most researchers. In this study, we propose a novel morphological classification method that classifies multiple diagnostic features into 5 categories and 7 subcategories. Our results revealed that 65.2% (1893 of 2896) of the positive cases were confirmed through the identification of mites, eggs or fecal pellets, whereas up to 34.6% (1003 of 2896) of the positive cases were confirmed through the identification of mite or eggshell fragments. Therefore, the important diagnostic values of mite and eggshell fragments should be emphasized. Importantly, for the first time, mite and eggshell fragments were classified into 7 subcategories, some of which are easily ignored or confused with contaminating artefacts. We believe that this novel morphological classification method will be beneficial for operator training in interpreting slides and in improving the 2020 IACS Criteria.

PurposeThis study aimed to explore the association of preoperative magnetic resonance imaging (MRI) tumor morphological classification with early recurrence (ER) and overall survival (OS) after radical surgery of hepatocellular carcinoma (HCC).Patients and MethodsA retrospective analysis of 296 patients with HCC who underwent radical resection was performed. On the basis of LI-RADS, tumor imaging morphology was classified into three types. The clinical imaging features, ER, and survival rates of three types were compared. Univariate and multivariate Cox regression analyses were conducted to identify prognostic factors associated with OS and ER after hepatectomy for HCC.ResultsThere were 167 tumors of type 1, 95 of type 2, and 34 of type 3. In patients with type 3 HCC, postoperative mortality and ER were significantly higher than in patients with type 1 and type 2 (55.9% versus 32.6% versus 27.5% and 52.9% versus 33.7% versus 28.7%). In multivariate analysis, the LI-RADS morphological type was a stronger risk factor for predicting poor OS [hazard ratio (HR) 2.77, 95% confidence interval (CI) 1.59–4.85, P < 0.001] and ER (HR 2.14, 95% CI 1.24–3.70, P = 0.007). A subgroup analysis revealed that type 3 was associated with poor OS and ER in > 5 cm cases but not in < 5 cm cases.ConclusionsER and OS of patients with HCC undergoing radical surgery can be predicted using the preoperative tumor LI-RADS morphological type, which could help to select personalized treatment plans for patients with HCC in the future.

Aiming at the problem of high morphological similarity between the different types of neurons and the large intra-class difference, which is easy to lead to low accuracy of neuron classification, a neural morphology classification method based on feature reconstruction and self-cure residual network is proposed. Firstly, to address the problems of edge pixel weakening and feature erosion by padding strategies that tend to occur during the convolution process of conventional convolution, a feature reconstruction module is constructed at the back end of the backbone network to retain important central features and filter damaged edge features. Then, the attention to neuronal morphological features is enhanced by using a self-attentive weight module and a rank regularization loss method, where the self-attention weight module assigns a weight to each sample to capture the sample importance for weighted loss. In addition, the rank regularization module re-ranked these weights in descending order, dividing them into two groups of high and low weights and regularizing the two groups by enforcing margins between the two average weights. The method achieved superior classification results on the NeuroMorpho-rat dataset, with twelve-way classification accuracies of 96.7%, 86.94% and 85.84% on the Img_raw, Img_resample and Img_XYalign datasets, separately. Comparing with the other methods, the present method has a higher classification accuracy of neurons. Comparing with the original ResNet18 network, it can effectively improve the neuron classification accuracy. 针对不同类别神经元之间的形态相似度高、类内区别性大, 容易导致神经元分类准确率不高的问题, 提出了一种基于特征重构自愈残差网络的神经元形态分类方法。针对传统卷积造成边缘像素弱化和填充策略带来新像素侵蚀特征的问题, 在基础网络后端构建特征重构模块来保留重要的中心特征并过滤受损的边缘特征。利用自注意力权重模块和排序正则化损失方法增强对神经元形态特征的关注。自注意力权重模块为每个样本重新分配权重, 以此捕获样本重要性进行加权损失; 排序正则化模块则将这些权重按降序重新排序, 分为高低2组权重, 同时通过在2组平均权重之间强制执行边距进行正则化处理。所提方法在大鼠神经元形态数据集上进行实验, 实现了较为优良的分类效果, 在Img_raw、Img_resample和Img_XYalign数据集上进行十二分类的准确率分别达到了96.7%, 86.94%, 85.84%。与其他分类方法相比, 所提方法具有更高的神经元形态分类准确率, 相较于基础网络ResNet18, 有效地提升了神经元形态分类准确率。

Leptotrombidium (Acari: Trombiculidae) mites are carriers of Orientia tsutsugamushi, the bacterial pathogen causing scrub typhus in humans. Classification of Leptotrombidium is vital because limited mite species carry O. tsutsugamushi. Generally, Leptotrombidium at the larval stage (approximately 0.2 mm in size) are used for morphological identification. However, morphological identification is often challenging because it requires considerable skills and taxonomic expertise. In this study, we found that the full-length sequences of the mitochondrial cytochrome c oxidase subunit 1 gene varied among the significant Leptotrombidium. On the basis of these, we modified the canonical deoxyribonucleic acid (DNA) barcoding method for animals by redesigning the primer set to be suitable for Leptotrombidium. Polymerase chain reaction with the redesigned primer set drastically increased the detection sensitivity, especially against Leptotrombidium scutellare (approximately 17% increase), one of the significant mites carrying O. tsutsugamushi. Phylogenetic analysis showed that the samples morphologically classified as L. scutellare and Leptotrombidium pallidum were further split into 3 and 2 distinct subclusters respectively. The mean genetic distance (p-distance) between L. scutellare and L. pallidum was 0.2147, whereas the mean distances within each species were 0.052 and 0.044, respectively. Within L. scutellare, the mean genetic distances between the 3 subclusters were 0.1626-0.1732, whereas the distances within each subcluster were 0.003-0.017. Within L. pallidum, the mean genetic distance between the 2 subclusters was 0.1029, whereas the distances within each subcluster were 0.010-0.013. The DNA barcoding uncovered a broad genetic diversity of Leptotrombidium, especially of L. scutellare and L. pallidum, the notable species carrying O. tsutsugamushi. We conclude that the DNA barcoding using our primers enables precise and detailed classification of Leptotrombidium and implies the existence of a subgenotype in Leptotrombidium that had not been found by morphological identification.

Urban parks have significant cooling effects, which can both mitigate the urban heat is-land effect and are crucial to the sustainable development of the human habitat. Although studies have been conducted to explore the influence of urban park morphology on the cooling effect of parks, they are not sufficiently in depth. Therefore, this paper took 117 urban parks in the central city of Chengdu as the research objects based on the perspective of the quantitative classification of urban park morphology. Then, remote sensing interpretation, spatial statistics, and regression analysis were used, and the four indicators of cooling intensity, cooling distance, cooling area, and cooling efficiency of urban parks were integrated to explore the cooling effect of the different morphological types of urban parks. The results show that (1) urban parks in Chengdu could be divided into five categories, among which the cooling effect of round parks was the best, and the cooling efficiency was 0.7. (2) In terms of park cooling area, urban parks’ area and perimeter thresholds were 30 ha and 4000 m, respectively. (3) When the area and perimeter of urban parks reached 70 ha and 3000 m, respectively, the increase in the cooling distance slowed down. (4) The cooling efficiency of the park was best when the shape index (indicating the complexity of the park boundaries) of the urban park was 2.8. The results of the study provide theoretical support for the intensive use of urban park green space and help the construction and promotion of a beautiful and livable park city in Chengdu.

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ≈ 2.3 the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.