Mangrove Species Classification from Unmanned Aerial Vehicle Hyperspectral Images Using Object-Oriented Methods Based on Feature Combination and Optimization.

Accurate and timely acquisition of the spatial distribution of mangrove species is essential for conserving ecological diversity. Hyperspectral imaging sensors are recognized as effective tools for monitoring mangroves. However, the spatial complexity of mangrove forests and the spectral redundancy of hyperspectral images pose challenges to fine classification. Moreover, finely classifying mangrove species using only spectral information is difficult due to spectral similarities among species. To address these issues, this study proposes an object-oriented multi-feature combination method for fine classification. Specifically, hyperspectral images were segmented using multi-scale segmentation techniques to obtain different species of objects. Then, a variety of features were extracted, including spectral, vegetation indices, fractional order differential, texture, and geometric features, and a genetic algorithm was used for feature selection. Additionally, ten feature combination schemes were designed to compare the effects on mangrove species classification. In terms of classification algorithms, the classification capabilities of four machine learning classifiers were evaluated, including K-nearest neighbor (KNN), support vector machines (SVM), random forests (RF), and artificial neural networks (ANN) methods. The results indicate that SVM based on texture features achieved the highest classification accuracy among single-feature variables, with an overall accuracy of 97.04%. Among feature combination variables, ANN based on raw spectra, first-order differential spectra, texture features, vegetation indices, and geometric features achieved the highest classification accuracy, with an overall accuracy of 98.03%. Texture features and fractional order differentiation are identified as important variables, while vegetation index and geometric features can further improve classification accuracy. Object-based classification, compared to pixel-based classification, can avoid the salt-and-pepper phenomenon and significantly enhance the accuracy and efficiency of mangrove species classification. Overall, the multi-feature combination method and object-based classification strategy proposed in this study provide strong technical support for the fine classification of mangrove species and are expected to play an important role in mangrove restoration and management.

Ribemansides A and B, TRPC6 Inhibitors from Ribes manshuricum That Suppress TGF-ß1-Induced Fibrogenesis in HK-2 Cells.

Two new acylated ß-hydroxynitrile glycosides, ribemansides A (1) and B (2), were isolated from the aerial parts of Ribes manshuricum. Their structures were elucidated by comprehensive spectroscopic analysis. Ribemansides A and B inhibited transforming growth factor ß1 (TGF-ß1)-induced expression of α-smooth muscle actin, fibronectin release, and changes in cell morphology in the human proximal tubular epithelial cell line (human kidney-2, HK-2). Further biological evaluation demonstrated that both 1 and 2 inhibit the activity of canonical transient receptor potential cation channel 6 (TRPC6), with IC50 values of 24.5 and 25.6 µM, respectively. The antifibrogenic effect of these compounds appears to be mediated through TRPC6 inhibition, since the TRPC6 inhibitor, SAR7334, also suppressed TGF-ß1-induced fibrogenesis in HK-2 cells.

DM-CNN: Dynamic Multi-scale Convolutional Neural Network with uncertainty quantification for medical image classification.

Convolutional neural network (CNN) has promoted the development of diagnosis technology of medical images. However, the performance of CNN is limited by insufficient feature information and inaccurate attention weight. Previous works have improved the accuracy and speed of CNN but ignored the uncertainty of the prediction, that is to say, uncertainty of CNN has not received enough attention. Therefore, it is still a great challenge for extracting effective features and uncertainty quantification of medical deep learning models In order to solve the above problems, this paper proposes a novel convolutional neural network model named DM-CNN, which mainly contains the four proposed sub-modules : dynamic multi-scale feature fusion module (DMFF), hierarchical dynamic uncertainty quantifies attention (HDUQ-Attention) and multi-scale fusion pooling method (MF Pooling) and multi-objective loss (MO loss). DMFF select different convolution kernels according to the feature maps at different levels, extract different-scale feature information, and make the feature information of each layer have stronger representation ability for information fusion HDUQ-Attention includes a tuning block that adjust the attention weight according to the different information of each layer, and a Monte-Carlo (MC) dropout structure for quantifying uncertainty MF Pooling is a pooling method designed for multi-scale models, which can speed up the calculation and prevent overfitting while retaining the main important information Because the number of parameters in the backbone part of DM-CNN is different from other modules, MO loss is proposed, which has a fast optimization speed and good classification effect DM-CNN conducts experiments on publicly available datasets in four areas of medicine (Dermatology, Histopathology, Respirology, Ophthalmology), achieving state-of-the-art classification performance on all datasets. DM-CNN can not only maintain excellent performance, but also solve the problem of quantification of uncertainty, which is a very important task for the medical field. The code is available: https://github.com/QIANXIN22/DM-CNN.

EHDFL: Evolutionary hybrid domain feature learning based on windowed fast Fourier convolution pyramid for medical image classification.

With the development of modern medical technology, medical image classification has played an important role in medical diagnosis and clinical practice. Medical image classification algorithms based on deep learning emerge in endlessly, and have achieved amazing results. However, most of these methods ignore the feature representation based on frequency domain, and only focus on spatial features. To solve this problem, we propose a hybrid domain feature learning (HDFL) module based on windowed fast Fourier convolution pyramid, which combines the global features with a wide range of receptive fields in frequency domain and the local features with multiple scales in spatial domain. In order to prevent frequency leakage, we construct a Windowed Fast Fourier Convolution (WFFC) structure based on Fast Fourier Convolution (FFC). In order to learn hybrid domain features, we combine ResNet, FPN, and attention mechanism to construct a hybrid domain feature learning module. In addition, a super-parametric optimization algorithm is constructed based on genetic algorithm for our classification model, so as to realize the automation of our super-parametric optimization. We evaluated the newly published medical image classification dataset MedMNIST, and the experimental results show that our method can effectively learning the hybrid domain feature information of frequency domain and spatial domain.

