Semantic segmentation of urban environments: Leveraging U-Net deep learning model for cityscape image analysis.

Semantic segmentation of cityscapes via deep learning is an essential and game-changing research topic that offers a more nuanced comprehension of urban landscapes. Deep learning techniques tackle urban complexity and diversity, which unlocks a broad range of applications. These include urban planning, transportation management, autonomous driving, and smart city efforts. Through rich context and insights, semantic segmentation helps decision-makers and stakeholders make educated decisions for sustainable and effective urban development. This study investigates an in-depth exploration of cityscape image segmentation using the U-Net deep learning model. The proposed U-Net architecture comprises an encoder and decoder structure. The encoder uses convolutional layers and down sampling to extract hierarchical information from input images. Each down sample step reduces spatial dimensions, and increases feature depth, aiding context acquisition. Batch normalization and dropout layers stabilize models and prevent overfitting during encoding. The decoder reconstructs higher-resolution feature maps using "UpSampling2D" layers. Through extensive experimentation and evaluation of the Cityscapes dataset, this study demonstrates the effectiveness of the U-Net model in achieving state-of-the-art results in image segmentation. The results clearly shown that, the proposed model has high accuracy, mean IOU and mean DICE compared to existing models.

Brain image fusion-based tumour detection using grey level co-occurrence matrix Tamura feature extraction with backpropagation network classification.

Most challenging task in medical image analysis is the detection of brain tumours, which can be accomplished by methodologies such as MRI, CT and PET. MRI and CT images are chosen and fused after preprocessing and SWT-based decomposition stage to increase efficiency. The fused image is obtained through ISWT. Further, its features are extracted through the GLCM-Tamura method and fed to the BPN classifier. Will employ supervised learning with a non-knowledge-based classifier for picture classification. The classifier utilized Trained databases of the tumour as benign or malignant from which the tumour region is segmented via k-means clustering. After the software needs to be implemented, the health status of the patients is notified through GSM. Our method integrates image fusion, feature extraction, and classification to distinguish and further segment the tumour-affected area and to acknowledge the affected person. The experimental analysis has been carried out regarding accuracy, precision, recall, F-1 score, RMSE and MAP.

Frequency of Missed Findings on Chest Radiographs (CXRs) in an International, Multicenter Study: Application of AI to Reduce Missed Findings.

BACKGROUND: Missed findings in chest X-ray interpretation are common and can have serious consequences. METHODS: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1-not important; 5-critical importance). All CXRs were processed with the AI model (Qure.ai) and outputs were recorded for the presence of findings. Data were analyzed to obtain area under the ROC curve (AUC). RESULTS: Of 410 CXRs (410/2407, 18.9%) with unreported/missed findings, 312 (312/410, 76.1%) findings were clinically important: pulmonary nodules (n = 157), consolidation (60), linear opacities (37), mediastinal widening (21), hilar enlargement (17), pleural effusions (11), rib fractures (6) and pneumothoraces (3). AI detected 69 missed findings (69/131, 53%) with an AUC of up to 0.935. The AI model was generalizable across different sites, geographic locations, patient genders and age groups. CONCLUSION: A substantial number of important CXR findings are missed; the AI model can help to identify and reduce the frequency of important missed findings in a generalizable manner.

N,N-Ru(II)-p-cymene-poly(N-vinylpyrrolidone) surface functionalized gold nanoparticles: from organoruthenium complex to nanomaterial for antiproliferative activity.

