Valuable Features Research Articles

Computed tomography enterography-based deep learning radiomics to predict stratified healing in patients with Crohn's disease: a multicenter study.

This study developed a deep learning radiomics (DLR) model utilizing baseline computed tomography enterography (CTE) to non-invasively predict stratified healing in Crohn's disease (CD) patients following infliximab (IFX) treatment. The study included 246 CD patients diagnosed at three hospitals. From the first two hospitals, 202 patients were randomly divided into a training cohort (n = 141) and a testing cohort (n = 61) in a 7:3 ratio. The remaining 44 patients from the third hospital served as the validation cohort. Radiomics and deep learning features were extracted from both the active lesion wall and mesenteric adipose tissue. The most valuable features were selected using univariate analysis and least absolute shrinkage and selection operator (LASSO) regression. Multivariate logistic regression was then employed to construct the radiomics, deep learning, and DLR models. Model performance was evaluated using receiver operating characteristic (ROC) curves. The DLR model achieved an area under the ROC curve (AUC) of 0.948 (95% CI: 0.916-0.980), 0.889 (95% CI: 0.803-0.975), and 0.938 (95% CI: 0.868-1.000) in the training, testing, and validation cohorts, respectively in predicting mucosal healing (MH). Furthermore, the diagnostic performance of DLR model in predicting transmural healing (TH) was 0.856 (95% CI: 0.776-0.935). We have developed a DLR model based on the radiomics and deep learning features of baseline CTE to predict stratified healing (MH and TH) in CD patients following IFX treatment with high accuracies in both testing and external cohorts. The deep learning radiomics model developed in our study, along with the nomogram, can intuitively, accurately, and non-invasively predict stratified healing at baseline CT enterography. Early prediction of mucosal and transmural healing in Crohn's Disease patients is beneficial for treatment planning. This model demonstrated excellent performance in predicting mucosal healing and had a diagnostic performance in predicting transmural healing of 0.856. CT enterography images of active lesion walls and mesenteric adipose tissue exhibit an association with stratified healing in Crohn's disease patients.

A CT-based radiomics analyses for differentiating drug‑resistant and drug-sensitive pulmonary tuberculosis.

To explore the value of computed tomography based radiomics in the differential diagnosis of drug-sensitive and drug-resistant pulmonary tuberculosis. The clinical and computed tomography image data of 177 patients who were diagnosed with pulmonary tuberculosis through sputum culture and completed drug-susceptibility testing from April 2018 to December 2020 at the Second Hospital of Nanjing were retrospectively analyzed. Patients with drug-resistant pulmonary tuberculosis (n = 78) and drug-sensitive pulmonary tuberculosis (n = 99) were randomly divided into a training set (n = 124) and a validation set (n = 53) at a ratio of 7:3. Regions of interest were drawn to delineate the lesions and radiomics features were extracted from non-contrast computed tomography images. A radiomics signature based on the valuable radiomics features was constructed and a radiomics score was calculated. Demographic data, clinical symptoms, laboratory results and computed tomography imaging characteristics were evaluated to establish a clinical model. Combined with the Rad-score and clinical factors, a radiomics-clinical model nomogram was constructed. Thirteen features were used to construct the radiomics signature. The radiomics signature showed good discrimination in the training set (area under the curve (AUC), 0.891; 95% confidence interval (CI), 0.832-0.951) and the validation set (AUC, 0.803; 95% CI, 0.674-0.932). In the clinical model, the AUC of the training set was 0.780(95% CI, 0.700-0.859), while the AUC of the validation set was 0.692 (95% CI, 0.546-0.839). The radiomics-clinical model showed good calibration and discrimination in the training set (AUC, 0.932;95% CI, 0.888-0.977) and the validation set (AUC, 0.841; 95% CI, 0.719-0.962). Simple radiomics signature is of great value in differentiating drug-sensitive and drug-resistant pulmonary tuberculosis patients. The radiomics-clinical model nomogram showed good predictive, which may help clinicians formulate precise treatments.

