A novel image mining technique for classification of mammograms using hybrid feature selection

The image mining technique deals with the extraction of implicit knowledge and image with data relationship or other patterns not explicitly stored in the images. It is an extension of data mining to image domain. The main objective of this paper is to apply image mining in the domain such as breast mammograms to classify and detect the cancerous tissue. Mammogram image can be classified into normal, benign, and malignant class. Total of 26 features including histogram intensity features and gray-level co-occurrence matrix features are extracted from mammogram images. A hybrid approach of feature selection is proposed, which approximately reduces 75% of the features, and new decision tree is used for classification. The most interesting one is that branch and bound algorithm that is used for feature selection provides the best optimal features and no where it is applied or used for gray-level co-occurrence matrix feature selection from mammogram. Experiments have been taken for a data set of 300 images taken from MIAS of different types with the aim of improving the accuracy by generating minimum number of rules to cover more patterns. The accuracy obtained by this method is approximately 97.7%, which is highly encouraging.     

Texture-based features for classification of mammograms using decision tree

Mammogram—breast X-ray—is considered the most effective, low cost, and reliable method in early detection of breast cancer. Although general rules for the differentiation between benign and malignant breast lesions exist, only 15–30 % of masses referred for surgical biopsy are actually malignant. In this work, an approach is proposed to develop a computer-aided classification system for cancer detection from digital mammograms. The proposed system consists of three major steps. The first step is region of interest (ROI) extraction of 256 × 256 pixels size. The second step is the feature extraction; we used a set of 19 GLCM and GLRLM features, and the 19 (nineteen) features extracted from gray-level run-length matrix and gray-level co-occurrence matrix could distinguish malignant masses from benign masses with an accuracy of 96.7 %. Further analysis was carried out by involving only 12 of the 19 features extracted, which consists of 5 features extracted from GLCM matrix and 7 features extracted from GLRL matrix. The 12 selected features are as follows: Energy, Inertia, Entropy, Maxprob, Inverse, SRE, LRE, GLN, RLN, LGRE, HGRE, and SRLGE; ARM with 12 features as prediction can distinguish malignant mass image and benign mass with a level of accuracy of 93.6 %. Further analysis showed that area under the receiver operating curve was 0.995, which means that the accuracy level of classification is good or very good. Based on that data, it was concluded that texture analysis based on GLCM and GLRLM could distinguish malignant image and benign image with considerably good result. The third step is the classification process; we used the technique of decision tree using image content to classify between normal and cancerous masses. The proposed system was shown to have the large potential for cancer detection from digital mammograms.     

(La2/5Ba2/5Ca1/5)(Mn(2/5)-x Ni x Ti3/5)O3: Rietveld studies, dielectric and magnetic properties of new perovskite-related oxides

Oxides of the type (La_2/5Ba_2/5Ca_1/5)(Mn_(2/5)-x _Ni x _Ti3/5)O₃ (0 ≤ x ≤ 0.4) have been synthesized by the ceramic route. All the above oxides have been found to crystallize in the cubic perovskite structure. Rietveld refinement of the Ni-based oxide, (La_2/5Ba_2/5Ca_1/5)(Ni_2/5Ti_3/5)O₃ gave rise to a composition (La_0.44Ba_0.38Ca_0.18) (Ni_0.42Ti_0.58)O_2.85(6) and the refined lattice parameter obtained was 3.9411(2) Å (space group Pm3m;R(F²) = 0.026,R _p = 0.074,wR _p = 0.087). A shift from antiferromagnetic to paramagnetic behaviour is observed with increase in nickel concentration, the Mn-rich phases showing antiferromagnetism around 5 K. There is a systematic decrease in the dielectric constant, ε and loss tangent with increase in Ni concentration (from ε = 592 forx = 0 to ε = 78 forx = 0.4).     

