1
|
Pan P, Shao M, He P, Hu L, Zhao S, Huang L, Zhou G, Zhang J. Lightweight cotton diseases real-time detection model for resource-constrained devices in natural environments. FRONTIERS IN PLANT SCIENCE 2024; 15:1383863. [PMID: 38903431 PMCID: PMC11187009 DOI: 10.3389/fpls.2024.1383863] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 05/16/2024] [Indexed: 06/22/2024]
Abstract
Cotton, a vital textile raw material, is intricately linked to people's livelihoods. Throughout the cotton cultivation process, various diseases threaten cotton crops, significantly impacting both cotton quality and yield. Deep learning has emerged as a crucial tool for detecting these diseases. However, deep learning models with high accuracy often come with redundant parameters, making them challenging to deploy on resource-constrained devices. Existing detection models struggle to strike the right balance between accuracy and speed, limiting their utility in this context. This study introduces the CDDLite-YOLO model, an innovation based on the YOLOv8 model, designed for detecting cotton diseases in natural field conditions. The C2f-Faster module replaces the Bottleneck structure in the C2f module within the backbone network, using partial convolution. The neck network adopts Slim-neck structure by replacing the C2f module with the GSConv and VoVGSCSP modules, based on GSConv. In the head, we introduce the MPDIoU loss function, addressing limitations in existing loss functions. Additionally, we designed the PCDetect detection head, integrating the PCD module and replacing some CBS modules with PCDetect. Our experimental results demonstrate the effectiveness of the CDDLite-YOLO model, achieving a remarkable mean average precision (mAP) of 90.6%. With a mere 1.8M parameters, 3.6G FLOPS, and a rapid detection speed of 222.22 FPS, it outperforms other models, showcasing its superiority. It successfully strikes a harmonious balance between detection speed, accuracy, and model size, positioning it as a promising candidate for deployment on an embedded GPU chip without sacrificing performance. Our model serves as a pivotal technical advancement, facilitating timely cotton disease detection and providing valuable insights for the design of detection models for agricultural inspection robots and other resource-constrained agricultural devices.
Collapse
Affiliation(s)
- Pan Pan
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
| | - Mingyue Shao
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
| | - Peitong He
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
| | - Lin Hu
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
| | - Sijian Zhao
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Longyu Huang
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
- Institute of Cotton Research, Chinese Academy of Agricultural Sciences, Anyang, China
| | - Guomin Zhou
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
- Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang, China
| | - Jianhua Zhang
- Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- National Agriculture Science Data Center, Beijing, China
- National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya, China
| |
Collapse
|
2
|
Abbasi EY, Deng Z, Ali Q, Khan A, Shaikh A, Reshan MSA, Sulaiman A, Alshahrani H. A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction. Heliyon 2024; 10:e25369. [PMID: 38352790 PMCID: PMC10862685 DOI: 10.1016/j.heliyon.2024.e25369] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 12/13/2023] [Accepted: 01/25/2024] [Indexed: 02/16/2024] Open
Abstract
In recent years, scientific data on cancer has expanded, providing potential for a better understanding of malignancies and improved tailored care. Advances in Artificial Intelligence (AI) processing power and algorithmic development position Machine Learning (ML) and Deep Learning (DL) as crucial players in predicting Leukemia, a blood cancer, using integrated multi-omics technology. However, realizing these goals demands novel approaches to harness this data deluge. This study introduces a novel Leukemia diagnosis approach, analyzing multi-omics data for accuracy using ML and DL algorithms. ML techniques, including Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR), Gradient Boosting (GB), and DL methods such as Recurrent Neural Networks (RNN) and Feedforward Neural Networks (FNN) are compared. GB achieved 97 % accuracy in ML, while RNN outperformed by achieving 98 % accuracy in DL. This approach filters unclassified data effectively, demonstrating the significance of DL for leukemia prediction. The testing validation was based on 17 different features such as patient age, sex, mutation type, treatment methods, chromosomes, and others. Our study compares ML and DL techniques and chooses the best technique that gives optimum results. The study emphasizes the implications of high-throughput technology in healthcare, offering improved patient care.
