Architectural Distortion-Based Digital Mammograms Classification Using Depth Wise Convolutional Neural Network

Architectural distortion is the third most suspicious appearance on a mammogram representing abnormal regions. Architectural distortion (AD) detection from mammograms is challenging due to its subtle and varying asymmetry on breast mass and small size. Automatic detection of abnormal ADs regions in mammograms using computer algorithms at initial stages could help radiologists and doctors. The architectural distortion star shapes ROIs detection, noise removal, and object location, affecting the classification performance, reducing accuracy. The computer vision-based technique automatically removes the noise and detects the location of objects from varying patterns. The current study investigated the gap to detect architectural distortion ROIs (region of interest) from mammograms using computer vision techniques. Proposed an automated computer-aided diagnostic system based on architectural distortion using computer vision and deep learning to predict breast cancer from digital mammograms. The proposed mammogram classification framework pertains to four steps such as image preprocessing, augmentation and image pixel-wise segmentation. Architectural distortion ROI's detection, training deep learning, and machine learning networks to classify AD's ROIs into malignant and benign classes. The proposed method has been evaluated on three databases, the PINUM, the CBIS-DDSM, and the DDSM mammogram images, using computer vision and depth-wise 2D V-net 64 convolutional neural networks and achieved 0.95, 0.97, and 0.98 accuracies, respectively. Experimental results reveal that our proposed method outperforms as compared with the ShuffelNet, MobileNet, SVM, K-NN, RF, and previous studies.

Computer Vision-Based Microcalcification Detection in Digital Mammograms Using Fully Connected Depthwise Separable Convolutional Neural Network

Microcalcification clusters in mammograms are one of the major signs of breast cancer. However, the detection of microcalcifications from mammograms is a challenging task for radiologists due to their tiny size and scattered location inside a denser breast composition. Automatic CAD systems need to predict breast cancer at the early stages to support clinical work. The intercluster gap, noise between individual MCs, and individual object’s location can affect the classification performance, which may reduce the true-positive rate. In this study, we propose a computer-vision-based FC-DSCNN CAD system for the detection of microcalcification clusters from mammograms and classification into malignant and benign classes. The computer vision method automatically controls the noise and background color contrast and directly detects the MC object from mammograms, which increases the classification performance of the neural network. The breast cancer classification framework has four steps: image preprocessing and augmentation, RGB to grayscale channel transformation, microcalcification region segmentation, and MC ROI classification using FC-DSCNN to predict malignant and benign cases. The proposed method was evaluated on 3568 DDSM and 2885 PINUM mammogram images with automatic feature extraction, obtaining a score of 0.97 with a 2.35 and 0.99 true-positive ratio with 2.45 false positives per image, respectively. Experimental results demonstrated that the performance of the proposed method remains higher than the traditional and previous approaches.

[Ectopic thyroid tissue after total thyroidectomy]

Ectopic thyroid gland tissue can occur either as the only detectable thyroid gland tissue or in addition to a normotopic thyroid gland. After a total thyroidectomy thyroid-stimulating hormone (TSH) can induce a compensatory volume increase of previously asymptomatic ectopic tissue. This hyperplastic ectopic tissue can occur as an unclear cervical space-occupying lesion. Prior to surgical exploration of an unclear cervical mass the possibility of ectopic thyroid tissue should be included in the differential diagnostic considerations.

In vitro permeation through porcine buccal mucosa of caffeic acid phenetyl ester (CAPE) from a topical mucoadhesive gel containing propolis

Recent studies have shown that propolis has on the oral cavity appreciable antibacterial, antifungal and antiviral actions, as well as anti-inflammatory, anaesthetic and cytostatic properties. In light of these studies, an assessment of the diffusion and permeation of caffeic acid phenetyl ester (CAPE) through porcine buccal mucosa was considered useful as a possible application in the stomatological field. To do so, a mucoadhesive topical gel was prepared to apply to the buccal mucosa. The gel was formulated in such a way as to improve the solubility of the propolis, conducting to an increase of the flux. The mucosal permeation of CAPE from the formulation was evaluated using Franz cells, with porcine buccal mucosa as septum between the formulation (donor compartment) and the receptor phase chamber. The diffusion through the membrane was determined by evaluating the amount of CAPE present in the receiving solution, the flux and the permeation coefficient (at the steady state) in the different formulations at set intervals. Qualitative and quantitative determinations were done by HPLC analysis. From the results, CAPE allowed a high permeability coefficient in comparison to the coefficient of other molecules, as expected from its physical-chemical structure. Moreover, the developed gel improved the CAPE flux approximately 35 times more with respect to an ethanol solution formulated at the same gel concentration. The developed gel was also tested in order to evaluate the mucoadhesive behaviour and comfort in vivo on 10 volunteers in a period of 8 h. The in vivo evaluation of mucoadhesive gel revealed adequate comfort and non-irritancy during the period of study and it was well accepted by the volunteers.

