1
|
Steele SR, Ranjan R, Sharrer K, Tsukuda S, Good C. Computer-Simulated Virtual Image Datasets to Train Machine Learning Models for Non-Invasive Fish Detection in Recirculating Aquaculture. SENSORS (BASEL, SWITZERLAND) 2024; 24:5816. [PMID: 39275727 PMCID: PMC11398205 DOI: 10.3390/s24175816] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/29/2024] [Revised: 08/28/2024] [Accepted: 09/02/2024] [Indexed: 09/16/2024]
Abstract
Artificial Intelligence (AI) and Machine Learning (ML) can assist producers to better manage recirculating aquaculture systems (RASs). ML is a data-intensive process, and model performance primarily depends on the quality of training data. Relatively higher fish density and water turbidity in intensive RAS culture produce major challenges in acquiring high-quality underwater image data. Additionally, the manual image annotation involved in model training can be subjective, time-consuming, and labor-intensive. Therefore, the presented study aimed to simulate fish schooling behavior for RAS conditions and investigate the feasibility of using computer-simulated virtual images to train a robust fish detection model. Additionally, to expedite the model training and automate the virtual image annotation, a process flow was developed. The 'virtual model' performances were compared with models trained on real-world images and combinations of real and virtual images. The results of the study indicate that the virtual model trained solely with computer-simulated images could not perform satisfactorily (mAP = 62.8%, F1 score = 0.61) to detect fish in a real RAS environment; however, replacing a small number of the virtual images with real images in the training dataset significantly improved the model's performance. The M6 mixed model trained with 630 virtual and 70 real images (virtual-to-real image ratio: 90:10) achieved mAP and F1 scores of 91.8% and 0.87, respectively. Furthermore, the training time cost for the M6 model was seven times shorter than that for the 'real model'. Overall, the virtual simulation approach exhibited great promise in rapidly training a reliable fish detection model for RAS operations.
Collapse
Affiliation(s)
- Sullivan R Steele
- The Conservation Fund Freshwater Institute, Shepherdstown, WV 25443, USA
| | - Rakesh Ranjan
- The Conservation Fund Freshwater Institute, Shepherdstown, WV 25443, USA
| | - Kata Sharrer
- The Conservation Fund Freshwater Institute, Shepherdstown, WV 25443, USA
| | - Scott Tsukuda
- The Conservation Fund Freshwater Institute, Shepherdstown, WV 25443, USA
| | - Christopher Good
- The Conservation Fund Freshwater Institute, Shepherdstown, WV 25443, USA
| |
Collapse
|
2
|
Pothugunta K, Liu X, Susarla A, Padman R. Assessing inclusion and representativeness on digital platforms for health education: Evidence from YouTube. J Biomed Inform 2024; 157:104669. [PMID: 38880237 DOI: 10.1016/j.jbi.2024.104669] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Revised: 05/22/2024] [Accepted: 06/05/2024] [Indexed: 06/18/2024]
Abstract
BACKGROUND Studies confirm that significant biases exist in online recommendation platforms, exacerbating pre-existing disparities and leading to less-than-optimal outcomes for underrepresented demographics. We study issues of bias in inclusion and representativeness in the context of healthcare information disseminated via videos on the YouTube social media platform, a widely used online channel for multi-media rich information. With one in three US adults using the Internet to learn about a health concern, it is critical to assess inclusivity and representativeness regarding how health information is disseminated by digital platforms such as YouTube. METHODS Leveraging methods from fair machine learning (ML), natural language processing and voice and facial recognition methods, we examine inclusivity and representativeness of video content presenters using a large corpus of videos and their metadata on a chronic condition (diabetes) extracted from the YouTube platform. Regression models are used to determine whether presenter demographics impact video popularity, measured by the video's average daily view count. A video that generates a higher view count is considered to be more popular. RESULTS The voice and facial recognition methods predicted the gender and race of the presenter with reasonable success. Gender is predicted through voice recognition (accuracy = 78%, AUC = 76%), while the gender and race predictions use facial recognition (accuracy = 93%, AUC = 92% and accuracy = 82%, AUC = 80%, respectively). The gender of the presenter is more significant for video views only when the face of the presenter is not visible while videos with male presenters with no face visibility have a positive relationship with view counts. Furthermore, videos with white and male presenters have a positive influence on view counts while videos with female and non - white group have high view counts. CONCLUSION Presenters' demographics do have an influence on average daily view count of videos viewed on social media platforms as shown by advanced voice and facial recognition algorithms used for assessing inclusion and representativeness of the video content. Future research can explore short videos and those at the channel level because popularity of the channel name and the number of videos associated with that channel do have an influence on view counts.
