Pub Date : 2025-08-09DOI: 10.1016/j.slast.2025.100338
Wenbo Zhao , Yu Wang
Optic disc and cup segmentation is a crucial subfield of computer vision, playing a pivotal role in automated pathological image analysis. It enables precise, efficient, and automated diagnosis of ocular conditions, significantly aiding clinicians in real-world medical applications. However, due to the scarcity of medical segmentation data and the insufficient integration of global contextual information, the segmentation accuracy remains suboptimal. This issue becomes particularly pronounced in optic disc and cup cases with complex anatomical structures and ambiguous boundaries. In order to address these limitations, this paper introduces a self-supervised training strategy integrated with a newly designed network architecture to improve segmentation accuracy. Specifically,we initially propose a non-local dual deformable convolutional block,which aims to capture the irregular image patterns( boundary). Secondly,we modify the traditional vision transformer and design an adaptive K-Nearest Neighbors(KNN) transformation block to extract the global semantic context from images. Finally,an initialization strategy based on self-supervised training is proposed to reduce the burden on the network on labeled data. Comprehensive experimental evaluations demonstrate the effectiveness of our proposed method, which outperforms previous networks and achieves state-of-the-art performance,with IOU scores of 0.9577 for the optic disc and 0.8399 for the optic cup on the REFUGE dataset.
{"title":"Self-supervised disc and cup segmentation via non-local deformable convolution and adaptive transformer","authors":"Wenbo Zhao , Yu Wang","doi":"10.1016/j.slast.2025.100338","DOIUrl":"10.1016/j.slast.2025.100338","url":null,"abstract":"<div><div>Optic disc and cup segmentation is a crucial subfield of computer vision, playing a pivotal role in automated pathological image analysis. It enables precise, efficient, and automated diagnosis of ocular conditions, significantly aiding clinicians in real-world medical applications. However, due to the scarcity of medical segmentation data and the insufficient integration of global contextual information, the segmentation accuracy remains suboptimal. This issue becomes particularly pronounced in optic disc and cup cases with complex anatomical structures and ambiguous boundaries. In order to address these limitations, this paper introduces a self-supervised training strategy integrated with a newly designed network architecture to improve segmentation accuracy. Specifically,we initially propose a non-local dual deformable convolutional block,which aims to capture the irregular image patterns(<span><math><mrow><mi>i</mi><mo>.</mo><mi>e</mi><mo>.</mo></mrow></math></span> boundary). Secondly,we modify the traditional vision transformer and design an adaptive K-Nearest Neighbors(KNN) transformation block to extract the global semantic context from images. Finally,an initialization strategy based on self-supervised training is proposed to reduce the burden on the network on labeled data. Comprehensive experimental evaluations demonstrate the effectiveness of our proposed method, which outperforms previous networks and achieves state-of-the-art performance,with IOU scores of 0.9577 for the optic disc and 0.8399 for the optic cup on the REFUGE dataset.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"34 ","pages":"Article 100338"},"PeriodicalIF":3.7,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144823210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-01DOI: 10.1016/j.slast.2025.100339
Qingyu Wang, Wenyao Zhong, Xingmiao Feng
Background: In recent years, nanosilver gel has gained attention due to its excellent antimicrobial properties and wound healing effects. Meanwhile, the comprehensive care model has improved the rehabilitation environment for patients with its holistic and individualized care approach. This study aimed to investigate the promoting effects of nanosilver gel on wound healing in hand injury patients and the intervention effects of the comprehensive care model.
Methods: This study adopted a randomized controlled trial (RCT) design. A total of 120 hand injury patients admitted to the Hand Surgery Department of Beijing Jishuitan Hospital between January 2020 and January 2023 were enrolled and randomly allocated into three groups (n=40 each). The control group (C group) received standard care, experimental group A (Exp A) underwent a comprehensive nursing intervention, and experimental group B (Exp B) received additional nanosilver gel dressing treatment based on the comprehensive nursing protocol. Primary outcome measures included wound healing time, pain intensity (visual analogue scale (VAS) score), functional recovery (grip strength, hand dexterity, and range of motion), and wound healing rate.
Results: Exp group B had notably better outcomes in terms of wound healing time, pain intensity, functional recovery, and wound healing rate versus C group and Exp group A.
