MethodsXPub Date : 2025-07-23DOI: 10.1016/j.mex.2025.103530
Rogerio Cichota, Xiumei Yang
{"title":"Simulating forage plantain growth and defoliation in APSIM","authors":"Rogerio Cichota, Xiumei Yang","doi":"10.1016/j.mex.2025.103530","DOIUrl":"10.1016/j.mex.2025.103530","url":null,"abstract":"<div><div>The methodology used to develop and test a crop system model to simulate growth and defoliation management of plantain forage (<em>Plantago lanceolata</em> L.) in the Agricultural Production Systems Simulator (APSIM) framework is presented. The model has been primarily developed based on data from New Zealand, but it should be applicable in other regions, and it can be extended to account for new cultivars being released in the market. The model is capable of simulating pure forage plantain stands and can also be used in mixed swards with other forage species within the APSIM framework. Validation tests for the current stage focused on pure forage plantain stands in New Zealand; results showed a good model performance when predicting biomass accumulation over a growing season and nitrogen content (with NSE > 0.8), although predictions for individual defoliation events were not very accurate (NSE between -1.0 and 0.6). More data is needed to improve how the model describes biomass partition among plant organs and how this is affected by environmental conditions and defoliations. This model contributes to the ongoing efforts to explore alternative crops and improve management of grazing systems, aiming to reduce environmental impacts while maintaining productivity.<ul><li><span>•</span><span><div>Data to describe various aspects of plantain forage were gathered from literature and field trials</div></span></li><li><span>•</span><span><div>Model built to simulate plant growth and re-growth after defoliations within APSIM</div></span></li><li><span>•</span><span><div>The model can be used in monoculture and mixed swards</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103530"},"PeriodicalIF":1.9,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-23DOI: 10.1016/j.mex.2025.103529
Deepak Thazhakkattu Vasu , Kiruthika Selvakumar , Siti Hazirah Binti Samsuri , Roberta Ong Yi Li , Liow Kai Jun , Mark Isaac Fernandez , Ng Jia Yuet , Imtiyaz Ali Mir , Chan Siow Cheng , Tan Yin Qing
{"title":"The effects of dynamic neuromuscular stabilization (DNS) approach on gait, lumbopelvic functional stability and abdominal core strength among adolescent idiopathic scoliosis (AIS): A randomized controlled trial study protocol","authors":"Deepak Thazhakkattu Vasu , Kiruthika Selvakumar , Siti Hazirah Binti Samsuri , Roberta Ong Yi Li , Liow Kai Jun , Mark Isaac Fernandez , Ng Jia Yuet , Imtiyaz Ali Mir , Chan Siow Cheng , Tan Yin Qing","doi":"10.1016/j.mex.2025.103529","DOIUrl":"10.1016/j.mex.2025.103529","url":null,"abstract":"<div><h3>Introduction</h3><div>Adolescent Idiopathic Scoliosis (AIS) is a three-dimensional spinal deformity affecting young adults aged 10 years and above. Severity of scoliosis usually increase with aged, and hence early detection of scoliosis is crucial for conservative treatment to avoid surgery and preserving health-related quality of life. This study aim to evaluate the effectiveness of Dynamic Neuromuscular Stabilization (DNS) approach in gait, abdominal core stability and lumbopelvic functional stability in individual with AIS.</div></div><div><h3>Methods</h3><div>24 targeted AIS participants will be randomly allocated into two group for 12-week interventions, three times per week including 2 non-supervised sessions. Outcome measure will be assessed using measuring tape, stabilizer pressure biofeedback, wearable sensor BTS G-walk® with treadmill. Paired <em>t</em>-test will be used to assess within groups and independent <em>t</em>-test will be used to assess the efficacy of intervention between groups.</div></div><div><h3>Results</h3><div>This study protocol hypothesizes that DNS approach will have a more significant impact on improving the gait, core stability and lumbopelvic stability among AIS.</div></div><div><h3>Conclusion</h3><div>DNS approach can be effectively implemented in clinical settings to enhance the physical and functional mobility AIS patients.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103529"},"PeriodicalIF":1.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-23DOI: 10.1016/j.mex.2025.103526
