Alternative Segmentation Research Articles

Automatic maxillary sinus segmentation and pathology classification on cone-beam computed tomographic images using deep learning

BackgroundMaxillofacial complex automated segmentation could alternative traditional segmentation methods to increase the effectiveness of virtual workloads. The use of DL systems in the detection of maxillary sinus and pathologies will both facilitate the work of physicians and be a support mechanism before the planned surgeries.ObjectiveThe aim was to use a modified You Only Look Oncev5x (YOLOv5x) architecture with transfer learning capabilities to segment both maxillary sinuses and maxillary sinus diseases on Cone-Beam Computed Tomographic (CBCT) images.MethodsData set consists of 307 anonymised CBCT images of patients (173 women and 134 males) obtained from the radiology archive of the Department of Oral and Maxillofacial Radiology. Bilateral maxillary sinuses CBCT scans were used to identify mucous retention cysts (MRC), mucosal thickenings (MT), total and partial opacifications, and healthy maxillary sinuses without any radiological features.ResultsRecall, precision and F1 score values for total maxillary sinus segmentation were 1, 0.985 and 0.992, respectively; 1, 0.931 and 0.964 for healthy maxillary sinus segmentation; 0.858, 0.923 and 0.889 for MT segmentation; 0.977, 0.877 and 0.924 for MRC segmentation; 1, 0.942 and 0.970 for sinusitis segmentation.ConclusionThis study demonstrates that maxillary sinuses can be segmented, and maxillary sinus diseases can be accurately detected using the AI model.

Multiple myeloma segmentation net (MMNet): an encoder-decoder-based deep multiscale feature fusion model for multiple myeloma segmentation in magnetic resonance imaging.

Patients with multiple myeloma (MM), a malignant disease involving bone marrow plasma cells, shows significant susceptibility to bone degradation, impairing normal hematopoietic function. The accurate and effective segmentation of MM lesion areas is crucial for the early detection and diagnosis of myeloma. However, the presence of complex shape variations, boundary ambiguities, and multiscale lesion areas, ranging from punctate lesions to extensive bone damage, presents a formidable challenge in achieving precise segmentation. This study thus aimed to develop a more accurate and robust segmentation method for MM lesions by extracting rich multiscale features. In this paper, we propose a novel, multiscale feature fusion encoding-decoding model architecture specifically designed for MM segmentation. In the encoding stage, our proposed multiscale feature extraction module, dilated dense connected net (DCNet), is employed to systematically extract multiscale features, thereby augmenting the model's sensing field. In the decoding stage, we propose the CBAM-atrous spatial pyramid pooling (CASPP) module to enhance the extraction of multiscale features, enabling the model to dynamically prioritize both channel and spatial information. Subsequently, these features are concatenated with the final output feature map to optimize segmentation outcomes. At the feature fusion bottleneck layer, we incorporate the dynamic feature fusion (DyCat) module into the skip connection to dynamically adjust feature extraction parameters and fusion processes. We assessed the efficacy of our approach using a proprietary dataset of MM, yielding notable advancements. Our dataset comprised 753 magnetic resonance imaging (MRI) two-dimensional (2D) slice images of the spinal regions from 45 patients with MM, along with their corresponding ground truth labels. These images were primarily obtained from three sequences: T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and short tau inversion recovery (STIR). Using image augmentation techniques, we expanded the dataset to 3,000 images, which were employed for both model training and prediction. Among these, 2,400 images were allocated for training purposes, while 600 images were reserved for validation and testing. Our method showed increase in the intersection over union (IoU) and Dice coefficients by 7.9 and 6.7 percentage points, respectively, as compared to the baseline model. Furthermore, we performed comparisons with alternative image segmentation methodologies, which confirmed the sophistication and efficacy of our proposed model. Our proposed multiple myeloma segmentation net (MMNet), can effectively extract multiscale features from images and enhance the correlation between channel and spatial information. Furthermore, a systematic evaluation of the proposed network architecture was conducted on a self-constructed, limited dataset. This endeavor holds promise for offering valuable insights into the development of algorithms for future clinical applications.