AER-Net: Attention-Enhanced Residual Refinement Network for Nuclei Segmentation and Classification in Histology Images

The acurate segmentation and classification of nuclei in histological images are crucial for the diagnosis and treatment of colorectal cancer. However, the aggregation of nuclei and intra-class variability in histology images present significant challenges for nuclei segmentation and classification. In addition, the imbalance of various nuclei classes exacerbates the difficulty of nuclei classification and segmentation using deep learning models. To address these challenges, we present a novel attention-enhanced residual refinement network (AER-Net), which consists of one encoder and three decoder branches that have same network structure. In addition to the nuclei instance segmentation branch and nuclei classification branch, one branch is used to predict the vertical and horizontal distance from each pixel to its nuclear center, which is combined with output by the segmentation branch to improve the final segmentation results. The AER-Net utilizes an attention-enhanced encoder module to focus on more valuable features. To further refine predictions and achieve more accurate results, an attention-enhancing residual refinement module is employed at the end of each encoder branch. Moreover, the coarse predictions and refined predictions are combined by using a loss function that employs cross-entropy loss and generalized dice loss to efficiently tackle the challenge of class imbalance among nuclei in histology images. Compared with other state-of-the-art methods on two colorectal cancer datasets and a pan-cancer dataset, AER-Net demonstrates outstanding performance, validating its effectiveness in nuclear segmentation and classification.

VRIO Analysis in Developing Branding Strategies for Egg-Based Food Products as Souvenirs from Blitar – Local Perspective

Blitar is rich in tourism potential. The local economy stands to benefit significantly from tourism, creating job opportunities and enhancing community development. Blitar's position as a major egg producer offers unique opportunities for developing egg-based souvenirs. However, challenges include identifying appealing products and effective branding strategy is required to enhance the marketability of these products, fostering economic growth and tourism in the region. This study utilizes a mixed-method approach to explore consumer perceptions of egg-based processed products in Blitar, combining quantitative surveys with qualitative interviews of business actors. A survey of 61 respondents gathered measurable data on consumer preferences and factors influencing purchasing decisions. In-depth interviews provided insights into marketing strategies and challenges faced by producers. The study employs descriptive statistics and VRIO analysis to develop effective branding strategies for promoting processed egg products as signature souvenirs from. The analysis reveals that respondents indicating higher interest in egg-based products as souvenirs from Blitar as food significantly influences their choice of tourist destinations, with a strong preference for local ingredients. However, awareness of Blitar’s egg production potential is low, leading to limited appeal for egg-based products. The VRIO analysis shows organizational weaknesses hinder competitive advantage despite valuable product features. Effective branding strategies tailored to consumer expectations are crucial for market success. Enhancing product awareness and education through organized action can further strengthen the appeal of these culinary offerings in tourism.

Deep learning-driven super-resolution in Raman hyperspectral imaging: Efficient high-resolution reconstruction from low-resolution data

Deep learning (DL) has become an indispensable tool in hyperspectral data analysis, automatically extracting valuable features from complex, high-dimensional datasets. Super-resolution reconstruction, an essential aspect of hyperspectral data, involves enhancing spatial resolution, particularly relevant to low-resolution hyperspectral data. Yet, the pursuit of super-resolution in hyperspectral analysis is fraught with challenges, including acquiring ground truth high-resolution data for training, generalization, and scalability. The pressing issue of extended spectral acquisition times, notably for high-resolution scans, is a significant roadblock in hyperspectral imaging. Super-resolution methods offer a promising solution by providing higher spatial resolution data to expedite data collection and yield more efficient outcomes. This paper delves into a practical application of these concepts using Raman imaging, where spectral acquisition times can be prohibitively long. In this context, DL-based super-resolution models demonstrate their efficacy by predicting and reconstructing high-resolution Raman data from low-resolution input, eliminating the need for resource-intensive high-resolution scans. While previous work often relied on substantial high-resolution datasets, this study showcases the ability to achieve similar outcomes even with limited data, presenting a more practical and cost-effective approach. The results offer a glimpse into the transformative potential of this technology to streamline hyperspectral imaging applications by saving valuable time and resources through the successful generation of high-resolution data from low-resolution inputs.

ARMNet: A Network for Image Dimensional Emotion Prediction Based on Affective Region Extraction and Multi-Channel Fusion.