Collapse
Affiliation(s)
| | - Xiao Liu
- Arizona State University, Tempe, AZ, USA
| | | | - Rema Padman
- Carnegie Mellon University, Pittsburgh, PA, USA
| |
Collapse
|
3
|
Dong R, Shiraiwa A, Pawasut A, Sreechun K, Hayashi T. Diagnosis of Citrus Greening Using Artificial Intelligence: A Faster Region-Based Convolutional Neural Network Approach with Convolution Block Attention Module-Integrated VGGNet and ResNet Models. PLANTS (BASEL, SWITZERLAND) 2024; 13:1631. [PMID: 38931063 PMCID: PMC11207255 DOI: 10.3390/plants13121631] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 05/31/2024] [Accepted: 06/07/2024] [Indexed: 06/28/2024]
Abstract
The vector-transmitted Citrus Greening (CG) disease, also called Huanglongbing, is one of the most destructive diseases of citrus. Since no measures for directly controlling this disease are available at present, current disease management integrates several measures, such as vector control, the use of disease-free trees, the removal of diseased trees, etc. The most essential issue in integrated management is how CG-infected trees can be detected efficiently. For CG detection, digital image analyses using deep learning algorithms have attracted much interest from both researchers and growers. Models using transfer learning with the Faster R-CNN architecture were constructed and compared with two pre-trained Convolutional Neural Network (CNN) models, VGGNet and ResNet. Their efficiency was examined by integrating their feature extraction capabilities into the Convolution Block Attention Module (CBAM) to create VGGNet+CBAM and ResNet+CBAM variants. ResNet models performed best. Moreover, the integration of CBAM notably improved CG disease detection precision and the overall performance of the models. Efficient models with transfer learning using Faster R-CNN were loaded on web applications to facilitate access for real-time diagnosis by farmers via the deployment of in-field images. The practical ability of the applications to detect CG disease is discussed.
Collapse
Affiliation(s)
- Ruihao Dong
- Faculty of Informatics, Kansai University, Takatsuki 569-1095, Osaka, Japan;
| | - Aya Shiraiwa
- Electrical Engineering and Computer Science, Tottori University, Tottori 680-8552, Tottori, Japan;
| | - Achara Pawasut
- Royal Project Foundation, 910 Moo 3, T. Maehia, Muang, Chiang Mai 50200, Thailand; (A.P.); (K.S.)
| | - Kesaraporn Sreechun
- Royal Project Foundation, 910 Moo 3, T. Maehia, Muang, Chiang Mai 50200, Thailand; (A.P.); (K.S.)
| | - Takefumi Hayashi
- Faculty of Informatics, Kansai University, Takatsuki 569-1095, Osaka, Japan;
| |
Collapse
|
4
|
Debelee TG. Skin Lesion Classification and Detection Using Machine Learning Techniques: A Systematic Review. Diagnostics (Basel) 2023; 13:3147. [PMID: 37835889 PMCID: PMC10572538 DOI: 10.3390/diagnostics13193147] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Revised: 09/22/2023] [Accepted: 09/24/2023] [Indexed: 10/15/2023] Open
Abstract
Skin lesions are essential for the early detection and management of a number of dermatological disorders. Learning-based methods for skin lesion analysis have drawn much attention lately because of improvements in computer vision and machine learning techniques. A review of the most-recent methods for skin lesion classification, segmentation, and detection is presented in this survey paper. The significance of skin lesion analysis in healthcare and the difficulties of physical inspection are discussed in this survey paper. The review of state-of-the-art papers targeting skin lesion classification is then covered in depth with the goal of correctly identifying the type of skin lesion from dermoscopic, macroscopic, and other lesion image formats. The contribution and limitations of various techniques used in the selected study papers, including deep learning architectures and conventional machine learning methods, are examined. The survey then looks into study papers focused on skin lesion segmentation and detection techniques that aimed to identify the precise borders of skin lesions and classify them accordingly. These techniques make it easier to conduct subsequent analyses and allow for precise measurements and quantitative evaluations. The survey paper discusses well-known segmentation algorithms, including deep-learning-based, graph-based, and region-based ones. The difficulties, datasets, and evaluation metrics particular to skin lesion segmentation are also discussed. Throughout the survey, notable datasets, benchmark challenges, and evaluation metrics relevant to skin lesion analysis are highlighted, providing a comprehensive overview of the field. The paper concludes with a summary of the major trends, challenges, and potential future directions in skin lesion classification, segmentation, and detection, aiming to inspire further advancements in this critical domain of dermatological research.