Steganography in QR Codes—Information Hiding with Suboptimal Segmentation

This paper describes a new steganographic method for QR codes. Unlike most information-hiding techniques in this field, it does not rely on the error correction property. Instead, it uses the segmentation feature of QR codes. Encoding of data in a QR code is achieved by creating segments of specific modes, chosen according to data type in order to save space. However, the segmentation does not have to be optimal. A secret message may be embedded into a QR code by selecting an alternative segment type. The presented method generates valid QR codes that may be decoded with standard readers. The solution has been tested using several QR decoders, and it has been confirmed that only the regular message was returned. Additionally, the error correction quality of produced codes is not diminished. The described algorithm is suitable for either digital or printed media, and in both cases, QR codes retain secret data.

Towards Metric-Driven Difference Detection between Receptive and Nonreceptive Endometrial Samples Using Automatic Histology Image Analysis

This paper presents a technique that can potentially help to determine the receptivity stage of the endometrium from histology images by automatically measuring the stromal nuclear changes. The presented technique is composed of an image segmentation model and the statistical evolution of segmented areas in hematoxylin and eosin (HE)-stained histology images. Three different endometrium receptivity stages, namely pre-receptive, post-receptive, and receptive, were compared. An ensemble-based AI model was proposed for histology image segmentation, which is based on individual UNet++, UNet, and ResNet34-UNet segmentation models. The performance of the ensemble-based technique was assessed using the Dice score and intersection over unit (IoU) values. In comparison to alternative segmentation architectures that were applied singly, the current ensemble-based method obtained higher Dice score (0.95) and IoU (0.90) values. The statistical comparison highlighted a noticeable difference in the number of nuclei and the size of the stroma tissue. The proposed technique demonstrated the positive potential for practical implementation for automatic endometrial tissue analysis.

Effects of segmentation in composite phase change material on melting/solidification performance of triplex‐tube thermal energy storage systems

AbstractIn this work, a numerical evaluation of the melting/solidification performance of phase change material (PCM) filled inside a triplex‐tube latent heat storage unit has been carried out. To enhance the melting/solidification performance, the porous Cu metal foam (MF) was embedded inside PCM (termed as composite PCM). Alternative segments of pure PCM and composite PCM have been allocated in such a way that both the pure PCM and composite PCM occupy the equal annular area (i.e., equal volumes). Influence of increasing number of segments was delineated on the melting/solidification rate, complete melting time, and thermal energy storage/recovery enhancement. The comparisons were drawn with reference to the model having two segments of PCM and composite PCM. The results show that the model containing 64 segments with alternate allocations of PCM and composite PCM has a faster melting/solidification rate than other models. With 32 alternate segments of MF, the full melting/solidification time reduced by 23%/77% with respect to the case with one segment of MF only. The melting/solidification performance gets saturated beyond 32 segments (M‐5) and negligible variation (only ~1%) in the thermal performance was noticed upon further segmentation. Finally, the model M‐5 proved as the best model considering the aspects of augmented melting/solidification rate and associated complexities. Moreover, the heterogeneity of MF applied in 32‐segment model confirmed that the anisotropic MF results in an increased melting rate and leads over other random isotropic distributions of MF.

