Intelligence-based medicine最新文献

{"title":"Deep learning-based approach to diagnose lung cancer using CT-scan images","authors":"Mohammad Q. Shatnawi,&nbsp;Qusai Abuein,&nbsp;Romesaa Al-Quraan","doi":"10.1016/j.ibmed.2024.100188","DOIUrl":"10.1016/j.ibmed.2024.100188","url":null,"abstract":"<div><div>The work in this research focuses on the automatic classification and prediction of lung cancer using computed tomography (CT) scans, employing Deep Learning (DL) strategies, specifically Enhanced Convolutional Neural Networks (CNNs), to enable rapid and accurate image analysis. This research designed and developed pre-trained models, including ConvNeXtSmall, VGG16, ResNet50, InceptionV3, and EfficientNetB0, to classify lung cancer. The dataset was divided into four classes, consisting of 338 images of adenocarcinoma, 187 images of large cell carcinoma, 260 images of squamous cell carcinoma, and 215 normal images. Notably, The Enhanced CNN model achieved an unprecedented testing accuracy of 100 %, outperforming all other models, which included ConvNeXt at 87 %, VGG16 at 99 %, ResNet50 at 94.5 %, InceptionV3 at 76.9 %, and EfficientNetB0 at 97.9 %. The study of this research is considered the first one that hits 100 % testing accuracy with an Enhanced CNN, demonstrating significant advancements in lung cancer detection through the application of sophisticated image enhancement techniques and innovative model architectures. This highlights the potential of Enhanced CNN models in transforming lung cancer diagnostics and emphasizes the importance of integrating advanced image processing techniques into clinical practice.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100188"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Features and eigenspectral densities analyses for machine learning and classification of severities in chronic obstructive pulmonary diseases","authors":"Timothy Albiges,&nbsp;Zoheir Sabeur,&nbsp;Banafshe Arbab-Zavar","doi":"10.1016/j.ibmed.2025.100217","DOIUrl":"10.1016/j.ibmed.2025.100217","url":null,"abstract":"<div><div>Chronic Obstructive Pulmonary Disease (COPD) has been presenting highly significant global health challenges for many decades. Equally, it is important to slow down this disease's ever-increasingly challenging impact on hospital patient loads. It has become necessary, if not critical, to capitalise on existing knowledge of advanced artificial intelligence to achieve the early detection of COPD and advance personalised care of COPD patients from their homes. The use of machine learning and reaching out on the classification of the multiple types of COPD severities effectively and at progressively acceptable levels of confidence is of paramount importance. Indeed, this capability will feed into highly effective personalised care of COPD patients from their homes while significantly improving their quality of life.</div><div>Auscultation lung sound analysis has emerged as a valuable, non-invasive, and cost-effective remote diagnostic tool of the future for respiratory conditions such as COPD. This research paper introduces a novel machine learning-based approach for classifying multiple COPD severities through the analysis of lung sound data streams. Leveraging two open datasets with diverse acoustic characteristics and clinical manifestations, the research study involves the transformation and decomposition of lung sound data matrices into their eigenspace representation in order to capture key features for machine learning and detection. Early eigenvalue spectra analyses were also performed to discover their distinct manifestations under the multiple established COPD severities. This has led us into projecting our experimental data matrices into their eigenspace with the use of the manifested data features prior to the machine learning process. This was followed by various methods of machine classification of COPD severities successfully. Support Vector Classifiers, Logistic Regression, Random Forests and Naive Bayes Classifiers were deployed. Systematic classifier performance metrics were also adopted; they showed early promising classification accuracies beyond 75 % for distinguishing COPD severities.</div><div>This research benchmark contributes to computer-aided medical diagnosis and supports the integration of auscultation lung sound analyses into COPD assessment protocols for individualised patient care and treatment. Future work involves the acquisition of larger volumes of lung sound data while also exploring multi-modal sensing of COPD patients for heterogeneous data fusion to advance COPD severity classification performance.