Collapse
Affiliation(s)
- Taye Girma Debelee
- Ethiopian Artificial Intelligence Institute, Addis Ababa 40782, Ethiopia;
- Department of Electrical and Computer Engineering, Addis Ababa Science and Technology University, Addis Ababa 16417, Ethiopia
| |
Collapse
|
5
|
Shafi I, Fatima A, Afzal H, Díez IDLT, Lipari V, Breñosa J, Ashraf I. A Comprehensive Review of Recent Advances in Artificial Intelligence for Dentistry E-Health. Diagnostics (Basel) 2023; 13:2196. [PMID: 37443594 DOI: 10.3390/diagnostics13132196] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Revised: 06/14/2023] [Accepted: 06/23/2023] [Indexed: 07/15/2023] Open
Abstract
Artificial intelligence has made substantial progress in medicine. Automated dental imaging interpretation is one of the most prolific areas of research using AI. X-ray and infrared imaging systems have enabled dental clinicians to identify dental diseases since the 1950s. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, and machine- and deep-learning models for dental disease diagnoses using X-ray and near-infrared imagery. Despite the notable development of AI in dentistry, certain factors affect the performance of the proposed approaches, including limited data availability, imbalanced classes, and lack of transparency and interpretability. Hence, it is of utmost importance for the research community to formulate suitable approaches, considering the existing challenges and leveraging findings from the existing studies. Based on an extensive literature review, this survey provides a brief overview of X-ray and near-infrared imaging systems. Additionally, a comprehensive insight into challenges faced by researchers in the dental domain has been brought forth in this survey. The article further offers an amalgamative assessment of both performances and methods evaluated on public benchmarks and concludes with ethical considerations and future research avenues.
Collapse
Affiliation(s)
- Imran Shafi
- College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad 44000, Pakistan
| | - Anum Fatima
- National Centre for Robotics, National University of Sciences and Technology (NUST), Islamabad 44000, Pakistan
| | - Hammad Afzal
- Military College of Signals (MCS), National University of Sciences and Technology (NUST), Islamabad 44000, Pakistan
| | - Isabel de la Torre Díez
- Department of Signal Theory and Communications and Telematic Engineering, University of Valladolid, Paseo de Belén 15, 47011 Valladolid, Spain
| | - Vivian Lipari
- Research Unit in Food Technologies, Agro-Food Industries and Nutrition, Universidad Europea del Atlántico, Isabel Torres 21, 39011 Santander, Spain
- Research Unit in Food Technologies, Agro-Food Industries and Nutrition, Universidad Internacional Iberoamericana, Campeche 24560, Mexico
- Research Unit in Food Technologies, Agro-Food Industries and Nutrition, Fundación Universitaria Internacional de Colombia, Bogotá 111311, Colombia
| | - Jose Breñosa
- Research Unit in Food Technologies, Agro-Food Industries and Nutrition, Universidad Europea del Atlántico, Isabel Torres 21, 39011 Santander, Spain
- Universidade Internacional do Cuanza, Cuito EN250, Bié, Angola
- Research Unit in Food Technologies, Agro-Food Industries and Nutrition, Universidad Internacional Iberoamericana Arecibo, Puerto Rico, PR 00613, USA
| | - Imran Ashraf
- Department of Information and Communication Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea
| |
Collapse
|
6
|
Chung YW, Choi IY. Detection of abnormal extraocular muscles in small datasets of computed tomography images using a three-dimensional variational autoencoder. Sci Rep 2023; 13:1765. [PMID: 36720904 PMCID: PMC9889739 DOI: 10.1038/s41598-023-28082-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2022] [Accepted: 01/12/2023] [Indexed: 02/02/2023] Open
Abstract
We sought to establish an unsupervised algorithm with a three-dimensional (3D) variational autoencoder model (VAE) for the detection of abnormal extraocular muscles in small datasets of orbital computed tomography (CT) images. 334 CT images of normal orbits and 96 of abnormal orbits diagnosed as thyroid eye disease were used for training and validation; 24 normal and 11 abnormal orbits were used for the test. A 3D VAE was developed and trained. All images were preprocessed to emphasize extraocular muscles and to suppress background noise (e.g., high signal intensity from bones). The optimal cut-off value was identified through receiver operating characteristic (ROC) curve analysis. The ability of the model to detect muscles of abnormal size was assessed by visualization. The model achieved a sensitivity of 79.2%, specificity of 72.7%, accuracy of 77.1%, F1-score of 0.667, and AUROC of 0.801. Abnormal CT images correctly identified by the model showed differences in the reconstruction of extraocular muscles. The proposed model showed potential to detect abnormalities in extraocular muscles using a small dataset, similar to the diagnostic approach used by physicians. Unsupervised learning could serve as an alternative detection method for medical imaging studies in which annotation is difficult or impossible to perform.
Collapse
Affiliation(s)
- Yeon Woong Chung
- Department of Ophthalmology and Visual Science, St. Vincent's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.,Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Banpo Dae-Ro 222, Seoul, 06591, Republic of Korea
| | - In Young Choi
- Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Banpo Dae-Ro 222, Seoul, 06591, Republic of Korea.
| |
Collapse
|