THE ROLE OF THE BANKING SYSTEM IN PROVIDING FINANCIAL RESOURCES FOR THE DEVELOPMENT OF THE ECONOMY

The banking system is an important tool of economic development, providing financial resources for enterprises, government institutions and private individuals. It plays a key role in the redistribution of capital, contributing to the efficient functioning of the market economy. Through the mechanisms of attracting deposits and providing loans, banks provide the necessary conditions for financing investments, which in turn stimulates economic growth and development. Intensive changes in intersectoral relations require new approaches to their understanding and analysis. The role of the banking system in the economic growth of the real sector and the overall structural restructuring of the economy is the object of research by many foreign scientists [3]. International experience demonstrates the ambiguity of these relationships, as the impact of the banking sector in developing countries and in highly developed economies differs in its nature, direction and depth of consequences. For example, in the context of the active development of non-banking financial markets (financial leasing, insurance services, fund operations, factoring, etc.) as alternative sources of ensuring institutional changes and structural reforms in developed countries, the role of the banking sector is more noticeable in the growth of weaker economies, where the alternative segment is developing slower. An important role is also played by the economic cycle in which a particular country is [1]. In particular, during a recession, the causal relationships between changes in the development of the banking sector and the rate of economic growth are usually better traced than during a period of relative macroeconomic stability. Finally, it is worth considering the perspective of analyzing these relationships: in the short term, the consequences are unstable and less obvious due to the principle of the lag reaction of the economy to changes in the banking system[3]. Banks collect savings from households and businesses by offering a variety of deposit products such as savings accounts, time deposits and certificates of deposit. This allows the concentration of a large amount of capital, which can be used for lending. Attracting savings ensures the stability of the banking system and the ability to make long-term investments.

Superpixel-Based Graph Convolutional Network for UAV Forest Fire Image Segmentation

Given the escalating frequency and severity of global forest fires, it is imperative to develop advanced detection and segmentation technologies to mitigate their impact. To address the challenges of these technologies, the development of deep learning-based forest fire surveillance has significantly accelerated. Nevertheless, the integration of graph convolutional networks (GCNs) in forest fire detection remains relatively underexplored. In this context, we introduce a novel superpixel-based graph convolutional network (SCGCN) for forest fire image segmentation. Our proposed method utilizes superpixels to transform images into a graph structure, thereby reinterpreting the image segmentation challenge as a node classification task. Additionally, we transition the spatial graph convolution operation to a GraphSAGE graph convolution mechanism, mitigating the class imbalance issue and enhancing the network’s versatility. We incorporate an innovative loss function to contend with the inconsistencies in pixel dimensions within superpixel clusters. The efficacy of our technique is validated on two different forest fire datasets, demonstrating superior performance compared to four alternative segmentation methodologies.

Evaluating private and system-wide impacts of freight eco-routing

Freight is crucial for economic development, but the trucks hauling this freight significantly contribute towards greenhouse gas emissions, advancing global climate change and criteria pollutant emissions that affect local community health. Hence, this work explores the opportunities and challenges associated with freight eco-routing to mitigate these freight-related externalities in Southern California. To this end, the authors establish the private impacts of a single carrier eco-routing its fleet of freight vehicles with a point-to-point routing tool. Further, the authors investigate network-wide freight eco- routing's system effects with the novel origin-based algorithm for multi-class Traffic Assignment by Paired Alternative Segments (mTAPAS). Overall, the study showcases the potential opportunities with freight eco-routing in reducing transportation-related externalities. However, it also highlights implementation challenges due to a lack of monetary incentives for carriers and regulators to account for these externalities in their decision-making.

CNN-IKOA: convolutional neural network with improved Kepler optimization algorithm for image segmentation: experimental validation and numerical exploration

Chest diseases, especially COVID-19, have quickly spread throughout the world and caused many deaths. Finding a rapid and accurate diagnostic tool was indispensable to combating these diseases. Therefore, scientists have thought of combining chest X-ray (CXR) images with deep learning techniques to rapidly detect people infected with COVID-19 or any other chest disease. Image segmentation as a preprocessing step has an essential role in improving the performance of these deep learning techniques, as it could separate the most relevant features to better train these techniques. Therefore, several approaches were proposed to tackle the image segmentation problem accurately. Among these methods, the multilevel thresholding-based image segmentation methods won significant interest due to their simplicity, accuracy, and relatively low storage requirements. However, with increasing threshold levels, the traditional methods have failed to achieve accurate segmented features in a reasonable amount of time. Therefore, researchers have recently used metaheuristic algorithms to tackle this problem, but the existing algorithms still suffer from slow convergence speed and stagnation into local minima as the number of threshold levels increases. Therefore, this study presents an alternative image segmentation technique based on an enhanced version of the Kepler optimization algorithm (KOA), namely IKOA, to better segment the CXR images at small, medium, and high threshold levels. Ten CXR images are used to assess the performance of IKOA at ten threshold levels (T-5, T-7, T-8, T-10, T-12, T-15, T-18, T-20, T-25, and T-30). To observe its effectiveness, it is compared to several metaheuristic algorithms in terms of several performance indicators. The experimental outcomes disclose the superiority of IKOA over all the compared algorithms. Furthermore, the IKOA-based segmented CXR images at eight different threshold levels are used to train a newly proposed CNN model called CNN-IKOA to find out the effectiveness of the segmentation step. Five performance indicators, namely overall accuracy, precision, recall, F1-score, and specificity, are used to disclose the CNN-IKOA’s effectiveness. CNN-IKOA, according to the experimental outcomes, could achieve outstanding outcomes for the images segmented at T-12, where it could reach 94.88% for overall accuracy, 96.57% for specificity, 95.40% for precision, and 95.40% for recall.

