1
|
Shahin M, Chen FF, Maghanaki M, Hosseinzadeh A, Zand N, Khodadadi Koodiani H. Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm. SENSORS (BASEL, SWITZERLAND) 2024; 24:3247. [PMID: 38794102 PMCID: PMC11125435 DOI: 10.3390/s24103247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/24/2024] [Revised: 05/11/2024] [Accepted: 05/14/2024] [Indexed: 05/26/2024]
Abstract
Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.
Collapse
Affiliation(s)
- Mohammad Shahin
- Mechanical Engineering Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA; (M.S.); (A.H.)
| | - F. Frank Chen
- Mechanical Engineering Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA; (M.S.); (A.H.)
| | - Mazdak Maghanaki
- Mechanical Engineering Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA; (M.S.); (A.H.)
| | - Ali Hosseinzadeh
- Mechanical Engineering Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA; (M.S.); (A.H.)
| | - Neda Zand
- Computer Science Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA
| | - Hamid Khodadadi Koodiani
- Civil & Environmental Engineering Department, The University of Texas at San Antonio, San Antonio, TX 78249, USA
| |
Collapse
|
2
|
Montoya ID, Volkow ND. IUPHAR Review: New strategies for medications to treat substance use disorders. Pharmacol Res 2024; 200:107078. [PMID: 38246477 PMCID: PMC10922847 DOI: 10.1016/j.phrs.2024.107078] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Revised: 01/11/2024] [Accepted: 01/15/2024] [Indexed: 01/23/2024]
Abstract
Substance use disorders (SUDs) and drug overdose are a public health emergency and safe and effective treatments are urgently needed. Developing new medications to treat them is expensive, time-consuming, and the probability of a compound progressing to clinical trials and obtaining FDA-approval is low. The small number of FDA-approved medications for SUDs reflects the low interest of pharmaceutical companies to invest in this area due to market forces, characteristics of the population (e.g., stigma, and socio-economic and legal disadvantages), and the high bar regulatory agencies set for new medication approval. In consequence, most research on medications is funded by government agencies, such as the National Institute on Drug Abuse (NIDA). Multiple scientific opportunities are emerging that can accelerate the discovery and development of new medications for SUDs. These include fast and efficient tools to screen new molecules, discover new medication targets, use of big data to explore large clinical data sets and artificial intelligence (AI) applications to make predictions, and precision medicine tools to individualize and optimize treatments. This review provides a general description of these new research strategies for the development of medications to treat SUDs with emphasis on the gaps and scientific opportunities. It includes a brief overview of the rising public health toll of SUDs; the justification, challenges, and opportunities to develop new medications; and a discussion of medications and treatment endpoints that are being evaluated with support from NIDA.
Collapse
Affiliation(s)
- Ivan D Montoya
- Division of Therapeutics and Medical Consequences, National Institute on Drug Abuse, 3 White Flint North, North Bethesda, MD 20852, United States.
