Search results

Hundreds of thousands of deaths each year in the world are caused by breast cancer (BC). An early-stage diagnosis of this disease can positively reduce the morbidity and mortality rate by helping to select the most appropriate treatment options, especially by using histological BC images for the diagnosis.

The present study proposes and evaluates a novel approach which consists of 24 deep hybrid heterogenous ensembles that combine the strength of seven deep learning techniques (DenseNet 201, Inception V3, VGG16, VGG19, Inception-ResNet-V3, MobileNet V2 and ResNet 50) for feature extraction and four well-known classifiers (multi-layer perceptron, support vector machines, K-nearest neighbors and decision tree) by means of hard and weighted voting combination methods for histological classification of BC medical image. Furthermore, the best deep hybrid heterogenous ensembles were compared to the deep stacked ensembles to determine the best strategy to design the deep ensemble methods. The empirical evaluations used four classification performance criteria (accuracy, sensitivity, precision and F1-score), fivefold cross-validation, Scott–Knott (SK) statistical test and Borda count voting method. All empirical evaluations were assessed using four performance measures, including accuracy, precision, recall and F1-score, and were over the histological BreakHis public dataset with four magnification factors (40×, 100×, 200× and 400×). SK statistical test and Borda count were also used to cluster the designed techniques and rank the techniques belonging to the best SK cluster, respectively.

Results showed that the deep hybrid heterogenous ensembles outperformed both their singles and the deep stacked ensembles and reached the accuracy values of 96.3, 95.6, 96.3 and 94 per cent across the four magnification factors 40×, 100×, 200× and 400×, respectively.

The proposed deep hybrid heterogenous ensembles can be applied for the BC diagnosis to assist pathologists in reducing the missed diagnoses and proposing adequate treatments for the patients.

COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT) and chest x-ray (CXR) modalities, depending on the stage of infection. However, with so many patients and so few doctors, it has become difficult to keep abreast of the disease. Deep learning models have been developed in order to assist in this respect, and vision transformers are currently state-of-the-art methods, but most techniques currently focus only on one modality (CXR).

This work aims to leverage the benefits of both CT and CXR to improve COVID-19 diagnosis. This paper studies the differences between using convolutional MobileNetV2, ViT DeiT and Swin Transformer models when training from scratch and pretraining on the MedNIST medical dataset rather than the ImageNet dataset of natural images. The comparison is made by reporting six performance metrics, the Scott–Knott Effect Size Difference, Wilcoxon statistical test and the Borda Count method. We also use the Grad-CAM algorithm to study the model's interpretability. Finally, the model's robustness is tested by evaluating it on Gaussian noised images.

Although pretrained MobileNetV2 was the best model in terms of performance, the best model in terms of performance, interpretability, and robustness to noise is the trained from scratch Swin Transformer using the CXR (accuracy = 93.21 per cent) and CT (accuracy = 94.14 per cent) modalities.

Models compared are pretrained on MedNIST and leverage both the CT and CXR modalities.

Histopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.

Three pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.

This study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.

The best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

This study aims to investigate the relationship between organizational citizenship behavior for the environment (OCBE) of managers and the constructs of the theory of planned behavior: perceived behavioral control (PBC) and attitude toward the environment. The current study also aims to explore the magnitude of this relationship with subjective norms as a moderating variable.

Data were sourced from a total number of 140 respondents (managers) from different firms in The Netherlands through an online questionnaire by using a mixture of structured, semi-structured and open-ended questions. Having used the correlation test, the study first conducts the exploratory factor analysis and then the reliability test. Finally, it estimates the coefficients by applying the hierarchical regression model to find the relationship between dependent and explanatory variables.

Diagnostic test results revealed that data are highly reliable. The coefficient results indicate that PBC and environmental attitude have positive and significant relationships with OCBE. Additionally, subjective norms have a significant and positive effect on strengthening the relationship between PBC and OCBE; however, it has no impact on the relationship between environmental attitude and OCBE.

This study has some caveats. First, the results presented in the research are derived from a single moment in time. The second limitation has to do with the insignificant results for the construct of environmental attitude. Third, this study comprises a data set obtained from different companies in The Netherlands.

Organizations that want to increase their environmental performance could look at the PBC, environmental attitude and subjective norms of the managers in regard to OCBE.

The results of the study contribute to the understanding of the way PBC, environmental attitude and subjective norms positively affect OCBE. Future research should investigate organizational citizenship within business firms by considering corporate social responsibility as a key variable.

The purpose of this study is to explain the components of competitive priorities of Indian service firms, to find out the competitive priorities of different service industries in India and to find out how these competitive priorities change across low- and high-performing service firms.

An empirical study of 166 firms from five different service industries is undertaken in New Delhi and its surroundings.

The results reveal the presence of three competitive priorities in the services sector in India: cost, flexibility and quality/delivery, with quality/delivery being the most distinctive competitive priority. Hotel and auto-repair industries are found to be focused on controlling costs, while hospitals, banks and private colleges prioritized quality/delivery. For high-performing firms, cost is the top most competitive priority, followed by quality/delivery and flexibility, while for low-performing firms, quality/delivery remains the top most competitive priority, followed by flexibility and cost.