Conclusion: This study demonstrates that the combination of nanosilver gel and the comprehensive care model significantly improves wound healing outcomes in hand injury patients, providing a new and effective possibility for the treatment of hand injuries.
{"title":"Nanosilver Gel, as a novel therapeutic approach, ameliorates wound healing in hand injury patients.","authors":"Qingyu Wang, Wenyao Zhong, Xingmiao Feng","doi":"10.1016/j.slast.2025.100339","DOIUrl":"https://doi.org/10.1016/j.slast.2025.100339","url":null,"abstract":"<p><strong>Background: </strong>In recent years, nanosilver gel has gained attention due to its excellent antimicrobial properties and wound healing effects. Meanwhile, the comprehensive care model has improved the rehabilitation environment for patients with its holistic and individualized care approach. This study aimed to investigate the promoting effects of nanosilver gel on wound healing in hand injury patients and the intervention effects of the comprehensive care model.</p><p><strong>Methods: </strong>This study adopted a randomized controlled trial (RCT) design. A total of 120 hand injury patients admitted to the Hand Surgery Department of Beijing Jishuitan Hospital between January 2020 and January 2023 were enrolled and randomly allocated into three groups (n=40 each). The control group (C group) received standard care, experimental group A (Exp A) underwent a comprehensive nursing intervention, and experimental group B (Exp B) received additional nanosilver gel dressing treatment based on the comprehensive nursing protocol. Primary outcome measures included wound healing time, pain intensity (visual analogue scale (VAS) score), functional recovery (grip strength, hand dexterity, and range of motion), and wound healing rate.</p><p><strong>Results: </strong>Exp group B had notably better outcomes in terms of wound healing time, pain intensity, functional recovery, and wound healing rate versus C group and Exp group A.</p><p><strong>Conclusion: </strong>This study demonstrates that the combination of nanosilver gel and the comprehensive care model significantly improves wound healing outcomes in hand injury patients, providing a new and effective possibility for the treatment of hand injuries.</p>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":" ","pages":"100339"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144776908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-01DOI: 10.1016/j.slast.2025.100337
Komel Tariq, Nosheen Fatima Rana, Sabah Javaid, Muneeba Khadim
Implant-associated infections remain a significant challenge in orthopaedic and dental implants because they frequently result in implant failure, extended hospital stays, reoperations, and increased healthcare costs. Studies have shown that the cost of managing orthopaedic implant infections can range from USD 30,000 to over USD 100,000 per case, depending on severity and required surgical interventions. One of the primary pathogens responsible for these infections is Staphylococcus aureus, known for its potential to make biofilms on the surfaces of implants. To address this problem, this study investigates the formation of calcium phosphate-based biomimetic coatings substituted with calcium-doped ZnO nanoparticles on titanium discs to strengthen the antibacterial properties and enhance tissue integration. The SEM analysis of discs revealed uniform and dense coating layers with negligible surface defects, indicating a strong adhesive coating on titanium discs. The biomimetic-coated titanium implants with Ca-doped ZnO NPs were then evaluated for antibacterial activity using a closed system in an in vitro biofilm model. In case of 14 days treated disc, a significant increase in the antibacterial properties was observed against (Staphylococcus aureus, p < 0.0001). These findings suggest that calcium phosphate-based biomimetic coatings, doped with calcium-doped ZnO NPs show great potential for reducing the risk for implant-associated infections and improving the success rate of implants in clinical settings.