Compared with discrete emotion space, image emotion analysis based on dimensional emotion space can more accurately represent fine-grained emotion. Meanwhile, this high-precision representation of emotion requires dimensional emotion prediction methods to sense and capture emotional information in images as accurately and richly as possible. However, the existing methods mainly focus on emotion recognition by extracting the emotional regions where salient objects are located while ignoring the joint influence of objects and background on emotion. Furthermore, in the existing literature, when fusing multi-level features, no consideration has been given to the varying contributions of features from different levels to emotional analysis, which makes it difficult to distinguish valuable and useless features and cannot improve the utilization of effective features. This paper proposes an image emotion prediction network named ARMNet. In ARMNet, a unified affective region extraction method that integrates eye fixation detection and attention detection is proposed to enhance the combined influence of objects and backgrounds. Additionally, the multi-level features are fused with the consideration of their different contributions through an improved channel attention mechanism. In comparison to the existing methods, experiments conducted on the CGnA10766 dataset demonstrate that the performance of valence and arousal, as measured by Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²), has improved by 4.74%, 3.53%, 3.62%, 1.93%, 6.29%, and 7.23%, respectively. Furthermore, the interpretability of the network is enhanced through the visualization of attention weights corresponding to emotional regions within the images.

Efficient Phase Step Determination Approach for Four-Quadrant Wind Imaging Interferometer

A four-quadrant wind imaging interferometer is a new generation of wind imaging interferometer with the valuable features of being monolithic, compact, light, and insensitive to temporal variations in the source. Its applications include remote sensing of the wind field of the upper atmosphere and observing important dynamical processes in the mesosphere and lower thermosphere. In this paper, we describe a new phase step determination approach based on the Lissajous figure, which provides an efficient, accurate, and visual method for the characterization and calibration of this type of instrument. Using the data from wavelength or thermal fringe scanning, the phase steps, relative intensities, and instrument visibilities of four quadrants can be retrieved simultaneously. A general model for the four-quadrant wind imaging interferometer is described and the noise sensitivity of this method is analyzed. This approach was successfully implemented with four-quadrant wind imaging interferometer prototypes, and its feasibility was experimentally verified.

Detection of Cyber-Physical Attacks in Additive Manufacturing: An LSTM-Based Autoencoder Method Utilizing Reconstruction Error Analysis from Side-Channel Monitoring

To identify cyber-physical threats in additive manufacturing systems, this study proposes an advanced technique utilizing data from side-channel monitoring. The method combines several key approaches for preprocessing, analyzing, and classifying time-series data, ensuring robust attack detection capabilities. A predefined Window Sliding (FWS) preprocessing method segments continuous time-series data into manageable windows of specified size, making analysis more efficient. Next, we employ Discrete Wavelet Transform (DWT) to extract features from each window, capturing essential information across various frequency bands. Particle Swarm Optimization (PSO) is then used to refine the DWT coefficients, isolating the most valuable features to enhance classification performance by focusing on the most informative characteristics. The optimal feature set is used to train a deep learning (DL) model capable of identifying anomalies through reconstruction errors, specifically an LSTM-A autoencoder. Our results demonstrate that this approach can distinguish between normal and attack scenarios with an accuracy rate of 99% when applied to side-channel attack detection in additive manufacturing. This method provides a scalable and adaptable solution to safeguard cyber-physical systems against sophisticated cyberattacks while improving detection accuracy.

The Essence of the Ex aequo et bono Method and the Rules of its Application for the Resolution of International Disputes

One of the most important functions of law is the resolution of disputes. However, legal means of dispute resolution, such as judicial settlement and arbitration, are often not chosen by the parties involved in international disputes. This can be explained by several reasons. In legal doctrine, it is a common view that parties avoid legal means due to the binding nature of the decisions rendered, yet this is far from the only reason why parties refuse these methods. In particular, one of the main reasons they avoid legal means is the uncertainty regarding whether the decision based on law will be equitable. There are many grounds for this, as legal norms contained in international legal documents, adopted several decades ago, may not correspond to modern realities. Therefore, the application of such norms can quite reasonably raise concerns among the parties about the potential for an inequitable decision based on them. In such cases, the method of ex aequo et bono may prove to be a practical tool for excluding the possibility of an inequitable decision based on legal norms. Contrary to popular misconception, the use of the ex aequo et bono method does not imply a complete rejection of legal norms. When applying this method, basic legal norms are often used to provide a legal foundation for decisions and to enhance their overall objectivity. However, in the application of the method ex aequo et bono, those legal norms that may lead to an inequitable decision are not applied. In this case, an equitable decision is often determined based on an analysis of the goals and principles of legal documents regulating the relevant issues, including an analysis of the document containing the legal norm whose application could have led to an inequitable decision. Thus, the ex aequo et bono method is a rather flexible peaceful means, combining valuable features of both equity and law. There is a deficit of information regarding the ex aequo et bono method in international legal documents. In particular, the lack of a clear definition, conditions, and rules for applying the ex aequo et bono method presents a significant obstacle to its extensive use in international practice. Therefore, appropriate lawmaking work should be undertaken in this area to fill legal gaps. The goal of the scientific article is to study the legal aspects of the ex aequo et bono method and identify the main problems negatively affecting the practice of its application. The results of the research showed the high practical value of the ex aequo et bono method in dispute resolution, especially in modern conditions when the use of flexible means is becoming increasingly relevant. The article aimed to condense, specify and expand legal knowledge about the ex aequo et bono method and may present significant scientific value for lawyers interested in judicial and arbitration practices; legal scholars; practicing judges and arbitrators; parties with unresolved disputes; as well as philosophers researching the relationship between equity and law.