Collapse
Affiliation(s)
- Erum Yousef Abbasi
- State Key Laboratory of Wireless Network Positioning and Communication Engineering Integration Research, School of Electronics Engineering, Beijing University of Posts and Telecommunications, Beijing, China
| | - Zhongliang Deng
- State Key Laboratory of Wireless Network Positioning and Communication Engineering Integration Research, School of Electronics Engineering, Beijing University of Posts and Telecommunications, Beijing, China
| | - Qasim Ali
- Department of Software Engineering, Mehran University of Engineering and Technology, Jamshoro, Pakistan
| | - Adil Khan
- State Key Laboratory of Wireless Network Positioning and Communication Engineering Integration Research, School of Electronics Engineering, Beijing University of Posts and Telecommunications, Beijing, China
| | - Asadullah Shaikh
- Department of Information Systems, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia
| | - Mana Saleh Al Reshan
- Department of Information Systems, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia
- Scientific and Engineering Research Centre, Najran University, Najran, 61441, Saudi Arabia
| | - Adel Sulaiman
- Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia
| | - Hani Alshahrani
- Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia
| |
Collapse
|
3
|
Farooq H, Saleem S, Aleem I, Iftikhar A, Sheikh UN, Naveed H. Toward interpretable and generalized mitosis detection in digital pathology using deep learning. Digit Health 2024; 10:20552076241255471. [PMID: 38778869 PMCID: PMC11110526 DOI: 10.1177/20552076241255471] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Accepted: 05/01/2024] [Indexed: 05/25/2024] Open
Abstract
Objective The mitotic activity index is an important prognostic factor in the diagnosis of cancer. The task of mitosis detection is difficult as the nuclei are microscopic in size and partially labeled, and there are many more non-mitotic nuclei compared to mitotic ones. In this paper, we highlight the challenges of current mitosis detection pipelines and propose a method to tackle these challenges. Methods Our proposed methodology is inspired from recent research on deep learning and an extensive analysis on the dataset and training pipeline. We first used the MiDoG'22 dataset for training, validation, and testing. We then tested the methodology without fine-tuning on the TUPAC'16 dataset and on a real-time case from Shaukat Khanum Memorial Cancer Hospital and Research Centre. Results Our methodology has shown promising results both quantitatively and qualitatively. Quantitatively, our methodology achieved an F1-score of 0.87 on the MiDoG'22 dataset and an F1-score of 0.83 on the TUPAC dataset. Qualitatively, our methodology is generalizable and interpretable across various datasets and clinical settings. Conclusion In this paper, we highlight the challenges of current mitosis detection pipelines and propose a method that can accurately predict mitotic nuclei. We illustrate the accuracy, generalizability, and interpretability of our approach across various datasets and clinical settings. Our methodology can speed up the adoption of computer-aided digital pathology in clinical settings.