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100217"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting patient no-shows using machine learning: A comprehensive review and future research agenda","authors":"Khaled M. Toffaha ,&nbsp;Mecit Can Emre Simsekler ,&nbsp;Mohammed Atif Omar ,&nbsp;Imad ElKebbi","doi":"10.1016/j.ibmed.2025.100229","DOIUrl":"10.1016/j.ibmed.2025.100229","url":null,"abstract":"<div><div>Patient no-shows for scheduled medical appointments pose significant challenges to healthcare systems, resulting in wasted resources, increased costs, and disrupted continuity of care. This comprehensive review examines state-of-the-art machine learning (ML) approaches for predicting patient no-shows in outpatient settings, analyzing 52 publications from 2010 to 2025.</div><div>The study reveals significant advancements in the field, with Logistic Regression (LR) as the most commonly used model in 68% of the studies. Tree-based models, ensemble methods, and deep learning techniques have gained traction in recent years, reflecting the field’s evolution. The best-performing models achieved Area Under the Curve (AUC) scores between 0.75 and 0.95, with accuracy ranging from 52% to 99.44%. Methodologically, researchers addressed common challenges such as class imbalance using various sampling techniques and employed a wide range of feature selection methods to improve model efficiency. The review also highlighted the importance of considering temporal factors and the context-dependent nature of no-show behavior across different healthcare settings.</div><div>Using the ITPOSMO framework (Information, Technology, Processes, Objectives, Staffing, Management, and Other Resources), the study identified several gaps in current ML approaches. Key challenges include data quality and completeness, model interpretability, and integration with existing healthcare systems. Future research directions include improving data collection methods, incorporating organizational factors, ensuring ethical implementation, and developing standardized approaches for handling data imbalance. The review also suggests exploring new data sources, utilizing ML algorithms to analyze patient behavior patterns, and using transfer learning techniques to adapt models across different healthcare facilities.</div><div>By addressing these challenges, healthcare providers can leverage ML to improve resource allocation, enhance patient care quality, and advance predictive analytics in healthcare. This comprehensive review underscores the potential of ML in predicting no-shows while acknowledging the complexities and challenges in its practical implementation.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100229"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid vision transformer and Xception model for reliable CT-based ovarian neoplasms diagnosis","authors":"Eman Hussein Alshdaifat ,&nbsp;Hasan Gharaibeh ,&nbsp;Amer Mahmoud Sindiani ,&nbsp;Rola Madain ,&nbsp;Asma'a Mohammad Al-Mnayyis ,&nbsp;Hamad Yahia Abu Mhanna ,&nbsp;Rawan Eimad Almahmoud ,&nbsp;Hanan Fawaz Akhdar ,&nbsp;Mohammad Amin ,&nbsp;Ahmad Nasayreh ,&nbsp;Raneem Hamad","doi":"10.1016/j.ibmed.2025.100227","DOIUrl":"10.1016/j.ibmed.2025.100227","url":null,"abstract":"<div><div>Ovarian cancer is a major global health concern, characterized by high mortality rates and a lack of accurate diagnostic methods. Rapid and accurate detection of ovarian cancer is essential to improve patient outcomes and formulate appropriate treatment protocols. Medical imaging methods are essential for identifying ovarian cancer; however, achieving accurate diagnosis remains a challenge. This paper presents a robust methodology for ovarian cancer detection, including the identification and classification of benign and malignant tumors, using the Xception_ViT model. This hybrid approach was chosen because it combines the advantages of traditional CNN-based models (such as Xception) with the capabilities of modern Transformers-based models (such as ViT). This combination allows the model to take advantage of Xception, which extracts features from images. The Vision Transformer (ViT) model is then used to identify connections between diverse visual elements, enhancing the model's understanding of complex components. A Multi-Layer Perceptron (MLP) layer is finally integrated with the proposed model for image classification. The effectiveness of the model is evaluated using three computed tomography (CT) image datasets from King Abdullah University Hospital (KAUH) in Jordan. The first dataset consists of the ovarian cancer computed tomography dataset (KAUH-OCCTD), the second is the benign ovarian tumors dataset (KAUH-BOTD), and the third is the malignant ovarian tumors dataset (KAUH-MOTD). The