Pub Date : 2025-10-27DOI: 10.1016/j.slast.2025.100360
Haoyang Liu , Qiurong Xie
The integration of artificial intelligence (AI) into rehabilitation science is revolutionizing traditional therapeutic models, offering innovative solutions that enhance the precision, efficiency, and accessibility of rehabilitation services. This review explores the diverse applications of AI in rehabilitation, focusing on key technologies such as machine learning, deep learning, computer vision, natural language processing, and robotics. A key innovation is the proposed AI-empowered rehabilitation model, which transforms fragmented processes into an interactive, adaptive system with real-time assessment during interventions. AI-driven advancements in impairment assessment, intervention planning and delivery, post-discharge care, and patient education are driving a shift from experience-driven to data-model-driven rehabilitation systems. Notable AI-driven applications include AI-powered exoskeletons for motor rehabilitation (e.g., in stroke recovery), NLP-driven cognitive therapy, and tele-rehabilitation platforms that enable remote monitoring and adaptive interventions. Despite these advancements, challenges remain, including data limitations, ethical concerns, regulatory requirements, and clinical integration barriers. Addressing these challenges requires interdisciplinary collaboration to ensure AI's responsible and effective deployment in rehabilitation. This review highlights the transformative potential of AI in rehabilitation and emphasizes the need for continued research and validation to optimize patient outcomes and accessibility.
{"title":"Applications of artificial intelligence in rehabilitation: technological innovation and transformation of clinical practice","authors":"Haoyang Liu , Qiurong Xie","doi":"10.1016/j.slast.2025.100360","DOIUrl":"10.1016/j.slast.2025.100360","url":null,"abstract":"<div><div>The integration of artificial intelligence (AI) into rehabilitation science is revolutionizing traditional therapeutic models, offering innovative solutions that enhance the precision, efficiency, and accessibility of rehabilitation services. This review explores the diverse applications of AI in rehabilitation, focusing on key technologies such as machine learning, deep learning, computer vision, natural language processing, and robotics. A key innovation is the proposed AI-empowered rehabilitation model, which transforms fragmented processes into an interactive, adaptive system with real-time assessment during interventions. AI-driven advancements in impairment assessment, intervention planning and delivery, post-discharge care, and patient education are driving a shift from experience-driven to data-model-driven rehabilitation systems. Notable AI-driven applications include AI-powered exoskeletons for motor rehabilitation (e.g., in stroke recovery), NLP-driven cognitive therapy, and tele-rehabilitation platforms that enable remote monitoring and adaptive interventions. Despite these advancements, challenges remain, including data limitations, ethical concerns, regulatory requirements, and clinical integration barriers. Addressing these challenges requires interdisciplinary collaboration to ensure AI's responsible and effective deployment in rehabilitation. This review highlights the transformative potential of AI in rehabilitation and emphasizes the need for continued research and validation to optimize patient outcomes and accessibility.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100360"},"PeriodicalIF":3.7,"publicationDate":"2025-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145402667","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 : 2025-10-25DOI: 10.1016/j.slast.2025.100358
Ande Jiao , Xin Zhang , Lili Wang , Yan Wang , Gang Xu , Yanping Huo
Left main coronary artery bifurcation disease is a treatment challenge in the field of coronary heart disease, characterized by high risk, poor prognosis, poor long-term efficacy of drug therapy, and high mortality rate. Although traditional interventional treatment strategies such as single stent and double stent procedures are widely used, the high rate of restenosis of the left circumflex branch (LCX) opening after the placement of the main stent remains a major problem. Thermal infrared imaging can monitor tissue blood flow perfusion and metabolic status in real-time and non invasively, providing a new evaluation method for coronary intervention therapy. The aim of this study is to explore the application value of thermal infrared imaging in the treatment of left main coronary bifurcation lesions with drug balloon (DCB), evaluate its effectiveness and safety in optimizing treatment parameters, reducing restenosis rate, and minimizing adverse cardiac events, and compare it with traditional double stent strategy. All patients in this article underwent preoperative and postoperative thermal infrared imaging to monitor changes in vascular wall temperature and blood flow perfusion. Using a high-sensitivity infrared thermal imager, real-time imaging and postoperative follow-up imaging are used to analyze drug release, vascular response, and long-term efficacy. The main outcome measures include immediate postoperative angiography results, incidence of major adverse cardiac events (MACE) within 1 year after surgery, intravascular ultrasound (IVUS) parameters, and thermal infrared imaging features. The results showed that the drug balloon group was significantly better than the double stent group in reducing the rate of left circumflex branch restenosis, late lumen loss (LLL), and MACE (P < 0.05). Thermal infrared imaging shows that the temperature changes of the blood vessel wall during drug balloon dilation are related to good treatment response, and the blood flow perfusion and metabolic status of the drug balloon group are better during postoperative follow-up. The thermal infrared imaging features are significantly correlated with vascular angiography and IVUS results, and can effectively predict vascular restenosis and adverse events.
