Purpose CEST MRI allows for indirect detection of molecules with exchangeable protons, measured as a reduction in water signal because of continuous transfer of saturated protons. CEST requires saturation pulses on the order of a second, as well as repeated acquisitions at different offset frequencies. The resulting extended scan time makes CEST susceptible to subject motion, which introduces field inhomogeneity, shifting offset frequencies and causing distortions in CEST spectra that resemble true CEST effects. This is a particular problem for molecules that resonate close to water, such as hydroxyl group in glycogen. To address this, a technique for real‐time measurement and correction of motion and field inhomogeneity is proposed. Methods A CEST sequence was modified to include double volumetric navigators (DvNavs) for real‐time simultaneous motion and shim correction. Phantom tests were conducted to investigate the effects of motion and shim changes on CEST quantification and to validate the accuracy of DvNav motion and shim estimates. To evaluate DvNav shim and motion correction in vivo, acquisitions including 5 experimental conditions were performed in the calf muscle of 2 volunteers. Results Phantom data show that DvNav‐CEST accurately estimates frequency and linear gradient changes because of motion and corrects resulting image distortions. In addition, DvNav‐CEST improves CEST quantification in vivo in the presence of motion. Conclusion The proposed technique allows for real‐time simultaneous motion and shim correction with no additional scanning time, enabling accurate CEST quantification even in the presence of motion and field inhomogeneity.

Purpose Cervical cancer is the 4th most common cancer among women, worldwide. Incidence and mortality rates are consistently increasing, especially in developing countries, due to the shortage of screening facilities, limited skilled professionals, and lack of awareness. Cervical cancer is screened using visual inspection after application of acetic acid (VIA), papanicolaou (Pap) test, human papillomavirus (HPV) test and histopathology test. Inter- and intra-observer variability may occur during the manual diagnosis procedure, resulting in misdiagnosis. The purpose of this study was to develop an integrated and robust system for automatic cervix type and cervical cancer classification using deep learning techniques. Methods 4005 colposcopy images and 915 histopathology images were collected from different local health facilities and online public datasets. Different pre-trained models were trained and compared for cervix type classification. Prior to classification, the region of interest (ROI) was extracted from cervix images by training and validating a lightweight MobileNetv2-YOLOv3 model to detect the transformation region. The extracted cervix images were then fed to the EffecientNetb0 model for cervix type classification. For cervical cancer classification, an EffecientNetB0 pre-trained model was trained and validated using histogram matched histopathological images. Results Mean average precision (mAP) of 99.88% for the region of interest (ROI) extraction, and test accuracies of 96.84% and 94.5% were achieved for the cervix type and cervical cancer classification, respectively. Conclusion The experimental results demonstrate that the proposed system can be used as a decision support tool in the diagnosis of cervical cancer, especially in low resources settings, where the expertise and the means are limited.

Background: Skin diseases are the fourth most common cause of human illness which results in enormous non-fatal burden in daily life activities. They are caused by chemical, physical and biological factors. Visual assessment in combination with clinical information is the common diagnostic procedure for diseases. However, these procedures are manual, time-consuming, and require experience and excellent visual perception. Objectives: In this study, an automated system is proposed for the diagnosis of five common skin diseases by using data from clinical images and patient information using deep learning pre-trained mobilenet-v2 model. Methods: Clinical images were acquired using different smartphone cameras and patient's information were collected during patient registration. Different data preprocessing and augmentation techniques were applied to boost the performance of the model prior to training. Results: A multiclass classification accuracy of 97.5%, sensitivity of 97.7% and precision of 97.7% has been achieved using the proposed technique for the common five skin disease. The results demonstrate that, the developed system provides excellent diagnosis performance for the five skin diseases. Conclusion:The system has been designed as a smartphone application and it has the potential to be used as a decision support system in low resource settings, where both the expert dermatologist and the means are limited. | INTRODUCTIONSkin is the largest organ of the body which provides protection, regulates the body fluids and temperature, and enables sense of the external environment. 1 Skin diseases are the most common cause of all human illnesses which affects almost 900 million people in the world at any time. 2 According to the global burden of disease project, skin disease is the fourth leading cause of non-fatal disease burden throughout the world. 3 An estimated 21%-87% of children in Africa are affected by skin diseases. 4 Skin disease can cause financial, socio-economic, and psychological burden to the community and place a strain on health professionals. [5][6][7][8][9][10][11][12] Moreover, skin diseases may cause a sense of depression, frustration, isolation, and even suicidal ideation. 13 The pattern of skin diseases varies due to environmental factors, hygienic standards, social customs, and genetics. In developing countries, infection and infestation are more common. 4 There are more than 3000 known skin diseases worldwide. 14 According to a preliminary study conducted for this research, acne vulgaris, atopic dermatitis, lichen planus, onychomycosisThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

No abstract

No abstract