{"title":"Titanium surface functionalization with calcium-doped ZnO nanoparticles for hard tissue implant applications","authors":"Komel Tariq, Nosheen Fatima Rana, Sabah Javaid, Muneeba Khadim","doi":"10.1016/j.slast.2025.100337","DOIUrl":"10.1016/j.slast.2025.100337","url":null,"abstract":"<div><div>Implant-associated infections remain a significant challenge in orthopaedic and dental implants because they frequently result in implant failure, extended hospital stays, reoperations, and increased healthcare costs. Studies have shown that the cost of managing orthopaedic implant infections can range from USD 30,000 to over USD 100,000 per case, depending on severity and required surgical interventions. One of the primary pathogens responsible for these infections is <em>Staphylococcus aureus,</em> known for its potential to make biofilms on the surfaces of implants. To address this problem, this study investigates the formation of calcium phosphate-based biomimetic coatings substituted with calcium-doped ZnO nanoparticles on titanium discs to strengthen the antibacterial properties and enhance tissue integration. The SEM analysis of discs revealed uniform and dense coating layers with negligible surface defects, indicating a strong adhesive coating on titanium discs. The biomimetic-coated titanium implants with Ca-doped ZnO NPs were then evaluated for antibacterial activity using a closed system in an <em>in vitro</em> biofilm model. In case of 14 days treated disc, a significant increase in the antibacterial properties was observed against (<em>Staphylococcus aureus, p</em> < 0.0001)<em>.</em> These findings suggest that calcium phosphate-based biomimetic coatings, doped with calcium-doped ZnO NPs show great potential for reducing the risk for implant-associated infections and improving the success rate of implants in clinical settings.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"33 ","pages":"Article 100337"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-01DOI: 10.1016/j.slast.2025.100311
Jamien Lim , Tal Murthy
{"title":"Literature highlights column: From the literature life sciences discovery and technology highlights","authors":"Jamien Lim , Tal Murthy","doi":"10.1016/j.slast.2025.100311","DOIUrl":"10.1016/j.slast.2025.100311","url":null,"abstract":"","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"33 ","pages":"Article 100311"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144250861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-28DOI: 10.1016/j.slast.2025.100323
Muhammad Zeeshan Tahir , Xingzheng Lyu , Muhammad Nasir , Wengan He , Abeer Aljohani , Sanyuan Zhang
Diabetic Retinopathy (DR) is a complication of diabetes that can cause vision impairment and lead to permanent blindness if left undiagnosed. The increasing number of diabetic patients, coupled with a shortage of ophthalmologists, highlights the urgent need for automated screening tools for early DR diagnosis. Among the earliest and most detectable signs of DR are microaneurysms (MAs). However, detecting MAs in fundus images remains challenging due to several factors, including image quality limitations, the subtle appearance of MA features, and the wide variability in color, shape, and texture. To address these challenges, we propose a novel preprocessing pipeline that enhances the overall image quality, facilitating feature learning and improving the detection of subtle MA features in low-quality fundus images. Building on this preprocessing technique, we further develop a lightweight Attention U-Net model that significantly reduces the number of model parameters while achieving superior performance. By incorporating an attention mechanism, the model focuses on the subtle features of MAs, leading to more precise segmentation results. We evaluated our method on the IDRID dataset, achieving a sensitivity of 0.81 and specificity of 0.99, outperforming existing MA segmentation models. To validate its generalizability, we tested it on the E-Ophtha dataset, where it achieved a sensitivity of 0.59 and specificity of 0.99. Despite its lightweight design, our model demonstrates robust performance under challenging conditions such as noise and varying lighting, making it a promising tool for clinical applications and large-scale DR screening.
{"title":"Efficient microaneurysm segmentation in retinal images via a lightweight Attention U-Net for early DR diagnosis","authors":"Muhammad Zeeshan Tahir , Xingzheng Lyu , Muhammad Nasir , Wengan He , Abeer Aljohani , Sanyuan Zhang","doi":"10.1016/j.slast.2025.100323","DOIUrl":"10.1016/j.slast.2025.100323","url":null,"abstract":"<div><div>Diabetic Retinopathy (DR) is a complication of diabetes that can cause vision impairment and lead to permanent blindness if left undiagnosed. The increasing number of diabetic patients, coupled with a shortage of ophthalmologists, highlights the urgent need for automated screening tools for early DR diagnosis. Among the earliest and most detectable signs of DR are microaneurysms (MAs). However, detecting MAs in fundus images remains challenging due to several factors, including image quality limitations, the subtle appearance of MA features, and the wide variability in color, shape, and texture. To address these challenges, we propose a novel preprocessing pipeline that enhances the overall image quality, facilitating