three datasets collected from 500 women are characterized by their diversity in ovarian tumor classification and are the first of their kind collected in Jordan. The proposed model Xception_ViT achieved an accuracy of 98.09 % in identifying ovarian cancer on the KAUH-OCCTD dataset, and an accuracy of 96.05 % and 98.73 % on the KAUH-BOTD and KAUH-MOTD datasets, respectively, in distinguishing between benign and malignant ovarian tumors. The proposed model outperformed the pre-trained models on all three datasets. The results demonstrate that the proposed model can classify ovarian tumors. This method could also greatly enhance the efficiency of novice radiologists in evaluating ovarian malignancies and assist gynecologists in providing improved treatment alternatives for these individuals.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100227"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can artificial intelligence help physicians using diaphragmatic ultrasound?","authors":"Tianjie Zhang ,&nbsp;Changchun Li ,&nbsp;Dongwei Xu ,&nbsp;Yan Liu ,&nbsp;Qi Zhang ,&nbsp;Ye Song","doi":"10.1016/j.ibmed.2025.100202","DOIUrl":"10.1016/j.ibmed.2025.100202","url":null,"abstract":"<div><h3>Purpose</h3><div>We investigated the role of artificially intelligent architecture based on deep learning radiomics (DLR) in analyzing M-mode and B-mode ultrasound videos of the diaphragm for diaphragmatic ultrasound.</div></div><div><h3>Methods</h3><div>A total of 196 subjects underwent pulmonary function and ultrasonic examination of the diaphragm. All diaphragmatic ultrasound videos were collected by experienced sonographers as the entire dataset used in this study. The experiment was partitioned into two parts. First, the diaphragm images (including M-mode and B-mode) of 157 subjects were input into the artificial intelligence architecture by the AI team. Second, the test set comprised 39 subjects, each equipped with three mobility images and three thickness images. We applied the proposed parameter calculation method to this set. The method entails segmenting the images, extracting the diaphragmatic motion and thickness variation curves from the segmentation results, and subsequently analyzing these curves to acquire the target parameters. Concurrently, we documented the time taken for each measurement. In parallel, three medical professionals performed analogue measurements. We analysed the accuracy and consistency of the artificial intelligence measurements.</div></div><div><h3>Results</h3><div>The study included a total of 196 subjects. The optimal segmentation model achieved dice scores of 73.51 % and 80.76 % on the test sets of mobility images and thickness images, respectively. Our method yielded results similar to those obtained by senior sonographers and demonstrated a high level of consistency with all three medical professionals, particularly the senior sonographer, in the measurements of diaphragm excursion (DE), diaphragm contraction duration (DCD), and diaphragmatic thickness at the end of inspiration (DTei). Meanwhile, our proposed method exhibited the highest level of time efficiency. The average duration for measuring the mobility images was 1.49s and for thickness images was 0.68s, compared to critical care physicians (8.23s, 15.89s), junior sonographers (6.14s, 9.69s), and senior sonographers (4.48s,6 0.77s).</div></div><div><h3>Conclusions</h3><div>Our study suggests that artificial intelligence can assist physicians in obtaining accurate diaphragmatic ultrasound data and reducing interobserver variability. Additionally, it could also improve time efficiency in this process.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100202"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence and patient care: Perspectives of audiologists and speech-language pathologists","authors":"Komal Aggarwal ,&nbsp;Rohit Ravi ,&nbsp;Krishna Yerraguntla","doi":"10.1016/j.ibmed.2025.100214","DOIUrl":"10.1016/j.ibmed.2025.100214","url":null,"abstract":"<div><h3>Background</h3><div>Artificial Intelligence has been implemented across various fields, including healthcare, where it has significantly advanced patient care in recent years. The present study aimed to explore the perspectives of audiologists and speech-language pathologists (ASLPs) toward AI in patient care.</div></div><div><h3>Methods</h3><div>The study employed a cross-sectional design with a convenience sampling method. The questionnaire included 27 questions consisting of demographic details and perspectives towards AI in audiology and speech language pathology services. Descriptive statistics were performed to analyze the data.