Daniel Davids , Neil Grant , Shivika Mittal , Adam Hawkes , Gbemi Oluleye
{"title":"Combined warming index energy system analysis framework for methane leakage rate and carbon capture rate uncertainty","authors":"Daniel Davids , Neil Grant , Shivika Mittal , Adam Hawkes , Gbemi Oluleye","doi":"10.1016/j.mex.2025.103526","DOIUrl":"10.1016/j.mex.2025.103526","url":null,"abstract":"<div><div>Fossil fuels dominate the production of hydrogen and will continue to contribute in a decarbonised future. Blue hydrogen production from natural gas with carbon capture and storage technology applied is seen as the major route for natural gas in a future Hydrogen Economy. Methane leakage rate in natural gas supply chains and carbon capture rate are two critical parameters for the success of blue hydrogen. Despite this, the linked effect of the variables are difficult to identify, especially in terms of their impacts on decarbonisation metrics within the energy system. We formulate a new Combined Warming Index (CWI) measure and develop a framework for analysing the influence of methane leakage rate and carbon capture rate on blue hydrogen viability and other relevant energy system characteristics.</div><div>Framework outline:</div><div>• Investigate energy system scenarios within a range of methane leakage rates and carbon capture rates (varying Combined Warming Indices [CWI]) on blue hydrogen.</div><div>• Analyse important energy system dynamic parameter indicators versus the Combined Warming Index (CWI).</div><div>• Resultant energy system trends for methane leakage rates and carbon capture rates analysed against Combined Warming Index (CWI) establish unique property envelopes that reveal the state of the energy system at conditions and periods of interest.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103526"},"PeriodicalIF":1.9,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A multi-objective multi-period mathematical programming model for integrated project portfolio optimization and contractor selection","authors":"Mostafa Zahedirad , Kaveh Khalili-Damghani , Vahidreza Ghezavati , Alireza Rashidi Komijan","doi":"10.1016/j.mex.2025.103522","DOIUrl":"10.1016/j.mex.2025.103522","url":null,"abstract":"<div><div>This paper addresses the challenges of project portfolio optimization and contractor selection through two proposed scenarios. In the first scenario, two separate mixed-integer mathematical programming models are presented: one for project portfolio optimization and the other for contractor selection. In this approach, the decision variables from the project portfolio optimization model are treated as parameters in the contractor selection model. In the second scenario, an integrated mixed-integer mathematical programming model is introduced to simultaneously address both project portfolio optimization and contractor selection. Both scenarios consider multiple objectives, such as profit, risk, technical capability, and costs, along with numerous constraints, including relationships, inflation rates, and resources. The multi-objective optimization models are solved using goal programming (GP). A practical case study is conducted, comparing the two scenarios and demonstrating that the second scenario outperforms the first in terms of results. Additionally, the time complexity of both scenarios is analyzed, taking into account different numbers of variables and constraints. The analysis reveals that the second scenario exhibits superior performance in terms of CPU time.<ul><li><span>•</span><span><div>This method applies goal programming (GP) to solve the mixed-integer mathematical programming models for project portfolio optimization and contractor selection, thoroughly comparing the two scenarios using a practical example.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103522"},"PeriodicalIF":1.9,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-22DOI: 10.1016/j.mex.2025.103525
Morena Xaba, Sivuyisiwe Mapukata, Teboho Mokhena