feature learning and improving the detection of subtle MA features in low-quality fundus images. Building on this preprocessing technique, we further develop a lightweight Attention U-Net model that significantly reduces the number of model parameters while achieving superior performance. By incorporating an attention mechanism, the model focuses on the subtle features of MAs, leading to more precise segmentation results. We evaluated our method on the IDRID dataset, achieving a sensitivity of 0.81 and specificity of 0.99, outperforming existing MA segmentation models. To validate its generalizability, we tested it on the E-Ophtha dataset, where it achieved a sensitivity of 0.59 and specificity of 0.99. Despite its lightweight design, our model demonstrates robust performance under challenging conditions such as noise and varying lighting, making it a promising tool for clinical applications and large-scale DR screening.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"34 ","pages":"Article 100323"},"PeriodicalIF":3.7,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-23DOI: 10.1016/j.slast.2025.100336
Muhammad Waqar , Zeshan Aslam Khan , Shanzey Tariq Khawaja , Naveed Ishtiaq Chaudhary , Saadia Khan , Khalid Mehmood Cheema , Muhammad Farhan Khan , Syed Sohail Ahmed , Muhammad Asif Zahoor Raja
Deep learning (DL) has had an incredible influence on many different scientific areas over the past couple of decades. Particularly in the field of healthcare, DL strategies were able to outclass other existing methodologies in image processing. The rapid expansion of the monkeypox endemic to over 40 nations apart from Africa has prompted serious worries in the realm of public health. Given that monkeypox can have symptoms that are akin to both chickenpox and measles, early detection can be difficult. Fortunately, due to the developments in artificial intelligence approaches, it can be implemented to promptly and accurately identify monkeypox disease using visual data information. Many DL driven techniques have already been exploited in the literature for skin related issues, which have provided accurate results to some extent. These models were dependent on extensive computational and time resources due to which the real-time applicability is difficult. Rather of building and training CNNs from scratch, this study uses transfer learning (TL) technique to fine-tune pre-trained networks, particularly exploiting various versions of ConvNeXt, by substituting last layer with additional task specific ones. A number of pre-processing and data augmentation methods have also been assessed and adjusted with regard to computing time and performance. The proposed study performs the binary and multi class monkeypox disease classification task. Promising accurate results of 99.9 % on the benchmark MSLD (binary class) dataset and 94 % on the MSLD v2.0 (multi-class) dataset is obtained by fine-tuned TL-based ConvNeXtSmall and ConvNeXtBase architecture with Adafactor optimization technique, demonstrating the practicality of the suggested framework as a substitute for the current ones. The proposed model is assessed through both standard train-test split and k-fold cross validation techniques. Furthermore, performance of models is also assessed on several other metrics including recall, F1 score, precision and multiple statistical tests incorporated with explainable AI methods for better interpretability of results. The concerns regarding the real-time applicability are tackled by utilizing the less time consuming and computationally efficient networks through the exploitation of transfer learning capabilities. Moreover, the explainable findings of the proposed study will be highly valuable for the healthcare professionals to understand the decisive behavior of the model and make informed clinical decisions.
{"title":"Explainable clinical diagnosis through unexploited yet optimized fine-tuned ConvNeXt Models for accurate monkeypox disease classification","authors":"Muhammad Waqar , Zeshan Aslam Khan , Shanzey Tariq Khawaja , Naveed Ishtiaq Chaudhary , Saadia Khan , Khalid Mehmood Cheema , Muhammad Farhan Khan , Syed Sohail Ahmed , Muhammad Asif Zahoor Raja","doi":"10.1016/j.slast.2025.100336","DOIUrl":"10.1016/j.slast.2025.100336","url":null,"abstract":"<div><div>Deep learning (DL) has had an incredible influence on many different scientific areas over the past couple of decades. Particularly in the field of healthcare, DL strategies were able to outclass other existing methodologies in image processing. The rapid expansion of the monkeypox endemic to over 40 nations apart from Africa has prompted serious worries in the realm of public health. Given that monkeypox can have symptoms that are akin to both chickenpox and measles, early detection can be difficult. Fortunately, due to the developments in artificial intelligence approaches, it can be implemented to promptly and accurately identify monkeypox disease using visual data information. Many DL driven techniques have already been exploited in the literature for skin related issues, which have provided accurate results to some extent. These models were dependent on extensive computational and time resources due to which the real-time applicability is difficult. Rather of building and training CNNs from scratch, this study uses transfer learning (TL) technique to fine-tune pre-trained networks, particularly exploiting various versions of ConvNeXt, by substituting last layer with additional task specific ones. A number of pre-processing and data augmentation methods have also been assessed and adjusted with regard to computing time and performance. The proposed study performs the binary and multi class monkeypox disease classification task. Promising accurate results of 99.9 % on the benchmark MSLD (binary class) dataset and 94 % on the MSLD v2.0 (multi-class) dataset is obtained by fine-tuned TL-based ConvNeXtSmall and ConvNeXtBase architecture with Adafactor optimization technique, demonstrating the practicality of the suggested framework as a substitute for the current ones. The proposed model is assessed through both standard train-test split and k-fold cross validation techniques. Furthermore, performance of models is also assessed on several other metrics including recall, F1 score, precision and multiple statistical tests incorporated with explainable AI methods for better interpretability of results. The concerns regarding the real-time applicability are tackled by utilizing the less time consuming and computationally efficient networks through the exploitation of transfer learning capabilities. Moreover, the explainable findings of the proposed study will be highly valuable for the healthcare professionals to understand the decisive behavior of the model and make informed clinical decisions.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"33 ","pages":"Article 100336"},"PeriodicalIF":3.7,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144719154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-23DOI: 10.1016/j.slast.2025.100334
Jing Yang , Muhammad Abubakar Siddique , Hafeez Ullah , Ghulam Gilanie , Lip Yee Por , Samah Alshathri , Walid El-Shafai , Haya Aldossary , Thippa Reddy Gadekallu
Brain tumors pose a significant risk to human life, making accurate grading essential for effective treatment planning and improved survival rates. Magnetic Resonance Imaging (MRI) plays a crucial role in this process. The objective of this study was to develop an automated brain tumor grading system utilizing deep learning techniques. A dataset comprising 293 MRI scans from patients was obtained from the Department of Radiology at Bahawal Victoria Hospital in Bahawalpur, Pakistan. The proposed approach integrates a specialized Convolutional Neural Network (CNN) with pre-trained models to classify brain tumors into low-grade (LGT) and high-grade (HGT) categories with high accuracy. To assess the model's robustness, experiments were conducted using various methods: (1) raw MRI slices, (2) MRI segments containing only the tumor area, (3) feature-extracted slices derived from the original images through the proposed CNN architecture, and (4) feature-extracted slices from tumor area-only segmented images using the proposed CNN. The MRI slices and the features extracted from them were labeled using machine learning models, including Support Vector Machine (SVM) and CNN architectures based on transfer learning, such as MobileNet, Inception V3, and ResNet-50. Additionally, a custom model was specifically developed for this research. The proposed model achieved an impressive peak accuracy of 99.45 %, with classification accuracies of 99.56 % for low-grade tumors and 99.49 % for high-grade tumors, surpassing traditional methods. These results not only enhance the accuracy of brain tumor grading but also improve computational efficiency by reducing processing time and the number of iterations required.
{"title":"BrainCNN: Automated brain tumor grading from magnetic resonance images using a convolutional neural network-based customized model","authors":"Jing Yang , Muhammad Abubakar Siddique , Hafeez Ullah , Ghulam Gilanie , Lip Yee Por , Samah Alshathri , Walid El-Shafai , Haya Aldossary , Thippa Reddy Gadekallu","doi":"10.1016/j.slast.2025.100334","DOIUrl":"10.1016/j.slast.2025.100334","url":null,"abstract":"<div><div>Brain tumors pose a significant risk to human life, making accurate grading essential for effective treatment planning and improved survival rates. Magnetic Resonance Imaging (MRI) plays a crucial role in this process. The objective of this study was to develop an automated brain tumor grading system utilizing deep learning techniques. A dataset comprising 293 MRI scans from patients was obtained from the Department of Radiology at Bahawal Victoria Hospital in Bahawalpur, Pakistan. The proposed approach integrates a specialized Convolutional Neural Network (CNN) with pre-trained models to classify brain tumors into low-grade (LGT) and high-grade (HGT) categories with high accuracy. To assess the model's robustness, experiments were conducted using various methods: (1) raw MRI slices, (2) MRI segments containing only the tumor area, (3) feature-extracted slices derived from the original images through the proposed CNN architecture, and (4) feature-extracted slices from tumor area-only segmented images using the proposed CNN. The MRI slices and the features extracted from them were labeled using machine learning models, including Support Vector Machine (SVM) and CNN architectures based on transfer learning, such as MobileNet, Inception V3, and ResNet-50. Additionally, a custom model was specifically developed for this research. The proposed model achieved an impressive peak accuracy of 99.45 %, with classification accuracies of 99.56 % for low-grade tumors and 99.49 % for high-grade tumors, surpassing traditional methods. These results not only enhance the accuracy of brain tumor grading but also improve computational efficiency by reducing processing time and the number of iterations required.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"34 ","pages":"Article 100334"},"PeriodicalIF":3.7,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144719153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-16DOI: 10.1016/j.slast.2025.100331