A Network with Composite Loss and Parameter-free Chunking Fusion Block for Super-Resolution MR Image.

MRI is often influenced by many factors, and single image super-resolution (SISR) based on a neural network is an effective and cost-effective alternative technique for the high-resolution restoration of low-resolution images. However, deep neural networks can easily lead to overfitting and make the test results worse. The network with a shallow training network is difficult to fit quickly and cannot completely learn training samples. To solve the above problems, a new end-to-end super-resolution (SR) method is proposed for magnetic resonance (MR) images. Firstly, in order to better fuse features, a parameter-free chunking fusion block (PCFB) is proposed, which can divide the feature map into n branches by splitting channels to obtain parameter-free attention. Secondly, the proposed training strategy including perceptual loss, gradient loss, and L1 loss has significantly improved the accuracy of model fitting and prediction. Finally, the proposed model and training strategy take the super-resolution IXISR dataset (PD, T1, and T2) as an example to compare with the existing excellent methods and obtain advanced performance. A large number of experiments have proved that the proposed method performs better than the advanced methods in highly reliable measurement.

Activation of TRPC6 channels contributes to (+)-conocarpan-induced apoptotic cell death in HK-2 cells.

(+)-Conocarpan (CNCP), a neolignan frequently found in many medicinal and edible plants displays a broad spectrum of bioactivity. Here, we demonstrated that CNCP induced apoptotic cell death in human kidney-2 (HK-2) cells in a concentration-dependent manner (IC50 = 19.3 µM) and led to the sustained elevation of intracellular Ca2+ ([Ca2+]i). Lower extracellular Ca2+ concentrations from 2.3 mM to 0 mM significantly suppressed the CNCP-induced Ca2+ response by 69.1%. Moreover, the depletion of intracellular Ca2+ stores using thapsigargin normalized CNCP-induced Ca2+ release from intracellular Ca2+ stores, suggesting that the CNCP-induced Ca2+ response involved both extracellular Ca2+ influx and Ca2+ release from intracellular Ca2+ stores. SAR7334, a TRPC3/6/7 channel inhibitor, but neither Pyr3, a selective TRPC3 channel inhibitor, nor Pico145, a TRPC1/4/5 inhibitor, suppressed the CNCP-induced Ca2+ response by 57.2% and decreased CNCP-induced cell death by 53.4%, suggesting a critical role for TRPC6 channels in CNCP-induced Ca2+ influx and apoptotic cell death. Further electrophysiological recording demonstrated that CNCP directly activated TRPC6 channels by increasing channel open probability with an EC50 value of 6.01 µM. Considered together, these data demonstrate that the direct activation of TRPC6 channels contributes to CNCP-induced apoptotic cell death in HK-2 cells. Our data point out the potential risk of renal toxicity from CNCP if used as a therapeutic agent.

Alkaloids from Corydalis decumbens suppress neuronal excitability in primary cultures of mouse neocortical neurons.

Eight previously undescribed alkaloids, named corydemine, dihydrocorydemine, corydedine, 8,13-dioxo-14-hydroxytetrahydropalmatine, egenine-α-N-oxide, egenine-ß-N-oxide, 7'-O-ethylegenine-α-N-oxide, and 7'-O-ethylegenine-ß-N-oxide, together with three known ones, muramine, l-tetrahydropalmatine, and (+)-egenine, were isolated from the bulbs of Corydalis decumbens. Their structures were elucidated by comprehensive spectroscopic analysis and chemical correlation. The isolated compounds were tested for their ability to modulate neuronal excitability in primary cultured neocortical neurons. Four of the compounds, corydemine, dihydrocorydemine, muramine, and l-tetrahydropalmatine, inhibited neuronal excitability with IC50 values of 3.6, 16.7, 13.5 and 14.0 µM, respectively.

The protective effects of Ribes diacanthum Pall on cisplatin-induced nephrotoxicity in mice.

ETHNOPHARMACOLOGICAL RELEVANCE: Ribes diacanthum Pall. (Saxifragaceae), a Mongolian folk medicinal plant, was used to treat urinary system diseases. The present work aims to investigate the protective effects of Ribes diacanthum Pall (RDP) against cisplatin-induced nephrotoxicity. METHODS: The renal injury was modeled by intraperitoneal injection of cisplatin for 5 consecutive days (5 mg/kg). Nephroprotection of RDP was investigated by oral administration of RDP aqueous extract at a daily dose of 40 mg/kg for 14 consecutive days, starting 7 days prior to cisplatin administration. RESULTS: We demonstrated that pretreatment with RDP aqueous extract protected the mice from death induced by cisplatin administration. RDP treatment also significantly reduced blood urea nitrogen (BUN) and serum creatinine (Cr) levels observed in cisplatin-administrated mice. Histopathological analysis demonstrated that RDP administration protected cisplatin-induced renal tubular cell apoptosis. Further western blotting analysis revealed that RDP significantly reversed cisplatin-increased expression levels of cleaved-Caspase-3, Bax and cisplatin-decreased expression level of Bcl-2 in renal tissue. Finally, RDP markedly enhanced enzyme activities of reduced superoxide dismutase (SOD), Heme oxygenase 1 (HO-1) and catalase (CAT), suppressed lipid peroxidation as well as reactive oxygen species (ROS) production. CONCLUSION: We concluded that RDP displayed nephroprotective effects against cisplatin-induced renal tubular cell apoptosis, possibly associated with both enhanced antioxidase activity and suppressed ROS generation. Given the major nephrotoxicity of cisplatin cancer chemotherapy, RDP might be a potential candidate for neoadjuvant chemotherapy.