After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis ...takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them.
•Decorrelation formulation based contrast improvement.•Lesion segmentation using modified MASK RCNN.•Transfer Learning based CNN features are extracted.•A Entropy-controlled LS-SVM based best CNN ...features are selected.
Malignant melanoma is considered to be one of the deadliest types of skin cancers which is responsible for the massive number of deaths worldwide. According to the American Cancer Society (ACS), more than a million Americans are living with this melanoma. Since 2019, 192,310 new cases of melanoma are registered, where 95,380 are noninvasive, and 96,480 are invasive. The numbers of deaths due to melanoma in 2019 alone are 7,230, comprising 4,740 men and 2,490 women. Melanoma may be curable if diagnosed at the earlier stages; however, the manual diagnosis is time-consuming and also dependent on the expert dermatologist. In this work, a fully automated computerized aided diagnosis (CAD) system is proposed based on the deep learning framework. In the proposed scheme, the original dermoscopic images are initially pre-processed using the decorrelation formulation technique, which later passes the resultant images to the MASK-RCNN for the lesion segmentation. In this step, the MASK RCNN model is trained using the segmented RGB images generated from the ground truth images of ISBI2016 and ISIC2017 datasets. The resultant segmented images are later passed to the DenseNet deep model for feature extraction. Two different layers, average pool and fully connected, are used for feature extraction, which are later combined, and the resultant vector is forwarded to the feature selection block for down - sampling using proposed entropy-controlled least square SVM (LS-SVM). Three datasets are utilized for validation - ISBI2016, ISBI2017, and HAM10000 to achieve an accuracy of 96.3%, 94.8%, and 88.5% respectively. Further, the performance of MASK-RCNN is also validated on ISBI2016 and ISBI2017 to attain an accuracy of 93.6% and 92.7%. To further increase our confidence in the proposed framework, a fair comparison with other state-of-the-art is also provided.
A review on extreme learning machine Wang, Jian; Lu, Siyuan; Wang, Shui-Hua ...
Multimedia tools and applications,
12/2022, Letnik:
81, Številka:
29
Journal Article
Recenzirano
Odprti dostop
Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising ...performance. In this paper, we hope to present a comprehensive review on ELM. Firstly, we will focus on the theoretical analysis including universal approximation theory and generalization. Then, the various improvements are listed, which help ELM works better in terms of stability, efficiency, and accuracy. Because of its outstanding performance, ELM has been successfully applied in many real-time learning tasks for classification, clustering, and regression. Besides, we report the applications of ELM in medical imaging: MRI, CT, and mammogram. The controversies of ELM were also discussed in this paper. We aim to report these advances and find some future perspectives.
Mutations in several general pre-mRNA splicing factors have been linked to myelodysplastic syndromes (MDSs) and solid tumors. These mutations have generally been assumed to cause disease by the ...resultant splicing defects, but different mutations appear to induce distinct splicing defects, raising the possibility that an alternative common mechanism is involved. Here we report a chain of events triggered by multiple splicing factor mutations, especially high-risk alleles in SRSF2 and U2AF1, including elevated R-loops, replication stress, and activation of the ataxia telangiectasia and Rad3-related protein (ATR)-Chk1 pathway. We further demonstrate that enhanced R-loops, opposite to the expectation from gained RNA binding with mutant SRSF2, result from impaired transcription pause release because the mutant protein loses its ability to extract the RNA polymerase II (Pol II) C-terminal domain (CTD) kinase—the positive transcription elongation factor complex (P-TEFb)—from the 7SK complex. Enhanced R-loops are linked to compromised proliferation of bone-marrow-derived blood progenitors, which can be partially rescued by RNase H overexpression, suggesting a direct contribution of augmented R-loops to the MDS phenotype.
Display omitted
•Mutations in splicing factors cause cell cycle arrest but distinct splicing defects•Causal mutations in SRSF2 and U2AF1 activate the ATR, but not ATM, pathway•R-loops are augmented genome-wide in SRSF2 and U2AF1 mutants•Overexpressed RNase H partially corrects growth defect of hematopoietic progenitors
Chen et al. report that myelodysplastic syndrome-associated mutations in splicing factors, including SRSF2 and U2AF1, cause cell growth defects through elevated R-loops, replication stress, and ATR-Chk1 activation. Mutant SRSF2 induces transcription pausing and, thus, R-loops, possibly because of its compromised ability in extracting p-TEFb from the 7SK complex at TSSs.
Multigene and genomic data sets have become commonplace in the field of phylogenetics, but many existing tools are not designed for such data sets, which often makes the analysis time‐consuming and ...tedious. Here, we present PhyloSuite, a (cross‐platform, open‐source, stand‐alone Python graphical user interface) user‐friendly workflow desktop platform dedicated to streamlining molecular sequence data management and evolutionary phylogenetics studies. It uses a plugin‐based system that integrates several phylogenetic and bioinformatic tools, thereby streamlining the entire procedure, from data acquisition to phylogenetic tree annotation (in combination with iTOL). It has the following features: (a) point‐and‐click and drag‐and‐drop graphical user interface; (b) a workplace to manage and organize molecular sequence data and results of analyses; (c) GenBank entry extraction and comparative statistics; and (d) a phylogenetic workflow with batch processing capability, comprising sequence alignment (mafft and macse), alignment optimization (trimAl, HmmCleaner and Gblocks), data set concatenation, best partitioning scheme and best evolutionary model selection (PartitionFinder and modelfinder), and phylogenetic inference (MrBayes and iq‐tree). PhyloSuite is designed for both beginners and experienced researchers, allowing the former to quick‐start their way into phylogenetic analysis, and the latter to conduct, store and manage their work in a streamlined way, and spend more time investigating scientific questions instead of wasting it on transferring files from one software program to another.