Unravelling the effects of disruptive crises on residents’ support for tourism. Lessons from COVID-19

Residents’ behaviour towards tourism could be affected by a major crisis such as the recent pandemic. In this context, we evaluate how specific elements, such as residents’ characteristics, perceptions on specific origins, and the development of alternative tourism activities and segments need to be considered in this analysis. The Social Exchange Theory is used as a conceptual framework, and the empirical analysis is done for Bangkok, a grand urban tourism destination. Our results indicate that residents are aware of the potential trade-off between economic prosperity and health concerns, and that they have a different perception towards tourists from different origins. Additionally, locals were more concerned about health considerations than foreigners. The findings and the conceptual framework can serve as guidelines for tourism organisations and authorities managing urban destinations in times of crises.

Bioengineering and Geomatics: Automatic Brain Image Segmentation using Two-Stage Pipeline with SNN and Watershed Algorithm

Digital image processing holds an increasingly essential role in the medical domain. This study emphasizes the significance of researching and implementing methods aimed at the segmentation of critical image regions and potential noise reduction, which is indispensable for medical professionals in disease diagnosis. Consequently, the investigation of software solutions in this context can substantially enhance diagnostic accuracy. In particular, neurology stands as a medical field wherein imaging plays a substantial contributory role. In pursuit of an automated brain image segmentation approach, this paper centers its attention on a two-step pipeline methodology to address the segmentation challenges inherent in medical imaging. The proposed method incorporates the use of a Self-Normalizing Neural Network (SNN) for denoising and employs the Watershed algorithm, typically employed in Geomatics imagery, for segmentation. Encouraging results are obtained, with a segmentation performance, as measured by IoU, reaching a noteworthy value of 0.93 when compared with alternative segmentation software.

Promotions, Information Asymmetry and Usage of Traditional Medicine in Central Uganda: A Qualitative Perspective

Background: While extant literature highlights several motivations for Traditional Medicine (TM) usage; few studies have examined how promotions and information asymmetries influence traditional medicine usage behaviors. This study aimed to map out information biases underlying the marketing and promotion of Traditional Medicines in Central Uganda and explored the dimensions of attitudes and usage behaviors of TM users.
 Methods: The study utilized a qualitative approach by conducting in-depth face-to-face semistructured interviews with TM users in the metropolitan parts of Central Uganda. The study participants were recruited from the Traditional Health Practitioners (THPs) clinics with the help of community development officers under the guidance of the National Council for Traditional Healers and Herbalists' Association (NACOTHA). Study participants gave their written consent, and their identities have since been kept confidential. Saturation point was reached at 34 respondents. Data was recorded and transcribed verbatim and analyzed using content analysis.
 Results: The study indicates that incomplete, inadequate and inconsistent information especially from TM promotions leads users to overly buy and use TM. Identified themes related to information asymmetry include unverifiable information, usage side effects, and absence of expiry dates on the labels, naturalness of TM, unclear dosage rates, limited diagnosis, limited usage guidelines, and lack of authentic approvals by regulatory bodies among others.
 Conclusions: The findings raise the need for policy guidelines in the alternative health segment and multi-agency regulation of THPs in Uganda. Further, massive community sensitization and customer education are recommended since the potential for information asymmetries in TM promotions is quite large.