{"title":"Clinical study on drug balloon therapy for left main coronary bifurcation lesions based on thermal infrared imaging","authors":"Ande Jiao , Xin Zhang , Lili Wang , Yan Wang , Gang Xu , Yanping Huo","doi":"10.1016/j.slast.2025.100358","DOIUrl":"10.1016/j.slast.2025.100358","url":null,"abstract":"<div><div>Left main coronary artery bifurcation disease is a treatment challenge in the field of coronary heart disease, characterized by high risk, poor prognosis, poor long-term efficacy of drug therapy, and high mortality rate. Although traditional interventional treatment strategies such as single stent and double stent procedures are widely used, the high rate of restenosis of the left circumflex branch (LCX) opening after the placement of the main stent remains a major problem. Thermal infrared imaging can monitor tissue blood flow perfusion and metabolic status in real-time and non invasively, providing a new evaluation method for coronary intervention therapy. The aim of this study is to explore the application value of thermal infrared imaging in the treatment of left main coronary bifurcation lesions with drug balloon (DCB), evaluate its effectiveness and safety in optimizing treatment parameters, reducing restenosis rate, and minimizing adverse cardiac events, and compare it with traditional double stent strategy. All patients in this article underwent preoperative and postoperative thermal infrared imaging to monitor changes in vascular wall temperature and blood flow perfusion. Using a high-sensitivity infrared thermal imager, real-time imaging and postoperative follow-up imaging are used to analyze drug release, vascular response, and long-term efficacy. The main outcome measures include immediate postoperative angiography results, incidence of major adverse cardiac events (MACE) within 1 year after surgery, intravascular ultrasound (IVUS) parameters, and thermal infrared imaging features. The results showed that the drug balloon group was significantly better than the double stent group in reducing the rate of left circumflex branch restenosis, late lumen loss (LLL), and MACE (<em>P</em> < 0.05). Thermal infrared imaging shows that the temperature changes of the blood vessel wall during drug balloon dilation are related to good treatment response, and the blood flow perfusion and metabolic status of the drug balloon group are better during postoperative follow-up. The thermal infrared imaging features are significantly correlated with vascular angiography and IVUS results, and can effectively predict vascular restenosis and adverse events.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100358"},"PeriodicalIF":3.7,"publicationDate":"2025-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416988","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 : 2025-10-01Epub Date: 2025-08-05DOI: 10.1016/j.slast.2025.100335
Rodrigo Moreno, Jonas Jensen, Shahbaz Tareq Bandesha, Simone Peters, Andres Faina, Kasper Stoy
Liquid-liquid extraction (LLE) is an essential operation in many laboratory experiments. However, most automatic LLE devices concentrate on detecting the liquid-liquid interface at one moment in the process, usually at separation, and pay little attention to the state of the liquids as they settle. In this paper, we present an LLE device with a moving optical sensor and light source that move along a vessel instead of the mixture moving relative to the sensor. Analyzing the patterns of light intensity with explainable automatic detection algorithms, the interface can be detected at different positions in the vessel with an error below 2 mm and monitored during the settling process. The device is tested using a mixture of clear oil and water and two extraction steps in a battery interface material synthesis process. Results show that the setup is able to detect interfaces at different positions along the vessel, even with changes in diameter. By monitoring the settling process, we also found that the biggest change in the signal detected occurs around the liquid-liquid interface position, and we also use this information to corroborate it. The recording of sensor measurements at different positions over time can be used to detect different properties of the liquids, which improves control over the process and could also alleviate reproducibility problems in areas of chemistry in which it is costly to repeat procedures.