Collapse
Affiliation(s)
- Hasan Farooq
- Computational Biology Research Lab, National University of Computer & Emerging Sciences, Islamabad, Pakistan
| | - Saira Saleem
- Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Iffat Aleem
- Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Ayesha Iftikhar
- Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Umer Nisar Sheikh
- Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Hammad Naveed
- Computational Biology Research Lab, National University of Computer & Emerging Sciences, Islamabad, Pakistan
| |
Collapse
|
4
|
Yao T, Wang C, Wang X, Li X, Jiang Z, Qi P. Enhancing percutaneous coronary intervention with heuristic path planning and deep-learning-based vascular segmentation. Comput Biol Med 2023; 166:107540. [PMID: 37806060 DOI: 10.1016/j.compbiomed.2023.107540] [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: 07/22/2023] [Revised: 09/21/2023] [Accepted: 09/28/2023] [Indexed: 10/10/2023]
Abstract
Percutaneous coronary intervention (PCI) is a minimally invasive technique for treating vascular diseases. PCI requires precise and real-time visualization and guidance to ensure surgical safety and efficiency. Existing mainstream guiding methods rely on hemodynamic parameters. However, these methods are less intuitive than images and pose some challenges to the decision-making of cardiologists. This paper proposes a novel PCI guiding assistance system by combining a novel vascular segmentation network and a heuristic intervention path planning algorithm, providing cardiologists with clear and visualized information. A dataset of 1077 DSA images from 288 patients is also collected in clinical practice. A Likert Scale is also designed to evaluate system performance in user experiments. Results of user experiments demonstrate that the system can generate satisfactory and reasonable paths for PCI. Our proposed method outperformed the state-of-the-art baselines based on three metrics (Jaccard: 0.4091, F1: 0.5626, Accuracy: 0.9583). The proposed system can effectively assist cardiologists in PCI by providing a clear segmentation of vascular structures and optimal real-time intervention paths, thus demonstrating great potential for robotic PCI autonomy.
Collapse
Affiliation(s)
- Tianliang Yao
- College of Electronics and Information Engineering, Tongji University, Shanghai, 200092, China.
| | - Chengjia Wang
- School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, EH14 4AP, United Kingdom; BHF Centre for Cardiovascular Science,University of Edinburgh, Edinburgh, EH16 4TJ, United Kingdom.
| | - Xinyi Wang
- School of Medicine, Tongji University, Shanghai, 200092, China.
| | - Xiang Li
- Departments of Cardiology and Nursing, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, 200072, China.
| | - Zhaolei Jiang
- Department of Cardiothoracic Surgery, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, 200092, China.
| | - Peng Qi
- College of Electronics and Information Engineering, Tongji University, Shanghai, 200092, China.
| |
Collapse
|
5
|
Bassani D, Brigo A, Andrews-Morger A. Federated Learning in Computational Toxicology: An Industrial Perspective on the Effiris Hackathon. Chem Res Toxicol 2023; 36:1503-1517. [PMID: 37584277 PMCID: PMC10523574 DOI: 10.1021/acs.chemrestox.3c00137] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Indexed: 08/17/2023]
Abstract
In silico approaches have acquired a towering role in pharmaceutical research and development, allowing laboratories all around the world to design, create, and optimize novel molecular entities with unprecedented efficiency. From a toxicological perspective, computational methods have guided the choices of medicinal chemists toward compounds displaying improved safety profiles. Even if the recent advances in the field are significant, many challenges remain active in the on-target and off-target prediction fields. Machine learning methods have shown their ability to identify molecules with safety concerns. However, they strongly depend on the abundance and diversity of data used for their training. Sharing such information among pharmaceutical companies remains extremely limited due to confidentiality reasons, but in this scenario, a recent concept named "federated learning" can help overcome such concerns. Within this framework, it is possible for companies to contribute to the training of common machine learning algorithms, using, but not sharing, their proprietary data. Very recently, Lhasa Limited organized a hackathon involving several industrial partners in order to assess the performance of their federated learning platform, called "Effiris". In this paper, we share our experience as Roche in participating in such an event, evaluating the performance of the federated algorithms and comparing them with those coming from our in-house-only machine learning models. Our aim is to highlight the advantages of federated learning and its intrinsic limitations and also suggest some points for potential improvements in the method.