{"title":"ChatGPT based method for obtaining repeatable and quantitative colorimetric measurements","authors":"Morena Xaba, Sivuyisiwe Mapukata, Teboho Mokhena","doi":"10.1016/j.mex.2025.103525","DOIUrl":"10.1016/j.mex.2025.103525","url":null,"abstract":"<div><div>The rise of artificial intelligence (AI) applications in the modern industry has been shown to boost productivity in many sectors such as manufacturing, mining, finance, marketing, pharmacy, textiles, and a few more industries. AI is a neural network system that is wired to learn by interacting with humans and by repetition of tasks. A sub-category of AI common to many ordinary citizens is the Chat Generative Pre-training Transformer (ChatGPT) a program of OpenAI Global, LLC., that generates human-like dialogue and responses from the user input.</div><div>• ChatGPT can be used to determine colorimetric values for the assessment of environmental pollutants such as congo red (CR) and coomassie brilliant blue (CBB) and prove its ability for consistent reproducibility.</div><div>• Several color models have been developed such as CIE Lab, RGB, and Xyz to quantify colors.</div><div>• We used ChatGPT, in conjunction with Color Grab which is an Android app, to quantitatively determine the RGB values of the pollutant solutions, and investigated the color difference ΔE, as well as the hue and chroma that facilitates the color absorption of the pollutants.</div><div>• The results from ChatGPT and Color Grab were confirmed with the well-established ultra-violet visible (UV–Vis) spectrophotometer.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103525"},"PeriodicalIF":1.6,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-18DOI: 10.1016/j.mex.2025.103521
Ramesh B T , Maruthi G V , Abhinav T , Shivakumar K Malladad , Lawrence J Fernandes , G M Mujeebullakhan , Ashok R Banagar , Srinivasa C V
{"title":"Estimation of Engineering Properties for Coconut Shell Powder Reinforced 100% Bio-Degradable Beeswax Composites to Replace Wood Materials","authors":"Ramesh B T , Maruthi G V , Abhinav T , Shivakumar K Malladad , Lawrence J Fernandes , G M Mujeebullakhan , Ashok R Banagar , Srinivasa C V","doi":"10.1016/j.mex.2025.103521","DOIUrl":"10.1016/j.mex.2025.103521","url":null,"abstract":"<div><div>Bio-degradability aligned with global warming will play a vital role to save the mother earth by saving the plenty of plants. Replacement of wood based structural parts with composites made with 100 % bio-degradable Bio-waste composites are the new trend in the structural stream now-a-days. Present work illustrates the synthesis of Beeswax to fabricate the composites in combination of coconut shell powder and preparation of composites of different grain sized coconut shell powder reinforcements. To understand the reason for improved mechanical properties SEM images were captured and a detailed analysis was made on these composites which shows the proper adhesion at 5000X magnification for 150 µm grain sized coconut shell powder reinforced composites. The following points will give the brief summary of the methods adopted,<ul><li><span>•</span><span><div>A method of bio resin extraction from beehives are being discussed in detail here in this method.</div></span></li><li><span>•</span><span><div>Selection of proper grain sized bio-degradable reinforcements with proper proportions are being discussed.</div></span></li><li><span>•</span><span><div>Mechanical and morphological analysis to understand the use of bio-degradable materials in the structural application and to replace the wood based materials.</div></span></li></ul>This is one of the unique and new technique to make use of bio-degradable resin and reinforcements in the fabrication of green materials.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103521"},"PeriodicalIF":1.6,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-18DOI: 10.1016/j.mex.2025.103517
Anuradha Yenkikar , Ved Prakash Mishra , Manish Bali , Tabassum Ara