</div></div><div><h3>Results</h3><div>Ninety-five ASLPs participated in the study, working across different work settings and with a mean age of 28.34 years, ranging between 18 and 47 years. Almost 50 % of participants reported AI tools can be helpful in diagnosis and planning the treatment. About One-fourth (25 %) believed that AI could help in rehabilitation. Few of participants (14.8 %) reported that AI may replace audiology and speech-language pathology services. ChatGPT was the most used platform by ASLPs in their practice. The ASLP clinicians believed AI would revolutionise ASLP practice without alarming effects on their employability.</div></div><div><h3>Conclusion</h3><div>The findings suggest that while AI has potential in ASLP practice, there is still a need for greater understanding and adoption of the technology.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100214"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143173632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic glioma segmentation based on efficient U-net model using MRI images","authors":"Yessine Amri ,&nbsp;Amine Ben Slama ,&nbsp;Zouhair Mbarki ,&nbsp;Ridha Selmi ,&nbsp;Hedi Trabelsi","doi":"10.1016/j.ibmed.2025.100216","DOIUrl":"10.1016/j.ibmed.2025.100216","url":null,"abstract":"<div><div>Gliomas are among the most aggressive and challenging brain tumors to diagnose and treat. Accurate segmentation of glioma regions in Magnetic Resonance Imaging (MRI) is essential for early diagnosis and effective treatment planning. This study proposes an optimized U-Net model tailored for glioma segmentation, addressing key challenges such as boundary delineation, computational efficiency, and generalizability. The proposed model integrates streamlined encoder-decoder pathways and optimized skip connections, achieving precise segmentation while reducing computational complexity. The model was validated on two datasets: TCGA-TCIA, containing 110 patients, and the multi-modal BraTS 2021 dataset. Comparative evaluations were conducted against state-of-the-art methods, including Attention U-Net, Trans-U-Net, DeepLabV3+, and 3D U-Net, using metrics such as Dice Coefficient, Intersection over Union (IoU), Hausdorff Distance (HD), and Structural Similarity Index (SSIM). The proposed U-Net achieved the highest performance across all metrics, with a Dice score of 92.54 %, IoU of 90.42 %, HD of 4.12 mm, and SSIM of 0.962 on the TCGA-TCIA dataset. On the BraTS dataset, it achieved comparable results, with a Dice score of 91.32 % and an IoU of 89.56 %. In contrast, other methods, such as Attention U-Net and DeepLabV3+, showed lower Dice scores of 85.62 % and 84.10 %, respectively, and higher HD values, indicating inferior boundary delineation. Additionally, the proposed model demonstrated computational efficiency, processing images in 1.5 s on average, compared to 5.0 s for Attention U-Net and 9.0 s for Trans-U-Net. These results underscore the potential of the optimized U-Net as a robust, accurate, and efficient tool for glioma segmentation. Future work will focus on clinical validation and extending the model to include automated glioma grading, further enhancing its applicability in medical imaging workflows.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100216"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing tuberculosis screening: A tailored CNN approach for accurate chest X-ray analysis and practical clinical integration","authors":"K.K. Mujeeb Rahman,&nbsp;Sedra Zulaikha,&nbsp;Banan Dhafer,&nbsp;Rawan Ahmed","doi":"10.1016/j.ibmed.2024.100196","DOIUrl":"10.1016/j.ibmed.2024.100196","url":null,"abstract":"<div><div>Pulmonary tuberculosis (PTB) is a chronic infectious disease claiming approximately 1.5 million lives annually, emphasizing the need for timely diagnosis to improve survival and limit its spread. Chest X-rays are effective for identifying TB-related lung abnormalities, often before symptoms arise, making early detection crucial. Our project enhances PTB screening by leveraging a CNN model trained on 12,848 images from reliable open-access datasets. The system achieves 99.72 % accuracy in binary classification (normal vs. abnormal) and 99.61 % in distinguishing healthy, TB, and non-TB cases, outperforming existing solutions. This ML-driven tool enables swift, cost-effective, and precise PTB detection, ensuring targeted treatment and addressing medicolegal needs through reliable and accountable diagnostics.