PD-0326 Alternative DL segmentation approaches for clinical partially-labeled HN data: transformers or Unet?

PD-0326 Alternative DL segmentation approaches for clinical partially-labeled HN data: transformers or Unet?

Modeling with Alternate Locations in X-ray Protein Structures.

In many molecular modeling applications, the standard procedure is still to handle proteins as single, rigid structures. While the importance of conformational flexibility is widely known, handling it remains challenging. Even the crystal structure of a protein usually contains variability exemplified in alternate side chain orientations or backbone segments. This conformational variability is encoded in PDB structure files by so-called alternate locations (AltLocs). Most modeling approaches either ignore AltLocs or resolve them with simple heuristics early on during structure import. We analyzed the occurrence and usage of AltLocs in the PDB and developed an algorithm to automatically handle AltLocs in PDB files enabling all structure-based methods using rigid structures to take the alternative protein conformations described by AltLocs into consideration. A respective software tool named AltLocEnumerator can be used as a structure preprocessor to easily exploit AltLocs. While the amount of data makes it difficult to show impact on a statistical level, handling AltLocs has a substantial impact on a case-by-case basis. We believe that the inspection and consideration of AltLocs is a very valuable approach in many modeling scenarios.

Strategic foresight of entrepreneurial firms in energy transition

PurposeThe purpose of this study is to explore the principal research query and whether strategic foresight deployed by entrepreneurial firms in energy transition aims at crafting future readiness.Design/methodology/approachWith a focus on entrepreneurial firms working in the alternative energy segment in the Indian context, the intent is to examine the deployment of strategic foresight by incumbent firms and their entrepreneurial journey. The authors have adopted the approach of Eisenhardt for this research. The area of interest for the authors entailing strategic foresight by entrepreneurial firms in energy transition aligns with defining features reflecting the aim of Eisenhardt method for this exploratory research coupled with constructivism.FindingsWhile the future scenarios in the energy sector have to be necessarily multiple, their alignment with different geographic, economic, demographic and political outlooks shall be defined by the pathways niched through the deployment of strategic foresight for arriving at those scenarios.Research limitations/implicationsStrategic foresight deployed by entrepreneurial firms has the potential to create future readiness through self-reliant sustainable economic value chains for local populace, thus propagating holistic development in remote regions.Originality/valueThis paper attempts to knit together the domains of strategic foresight, entrepreneurial firms and energy transition through case research and present the future thinking deployed for navigation in uncharted pathways by capturing the foresight component of these incumbent firms chosen through careful case selection. The narrative has been strengthened by the varied interviews across participants and the observations made by the authors during the research work.

Gene expression profiling and FDG-PET radiomics uncover radiometabolic signatures associated with outcome in DLBCL.

Emerging evidence indicates that chemoresistance is closely related to altered metabolism in cancer. Here, we hypothesized that distinct metabolic gene expression profiling (GEP) signatures might be correlated with outcome and with specific fluorodeoxyglucose positron emission tomography (FDG-PET) radiomic profiles in diffuse large B-cell lymphoma (DLBCL). We retrospectively analyzed a discovery cohort of 48 consecutive patients with DLBCL treated at our center with standard first-line chemoimmunotherapy by performing targeted GEP (T-GEP)- and FDG-PET radiomic analyses on the same target lesions at baseline. T-GEP-based metabolic profiling identified a 6-gene signature independently associated with outcomes in univariate and multivariate analyses. This signature included genes regulating mitochondrial oxidative metabolism (SCL25A1, PDK4, PDPR) that were upregulated and was inversely associated with genes involved in hypoxia and glycolysis (MAP2K1, HIF1A, GBE1) that were downregulated. These data were validated in 2 large publicly available cohorts. By integrating FDG-PET radiomics and T-GEP, we identified a radiometabolic signature (RadSig) including 4 radiomic features (histo kurtosis, histo energy, shape sphericity, and neighboring gray level dependence matrix contrast), significantly associated with the metabolic GEP-based signature (r= 0.43, P= .0027) and with progression-free survival (P= .028). These results were confirmed using different target lesions, an alternative segmentation method, and were validated in an independent cohort of 64 patients. RadSig retained independent prognostic value in relation to the International Prognostic Index score and metabolic tumor volume (MTV). Integration of RadSig and MTV further refined prognostic stratification. This study provides the proof of principle for the use of FDG-PET radiomics as a tool for noninvasive assessment of cancer metabolism and prognostic stratification in DLBCL.