A wealth of evidence supports the role of tumor immunotherapy as a vital therapeutic option in cancer. In recent decades, accumulated studies have revealed the anticancer activities of natural ...products and their derivatives. Increasing interest has been driven toward finding novel potential modulators of tumor immunotherapy from natural products, a hot research topic worldwide. These works of research mainly focused on natural products, including polyphenols (e.g., curcumin, resveratrol), cardiotonic steroids (e.g., bufalin and digoxin), terpenoids (e.g., paclitaxel and artemisinins), and polysaccharide extracts (e.g., lentinan). Compelling data highlight that natural products have a promising future in tumor immunotherapy. Considering the importance and significance of this topic, we initially discussed the integrated research progress of natural products and their derivatives, including target T cells, macrophages, B cells, NKs, regulatory T cells, myeloid‐derived suppressor cells, inflammatory cytokines and chemokines, immunogenic cell death, and immune checkpoints. Furthermore, these natural compounds inactivate several key pathways, including NF‐κB, PI3K/Akt, MAPK, and JAK/STAT pathways. Here, we performed a deep generalization, analysis, and summarization of the previous achievements, recent progress, and the bottlenecks in the development of natural products as tumor immunotherapy. We expect this review to provide some insight for guiding future research.
This review aims to summarize the integrated research progress of natural products (e.g. curcumin) on the tumor immunotherapy and key intracellular pathways.
Acute kidney injury (AKI) is frequently triggered by abundant reactive oxygen/nitrogen species (RONS) and leads to high morbidity and mortality in clinic. Unfortunately, the current clinical ...treatment options are only limited to supportive care, and hence, the development of nano‐antioxidants with high kidney enrichment is an attractive novel strategy for AKI management. Herein, self‐assembled ultrasmall nanodots are reported that consist of iron ion, gallic acid, and polyvinylpyrrolidone (denoted as FGP nanodots) as broad‐spectrum RONS scavengers to alleviate both glycerinum‐ and cis‐platinum‐ induced AKI in mice. Ultrasmall FGP nanodots (≈3.5 nm) offer efficient protection in vitro and reduce cellular apoptosis after H2O2 stimulation by eliminating various RONS including hydroxyl radical (·OH), superoxide anion (·O2−), nitric oxide (NO), and peroxynitrite (ONOO−), etc. In vivo duplex magnetic resonance/fluorescence imaging demonstrates preferential accumulation of FGP nanodots in the kidneys with rapid renal clearance through urine. Importantly, FGP nanodots exhibit remarkable RONS consumption in vivo with enhanced biocompatibility and biodegradability, resulting in superior therapeutic effect than small molecule drug (Amifostine) in two AKI mouse models. This study presents the promising potential of ultrasmall self‐assembled FGP nanodots as imaging contrast agent and broad‐spectrum antioxidant nanomedicine for AKI theranotics.
The biodegradable self‐assembled ultrasmall nanodots with preferential kidney accumulation and rapid excretion, which are composed of iron ion, gallic acid, and polyvinylpyrrolidone, are developed as broad‐spectrum reactive oxygen/nitrogen species scavengers (RONS) to alleviate both glycerinum‐ and cis‐platinum‐ induced acute kidney injury in mice.
An enantioselective catalytic alkoxylation/oxidative rearrangement of allylic alcohols has been established by using a Brønsted acid and chiral organoiodine. The presence of 20 mol % of an ...(S)‐proline‐derived C2‐symmetric chiral iodine led to enantioenriched α‐arylated β‐alkoxylated ketones in good yields and with high levels of enantioselectivity (84–94 % ee).
Shifting positions: Asymmetric catalytic alkoxylation/oxidative rearrangement of allylic alcohols was achieved by using a Brønsted acid and a chiral organoiodine. The reaction leads to optically active α‐arylated β‐etherized ketones in good yields and excellent stereoselectivity. Ts=4‐toluenesulfonyl.
To construct a long noncoding RNA (lncRNA)–microRNA (miRNA)–messenger RNA (mRNA) regulatory network related to epithelial ovarian cancer (EOC) cisplatin‐resistant, differentially expressed genes ...(DEGs), differentially expressed lncRNAs (DELs), and differentially expressed miRNAs (DEMs) between MDAH and TOV‐112D cells lines were identified. Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted to analyze the biological functions of DEGs. Downstream mRNAs or upstream lncRNAs for miRNAs were analyzed at miRTarBase 7.0 or DIANA‐LncBase V2, respectively. A total of 485 significant DEGs, 85 DELs, and 5 DEMs were identified. Protein–protein interaction (PPI) network of DEGs contrains 81 nodes and 141 edges was constructed, and 25 hub genes related to EOC cisplatin‐resistant were identified. Subsequently, a lncRNA–miRNA–mRNA regulatory network contains 4 lncRNAs, 4 miRNAs, and 35 mRNAs was established. Taken together, our study provided evidence concerning the alteration genes involved in EOC cisplatin‐resistant, which will help to unravel the mechanisms underlying drug resistant.
1.
A long noncoding RNA–microRNA–messenger RNA network related to epithelial ovarian cancer (EOC) cisplatin‐resistant was established.
2.
Genes involved in EOC cisplatin‐resistant were identified.