Regulation of prolactin, thyrotropin subunit, and gonadotropin subunit gene expression by pulsatile or continuous calcium signals

We investigated the importance of calcium (Ca2+) influx in increasing the steady state concentrations of mRNAs coding for the pituitary peptides PRL, alpha, and TSH, LH, and FSH beta-subunits. Adult female rat pituitaries were dissociated, plated for 48 h, then inserted into perifusion chambers. Secretory responses were measured after 2 and 22 h of perifusion, and after 24 h, the cells were recovered, total RNA was extracted, and mRNAs were assayed by dot blot hybridization. The first experiment examined the effect of the Ca2+ channel blocker verapamil (100 microM) on the stimulatory action of pulsatile TRH (4 nM; 60-min interval) or GnRH (100 pM; 60-min interval) on pituitary mRNAs. TRH pulses induced a significant increase (49-56%) in PRL, alpha, and TSH beta mRNAs. Similarly, GnRH pulses stimulated a rise in alpha (64%) and FSH beta (50%) mRNAs, but not LH beta. The effects of pulsatile TRH or GnRH were eliminated when verapamil was added to the medium, suggesting that Ca2+ influx is critical to the stimulatory action of TRH or GnRH. The second experiment examined the effect of pulsatile vs. continuous increases in intracellular Ca2+ on pituitary mRNA expression. Pulsatile Ca2+ signals were produced by giving 60-min pulses of 50 mM KCl, Bay K 8644 (10 microM), or Bay K 8644 (10 microM; in the presence of 10 mM KCl in the injectate) and vehicle pulses to controls. Continuous increases in intracellular Ca2+ were induced by perifusion with medium containing the Ca2+ ionophore A23187 (20 microM), and these groups were compared to that receiving continuous verapamil. Pulsatile increases in Ca2+ influx (KCl or Bay K 8644) stimulated significant elevations in all mRNAs studied (36-74% increase vs. controls), with the exception of TSH beta. The magnitude of the mRNA responses to pulsatile Ca2+ (vs. controls) was similar to that observed after TRH and GnRH pulses. In contrast, only LH beta was increased by A23187 (42% increase vs. controls; P < 0.05). PRL and alpha mRNAs were selectively diminished by A23187 (57% and 83% decreases vs. controls, respectively; P < 0.05) and verapamil (67% and 60%; P < 0.05). The data show that expression of these pituitary genes is regulated by Ca2+ and that a pulsatile Ca2+ signal is required to stimulate PRL, alpha, and FSH beta (but not LH beta).(ABSTRACT TRUNCATED AT 400 WORDS)

Analysis of tetracycline antibiotics and their common impurities by high-performance liquid chromatography using a polymeric column

The chromatographic separation of tetracycline, oxytetracycline, 6-demethyl-chlortetracycline, methacycline and minocycline, and the common impurities of tetracycline, oxytetracycline and chlortetracycline has been optimised on a Hamilton PRP-1 column using citrate-phosphate buffer with propan-2-ol and tetrahydrofuran as organic modifiers. Column efficiency was approximately doubled by the inclusion of 1% v/v dichloromethane in the mobile phase.

Application of 13C nuclear magnetic resonance spectroscopy to the analysis and structural investigation of tetracycline antibiotics and their common impurities

The spectral assignations of all the main resonances in the 13C nuclear magnetic resonance spectra in DMSO-d6 or D2O are presented and reviewed for ten of the principal tetracyclines in therapeutic use: tetracycline, chlortetracycline, 6-demethylchlortetracycline, minocycline, oxytetracycline, methacycline, meclocycline, doxycycline, rolitetracycline and lymecycline. NMR techniques employed include: proton noise-decoupled spectra, off-resonance decoupled spectra, nuclear Overhauser enhancement and the INEPT technique (insensitive nuclei enhanced by polarization transfer). 13C NMR is also examined as a means of detecting and identifying the principal degradation and isomerization products of tetracycline antibiotics. The analytical potential of 13C NMR is discussed with respect to quantitative analysis of impurities, studies on sites of protonation and metal-binding studies.

The identification and stereochemical study of tetracycline antibiotics by 1H nuclear magnetic resonance spectroscopy

The 1H NMR spectra of seven tetracycline antibiotics of clinical importance are reported and assigned as solutes in DMSO-d6 and other solvents. The data are analysed in terms of analytical utility and the provision of evidence of solute stereochemistry.