Design and modelling of a self-dispersing twisted pipe to mitigate settling in coal water suspension

The hydrotransport of the industrial powders and bulk solids such as minerals, mineral tailings, coal and ash is considered to be an efficient mode of transportation. The pipelines ranging from a few meters to few kilometers in length are used for such transportation purposes. If not well addressed, the issue of particle settling in such pipelines can lead to blockage and even bursting of the pipeline due to the continued deposition of the solids. The present study proposes the introduction of a twisted pipe section of a suitable length and geometry, that produces enough turbulence in the flow, sufficient for the re-dispersion of the already settled particles and check their further deposition. To achieve this objective, 5 different geometries (each having 4 different lengths) of twisted pipes are designed and used to model the dynamics of the particles’ flow through them and in their downstream region. A low influx velocity (where particle settling is expected) of 0.5 m/s is selected for all the cases and the influx solids’ mass concentration ranges from 40 to 60%. The results generated by the commercial CFD software are in good agreement with the experimental data. The parameters viz. mixing index, pressure loss, and specific energy consumption are evaluated to choose the best design of the twisted pipe section. The 0.2 m long 3 lobes twisted pipe section is found to deliver the suspension of highest homogeneity at the cost of a slight increase in pressure loss and specific energy consumption. The present solution ensures the mitigation of particles’ settling and the other related issues.     

Facile development,characterization, and evaluation of novel bicalutamide loaded pH-sensitive mesoporous silica nanoparticles for enhanced prostate cancer therapy

It is a challenge to deliver therapeutics exclusively to cancer cells, while sparing the normal cells. However, pH-sensitive delivery systems have proved to be highly efficient in fulfilling this task due to their ability to provide on-demand and selective release of drug at acidic tumor sites. As a proof of concept, here pH responsive drug delivery system based on mesoporous core shell nanoparticles (NPs) surrounded with poly acrylic acid (PAA) layers were prepared employing a facile synthesis strategy. Bicalutamide (BIC) was encased into surface functionalized MCM-41 nanoparticles via electrostatic interactions. The synthesized NPs were characterized by nitrogen adsorption and desorption isotherms, SEM-EDS, TEM, LXRD, and WXRD. In vitro release studies demonstrated that BIC-MSN-PAA NPs exhibited a higher release in the acidic media which varied inversely with the increase in pH. Further, the results of cell cytotoxicity assay were evident that BICMSNs exhibited more potent killing of both PC-3 and LNCaP cells than free BIC. PAA-MSNs also exhibited an enhanced cellular uptake and prolonged circulation time in vivo. The results are suggestive of the fact that PAA functionalized MSNs can serve as an effective pH-responsive template and hold a great potential ahead in controlled release and effective cancer treatment.     

Correction to: Recent Deep Learning Techniques,Challenges and Its Applications for Medical Healthcare System: A Review

Neural Processing Letters - A correction to this paper has been published: https://doi.org/10.1007/s11063-021-10527-5     

Kalkitoxin Reduces Osteoclast Formation and Resorption and Protects against Inflammatory Bone Loss

Osteoclasts, bone-specified multinucleated cells produced by monocyte/macrophage, are involved in numerous bone destructive diseases such as arthritis, osteoporosis, and inflammation-induced bone loss. The osteoclast differentiation mechanism suggests a possible strategy to treat bone diseases. In this regard, we recently examined the in vivo impact of kalkitoxin (KT), a marine product obtained from the marine cyanobacterium Moorena producens (previously Lyngbya majuscula), on the macrophage colony-stimulating factor (M-CSF) and on the receptor activator of nuclear factor κB ligand (RANKL)-stimulated in vitro osteoclastogenesis and inflammation-mediated bone loss. We have now examined the molecular mechanism of KT in greater detail. KT decreased RANKL-induced bone marrow-derived macrophages (BMMs) tartrate-resistant acid phosphatase (TRAP)-multinucleated cells at a late stage. Likewise, KT suppressed RANKL-induced pit area and actin ring formation in BMM cells. Additionally, KT inhibited several RANKL-induced genes such as cathepsin K, matrix metalloproteinase (MMP-9), TRAP, and dendritic cell-specific transmembrane protein (DC-STAMP). In line with these results, RANKL stimulated both genes and protein expression of c-Fos and nuclear factor of activated T cells (NFATc1), and this was also suppressed by KT. Moreover, KT markedly decreased RANKL-induced p-ERK1/2 and p-JNK pathways at different time points. As a result, KT prevented inflammatory bone loss in mice, such as bone mineral density (BMD) and osteoclast differentiation markers. These experiments demonstrated that KT markedly inhibited osteoclast formation and inflammatory bone loss through NFATc1 and mitogen-activated protein kinase (MAPK) signaling pathways. Therefore, KT may have potential as a treatment for destructive bone diseases.