Ahsan Bilal Tariq , Muhammad Zaheer Sajid , Nauman Ali khan , Muhammad Fareed Hamid , Anwaar UlHaq , Jarrar Amjad
Due to challenges such as illumination variability, noise, and visual distortions, machine learning (ML) and deep learning (DL) approaches for skin disease evaluation remain complex. Traditional methods often neglect these issues, leading to skewed predictions and poor performance. This research leverages a diverse dataset and robust image processing techniques to enhance diagnostic accuracy under such demanding conditions. We propose Dermo-Transfer, a novel architecture that combines MobileNet with dense blocks and residual connections to improve skin disease severity classification by addressing problems such as vanishing gradients and overfitting. Our method incorporates multi-scale Retinex, gamma correction, and histogram equalization to enhance image quality and visibility. Furthermore, a quantum support vector machine (QSVM) classifier is employed to improve classification performance, providing confidence scores and effectively handling multi-class problems. The proposed approach significantly enhances diagnostic accuracy and outperforms previous models. Dermo-Transfer not only improves pattern recognition and classification accuracy but also robustly handles varying image quality and lighting conditions. Dermo-Transfer was trained on 77,314 images covering skin conditions such as molluscum, warts, eczema, psoriasis, lichen planus, seborrheic keratoses, atopic dermatitis, melanoma, basal cell carcinoma (BCC), melanocytic nevi (NV), benign keratosis, and other benign tumors. The Dermo-Transfer classification method achieved accuracies of 99 %, 98.5 %, 97.5 %, and 89 % across four datasets, demonstrating its effectiveness and potential utility for clinical diagnostics. Additionally, Dermo-Transfer outperformed SkinLesNet and MobileNet V2-LSTM in terms of classification accuracy. Experimental results also highlight how IoT devices and mobile applications can enhance the computational efficiency and practical deployment of the Dermo-Transfer model.
{"title":"An integrated deep learning framework using adaptive enhanced vision fusion and modified mobilenet architecture for precision classification of skin diseases with enhanced diagnostic performance","authors":"Ahsan Bilal Tariq , Muhammad Zaheer Sajid , Nauman Ali khan , Muhammad Fareed Hamid , Anwaar UlHaq , Jarrar Amjad","doi":"10.1016/j.slast.2025.100331","DOIUrl":"10.1016/j.slast.2025.100331","url":null,"abstract":"<div><div>Due to challenges such as illumination variability, noise, and visual distortions, machine learning (ML) and deep learning (DL) approaches for skin disease evaluation remain complex. Traditional methods often neglect these issues, leading to skewed predictions and poor performance. This research leverages a diverse dataset and robust image processing techniques to enhance diagnostic accuracy under such demanding conditions. We propose Dermo-Transfer, a novel architecture that combines MobileNet with dense blocks and residual connections to improve skin disease severity classification by addressing problems such as vanishing gradients and overfitting. Our method incorporates multi-scale Retinex, gamma correction, and histogram equalization to enhance image quality and visibility. Furthermore, a quantum support vector machine (QSVM) classifier is employed to improve classification performance, providing confidence scores and effectively handling multi-class problems. The proposed approach significantly enhances diagnostic accuracy and outperforms previous models. Dermo-Transfer not only improves pattern recognition and classification accuracy but also robustly handles varying image quality and lighting conditions. Dermo-Transfer was trained on 77,314 images covering skin conditions such as molluscum, warts, eczema, psoriasis, lichen planus, seborrheic keratoses, atopic dermatitis, melanoma, basal cell carcinoma (BCC), melanocytic nevi (NV), benign keratosis, and other benign tumors. The Dermo-Transfer classification method achieved accuracies of 99 %, 98.5 %, 97.5 %, and 89 % across four datasets, demonstrating its effectiveness and potential utility for clinical diagnostics. Additionally, Dermo-Transfer outperformed SkinLesNet and MobileNet V2-LSTM in terms of classification accuracy. Experimental results also highlight how IoT devices and mobile applications can enhance the computational efficiency and practical deployment of the Dermo-Transfer model.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"34 ","pages":"Article 100331"},"PeriodicalIF":3.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144669002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号