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100196"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Skin cancer detection using deep machine learning techniques","authors":"Olusoji Akinrinade,&nbsp;Chunglin Du","doi":"10.1016/j.ibmed.2024.100191","DOIUrl":"10.1016/j.ibmed.2024.100191","url":null,"abstract":"<div><div>Technological advancements have allowed people to have unfettered access to the internet from anywhere in the world. However, there is still little access to healthcare in rural and remote areas. This study highlights the potential of deep learning techniques in improving the early detection of skin cancer, a condition affecting millions globally. By addressing the challenges of class imbalance and dataset limitations, this research presents a model that can be integrated into digital health platforms, potentially saving lives by enabling earlier diagnosis and intervention, especially in underserved regions. The study also suggest using deep learning and few-shot learning when using machine learning techniques for skin cancer diagnosis. This study utilized a novel approach the use of raw images for training and test images for test data. These input images were then pre-processed using a deep model to identify and predict subsequent outputs using the model. In addition, the effect of the Convolutional Neural Network (CNN) effect in predicting accuracy using a skin lesion's texture to differentiate between benign and malignant lesions in the body was also examined using retrieved image elements from skin photos that were significant to skin cancer identification. The study focuses on using deep learning techniques to improve the detection of skin cancer from dermoscopic images. Deep learning a top-tier method for classifying skin lesions, was applied to create an end-to-end algorithm that could identify skin cancer more accurately. A variety of deep learning backbones were utilized, addressing the challenge of class imbalance in large datasets and seeking ways to boost performance even when only small datasets are available. To overcome these obstacles, the research leveraged transfer learning, data augmentation, and Generative Adversarial Networks (GANs). It further explored different sampling techniques and loss functions that could be effective for imbalanced datasets. The study also involved a comparison between ensemble models and hybrid models to determine which was more effective for the early detection of skin cancer. The paper concluded with a discussion of the challenges faced in the early detection of skin cancer, suggesting that while progress has been made, there are still significant hurdles to overcome.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of resource-efficient YOLO models for rapid and accurate recognition of intestinal parasitic eggs in stool microscopy","authors":"Kotteswaran Venkatesan ,&nbsp;Muthunayagam Muthulakshmi ,&nbsp;Balaji Prasanalakshmi ,&nbsp;Elangovan Karthickeien ,&nbsp;Harshini Pabbisetty ,&nbsp;Rahayu Syarifah Bahiyah","doi":"10.1016/j.ibmed.2025.100212","DOIUrl":"10.1016/j.ibmed.2025.100212","url":null,"abstract":"<div><div>Faster and reliable recognition of the specific species of intestinal parasite eggs in stool microscopic images is required for targeted and quick intervention of soil transmitted helminths (STH) disease. The main objective of the proposed work is to identify the effective light weight basic yolo models among the recent compact yolo variants such as yolov5n, yolov5s, yolov7, yolov7-tiny, yolov8n, yolov8s, yolov10n and yolov10s, that could assist in rapid and accurate recognition of 11 parasite species egg. The real time performance of the compact yolo models have been analyzed in embedded platforms: Raspberry Pi 4, Intel upSquared with the Neural Compute Stick 2 and Jetson Nano. Finally, Gradient-weighted class activation mapping (Grad-CAM) has been used as an explainable AI (XAI) visualization method to elucidate the egg detection performance of the proposed models. Yolov7-tiny achieved the overall highest mean Average Precision (mAP) score of 98.7 %. On contrary, yolov10n yielded highest recall and F1 score of 100 % and 98.6 %. On other hand, yolov8n took least inference time with processing speed of 55 frames per second with Jetson Nano. Notably, the proposed framework demonstrates superior performance in detection of egg classes - Enterobius vermicularis, Hookworm egg, Opisthorchis viverrine, Trichuris trichiura, and Taenia spp. which is a significant outcome of the current research. Further, Grad-CAM depicts the discriminative power of unique features in parasite eggs. Thus, this study demonstrates the effectiveness, compactness and inference latency analysis of basic compact yolo variants in learning the specific patterns, texture and shape of parasitic egg species, thereby potentially enhancing the diagnostic accuracy of STH.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100212"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}