{"title":"Movable optical sensor for automatic detection and monitoring of liquid-liquid interfaces.","authors":"Rodrigo Moreno, Jonas Jensen, Shahbaz Tareq Bandesha, Simone Peters, Andres Faina, Kasper Stoy","doi":"10.1016/j.slast.2025.100335","DOIUrl":"10.1016/j.slast.2025.100335","url":null,"abstract":"<p><p>Liquid-liquid extraction (LLE) is an essential operation in many laboratory experiments. However, most automatic LLE devices concentrate on detecting the liquid-liquid interface at one moment in the process, usually at separation, and pay little attention to the state of the liquids as they settle. In this paper, we present an LLE device with a moving optical sensor and light source that move along a vessel instead of the mixture moving relative to the sensor. Analyzing the patterns of light intensity with explainable automatic detection algorithms, the interface can be detected at different positions in the vessel with an error below 2 mm and monitored during the settling process. The device is tested using a mixture of clear oil and water and two extraction steps in a battery interface material synthesis process. Results show that the setup is able to detect interfaces at different positions along the vessel, even with changes in diameter. By monitoring the settling process, we also found that the biggest change in the signal detected occurs around the liquid-liquid interface position, and we also use this information to corroborate it. The recording of sensor measurements at different positions over time can be used to detect different properties of the liquids, which improves control over the process and could also alleviate reproducibility problems in areas of chemistry in which it is costly to repeat procedures.</p>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":" ","pages":"100335"},"PeriodicalIF":3.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144776907","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}
Polycystic Ovary Syndrome (PCOS) patients often have ovarian microcirculatory disorders. Traditional color Doppler imaging of microvascular is not sensitive enough and is prone to missed detection or artifact interference. This study is based on a high-frequency probe combined with SMI (Superb Microvascular Imaging) and ultrasound contrast imaging to achieve high signal-to-noise ratio acquisition and dynamic quantification of low-speed blood flow in microvascular, filling the gap in existing technology. This study sets low-pass filtering and low PRF (Pulse Repetition Frequency) to enhance the detection of low-speed flow signals in microvascular. SMI and CEUS (Contrast-Enhanced Ultrasound) sequences are collected in sequence, and the time points are calibrated synchronously on the same section to achieve multimodal image fusion. The ovarian area is semi-automatically segmented based on the U-Net model, and the ROI (Region of Interest) containing the vascular structure is extracted. The vascular density, average diameter, and number of branches are calculated using self-developed image analysis software, and the feature vector is derived. The CEUS time-intensity curve is fitted with a double exponential, and dynamic perfusion parameters such as peak time and perfusion half-life are extracted for microcirculation evaluation and hemodynamic analysis. The experiment shows that in the 10 ovarian ROIs analyzed, the vascular density ranges from 5.43 % to 8.45 %; the average diameter is 5.88 to 6.52 pixels; the branch number consistency difference rate is less than 3 %. The perfusion half-life is distributed between 21.8 and 25.1 s, and the peak time of the PCOS group is delayed by 0.5 s compared with the normal group, indicating that there are significant differences in their microvascular structure and perfusion function.
{"title":"Evaluation of ovarian microvascular structure in PCOS patients based on high-resolution ultrasound imaging technology","authors":"Xianyi Chen , Guoxu Lv , Jian Lv , Ruoyu Wang , Jinyi Zhu , Hongying Kuang","doi":"10.1016/j.slast.2025.100356","DOIUrl":"10.1016/j.slast.2025.100356","url":null,"abstract":"<div><div>Polycystic Ovary Syndrome (PCOS) patients often have ovarian microcirculatory disorders. Traditional color Doppler imaging of microvascular is not sensitive enough and is prone to missed detection or artifact interference. This study is based on a high-frequency probe combined with SMI (Superb Microvascular Imaging) and ultrasound contrast imaging to achieve high signal-to-noise ratio acquisition and dynamic quantification of low-speed blood flow in microvascular, filling the gap in existing technology. This study sets low-pass filtering and low PRF (Pulse Repetition Frequency) to enhance the detection of low-speed flow signals in microvascular. SMI and CEUS (Contrast-Enhanced Ultrasound) sequences are collected in sequence, and the time points are calibrated synchronously on the same section to achieve multimodal image fusion. The ovarian area is semi-automatically segmented based on the U-Net model, and the ROI (Region of Interest) containing the vascular structure is extracted. The vascular density, average diameter, and number of branches are calculated using self-developed image analysis software, and the feature vector is derived. The CEUS time-intensity curve is fitted with a double exponential, and dynamic perfusion parameters such as peak time and perfusion half-life are extracted for microcirculation evaluation and hemodynamic analysis. The experiment shows that in the 10 ovarian ROIs analyzed, the vascular density ranges from 5.43 % to 8.45 %; the average diameter is 5.88 to 6.52 pixels; the branch number consistency difference rate is less than 3 %. The perfusion half-life is distributed between 21.8 and 25.1 s, and the peak time of the PCOS group is delayed by 0.5 s compared with the normal group, indicating that there are significant differences in their microvascular structure and perfusion function.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100356"},"PeriodicalIF":3.7,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214448","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 : 2025-09-29DOI: 10.1016/j.slast.2025.100357
