Design of Optimal Deep Learning-Based Pancreatic Tumor and Nontumor Classification Model Using Computed Tomography Scans

Pancreatic tumor is a lethal kind of tumor and its prediction is really poor in the current scenario. Automated pancreatic tumor classification using computer-aided diagnosis (CAD) model is necessary to track, predict, and classify the existence of pancreatic tumors. Artificial intelligence (AI) can offer extensive diagnostic expertise and accurate interventional image interpretation. With this motivation, this study designs an optimal deep learning based pancreatic tumor and nontumor classification (ODL-PTNTC) model using CT images. The goal of the ODL-PTNTC technique is to detect and classify the existence of pancreatic tumors and nontumor. The proposed ODL-PTNTC technique includes adaptive window filtering (AWF) technique to remove noise existing in it. In addition, sailfish optimizer based Kapur’s Thresholding (SFO-KT) technique is employed for image segmentation process. Moreover, feature extraction using Capsule Network (CapsNet) is derived to generate a set of feature vectors. Furthermore, Political Optimizer (PO) with Cascade Forward Neural Network (CFNN) is employed for classification purposes. In order to validate the enhanced performance of the ODL-PTNTC technique, a series of simulations take place and the results are investigated under several aspects. A comprehensive comparative results analysis stated the promising performance of the ODL-PTNTC technique over the recent approaches.

Pre-registration UK diagnostic radiography student ability and confidence in interpretation of chest X-rays

Introduction Chest X-rays are the most frequently requested X-ray imaging in English hospitals. This study aimed to assess final year UK radiography student’s confidence and ability in image interpretation of chest X-rays. Methods Thirty-three diagnostic radiography students were invited to assess their confidence and ability in interpreting chest x-rays from a bank of n=10 cases using multiple choice answers. Data analysis included 2x2 contingency tables, Kappa for inter-rater reliability, a Likert scale of confidence for each case, and questions to assess individual interpretation skills and ways to increase the learning of the subject. Results Twenty-three students participated in the study. The pooled accuracy achieved was 61% (95% CI 38.4-77.7; k=0.22). The degree of confidence and ability varied depending upon the student and the conditions observed. High confidence was noted with COVID-19 (n=12/23; 52%), lung metastasis (n=14/23; 61%), and pneumothorax (n=13/23; 57%). Low confidence was noted with conditions of consolidation (n=8/23; 35%), haemothorax (n=8/23; 35%), and surgical emphysema (n=8/23; 35%). From the sample n=11 (48%), participants stated they felt they had the knowledge to interpret chest X-rays required for a newly qualified radiographer. Conclusion The results demonstrated final year radiography student’s confidence and ability in image interpretation of chest X-rays. Student feedback indicated a preference for learning support through university lectures, online study resources, and time spent with reporting radiographers on clinical practice to improve ability and confidence in interpreting chest X-rays.

The Effect of Human Activities Towards Coastal Dynamics and Sustainable Coastal Management

One of the disasters that often occur in coastal areas is abrasion. Abrasion causes coastal dynamics, including the East Coast of Rembang, Kragan Village, Kragan District, Rembang Regency. From 1975 to 1990, at least 50 meters of land from this area has been lost due to abrasion. This dynamic may become one of the causes of unsustainable management of the coastal environment and its natural resources. Various efforts have been made to overcome abrasion, but abrasion continues to hit this area, even until 2020. Qualitative and quantitative approaches were carried out in this study to discover the coast dynamics and various human activities that may trigger abrasion. Image interpretation, observation, interviews, and questionnaires were used as data collection techniques at three observation points in the Kragan Village area. This study concludes that the beach in Kragan Village has experienced dynamics with a total land loss of 46 meters from 2003 to 2020. Harmful activities carried out by humans resulted in abrasion so that the coast experienced dynamics. Human activities also affect coastal management, namely the basic principles of integrated coastal management and processes in the management of coastal areas.

Remote-Sensing Image Tile-Level Annotation Based on Discriminative Features and Expressive Visual Word Descriptors

Remote-sensing images play a crucial role in a wide range of applications and have been receiving significant attention. In recent years, great efforts have been made in developing various methods for intelligent interpretation of remote-sensing images. Generally speaking, machine learning-based methods of remote-sensing image interpretation require a large number of labeled samples and there are still not enough annotated datasets in the field of remote sensing. However, manual annotation of remote-sensing images is usually labor-intensive and requires expert knowledge and the accuracy of annotation results is relatively low. The goal of this paper is to propose a novel tile-level annotation method of remote-sensing images to obtain remote-sensing datasets which are well-labeled and contain accurate semantic concepts. Firstly, we use a set of images with defined semantic concepts to represent the training set and divide them into several nonoverlapping regions. Secondly, the color features, texture features, and spatial features of each region are extracted, and discriminative features are obtained by the weight optimization feature fusion method. Then, the features are quantized into visual words by applying a density-based clustering center selection method and an isolated feature point elimination method. And the remote-sensing images can be represented by a series of visual words. Finally, the LDA model is used to calculate the probabilities of semantic categories for each region. The experiments are conducted on remote-sensing images which demonstrate that our proposed method can achieve good performance on remote-sensing image tile-level annotation. The implications of our research can obtain annotated datasets with accurate semantic concepts for intelligent interpretation of remote-sensing images.