{"title":"Explainable forecasting of air quality index using a hybrid random forest and ARIMA model","authors":"Anuradha Yenkikar , Ved Prakash Mishra , Manish Bali , Tabassum Ara","doi":"10.1016/j.mex.2025.103517","DOIUrl":"10.1016/j.mex.2025.103517","url":null,"abstract":"<div><div>Accurate and interpretable prediction of the Air Quality Index (AQI) is critical for public health decision-making and environmental policy enforcement. This study presents a hybrid forecasting framework that combines the strengths of Random Forest Regression (RFR) and Autoregressive Integrated Moving Average (ARIMA) models to improve AQI prediction accuracy while maintaining model transparency. The RFR captures nonlinear relationships among pollutants, while ARIMA is used to model the temporal patterns in RFR residuals, forming a two-stage learning architecture. The model is trained and evaluated on multi-year AQI data from India and validated using an expanding window cross-validation strategy to maintain temporal integrity. To ensure transparency and interpretability, the study employs SHAP ((SHapley Additive Explanations) to uncover the influence of key pollutants such as PM₂.₅, NO₂, and SO₂. Additionally, Ljung-Box diagnostics and uncertainty bands are used to validate model adequacy. Compared to baseline models, the hybrid approach achieves lower Mean Squared Error (MSE = 508.46) and a higher R² score (0.94), confirming improved generalization. This research contributes a replicable, explainable, and efficient AQI forecasting framework suited for deployment in resource-constrained urban environments. The method comprises of:</div><div>Residual learning hybrid model: Random Forest for prediction + ARIMA for residual correction</div><div>Time-aware validation using expanding window cross-validation</div><div>Model interpretability through SHAP analysis</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103517"},"PeriodicalIF":1.9,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-18DOI: 10.1016/j.mex.2025.103512
Farah Hasan AlHusseini , Habeeb M. Abood
{"title":"Quasi Sasakian manifold endowed with vanishing pseudo quasi conformal curvature tensor","authors":"Farah Hasan AlHusseini , Habeeb M. Abood","doi":"10.1016/j.mex.2025.103512","DOIUrl":"10.1016/j.mex.2025.103512","url":null,"abstract":"<div><div>This study provides a fundamental understanding of the geometry of a quasi-Sasakian manifold (<span><math><mtext>QS</mtext></math></span>-manifold), highlighting their structural properties and enhancing the knowledge of their geometric framework. A pseudo quasi-conformal curvature tensor (<span><math><mtext>PQC</mtext></math></span>-curvature tensor) of <span><math><mtext>QS</mtext></math></span>-manifold has been identified. The components of the <span><math><mtext>PQC</mtext></math></span>-curvature tensor are established employing the <span><math><mi>G</mi></math></span>-adjoined structure space(<span><math><mtext>GADS</mtext></math></span>-space). It is demonstrated that the Ricci flat <span><math><mtext>QS</mtext></math></span>-manifold is locally equivalent to the product of the complex Euclidean space <span><math><msup><mrow><mi>C</mi></mrow><mi>n</mi></msup></math></span> and the real line. Furthermore, it has been demonstrated that a <span><math><mi>ξ</mi></math></span>-pseudo quasi conformal flat <span><math><mtext>QS</mtext></math></span>-manifold is a quasi-Einstein manifold. The conditions under which a quasi-symmetric <span><math><mtext>QS</mtext></math></span>-manifold becomes a quasi-Einstein manifold are also specified. Subsequently, it has been shown for <span><math><mtext>QS</mtext></math></span>-manifolds that pseudo quasi conformal symmetric and pseudo quasi conformal flat are equivalent.<ul><li><span>•</span><span><div>The pseudo quasi-conformal curvature tensor of the quasi Sasakian manifold has been identified.</div></span></li><li><span>•</span><span><div>The Ricci flat quasi Sasakian manifold is<span><math><mspace></mspace></math></span>studied.</div></span></li><li><span>•</span><span><div>An application of the quasi-symmetric quasi Sasakian manifold to be a quasi-Einstein manifold is specified.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103512"},"PeriodicalIF":1.6,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-18DOI: 10.1016/j.mex.2025.103520
Edgar D. Páez-Pérez, Araceli Hernández-Sánchez, Elvia Alfaro-Saldaña, J. Viridiana García-Meza