Qing Wang , Lina Sun , Wei Meng , Chen Chen
Early detection of juvenile clinical deterioration in acute care settings remains a significant problem in modern healthcare. This paper presents an AI-powered predictive analytics platform that combines transcriptome biomarker signals with structured vital signs, laboratory data, and unstructured clinical notes to improve early warning capabilities. The system uses ClinicalBERT to extract insights from clinical narratives, XGBoost to analyze tabular clinical information, and long short-term memory (LSTM) networks to simulate temporal dynamics. A meta-classifier combines multimodal data to produce real-time risk ratings for clinical deterioration. The performance evaluation utilizing five-fold cross-validation showed great accuracy, with an AUROC of 0.91, AUPRC of 0.83, and an average early warning lead time of 5.6 hours. Predictive markers included higher lactate levels, heart rate patterns, SpO₂ variability, and transcriptome signals indicating systemic inflammatory activation. Ablation investigations proved the importance of multimodal data fusion in increasing prediction robustness. The suggested strategy provides a scalable, interpretable, and high-performing hospital integration system that enables biomarker-informed, precision-based pediatric intervention options.
{"title":"AI-driven transcriptomic biomarker discovery for early identification of pediatric deterioration in Acute Care","authors":"Qing Wang , Lina Sun , Wei Meng , Chen Chen","doi":"10.1016/j.slast.2025.100357","DOIUrl":"10.1016/j.slast.2025.100357","url":null,"abstract":"<div><div>Early detection of juvenile clinical deterioration in acute care settings remains a significant problem in modern healthcare. This paper presents an AI-powered predictive analytics platform that combines transcriptome biomarker signals with structured vital signs, laboratory data, and unstructured clinical notes to improve early warning capabilities. The system uses ClinicalBERT to extract insights from clinical narratives, XGBoost to analyze tabular clinical information, and long short-term memory (LSTM) networks to simulate temporal dynamics. A meta-classifier combines multimodal data to produce real-time risk ratings for clinical deterioration. The performance evaluation utilizing five-fold cross-validation showed great accuracy, with an AUROC of 0.91, AUPRC of 0.83, and an average early warning lead time of 5.6 hours. Predictive markers included higher lactate levels, heart rate patterns, SpO₂ variability, and transcriptome signals indicating systemic inflammatory activation. Ablation investigations proved the importance of multimodal data fusion in increasing prediction robustness. The suggested strategy provides a scalable, interpretable, and high-performing hospital integration system that enables biomarker-informed, precision-based pediatric intervention options.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100357"},"PeriodicalIF":3.7,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208410","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 : 2025-09-22DOI: 10.1016/j.slast.2025.100355
R. Berenstein , V. Bloch , A. Beery , M.R. Prusty , J. Awwad , O. Amir-Segev , S. Miterani , M. Barak , G. Lidor , E. Fridman
To overcome a critical bottleneck in plant biotechnology workflows, a semiautomated system RoboSeed was developed to extract mature embryos from cereal grains such as barley. In contrast to the commonly used manual extraction, the robot employs a precision-controlled pressing rod which applies mechanical force along an optimal trajectory and angle to detach intact embryos. A custom image-processing pipeline determines grain orientation and morphology, enabling precise rod alignment at the optimal force application point. Validation experiments using two barley cultivars (Noga and Golden Promise) and soaking duration of 10 and 20 h revealed optimal force application point relative location in the range 0.5–0.6, achieving maximum extraction success rates of 56.2 % (Noga) and 36 % (GP) after 20 h soaking. RoboSeed operated with a median cycle time of 20.9 s per extraction, translating to 37.2 s per successful embryo, compared to 27.9 s with expert manual extraction. While current throughput is lower than conventional methods, RoboSeed offers significant advantages in consistency, reduced reliance on operator skill, and potential for scaling. Future improvements include full automation of grain singulation, robotic arms for post-extraction handling, and expanded testing across additional genotypes. RoboSeed’s modular design provides a robust foundation for scalable, high-throughput embryo extraction, with potential to accelerate cereal transformation, gene mapping studies, and tissue culture-based research.