Palladium(II) and platinum(II) thiophene-based thiosemicarbazones: Synthesis, properties, and anticancer studies

The aim of this study was to synthesize and investigate the cytotoxic profile of four palladium(II) and two platinum(II) complexes containing thiosemicarbazones derived from thiophene against tumor cells. They were fully characterized by various analytical techniques, including 1H, 13C{1H}, 31P{1H}, 135DEPT NMR, IR, UV–vis, X-ray diffraction, molar conductivity, and theoretical. Several techniques were used to evaluate the interaction of the complexes with DNA, such as gel electrophoresis, UV–vis spectroscopy, circular dichroism, viscosity measurements, fluorescence assay with Hoescht 33,258, and molecular docking. The results indicated that the complexes exhibited electrostatic and/or groove interaction with DNA, but only at high concentrations (100 µM). In vitro, cytotoxicity assays were performed using the MTT method, and the palladium(II) complexes showed remarkable cytotoxic activity against A549 and A2780cis cell lines. In particular, the PdT compound showed cytostatic behavior against the A549 tumor line, while the PdCH3 compound showed cytotoxic behavior against the A2780cis line. Further investigation of the most promising compound, PdCH3, in A2780cis revealed that it induced apoptosis by promoting cell accumulation in the sub-G1 phase and causing partial mitochondrial membrane depolarization. In addition, this complex significantly inhibited colony formation, leading to significant changes in cell morphology. However, no inhibition of cell migration was observed in the 3D cell model of DAOY cells. These findings provide valuable insights and structural features for the design of selective palladium complexes targeting ovarian tumor cells (A2780cis). The study highlights the potential of these complexes as cytotoxic agents against specific cancer cell lines, paving the way for future advances in medicinal chemistry research.

MBSFC: hyperspectral image classification based on multi-branch and spectral feature conversion

ABSTRACT Hyperspectral image classification (HSI) is a vital aspect of remote sensing technology. However, the high-dimensional nature of HSI and the continuous spectral bands significantly impact its classification performance. In this paper, we propose a classification method called MBSFC for HSI classification. MBSFC utilizes multi-branch and spectral feature conversion (SFC) techniques to eliminate redundant information and extract valuable features. Firstly, to preserve spectral-spatial information, the SFC block is introduced to eliminate redundant information through up-sampling. Subsequently, the feature maps from the SFC block and the spectral bands reduced by a factor of four are fed into three branches: the spectral branch, spatial-X branch, and spatial-Y branch. Each branch employs a 3D-CNN-based dense block and attention mechanism to extract useful features. Finally, the obtained features from the three branches are fused for HSI classification. To cater to different application scenarios, we divide MBSFC into three models with different network structures: MBSFC-s, MBSFC-m, and MBSFC-l. The MBSFC-l model, with a three-branch structure, achieves the best performance. The three models differ in the number of branches in the feature extraction. Experimental results on four publicly available hyperspectral datasets show that MBSFC achieves competitive results with small samples compared to other state-of-the-art methods. The code is available at https://github.com/TeresaTing/MBSFC.

Heuristic Heterogeneous Graph Reasoning Networks for Fact Verification.