| | - Nora D Volkow
- National Institute on Drug Abuse, 3 White Flint North, North Bethesda, MD 20852, United States
| |
Collapse
|
3
|
Cay G, Pfeifer VA, Lee M, Rouzi MD, Nunes AS, El-Refaei N, Momin AS, Atique MMU, Mehl MR, Vaziri A, Najafi B. Harnessing Speech-Derived Digital Biomarkers to Detect and Quantify Cognitive Decline Severity in Older Adults. Gerontology 2024; 70:429-438. [PMID: 38219728 PMCID: PMC11001511 DOI: 10.1159/000536250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2023] [Accepted: 01/08/2024] [Indexed: 01/16/2024] Open
Abstract
INTRODUCTION Current cognitive assessments suffer from floor/ceiling and practice effects, poor psychometric performance in mild cases, and repeated assessment effects. This study explores the use of digital speech analysis as an alternative tool for determining cognitive impairment. The study specifically focuses on identifying the digital speech biomarkers associated with cognitive impairment and its severity. METHODS We recruited older adults with varying cognitive health. Their speech data, recorded via a wearable microphone during the reading aloud of a standard passage, were processed to derive digital biomarkers such as timing, pitch, and loudness. Cohen's d effect size highlighted group differences, and correlations were drawn to the Montreal Cognitive Assessment (MoCA). A stepwise approach using a Random Forest model was implemented to distinguish cognitive states using speech data and predict MoCA scores based on highly correlated features. RESULTS The study comprised 59 participants, with 36 demonstrating cognitive impairment and 23 serving as cognitively intact controls. Among all assessed parameters, similarity, as determined by Dynamic Time Warping (DTW), exhibited the most substantial positive correlation (rho = 0.529, p < 0.001), while timing parameters, specifically the ratio of extra words, revealed the strongest negative correlation (rho = -0.441, p < 0.001) with MoCA scores. Optimal discriminative performance was achieved with a combination of four speech parameters: total pause time, speech-to-pause ratio, similarity via DTW, and intelligibility via DTW. Precision and balanced accuracy scores were found to be 88.1 ± 1.2% and 76.3 ± 1.3%, respectively. DISCUSSION Our research proposes that reading-derived speech data facilitates the differentiation between cognitively impaired individuals and cognitively intact, age-matched older adults. Specifically, parameters based on timing and similarity within speech data provide an effective gauge of cognitive impairment severity. These results suggest speech analysis as a viable digital biomarker for early detection and monitoring of cognitive impairment, offering novel approaches in dementia care.
Collapse
Affiliation(s)
- Gozde Cay
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA,
| | - Valeria A Pfeifer
- Department of Psychology, University of Arizona, Tucson, Arizona, USA
| | - Myeounggon Lee
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| | - Mohammad Dehghan Rouzi
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| | | | - Nesreen El-Refaei
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| | - Anmol Salim Momin
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| | - Md Moin Uddin Atique
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| | - Matthias R Mehl
- Department of Psychology, University of Arizona, Tucson, Arizona, USA
| | | | - Bijan Najafi
- Digital Health and Access Center (DiHAC), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas, USA
| |
Collapse
|
4
|
Dehghan Rouzi M, Moshiri B, Khoshnevisan M, Akhaee MA, Jaryani F, Salehi Nasab S, Lee M. Breast Cancer Detection with an Ensemble of Deep Learning Networks Using a Consensus-Adaptive Weighting Method. J Imaging 2023; 9:247. [PMID: 37998094 PMCID: PMC10671922 DOI: 10.3390/jimaging9110247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 10/20/2023] [Accepted: 10/24/2023] [Indexed: 11/25/2023] Open
Abstract
Breast cancer's high mortality rate is often linked to late diagnosis, with mammograms as key but sometimes limited tools in early detection. To enhance diagnostic accuracy and speed, this study introduces a novel computer-aided detection (CAD) ensemble system. This system incorporates advanced deep learning networks-EfficientNet, Xception, MobileNetV2, InceptionV3, and Resnet50-integrated via our innovative consensus-adaptive weighting (CAW) method. This method permits the dynamic adjustment of multiple deep networks, bolstering the system's detection capabilities. Our approach also addresses a major challenge in pixel-level data annotation of faster R-CNNs, highlighted in a prominent previous study. Evaluations on various datasets, including the cropped DDSM (Digital Database for Screening Mammography), DDSM, and INbreast, demonstrated the system's superior performance. In particular, our CAD system showed marked improvement on the cropped DDSM dataset, enhancing detection rates by approximately 1.59% and achieving an accuracy of 95.48%. This innovative system represents a significant advancement in early breast cancer detection, offering the potential for more precise and timely diagnosis, ultimately fostering improved patient outcomes.
Collapse
Affiliation(s)
- Mohammad Dehghan Rouzi
- School of Electrical and computer Engineering, College of Engineering, University of Tehran, Tehran 14174-66191, Iran; (M.D.R.); (B.M.); (M.A.A.)
| | - Behzad Moshiri
- School of Electrical and computer Engineering, College of Engineering, University of Tehran, Tehran 14174-66191, Iran; (M.D.R.); (B.M.); (M.A.A.)