{"title":"The RoboSeed facilitates automated extraction of cereal mature embryos","authors":"R. Berenstein , V. Bloch , A. Beery , M.R. Prusty , J. Awwad , O. Amir-Segev , S. Miterani , M. Barak , G. Lidor , E. Fridman","doi":"10.1016/j.slast.2025.100355","DOIUrl":"10.1016/j.slast.2025.100355","url":null,"abstract":"<div><div>To overcome a critical bottleneck in plant biotechnology workflows, a semiautomated system RoboSeed was developed to extract mature embryos from cereal grains such as barley. In contrast to the commonly used manual extraction, the robot employs a precision-controlled pressing rod which applies mechanical force along an optimal trajectory and angle to detach intact embryos. A custom image-processing pipeline determines grain orientation and morphology, enabling precise rod alignment at the optimal force application point. Validation experiments using two barley cultivars (Noga and Golden Promise) and soaking duration of 10 and 20 h revealed optimal force application point relative location in the range 0.5–0.6, achieving maximum extraction success rates of 56.2 % (Noga) and 36 % (GP) after 20 h soaking. RoboSeed operated with a median cycle time of 20.9 s per extraction, translating to 37.2 s per successful embryo, compared to 27.9 s with expert manual extraction. While current throughput is lower than conventional methods, RoboSeed offers significant advantages in consistency, reduced reliance on operator skill, and potential for scaling. Future improvements include full automation of grain singulation, robotic arms for post-extraction handling, and expanded testing across additional genotypes. RoboSeed’s modular design provides a robust foundation for scalable, high-throughput embryo extraction, with potential to accelerate cereal transformation, gene mapping studies, and tissue culture-based research.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100355"},"PeriodicalIF":3.7,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145139404","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 : 2025-09-19DOI: 10.1016/j.slast.2025.100349
Yujiao Zhang , Zijiao Yang , Shuhua Huang , Sujiao Sun , Zhuxian Liang
In the evaluation of acupuncture effects in traditional Chinese medicine (TCM), the unclear interpretation of microscopic mechanisms and the difficulty in verifying acupoint specificity due to insufficient resolution of MRI (Magnetic Resonance Imaging) are the main reasons for the difficulty. This paper adopts 7T ultra-high field MRI combined with dynamic ASL (arterial spin labeling) technology, taking advantage of its high spatial resolution and quantitative blood perfusion imaging, to achieve dynamic visualization of microcirculation at acupuncture points in patients with ulcerative colitis. Ulcerative colitis is an ideal site to verify the feasibility of this method because its lesion site is clear and easy to correspond with the body surface acupoint. This paper establishes a high-resolution imaging protocol based on 7T magnetic resonance imaging, adopts 0.5mm spatial resolution, and optimizes scanning parameters to adapt to the microstructural imaging requirements of the acupoint area. This paper introduces pCASL (pseudo-continuous arterial spin labeling) technology, sets the labeling duration and perfusion delay time, captures the changes in perfusion volume before and after acupuncture over time, and obtains a dynamic perfusion sequence. This paper adopts umbilical moxibustion therapy, selects specific meridian acupoints, sets a standard acupuncture stimulation scheme (needle insertion depth, frequency, and needle retention time), and simultaneously performs MRI scanning to achieve real-time acupuncture imaging acquisition. The acquired multi-time point images can be rigidly registered and mapped with standard templates, the blood flow intensity change curve of the acupuncture-related area can be extracted, and the time-perfusion function can be constructed to analyze the local response pattern. The experimental results show that the ΔCBF (Delta Cerebral Blood Flow) of 7T-ASL at Shenque, Tianshu and Zhongwan are 0.15, 0.12 and 0.18 respectively, and it has high sensitivity in capturing tiny blood flow changes under sub-millimeter resolution. The SNR (Signal-to-Noise Ratio) at Shenque, Tianshu and Zhongwan are 22, 25 and 24 respectively, and the CNR (Contrast-to-Noise Ratio) is 6.2, 6.5 and 6.7 respectively, which has significant advantages in the spatial identification of sensitive areas of neural regulation and the identification of perfusion response. The average rising rate, peak time and recovery time in all acupoints were 2.44%/s, 7.2s and 11.5s respectively, and the acupuncture effect took effect faster in local areas.