Existing studies on table-based fact verification generally capture linguistic evidence from claim-table subgraphs or logical evidence from program-table subgraphs independently. However, there is insufficient association interaction between the two types of evidence, which makes it difficult to obtain valuable consistency features between them. In this work, we propose heuristic heterogeneous graph reasoning networks (H2GRN) to capture the shared consistent evidence by strengthening associations between linguistic and logical evidence from two perspectives of graph construction and reasoning mechanism. Specifically, 1) to enhance the close connectivity of the two subgraphs, rather than simply connecting two subgraphs by the nodes with the same content (the constructed graph in this way has severe sparsity), we construct a heuristic heterogeneous graph, which relies on claim semantics as heuristic knowledge to guide the connections of the program-table subgraph, and in turn expands the connectivity of the claim-table subgraph through logical information of programs as heuristic knowledge; and 2) to establish adequate association interaction between linguistic evidence and logical evidence, we design multiview reasoning networks. In detail, we propose local-view multihop knowledge reasoning (MKR) networks to enable the current node to establish association not only with one-hop neighbors, but also with multihop neighbors, to capture context-richer evidence information. We execute MKR on heuristic claim-table and program-table subgraphs to learn context-richer linguistic evidence and logical evidence, respectively. Meanwhile, we develop global-view graph dual-attention networks (DAN) that execute on the entire heuristic heterogeneous graph, reinforcing global-level significant consistency evidence. Finally, the consistency fusion layer is devised to weaken the disagreement between the three types of evidence to assist in capturing consistent shared evidence for verifying claims. Experiments on TABFACT and FEVEROUS demonstrate the effectiveness of H2GRN.

Optimizing Retail Recommendation via Similarity Measures and Machine Learning Approach

Finding a suitable retail business with potential success in a specific location can be challenging for retailers. The process is often lengthy and inconsistent due to the subjective nature of expert opinions. Previous research has demonstrated several techniques that consider numerous influential attributes for location optimization problems. However, while many studies rely on a business's core data for analytical purposes, accessing this information is often a significant constraint. This study aims to address the challenge of extracting valuable location features to enhance the profitability of chosen businesses despite the inaccessibility of core business data. The proposed methodology involves three main steps. First, an analytical dataset must be created by utilizing geographic and demographic information. Second, we conduct similarity measures by applying Manhattan distance to the entire analytical dataset, using an ideal business outlet that contains the footfall information. Through this process, we can identify businesses that share similar characteristics with popular outlets. Finally, several supervised machine learning models are trained to employ the extracted meta-features. Experimental results show that the XGBoost classifier performs best with an 87% accuracy score, outperforming the baseline models. The proposed methodology in this research presents a robust framework that demonstrated remarkable efficiency in achieving the stated objectives and improving the performance of retail business recommendations within a given location. Future work could consider a broader range of features that could potentially enhance model performance by applying ensemble learning.

Effectiveness of the use of chickpea collection samples in breeding

Aim. To determine the breeding value the large number of collection chickpea (Cicer arietinum L.) varieties obtained from the International Crops Research Institute for the Semi-Arid Tropics (India, Patancheru, ICRISAT) and the National Center for Plant Genetic Resources of Ukraine (Kharkiv) was evaluated in 1995-2022 under the conditions of the steppe zone of Ukraine. Methods. Standard field and laboratory methods (phenological observations, hybridization, structural analysis, biochemical analysis of protein content in seeds according to the Kjeldahl method), statistical analysis. Results. Donors and sources of such economically valuable features as early maturity, increased productivity, protein content in seeds, large-seeded, resistance against pathogens on an artificially created infectious background were identified. The set of 12 varieties of chickpea were developed by artificial hybridization, which are recommended for cultivation in all zones of Ukraine. Conclusions.The characteristics of the created varieties are given, the most valuable collection genotypes for use in crossing programs are recommended.

Phenological, Morphological and Pomological Characteristics of ‘Samsun Güzeli’ Pear Genotype on BA29 Rootstock