- Department of Electrical and Computer Engineering, University of Waterloo, Ontario, ON N2L 3G1, Canada
| | | | - Mohammad Ali Akhaee
- School of Electrical and computer Engineering, College of Engineering, University of Tehran, Tehran 14174-66191, Iran; (M.D.R.); (B.M.); (M.A.A.)
| | - Farhang Jaryani
- Human Genome Sequencing Center, Baylor College of Medicine, Houston, TX 77030, USA;
| | - Samaneh Salehi Nasab
- Department of Computer Engineering, Lorestan University, Khorramabad 68151-44316, Iran;
| | - Myeounggon Lee
- College of Health Sciences, Dong-A University, Saha-gu, Busan 49315, Republic of Korea
| |
Collapse
|
5
|
Beheshtizadeh N, Gharibshahian M, Bayati M, Maleki R, Strachan H, Doughty S, Tayebi L. Vascular endothelial growth factor (VEGF) delivery approaches in regenerative medicine. Biomed Pharmacother 2023; 166:115301. [PMID: 37562236 DOI: 10.1016/j.biopha.2023.115301] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 07/28/2023] [Accepted: 08/05/2023] [Indexed: 08/12/2023] Open
Abstract
The utilization of growth factors in the process of tissue regeneration has garnered significant interest and has been the subject of extensive research. However, despite the fervent efforts invested in recent clinical trials, a considerable number of these studies have produced outcomes that are deemed unsatisfactory. It is noteworthy that the trials that have yielded the most satisfactory outcomes have exhibited a shared characteristic, namely, the existence of a mechanism for the regulated administration of growth factors. Despite the extensive exploration of drug delivery vehicles and their efficacy in delivering certain growth factors, the development of a reliable predictive approach for the delivery of delicate growth factors like Vascular Endothelial Growth Factor (VEGF) remains elusive. VEGF plays a crucial role in promoting angiogenesis; however, the administration of VEGF demands a meticulous approach as it necessitates precise localization and transportation to a specific target tissue. This process requires prolonged and sustained exposure to a low concentration of VEGF. Inaccurate administration of drugs, either through off-target effects or inadequate delivery, may heighten the risk of adverse reactions and potentially result in tumorigenesis. At present, there is a scarcity of technologies available for the accurate encapsulation of VEGF and its subsequent sustained and controlled release. The objective of this review is to present and assess diverse categories of VEGF administration mechanisms. This paper examines various systems, including polymeric, liposomal, hydrogel, inorganic, polyplexes, and microfluidic, and evaluates the appropriate dosage of VEGF for multiple applications.
Collapse
Affiliation(s)
- Nima Beheshtizadeh
- Department of Tissue Engineering, School of Advanced Technologies in Medicine, Tehran University of Medical Sciences, Iran; Regenerative Medicine group (REMED), Universal Scientific Education and Research Network (USERN), Tehran, Iran.
| | - Maliheh Gharibshahian
- Department of Tissue Engineering, School of Medicine, Shahroud University of Medical Sciences, Shahroud, Iran; Regenerative Medicine group (REMED), Universal Scientific Education and Research Network (USERN), Tehran, Iran
| | - Mohammad Bayati
- Department of Phytochemistry, Medicinal Plants and Drugs Research Institute, Shahid Beheshti University, Tehran, Iran
| | - Reza Maleki
- Department of Chemical Technologies, Iranian Research Organization for Science and Technology (IROST), P.O. Box 33535111, Tehran, Iran.
| | - Hannah Strachan
- Marquette University School of Dentistry, Milwaukee, WI 53233, USA
| | - Sarah Doughty
- Marquette University School of Dentistry, Milwaukee, WI 53233, USA
| | - Lobat Tayebi
- Marquette University School of Dentistry, Milwaukee, WI 53233, USA
| |
Collapse
|