{"title":"Application of high-resolution magnetic resonance imaging (MRI) in the evaluation of acupuncture effects in traditional Chinese medicine","authors":"Yujiao Zhang , Zijiao Yang , Shuhua Huang , Sujiao Sun , Zhuxian Liang","doi":"10.1016/j.slast.2025.100349","DOIUrl":"10.1016/j.slast.2025.100349","url":null,"abstract":"<div><div>In the evaluation of acupuncture effects in traditional Chinese medicine (TCM), the unclear interpretation of microscopic mechanisms and the difficulty in verifying acupoint specificity due to insufficient resolution of MRI (Magnetic Resonance Imaging) are the main reasons for the difficulty. This paper adopts 7T ultra-high field MRI combined with dynamic ASL (arterial spin labeling) technology, taking advantage of its high spatial resolution and quantitative blood perfusion imaging, to achieve dynamic visualization of microcirculation at acupuncture points in patients with ulcerative colitis. Ulcerative colitis is an ideal site to verify the feasibility of this method because its lesion site is clear and easy to correspond with the body surface acupoint. This paper establishes a high-resolution imaging protocol based on 7T magnetic resonance imaging, adopts 0.5mm spatial resolution, and optimizes scanning parameters to adapt to the microstructural imaging requirements of the acupoint area. This paper introduces pCASL (pseudo-continuous arterial spin labeling) technology, sets the labeling duration and perfusion delay time, captures the changes in perfusion volume before and after acupuncture over time, and obtains a dynamic perfusion sequence. This paper adopts umbilical moxibustion therapy, selects specific meridian acupoints, sets a standard acupuncture stimulation scheme (needle insertion depth, frequency, and needle retention time), and simultaneously performs MRI scanning to achieve real-time acupuncture imaging acquisition. The acquired multi-time point images can be rigidly registered and mapped with standard templates, the blood flow intensity change curve of the acupuncture-related area can be extracted, and the time-perfusion function can be constructed to analyze the local response pattern. The experimental results show that the ΔCBF (Delta Cerebral Blood Flow) of 7T-ASL at Shenque, Tianshu and Zhongwan are 0.15, 0.12 and 0.18 respectively, and it has high sensitivity in capturing tiny blood flow changes under sub-millimeter resolution. The SNR (Signal-to-Noise Ratio) at Shenque, Tianshu and Zhongwan are 22, 25 and 24 respectively, and the CNR (Contrast-to-Noise Ratio) is 6.2, 6.5 and 6.7 respectively, which has significant advantages in the spatial identification of sensitive areas of neural regulation and the identification of perfusion response. The average rising rate, peak time and recovery time in all acupoints were 2.44%/s, 7.2s and 11.5s respectively, and the acupuncture effect took effect faster in local areas.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100349"},"PeriodicalIF":3.7,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145114945","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 : 2025-09-19DOI: 10.1016/j.slast.2025.100350
Wenping Li , Zhiming Gu
In the study of bone density changes and sports injury rehabilitation, traditional image processing technology lacks accuracy in analysis, rehabilitation assessment methods lack quantitative and systematic analysis, and interdisciplinary comprehensive evaluation is lacking. This paper constructs an innovative cognitive assessment model that combines bone density changes, sports injury rehabilitation, and high-resolution medical image analysis. It uses high-resolution CT (Computed Tomography) images and X-ray images to extract bone density data. It uses image processing technology to remove noise, enhance, and standardize, providing accurate bone density values for subsequent input. GCN (Graph Convolutional Network) can be used to automatically identify and classify images of sports injury sites, extract features of the injured area, record and analyze the patient's physical activities during the rehabilitation stage, and evaluate the recovery process of sports injuries in real time. Combining bone density data with sports injury imaging features, XGBoost (Extreme Gradient Boosting) is used to build a cognitive evaluation model, which conducts a comprehensive analysis of multi-dimensional data and provides personalized rehabilitation evaluation. It can integrate technologies from fields such as medicine, engineering, and computer science to establish an interdisciplinary comprehensive evaluation system, achieve multi-angle and multi-dimensional analysis, and ensure the comprehensiveness and accuracy of the model. The experimental results show that the MAE (Mean Absolute Error) of the GCN in this paper is 0.131 in 10 different injury sites, and the average MSE (Mean Squared Error) is about 0.032, which has higher image analysis accuracy. The average accuracy and R² of XGBoost in six different samples are about 0.87 and 0.91, respectively, and the prediction effect of the cognitive evaluation model is apparent.