{"title":"Simplified method for purifying full-length major type IV pilins: PilA from Acidithiobacillus thiooxidans","authors":"Edgar D. Páez-Pérez, Araceli Hernández-Sánchez, Elvia Alfaro-Saldaña, J. Viridiana García-Meza","doi":"10.1016/j.mex.2025.103520","DOIUrl":"10.1016/j.mex.2025.103520","url":null,"abstract":"<div><div>Type IV major pilins are membrane-associated proteins that play critical roles in bacterial adaptation and survival across diverse environmental conditions, including potentially extreme ones. However, their expression and purification remain challenging due to their hydrophobic nature and tendency to aggregate. Here, we present a cost-effective method for the production and purification of recombinant full-length PilA, the major type IV pilin from the acidophilic bacterium <em>Acidithiobacillus thiooxidans</em>. By expressing the protein as a thioredoxin (Trx) fusion in <em>Escherichia coli</em> and using detergent-based solubilization combined with manual nickel affinity chromatography and spin-column anion exchange, we obtained stable and well folded protein suitable for downstream biophysical assays. Our approach eliminates the need for sophisticated FPLC systems and high-end chromatography columns, making it accessible to laboratories with limited resources. Structural stability of the purified protein was validated through intrinsic fluorescence spectroscopy under varying pH and denaturing conditions. This method can be readily adapted for the production of pilins from extremophilic and other pathogenic bacteria, providing a valuable tool for biotechnological and biomedical applications.<ul><li><span>•</span><span><div>Enables purification of full-length pilins without requiring FPLC or high-cost columns</div></span></li><li><span>•</span><span><div>Applicable to the expression and analysis of structurally challenging pilins</div></span></li><li><span>•</span><span><div>Produces material suitable for biophysical studies, including fluorescence-based assays and structural analyses</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103520"},"PeriodicalIF":1.6,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
MethodsXPub Date : 2025-07-17DOI: 10.1016/j.mex.2025.103519
Abhay Nath , Om Roy , Priyanka Silveri , Sanskruti Patel
{"title":"Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis","authors":"Abhay Nath , Om Roy , Priyanka Silveri , Sanskruti Patel","doi":"10.1016/j.mex.2025.103519","DOIUrl":"10.1016/j.mex.2025.103519","url":null,"abstract":"<div><div>Oral squamous cell carcinoma (OSCC) continues to present a major worldwide healthcare problem because patients have poor survival outcomes alongside frequent disease returns. Globocan predicts that, OSCC will result in 389,846 new cases and 188,438 deaths globally during 2022 while maintaining an extremely poor 5-year survival rate at about 50%. Our method applies residual connections with Squeeze-and-Excitation blocks along with hybrid attention systems and enhanced activation functions and optimization algorithms to boost gradient movement throughout feature extraction. Compared against established conventional CNN backbones (VGG16, ResNet50, DenseNet121, and more), the proposed ConvNeXt-SE-Attn model outperformed them in all aspects of discrimination and calibration, including precision 97.88% (vs. ≤94.2%), sensitivity 96.82% (vs. ≤92.5%), specificity 95.94% (vs. ≤93.1%), F1 score 97.31% (vs. ≤93.8%), AUC 0.9644 (vs. ≤0.945), and MCC 0.9397 (vs. ≤0.910). The findings are critical to the increased feature-representation power and the robustness of classification of the architecture.</div><div>The proposed architecture employs ConvNeXt backbone with SE blocks and hybrid attention to extract essential details within class boundaries which standard models usually miss.</div><div>The activation through Gaussian-based GReLU incorporates Swish activation together with DropPath regularization for producing smooth gradient patterns which lead to generalizable features across imbalanced datasets.</div><div>Grad-CAM enhances interpretability by showing which image sections lead to predictions in order to enable clinical decisions.</div><div>The model demonstrates its capability as an effective detection method for minimal variations in oral cells which supports precise non-invasive treatment approaches for OSCC.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103519"},"PeriodicalIF":1.6,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144696758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}