FriendlyClearMap: an optimized toolkit for mouse brain mapping and analysis.

Tissue clearing is currently revolutionizing neuroanatomy by enabling organ-level imaging with cellular resolution. However, currently available tools for data analysis require a significant time investment for training and adaptation to each laboratory's use case, which limits productivity. Here, we present FriendlyClearMap, an integrated toolset that makes ClearMap1 and ClearMap2's CellMap pipeline easier to use, extends its functions, and provides Docker Images from which it can be run with minimal time investment. We also provide detailed tutorials for each step of the pipeline. For more precise alignment, we add a landmark-based atlas registration to ClearMap's functions as well as include young mouse reference atlases for developmental studies. We provide an alternative cell segmentation method besides ClearMap's threshold-based approach: Ilastik's Pixel Classification, importing segmentations from commercial image analysis packages and even manual annotations. Finally, we integrate BrainRender, a recently released visualization tool for advanced 3-dimensional visualization of the annotated cells. As a proof of principle, we use FriendlyClearMap to quantify the distribution of the 3 main GABAergic interneuron subclasses (parvalbumin+ [PV+], somatostatin+, and vasoactive intestinal peptide+) in the mouse forebrain and midbrain. For PV+ neurons, we provide an additional dataset with adolescent vs. adult PV+ neuron density, showcasing the use for developmental studies. When combined with the analysis pipeline outlined above, our toolkit improves on the state-of-the-art packages by extending their function and making them easier to deploy at scale.

Predictive, preventive, and personalized management of retinal fluid via computer-aided detection app for optical coherence tomography scans.

Computer-aided detection systems for retinal fluid could be beneficial for disease monitoring and management by chronic age-related macular degeneration (AMD) and diabetic retinopathy (DR) patients, to assist in disease prevention via early detection before the disease progresses to a "wet AMD" pathology or diabetic macular edema (DME), requiring treatment. We propose a proof-of-concept AI-based app to help predict fluid via a "fluid score", prevent fluid progression, and provide personalized, serial monitoring, in the context of predictive, preventive, and personalized medicine (PPPM) for patients at risk of retinal fluid complications. The app comprises a convolutional neural network-Vision Transformer (CNN-ViT)-based segmentation deep learning (DL) network, trained on a small dataset of 100 training images (augmented to 992 images) from the Singapore Epidemiology of Eye Diseases (SEED) study, together with a CNN-based classification network trained on 8497 images, that can detect fluid vs. non-fluid optical coherence tomography (OCT) scans. Both networks are validated on external datasets. Internal testing for our segmentation network produced an IoU score of 83.0% (95% CI = 76.7-89.3%) and a DICE score of 90.4% (86.3-94.4%); for external testing, we obtained an IoU score of 66.7% (63.5-70.0%) and a DICE score of 78.7% (76.0-81.4%). Internal testing of our classification network produced an area under the receiver operating characteristics curve (AUC) of 99.18%, and a Youden index threshold of 0.3806; for external testing, we obtained an AUC of 94.55%, and an accuracy of 94.98% and an F1 score of 85.73% with Youden index. We have developed an AI-based app with an alternative transformer-based segmentation algorithm that could potentially be applied in the clinic with a PPPM approach for serial monitoring, and could allow for the generation of retrospective data to research into the varied use of treatments for AMD and DR. The modular system of our app can be scaled to add more iterative features based on user feedback for more efficient monitoring. Further study and scaling up of the algorithm dataset could potentially boost its usability in a real-world clinical setting. The online version contains supplementary material available at 10.1007/s13167-022-00301-5.