Türkiye has many local pear cultivars; some of them do not have much production and propagation potential due to their low quality and undesirable vegetative and generative characteristics. However, those that are superior in terms of fruit quality and yield characteristics have found a place for themselves in both local and national markets. In this respect, the ‘Samsun Güzeli’ genotype, which is an important local cultivar, is an ideal cultivar with many features and has a high potential to spread its cultivation all over Türkiye and other countries. ‘Samsun Güzeli’ is an autumn genotype, can easily meet the high demand in local and international markets due to its attractive color, smooth fruit shape and high quality. Despite all these valuable features, this cultivar is still not well known in Türkiye. There is a great need to disseminate cultivation and research on this subject. This study mainly aimed to reveal the phenological, morphological and pomological characteristics of the ‘Samsun Güzeli’ local pear genotype grafted on BA29, a commercially traded rootstock in 2021-2022. The results showed that the ‘Samsun Güzeli’ pear genotype completed its phenological cycle in 255 days in 2021 and 228 days in 2022 in Samsun climatic conditions. Fruit set rate of the genotype was 12.05% and the average yield was 17306.23 kg ha-1. It was also determined that the morphological characteristics averages were as the following; rootstock diameter 76.71 mm, trunk diameter 61.97 mm, trunk cross-sectional area 34.06 cm2, tree height 253.12 cm, canopy volume 0.96 m3, annual shoot length 37.19 cm and leaf area 11.74 cm2. Averages values of pomological and chemical properties recorded as the following; fruit weight 114.60 g, fruit volume 109.90 ml, soluble solid content (SSC) 13.16%, acidity 0.33%, and pH 4.37. In the sensory evaluations, the highest scores were obtained by juiciness (6.32) in the year 2022 while scores of overall visual quality were lowest in both years. In conclusion, it can be said that the ‘Samsun Güzeli’ genotype performs adequately in terms of fruit yield and quality on the standard dwarf rootstock and conducting new studies might be beneficial to disseminate the genotype.

Prediction of intraoperative press-fit stability of the acetabular cup in total hip arthroplasty using radiomics-based machine learning models

BackgroundPreoperative prediction of the acetabular cup press-fit stability in total hip arthroplasty is necessary for clinical decision-making. This study aims to establish and validate machine learning models to investigate the feasibility of predicting the intraoperative press-fit stability of the acetabular cup in total hip arthroplasty (THA). Methods226 patients who underwent primary THA from 2018 to 2022 in our hospital were retrospectively enrolled. Patients were divided into press-fit stable or unstable groups according to the intraoperative pull-out test of the implanted cup. Then, they were randomly assigned to the training or test cohort in an 8:2 ratio. We used 3Dslicer software to segment the region of interest (ROI) of the patient’s bilateral hip X-ray to extract radiomics features. The least absolute shrinkage and selection operator (LASSO) regression was used in our feature selection. Finally, four machine learning models were employed in this study, including support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost (XGB). Decision curve analysis (DCA), and receiver operating characteristic (ROC) curves of the models were plotted. The area under the curve (AUC), diagnostic accuracy, sensitivity, and specificity were calculated as well. The AUCs of the four models were compared using the DeLong test. ResultsTwenty-seven valuable radiomics features were determined by dimensionality reduction and selection. Regarding to the DeLong test, the AUC of the XGB model was significantly different from those of the other three models. (p < 0.05). Among all models, the XGB model exhibited the best performance with an AUC of 0.823 (95 % CI: 0.711–0.919) in the test cohort and showed optimal clinical efficacy according to the DCA. ConclusionMachine learning models based on X-ray radiomics can accurately predict the intraoperative press-fit stability of implanted cups preoperatively, providing surgeons with valuable information to lower the complication risk in THA.

Understanding the variability of the proximal femoral canal: A computational modeling study.

Statistical shape modeling (SSM) offers the potential to describe the morphological differences in similar shapes using a compact number of variables. Its application in orthopedics is rapidly growing. In this study, an SSM of the intramedullary canal of the proximal femur was built, with the aim to better understanding the complexity of its shape which may, in turn, enhance the preoperative planning of total hip arthroplasty (THA). This includes the prediction of the prosthetic femoral version (PFV) which is known to be highly variable amongst patients who have undergone THA. The model was built on three dimensional (3D) models of 64 femoral canals which were generated from pelvic computed tomography images including the proximal femur in the field of view. Principal component analysis (PCA) was performed on the mean shape derived from the model and each segmented canal. Five prominent modes of variations representing approximately 84% of the total 3D variations in the population of shapes were found to capture variability in size, proximal torsion, intramedullary femoral anteversion, varus/valgus orientation, and distal femoral shaft twist/torsion, respectively. It was established that the intramedullary femoral canal is highly variable in its size, shape, and orientation between different subjects. PCA-driven SSM is beneficial for identifying patterns and extracting valuable features of the femoral canal.