{"title":"Cognitive evaluation model and high-resolution medical images in sports injury rehabilitation under bone density changes","authors":"Wenping Li , Zhiming Gu","doi":"10.1016/j.slast.2025.100350","DOIUrl":"10.1016/j.slast.2025.100350","url":null,"abstract":"<div><div>In the study of bone density changes and sports injury rehabilitation, traditional image processing technology lacks accuracy in analysis, rehabilitation assessment methods lack quantitative and systematic analysis, and interdisciplinary comprehensive evaluation is lacking. This paper constructs an innovative cognitive assessment model that combines bone density changes, sports injury rehabilitation, and high-resolution medical image analysis. It uses high-resolution CT (Computed Tomography) images and X-ray images to extract bone density data. It uses image processing technology to remove noise, enhance, and standardize, providing accurate bone density values for subsequent input. GCN (Graph Convolutional Network) can be used to automatically identify and classify images of sports injury sites, extract features of the injured area, record and analyze the patient's physical activities during the rehabilitation stage, and evaluate the recovery process of sports injuries in real time. Combining bone density data with sports injury imaging features, XGBoost (Extreme Gradient Boosting) is used to build a cognitive evaluation model, which conducts a comprehensive analysis of multi-dimensional data and provides personalized rehabilitation evaluation. It can integrate technologies from fields such as medicine, engineering, and computer science to establish an interdisciplinary comprehensive evaluation system, achieve multi-angle and multi-dimensional analysis, and ensure the comprehensiveness and accuracy of the model. The experimental results show that the MAE (Mean Absolute Error) of the GCN in this paper is 0.131 in 10 different injury sites, and the average MSE (Mean Squared Error) is about 0.032, which has higher image analysis accuracy. The average accuracy and R² of XGBoost in six different samples are about 0.87 and 0.91, respectively, and the prediction effect of the cognitive evaluation model is apparent.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100350"},"PeriodicalIF":3.7,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145114994","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 : 2025-09-19DOI: 10.1016/j.slast.2025.100352
Jingjing Yang , Jinyan Chen , Lanying Shen
Objective
To screen serum markers for secondary lower extremity angiopathy (LEAD) in patients with type 2 diabetes mellitus (T2DM) and construct a nomogram prediction model accordingly.
Methods
The clinical data of 200 T2DM patients admitted to the hospital from December 2022 to October 2024 were retrospectively collected. It was also divided into modeling group (n = 160) and internal validation group (n = 40) in a 4:1 ratio by using the leave-out method. As the external validation group, clinical data from 100 T2DM patients who were admitted to other hospitals within the same time period were also gathered. Combined with previous reports of collecting serum marker data related to LEAD secondary to T2DM, key serum markers were screened using LASSO regression. Moreover, multifactorial analysis helped to clarify independent risk factors, and a nomogram prediction model was built and tested for accuracy.
Results
The incidence of LEAD in 200 T2DM patients in the hospital was 21.00 % (42/200). A total of 14 variables were screened by LASSO regression analysis. After multifactorial analysis, it was found that disease duration, history of alcohol consumption, mean platelet volume, fasting blood glucose, fibrinogen, high-sensitivity C-reactive protein, insulin-like growth factor 1, nucleotide binding oligomerization domain like receptor protein 3 were independent risk factors for LEAD secondary to T2DM.The results of model validation showed AUCs of 0.971, 0.900, and 0.959 for the modeling cohort, internal validation cohort, and external validation cohort, respectively. The Hosmer-Lemeshow test was χ2=6.607, 7.962, and 6.585 (p > 0.05). Positive net benefits were obtained by intervening with patients using a nomogram model within the high-risk threshold of 0 to 0.9.
Conclusion
In this study, eight risk factors associated with LEAD secondary to T2DM are screened by LASSO regression and multifactorial analysis, and a nomogram prediction model is constructed.