The relative merit of two segmentation approaches: executives views and a cost-benefit analysis

PurposeThis study aims to capture the views of executives about the merit of using the two segmentation approaches (quantitative vs qualitative). Furthermore, this study aimed to examine costs and benefits for two different segmentation approaches, using a minimax simple cost-benefit analysis (CBA) matrix.Design/methodology/approachA total of 16 semistructured interviews were conducted with executives within the University of Sharjah (UoS). Furthermore, a minimax approach was applied to the CBA study.FindingsEvidence in this study found that the financial cost of quantitative segmentation approaches was higher than qualitative approaches. However, the decision-makers trusted the quantitative approach more regardless of the incurred costs. The study also found that there was a limited knowledge about social marketing and segmentation among executives.Research limitations/implicationsLimitations of this study relate to the methodology applied, the sample selected and the lead research. Another factor is selection bias, which limited this study to one organization’s executives. It is conceivable that middle-level management would have had the desire to participate because they make the recommendations to top management in decision-making. The researcher did not collect precise data on time taken to design, implement and analyses the two segmentation studies, which qualified the precision of the CBA. Also, the fact that the sample includes participants from a relatively narrow range of disciplines should be noted as a limitation of the study.Practical implicationsThe current study provides a case study demonstrating how CBA provides a dollar amount estimate permitting alternate segmentation approaches to be compared and contrasted, assisting in the value estimation of any social marketing project.Social implicationsThe paper draws upon two streams of the literature: social marketing and CBA. The paper focused on the understanding of the literature, CBA offers a technique applicable to demonstrating cost savings that can be derived from choosing one method over another. Moreover, CBA assists in understanding the benefits or potential opportunity cost both financially and nonfinancially.Originality/valueThis paper presents one of the first studies conducting a CBA to compare and contrast two segmentation approaches in social marketing. The study provides interesting insights into the perceptions of management executives over alternative research methods, although the results are limited to a case study.

Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors

BackgroundFor brain tumors, identifying the molecular subtypes from magnetic resonance imaging (MRI) is desirable, but remains a challenging task. Recent machine learning and deep learning (DL) approaches may help the classification/prediction of tumor subtypes through MRIs. However, most of these methods require annotated data with ground truth (GT) tumor areas manually drawn by medical experts. The manual annotation is a time consuming process with high demand on medical personnel. As an alternative automatic segmentation is often used. However, it does not guarantee the quality and could lead to improper or failed segmented boundaries due to differences in MRI acquisition parameters across imaging centers, as segmentation is an ill-defined problem. Analogous to visual object tracking and classification, this paper shifts the paradigm by training a classifier using tumor bounding box areas in MR images. The aim of our study is to see whether it is possible to replace GT tumor areas by tumor bounding box areas (e.g. ellipse shaped boxes) for classification without a significant drop in performance.MethodIn patients with diffuse gliomas, training a deep learning classifier for subtype prediction by employing tumor regions of interest (ROIs) using ellipse bounding box versus manual annotated data. Experiments were conducted on two datasets (US and TCGA) consisting of multi-modality MRI scans where the US dataset contained patients with diffuse low-grade gliomas (dLGG) exclusively.ResultsPrediction rates were obtained on 2 test datasets: 69.86% for 1p/19q codeletion status on US dataset and 79.50% for IDH mutation/wild-type on TCGA dataset. Comparisons with that of using annotated GT tumor data for training showed an average of 3.0% degradation (2.92% for 1p/19q codeletion status and 3.23% for IDH genotype).ConclusionUsing tumor ROIs, i.e., ellipse bounding box tumor areas to replace annotated GT tumor areas for training a deep learning scheme, cause only a modest decline in performance in terms of subtype prediction. With more data that can be made available, this may be a reasonable trade-off where decline in performance may be counteracted with more data.