Organometallic Ru-arene complexes are promising as anticancer agents, but the lack of tumor uptake and poor solubility in the physiological medium impede their development. In order to deal with these challenges, we developed gold nanoparticles coated with Ru(arene)-functionalized PNVP-Py, where PNVP-Py is pyridine end-functionalized poly(N-vinylpyrrolidone). It is demonstrated that these particles exhibit higher anti-proliferative activity than the individual organometallic ruthenium(ii) complex of the type [Ru(η6-p-cymene)(NN)Cl]PF6, where NN is bis(4-methoxyphenylimino)acenaphthene, against colorectal adenocarcinoma cell lines. More specifically, a RuII(η6-p-cymene) complex containing a NN bidentate ligand has been prepared and characterized by spectral studies and X-ray crystallography. To tether the isolated complex onto the surface of the AuNPs, PNVP-Py, which contains a pyridine group at one end to coordinate to the Ru-complex and a suitable functional group at the other end to bind on the surface of the AuNPs, has been prepared and utilized to obtain the macromolecular complex [Ru(η6-p-cymene)(NN)(PNVP-Py)]Cl2. Next, stable Ru(p-cym)(NN)(PNVP-Py)@AuNPs were obtained via a ligand exchange reaction of citrate-stabilized AuNPs with a macromolecular complex by a direct 'grafting to' approach and characterized well. Despite the lower DNA cleavage activity, the nanoconjugate exhibits better cytotoxicity than the individual complex against HT-29 colorectal adenocarcinoma cells on account of its enhanced permeability across the cell membrane. The AO/EB staining assay revealed that the nanoconjugate is able to induce an apoptotic mode of cell death, which was further quantitatively evaluated by Annexin V-FITC/PI double assay. An immunofluorescence assay indicated the higher potency of the nanoconjugate to inhibit cyclin D1 gene expression that is required for cancer cell growth. To the best of our knowledge, this is the first report of the modification of an organometallic Ru(arene) complex into a Ru(arene)metallopolymer-gold nanoconjugate for the development of ruthenium-based nanomedicine for cancer treatment.

Resveratrol, cancer and cancer stem cells: A review on past to future.

Cancer remains to be an unresolved medical challenge despite of tremendous advancement in basic science research and clinical medicine. One of the major limitations is due to the side effects of chemotherapy which remains to be palliative without offering any permanent cure for cancer. Cancer stem cells (CSCs) are the subpopulation of cells in tumors that remain viable even after surgery, chemo- and radio-therapy that eventually responsible for tumor relapse. Hence, by eliminating non-stem cancer cells and cancer stem cells from the patient, permanent cure is expected. Phytochemicals have been under the intensive study to target these CSCs effectively and permanently as they do not cause any side effects. Resveratrol (RSV) is one such compound attaining lot of interest in recent days to target CSCs either alone or in combination. RSV has been used by several researchers to target cancer cells in a variety of disease models, however its CSC targeting abilities are under intensive study at present. This review is to summarize the effects of RSV under in vitro and in vivo conditions along with advantages and disadvantages of its uses against cancer cells and cancer stem cells. From the first reports on phytochemical applications against cancer and cancer stem cells in 1997 and 2002 respectively followed by later reports, up to date observations and developments are enlisted from PubMed in this comprehensive review. RSV is shown to be a potential compound having impact on altering the signal transduction pathways in cancer cells. However, the effects are variable under in vitro and in vivo conditions, and also with its use alone or in combination with other small molecules. Past research on RSV is emphasizing the importance of in vivo experimental models and clinical trials with different prospective combinations, is a hope for future promising treatment regimen.

ECG Signal Classification Using Various Machine Learning Techniques.

Electrocardiogram (ECG) signal is a process that records the heart rate by using electrodes and detects small electrical changes for each heat rate. It is used to investigate some types of abnormal heart function including arrhythmias and conduction disturbance. In this paper the proposed method is used to classify the ECG signal by using classification technique. First the Input signal is preprocessed by using filtering method such as low pass, high pass and butter worth filter to remove the high frequency noise. Butter worth filter is to remove the excess noise in the signal. After preprocessing peak points are detected by using peak detection algorithm and extract the features for the signal are extracted using statistical parameters. Finally, extracted features are classified by using SVM, Adaboost, ANN and Naïve Bayes classifier to classify the ECG signal database into normal or abnormal ECG signal. Experimental result shows that the accuracy of the SVM, Adaboost, ANN and Naïve Bayes classifier is 87.5%, 93%, 94 and 99.7%. Compared to other classifier naïve bayes classifier accuracy is high.

Effect of biosynthesized gold nanoparticles by Sargassum swartzii in alloxan induced diabetic rats.