Effective clinical decision support implementation using a multi filter and wrapper optimisation model for Internet of Things based healthcare data

Feature Selection (FS) is essential in the Internet of Things (IoT)-based Clinical Decision Support Systems (CDSS) to improve the accuracy and efficiency of the system. With the increasing number of sensors and devices used in healthcare, the volume of data generated is vast and complex. Relevant FS from this data is crucial in reducing computational overhead, improving the system’s interpretability, and enhancing the Decision-Making System (DMS) quality. FS also aids in addressing the problems of data redundancy and noise, which can negatively impact the system’s performance. FS is critical to developing practical and dependable CDSS in IoT-based healthcare sectors. This research proposes a two-phase FS model. Phase-I employs an ensemble of five Filter Methods (FM), followed by a Pearson Correlation Method (PCM). Phase-II uses the Binary Optimized Genetic Grey Wolf Optimization Algorithm (BOGGWOA) as a Wrapper Method (WM). This recommended model integrates the most valuable features of each filter. Then, it uses the Pearson Correlation Coefficient (PCC) to get rid of features that aren’t needed, a Support Vector Machine (SVM) to guess how accurate their classification will be, and BOGGWOA as the Wrapper Method (WM) to pick the most essential features with the best CA.

Leveraging denoising diffusion probabilistic model to improve the multi-thickness CT segmentation

Organs-at-risk (OARs) segmentation in computed tomography (CT) is a fundamental step in the radiotherapy workflow, which has been prone as a time-consuming and labor-intensive task. Deep neural networks (DNNs) have gained significant popularity in the field of OAR segmentation tasks, achieving remarkable progress in clinical practice. Typically, OARs are distributed throughout different areas of the body and require varying thicknesses of CT scans for better diagnosis and segmentation in clinical. Most DNN-based segmentation focuses on single-thickness CT scans, limiting their applicability to varying thicknesses due to a lack of diverse thickness-related feature learning. While pre-training with the denoising diffusion probabilistic model (DDPM) offers an effective solution for dense feature learning, current works are constrained in addressing feature diversity, as exemplified by scenarios such as multi-thickness CT. To address the above challenges, this paper introduces a novel pre-training approach called DiffMT. This approach leverages the DDPM to extract valuable features from multi-thickness CT images. By transferring the pre-trained DDPM to the downstream segmentation for fine-tuning, the model gains proficiency in learning diverse multi-thickness CT features, leading to precise segmentation across varied thicknesses. We explore DiffMT’s feature learning capacity through experiments involving pre-trained models of varying sizes and different denoising thicknesses. Subsequently, thorough experiments comparing DDPM-based segmentation with other state-of-the-art (SOTA) CT segmentation methods, along with assessments on diverse OARs and modalities, empirically demonstrate that the proposed DiffMT method outperforms the control methods. The codes are available at https://github.com/ychengrong/DiffMT.

Contrast-enhanced magnetic resonance neurography for diagnosing brachial plexopathy: improved visualization and additional imaging features

Contrast-enhanced magnetic resonance neurography (CE-MRN) holds promise for diagnosing brachial plexopathy by enhancing nerve visualization and revealing additional imaging features in various lesions. This study aims to validate CE-MRN’s efficacy in improving brachial plexus (BP) imaging across different patient cohorts. Seventy-one subjects, including 19 volunteers and 52 patients with BP compression/entrapment, injury, and neoplasms, underwent both CE-MRN and plain MRN. Two radiologists assessed nerve visibility, with inter-reader agreement evaluated. Quantitative parameters such as signal intensity (SI), contrast-to-noise ratio (CNR), and contrast ratio (CR) of the C7 nerve were measured. Both qualitative scoring and quantitative metrics were compared between CE-MRN and plain MRN within each patient group. Patient classification followed the Neuropathy Score Reporting and Data System (NS-RADS), summarizing additional imaging features for each brachial plexopathy type. Inter-reader agreement for qualitative assessment was strong. CE-MRN significantly enhanced BP visualization and nerve-tissue contrast across all cohorts, particularly in volunteers and patients with injuries. It also uncovered additional imaging features such as hypointense signals in ganglia, compressed nerve sites, and neoplastic enhancements. CE-MRN effectively mitigated muscle edema and vascular contamination, enabling precise classification of BP injuries. Overall, CE-MRN consistently enhances BP visualization and provides valuable imaging features for accurate diagnosis.