{"title":"Construction of a nomogram prediction model for screening of serum markers for lower extremity vasculopathy secondary to type 2 diabetes mellitus","authors":"Jingjing Yang , Jinyan Chen , Lanying Shen","doi":"10.1016/j.slast.2025.100352","DOIUrl":"10.1016/j.slast.2025.100352","url":null,"abstract":"<div><h3>Objective</h3><div>To screen serum markers for secondary lower extremity angiopathy (LEAD) in patients with type 2 diabetes mellitus (T2DM) and construct a nomogram prediction model accordingly.</div></div><div><h3>Methods</h3><div>The clinical data of 200 T2DM patients admitted to the hospital from December 2022 to October 2024 were retrospectively collected. It was also divided into modeling group (<em>n</em> = 160) and internal validation group (<em>n</em> = 40) in a 4:1 ratio by using the leave-out method. As the external validation group, clinical data from 100 T2DM patients who were admitted to other hospitals within the same time period were also gathered. Combined with previous reports of collecting serum marker data related to LEAD secondary to T2DM, key serum markers were screened using LASSO regression. Moreover, multifactorial analysis helped to clarify independent risk factors, and a nomogram prediction model was built and tested for accuracy.</div></div><div><h3>Results</h3><div>The incidence of LEAD in 200 T2DM patients in the hospital was 21.00 % (42/200). A total of 14 variables were screened by LASSO regression analysis. After multifactorial analysis, it was found that disease duration, history of alcohol consumption, mean platelet volume, fasting blood glucose, fibrinogen, high-sensitivity C-reactive protein, insulin-like growth factor 1, nucleotide binding oligomerization domain like receptor protein 3 were independent risk factors for LEAD secondary to T2DM.The results of model validation showed AUCs of 0.971, 0.900, and 0.959 for the modeling cohort, internal validation cohort, and external validation cohort, respectively. The Hosmer-Lemeshow test was <em>χ<sup>2</sup></em>=6.607, 7.962, and 6.585 (<em>p</em> > 0.05). Positive net benefits were obtained by intervening with patients using a nomogram model within the high-risk threshold of 0 to 0.9.</div></div><div><h3>Conclusion</h3><div>In this study, eight risk factors associated with LEAD secondary to T2DM are screened by LASSO regression and multifactorial analysis, and a nomogram prediction model is constructed.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100352"},"PeriodicalIF":3.7,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145115029","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 : 2025-09-19DOI: 10.1016/j.slast.2025.100353
Jonas Austerjost , Elias Knöchelmann , Thomas Kruse , Janina Kilian , Bastian Quaas , Michael W. Olszowy
Conventionally, the initialization of new prototypes and concepts in laboratory automation and life science software applications has required close collaboration between hardware and software experts, as well as lab personnel such as biologists, chemists, biotechnologists, or process engineers. This setup - still common today - often means that the ideas and requests of lab personnel must be translated into software applications by software developers, which frequently results in long development times. Low-Code Development Platforms (LCDPs) seek to address this challenge by providing a way to accelerate application development by reducing dependence on traditional software development methods, empowering lab personnel to build applications without writing extensive amount of code. By offering a visual, drag-and-drop interface, lab personnel can actively participate in the software development process. This helps democratize application creation and can lead to the quick setup of software solutions tailored to laboratory needs.
This study demonstrates the implementation of four different use cases in a bioprocessing laboratory environment using an open-source LCDP and commercially available upstream and downstream equipment. The LCDP facilitated the integration and control of different device types with varying communication protocols also enabling dashboarding, monitoring and data processing capabilities. This methodology highlights the suitability of LCDPs for rapidly prototyping and evaluating laboratory and bioprocess automation pipelines, potentially expediting the development of biotechnological production processes and products. All developed components are made available through a publicly accessible repository, facilitating reuse and further development by the scientific community.
{"title":"Low code, high impact: Application of low-code platforms to enable and democratize the development of laboratory digitalization and automation applications","authors":"Jonas Austerjost , Elias Knöchelmann , Thomas Kruse , Janina Kilian , Bastian Quaas , Michael W. Olszowy","doi":"10.1016/j.slast.2025.100353","DOIUrl":"10.1016/j.slast.2025.100353","url":null,"abstract":"<div><div>Conventionally, the initialization of new prototypes and concepts in laboratory automation and life science software applications has required close collaboration between hardware and software experts, as well as lab personnel such as biologists, chemists, biotechnologists, or process engineers. This setup - still common today - often means that the ideas and requests of lab personnel must be translated into software applications by software developers, which frequently results in long development times. Low-Code Development Platforms (LCDPs) seek to address this challenge by providing a way to accelerate application development by reducing dependence on traditional software development methods, empowering lab personnel to build applications without writing extensive amount of code. By offering a visual, drag-and-drop interface, lab personnel can actively participate in the software development process. This helps democratize application creation and can lead to the quick setup of software solutions tailored to laboratory needs.</div><div>This study demonstrates the implementation of four different use cases in a bioprocessing laboratory environment using an open-source LCDP and commercially available upstream and downstream equipment. The LCDP facilitated the integration and control of different device types with varying communication protocols also enabling dashboarding, monitoring and data processing capabilities. This methodology highlights the suitability of LCDPs for rapidly prototyping and evaluating laboratory and bioprocess automation pipelines, potentially expediting the development of biotechnological production processes and products. All developed components are made available through a publicly accessible repository, facilitating reuse and further development by the scientific community.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"35 ","pages":"Article 100353"},"PeriodicalIF":3.7,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145114986","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