Estimation of Suspended Sediment Concentration in Downstream of the Ba River Basin using Remote Sensing Images

Assessing the tendency of suspended sediment concentration (SSC) in the river watershedsenables a better understanding of the hydromorphological properties of its basins and the associatedprocesses. In addition, analyzing this trend is essential to address several important issues such as erosion,water pollution, human health risks, etc. Therefore, it is critical to determine a proper method to quantifyspatio-temporal variability in SSC. In recent years, remote sensing and GIS technologies are being widelyapplied to support scientists, researchers, and environmental resource investigators to quickly andsynchronously capture information on a large scale. The combination of remote sensing and GIS data willbecome the reliable and timely updated data source for the managers, researchers on many fields. Thereare several tools, software, algorithms being used in extracting information from satellites and support forthe analysis, image interpretation, data collection. The information from satellite images related to waterresources includes vegetational cover, flooding events on a large scale, rain forecast, populationdistribution, forest fire, landslide movements, sedimentation, etc., and especially information on waterquality, sediment concentration. This paper presents the initial result from LANDSAT satellite imageinterpretation to investigate the amount of sediment carried downstream of the Ba river basin.

Intracranial Lesion Detection and Artifact Characterization: Comparative Study of Susceptibility and T2*-Weighted Imaging in Dogs and Cats

Susceptibility-weighted imaging (SWI), an MRI sequence for the detection of hemorrhage, allows differentiation of paramagnetic and diamagnetic substances based on tissue magnetic susceptibility differences. The three aims of this retrospective study included a comparison of the number of areas of signal void (ASV) between SWI and T2*-weighted imaging (T2*WI), differentiation of hemorrhage and calcification, and investigation of image deterioration by artifacts. Two hundred twelve brain MRIs, 160 dogs and 52 cats, were included. The sequences were randomized and evaluated for presence/absence and numbers of ASV and extent of artifacts causing image deterioration by a single, blinded observer. In cases with a CT scan differentiation of paramagnetic (hemorrhagic) and diamagnetic (calcification) lesions was made, SWI was performed to test correct assignment using the Hounsfield Units. Non-parametric tests were performed to compare both sequences regarding detection of ASV and the effect of artifacts on image quality. The presence of ASV was found in 37 SWI sequences and 34 T2*WI sequences with a significant increase in ASV only in dogs >5 and ≤ 15 kg in SWI. The remaining weight categories showed no significance. CT examination was available in 11 cases in which 81 ASV were found. With the use of phase images, 77 were classified as paramagnetic and none as diamagnetic. A classification was not possible in four cases. At the level of the frontal sinus, significantly more severe artifacts occurred in cats and dogs (dogs, p < 0.001; cats, p = 0.001) in SWI. The frontal sinus artifact was significantly less severe in brachycephalic than non-brachycephalic dogs in both sequences (SWI, p < 0.001; T2*WI, p < 0.001). In conclusion, with the advantages of better detection of ASV in SWI compared with T2*WI and the opportunity to differentiate between paramagnetic and diamagnetic origin in most cases, SWI is generally recommended for dogs. Frontal sinus conformation appears to be a limiting factor in image interpretation.

Integration Applications of Image and Sonic Data in the Fault-Dominated Carbonate Reservoir in Tarim Basin

Carbonate reservoir is one of the most complex and important reservoirs in the world. It was confirmed that the slip-strike fault played a crucial role in the fault-dominated carbonate reservoir in Tarim basin. It is challenging to evaluate this kind of reservoir using the open-hole log or seismic data. Identifying and characterizing the fault-dominated carbonate reservoir were the objectives of this case study. High-definition borehole resistivity image and dipole sonic logs were run in several wells in the research area. It was revealed the detail features of the fault-dominated carbonate reservoir, such as natural fractures, faults or breccias. Compared with the typical geological model of strike-slip faults and outcrop features, the characteristics of the breccia zone and the fracture zone in the strike-slip fault system were summarized from the borehole image interpretation. A unique workflow was innovated with the integration of image and sonic data. Breccias and fractures were observed in the borehole image; and reflections or attenuations in Stoneley waveforms can provide indicating flag for permeable zones. Integrated with the other related geological data like mud logging or cores, the best pay zones in the fault-dominated carbonate reservoir were located. The characteristics of the strike-slip fault was revealed with the integration of the full-bore formation microimager and dipole shear sonic imager data. The fault core was a typical breccia zone with strong dissolution, which showed good potential in permeability, but it was found that some fault cores were filled with siliceous rock or intrusive rock. The features of the fillings in the fault zone were described based on the image and sonic data. The side cores or geochemical spectroscopy logs data helped to determine the mineralogy of the fillings. The fracture zones had clear responses in the image and sonic data too. The un-filled or half-filled breccia zone were the best zones in the fault-dominated carbonated reservoir. The details of the fault-dominated carbonate reservoir could be used in the future three-dimensional geological modelling.

SFE2D: A Hybrid Tool for Spatial and Spectral Feature Extraction

A crucial task for integrated geoscientific image (geo-image) interpretation is the relevant geological representation of multiple geo-images, which demands high-dimensional techniques for extracting latent geological features from high-dimensional geo-images. A standalone mathematical tool called SFE2D (spatiospectral feature extraction in two-dimension) is developed based on independent component analysis (ICA), continuous wavelet transform (CWT), k-means clustering segmentation, and RGB color processing that iteratively separates, extracts, clusters, and visualizes the highly correlated and overlapped geological features from multiple sources of geo-images. The SFE2D offers spatial feature extraction and wavelet-based spectral feature extraction for further extraction of frequency-dependent features. We show that the SFE2D is a robust tool for automated pattern recognition, fast pseudo-geological mapping, and detection of regions of interest with a wide range of applications in different scales, from regional geophysical surveys to the interpretation of microscopic images.