Biosynthesis of gold nanoparticles (AuNPs) using Sargassum swartzii and its anti-diabetic effect were studied using male wistar Albino rats. Formation of AuNPs were confirmed by UV-vis spectroscopy, Fourier transformed infrared (FTIR) spectroscopy, High-Resolution transmission electron microscopy (HR-TEM) and X-ray diffraction (XRD). Fasting blood glucose levels, serum insulin, hemoglobin and glycosylated hemoglobin levels in diabetic treated rats with AuNPs were significantly decreased compared to the control group. The results of the blood glucose level and serum insulin levels indicated that AuNPs could significantly improve the insulin resistance and glucose level in diabetic rats. AuNPs also shows reduction in anti-inflammation, tumor necrosis factor-alpha, interleukin-6 and high-sensitive C-reactive protein in diabetic rats. The data showed that AuNPs synthesized using S. swartzii exerted antidiabetic effect, accordingly improve pancreas, liver and kidney damage caused by alloxan induced diabetic rats.

CPAP pressure for prediction of oral appliance treatment response in obstructive sleep apnea.

STUDY OBJECTIVES: Mandibular advancement splints (MAS) are often preferred to CPAP treatment for OSA but are not always equally efficacious. High therapeutic CPAP pressure has been associated with MAS treatment failure in a Japanese population. We sought to assess the relationship between CPAP pressure and MAS treatment response in an Australian population. METHODS: Therapeutic CPAP pressure and MAS treatment response were obtained from a one-month crossover trial of both treatments. Predictive utility of CPAP pressure to identify MAS treatment response was assessed. RESULTS: Seventy-eight OSA patients were included (age 49.3 ± 11.1 years, BMI 29.1 ± 5.8 kg/m(2)) with predominantly moderate-severe OSA (AHI 30.0 ± 12.7/h). CPAP pressure was lower in MAS responders (MAS AHI < 10/h) 9.7 ± 1.6 vs. 11.7 ± 2.4 cm H O, p < 0.01, with area under ROC curve of 0.74 (95% CI 0.63-0.86), p < 0.01. The best cutoff value of 10.5 cm H O useful for discriminating MAS responders and non-responders in the previous Japanese population, was inadequate for prediction in the current population (0.47 negative predictive value [NPV]). However a cutoff of 13 cm H O identified MAS non-responders (1.0 NPV). Multivariate regression identified CPAP pressure (odds ratio [95% confidence interval] 0.53 [0.33-0.87], age (0.93 [0.87-0.99]) and AHI (0.92 [0.86-0.97]) as predictors of MAS treatment response (model r(2) = 0.54, p < 0.001). CONCLUSIONS: In Australian patients, the majority of whom are Caucasian, a higher therapeutic CPAP pressure requirement in conjunction with age and OSA severity characteristics may be useful to indicate likelihood of success with MAS as an alternative therapy.

Three-year prospective clinical and radiological results of a new flexible horseshoe acetabular cup.

We report the three-year results of a new flexible, horseshoe-shaped acetabular cup, with a carbon fibre reinforced polyetheretherketone (CFR-PEEK) bearing surface. The 3 mm thick composite cup is designed to conserve acetabular bone stock and reproduce a near-physiological stress distribution to the adjacent bone. The cup is intended to articulate against a large diameter ceramic femoral head to produce a low-wear bearing couple that generates minimal wear debris. A prospective, two-centre clinical study of the MITCH PCR cup was started in January 2007, to verify its safety and performance. Twenty-five MITCH PCR cups were implanted by three surgeons. There were 12 men and 13 women, with a mean age of 67.9 years (range 57.4 to 74.9). The mean Oxford hip score improved from 19.6 (SD 7.5) preoperatively to 43.5 (SD 7) at 3 years. The mean Harris hip score improved from 52.9 (SD 7) to 91.4 (SD 13.8) and the Euroqol-5D score increased from 62.6 (SD 18.4) to 82.8 (SD 19). One revision of the acetabular cup was undertaken at 21 months for squeaking. This has been investigated and modification of the articular geometry has resolved the problem, on in-vitro testing. Radiological analysis showed good early osseointegration of the MITCH PCR cup. However at three years, five cases of acetabular component migration and calcar resorption were observed. Three patients have subsequently undergone revision of the acetabular cup, at 41, 42 and 50 months respectively. The cause of the osteolysis is the subject of on-going investigation.