The paper enhances the understanding of competitive priorities in the Indian services sector. The identification of competitive priorities of different service industries in India and their dynamics across different industries add value to the current literature and fill an important research gap. Additionally, surveying diverse industries in this paper reveals a holistic picture of the Indian service industry and helps achieve some degree of cross-industry perspective.

This study attempts to explain the components of competitive priorities of Malaysian service firms and to find out the competitive priorities of different service industries in Malaysia, and how these competitive priorities change across “low performance” and “high performance” service industries.

An empirical study of 254 firms from nine different service industries is conducted to answer the objectives of this study.

Four competitive priorities are identified: cost, quality, delivery and flexibility. Six service industries namely fast food, hospital, retail store, bank, private college and accountant industries are found to be focused on quality while three industries namely hotel, auto‐repair and architect prioritized delivery. For both high performance and low performance firms, quality remained the top competitive priority followed by delivery, flexibility and cost.

This is the first study that identifies competitive priorities in the Malaysian service sector

The perception of Islamic finance by its various stakeholders is not always reconcilable. Its foundations and attributes are subject to a plurality of perceptions making it almost impossible to reach a consensus about them. This paper aims to understand the perception of Islamic finance by bank employees in Cameroon.

This research follows the interpretativist paradigm and is qualitative and exploratory in nature. The data are collected through semi-structured face-to-face interviews with bank employees, mainly branch managers. These interview data are analysed using the thematic analysis method.

Bank employees in Cameroon perceive Islamic finance as a finance that: targets everyone, regardless of religion, but Muslims first (Islamic finance is both inclusive and exclusive); offers original products and services; has a religious anchor that may hinder non-Muslim economic agents; has many advantages, mainly for financial institutions, and some limitations for financial institutions and their customers; is full of opportunities for its stakeholders; and is not yet fully practiced in Cameroon.

This study mobilises a qualitative approach, provides new insights into the research on the perception of Islamic finance and reaches a consensus on the perception of certain aspects and attributes of Islamic finance, namely, for the perception of the target and the Shariah compliance of Islamic finance. Furthermore, this study is a pioneering effort to understand bank employees’ perception of Islamic finance in non-Islamic and developing countries where Islamic finance is underdeveloped.

Total quality management (TQM) must include orientation towards quality awareness in the overall organisational processes in a firm. A successful TQM needs a supportive culture that can adapt to alterations and strengthen innovation. This study aims to confirm the association between the style of management known as organisational culture (OC) and TQM practices in manufacturing Small and Medium Enterprises (SMEs).

Data-driven research was drawn from self-assessment inquiries among 772 managers/owners of manufacturing SMEs of the Saudi Arabia Kingdom (KSA). The dominant culture was detected by means of a cross-sectional technique.

The findings enrich the literature by revealing a positive effect of OC on TQM execution in the manufacturing SMEs of KSA.

Prior to the execution of TQM operations, administrators of manufacturing SMEs should be aware of the culture within organisations so that TQM may be implemented.

The study suggests that organisations, particularly manufacturing SMEs, should constantly strive to enhance the TQM culture.

Amid intense competition among manufacturing SMEs, it is crucial to guarantee their high performance. This research assists society in evaluating the strength of a particular SME sector and further enables it to assess which SMEs really have a good OC–TQM relation.

The paper creates and presents various platforms of the OC and TQM as a unified body of knowledge.

The purpose of this paper is to analyse the role of hospital leaders and high-performance work practices (HPWPs) in intensive care units (ICUs) in organizational agility and its impact on healthcare personnel satisfaction.

This study was carried out in three ICUs of an important Spanish public hospital, one for adults, one paediatric and one neonatal. The unit of analysis was ICUs personnel (324 individuals: 14.5%, 48.8% and 36.7% from the categories of doctors, nurses and nurses' aides, respectively) who were invited to participate in the study. The sample had 248 individuals, with a sampling distribution by categories that was quite similar to that of the population. To test the hypotheses proposed, structural equations modeling (SEM) were used as the maximum likelihood estimation method.

The results confirm the proposed model and reveal the importance of the human dimension in ICUs on hospital agility and performance in terms of satisfaction of the clinical staff working in this area.

This paper is original because it analyses units of high complexity, such as ICUs from a management and non-clinical perspective. In addition, it studies the role of hospital managers and HPWPs on employee outcomes, as well as in-hospital responsiveness in a very dynamic context that demands agility on the management approach.

The purpose of this paper is to fill a gap in the existing literature that relates leadership style to total quality management (TQM) focus. Specifically, the study evaluates whether and how leadership style may affect the implementation of TQM practices.

A structured questionnaire was used to collect data from employees of different organizations operating in the manufacturing (n = 156) and service sectors (n = 147). Exploratory and confirmatory factor analyses as well as structural equation modeling were adopted to test the hypothesized research model.

The results revealed that transformational leadership has a positive impact in the implementation of TQM practices (e.g., customer focus, process management, human resource management, strategic planning and learning). It was also found that, regardless of industry type, manufacturing or service, transformational leadership has a significantly positive influence on TQM practices. In addition, it was noted that manufacturing companies showed a higher level of TQM practices than did service companies.

This study represents, to the best of the author’s knowledge, the first empirical examination of the relationship between transformational leadership and TQM in the service and manufacturing industries, with the goal of determining the differences between these two sectors. The study's conclusions may be useful for service and manufacturing organizations in achieving more effective leadership in the implementation of TQM.