Collapse
Affiliation(s)
- Davide Bassani
- Pharmaceutical Research &
Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., 4070 Basel, Switzerland
| | - Alessandro Brigo
- Pharmaceutical Research &
Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., 4070 Basel, Switzerland
| | - Andrea Andrews-Morger
- Pharmaceutical Research &
Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., 4070 Basel, Switzerland
| |
Collapse
|
6
|
Lee M. Deep Learning Techniques with Genomic Data in Cancer Prognosis: A Comprehensive Review of the 2021-2023 Literature. BIOLOGY 2023; 12:893. [PMID: 37508326 PMCID: PMC10376033 DOI: 10.3390/biology12070893] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Revised: 06/16/2023] [Accepted: 06/20/2023] [Indexed: 07/30/2023]
Abstract
Deep learning has brought about a significant transformation in machine learning, leading to an array of novel methodologies and consequently broadening its influence. The application of deep learning in various sectors, especially biomedical data analysis, has initiated a period filled with noteworthy scientific developments. This trend has majorly influenced cancer prognosis, where the interpretation of genomic data for survival analysis has become a central research focus. The capacity of deep learning to decode intricate patterns embedded within high-dimensional genomic data has provoked a paradigm shift in our understanding of cancer survival. Given the swift progression in this field, there is an urgent need for a comprehensive review that focuses on the most influential studies from 2021 to 2023. This review, through its careful selection and thorough exploration of dominant trends and methodologies, strives to fulfill this need. The paper aims to enhance our existing understanding of applications of deep learning in cancer survival analysis, while also highlighting promising directions for future research. This paper undertakes aims to enrich our existing grasp of the application of deep learning in cancer survival analysis, while concurrently shedding light on promising directions for future research in this vibrant and rapidly proliferating field.
Collapse
Affiliation(s)
- Minhyeok Lee
- School of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, Republic of Korea
| |
Collapse
|
7
|
Chen Y, Guo Y, Fan Q, Zhang Q, Dong Y. Health-Aware Food Recommendation Based on Knowledge Graph and Multi-Task Learning. Foods 2023; 12:foods12102079. [PMID: 37238897 DOI: 10.3390/foods12102079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 05/09/2023] [Accepted: 05/19/2023] [Indexed: 05/28/2023] Open
Abstract
Current food recommender systems tend to prioritize either the user's dietary preferences or the healthiness of the food, without considering the importance of personalized health requirements. To address this issue, we propose a novel approach to healthy food recommendations that takes into account the user's personalized health requirements, in addition to their dietary preferences. Our work comprises three perspectives. Firstly, we propose a collaborative recipe knowledge graph (CRKG) with millions of triplets, containing user-recipe interactions, recipe-ingredient associations, and other food-related information. Secondly, we define a score-based method for evaluating the healthiness match between recipes and user preferences. Based on these two prior perspectives, we develop a novel health-aware food recommendation model (FKGM) using knowledge graph embedding and multi-task learning. FKGM employs a knowledge-aware attention graph convolutional neural network to capture the semantic associations between users and recipes on the collaborative knowledge graph and learns the user's requirements in both preference and health by fusing the losses of these two learning tasks. We conducted experiments to demonstrate that FKGM outperformed four competing baseline models in integrating users' dietary preferences and personalized health requirements in food recommendations and performed best on the health task.
Collapse
Affiliation(s)
- Yi Chen
- Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China
| | - Yandi Guo
- Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China
| | - Qiuxu Fan
- Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China
| | - Qinghui Zhang
- Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China
| | - Yu Dong
- School of Computer Science, University of Technology Sydney, Sydney, NSW 2008, Australia
| |
Collapse
|
8
|
de León G, Cesbron J, Klein P, Leandri P, Losa M. Novel Methodology to Recover Road Surface Height Maps from Illuminated Scene through Convolutional Neural Networks. SENSORS (BASEL, SWITZERLAND) 2022; 22:6603. [PMID: 36081061 PMCID: PMC9460673 DOI: 10.3390/s22176603] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/20/2022] [Revised: 08/19/2022] [Accepted: 08/24/2022] [Indexed: 06/15/2023]
Abstract
Road surface properties have a major impact on pavement's life service conditions. Nowadays, contactless techniques are widely used to monitor road surfaces due to their portability and high precision. Among the different possibilities, laser profilometers are widely used, even though they have two major drawbacks: spatial information is missed and the cost of the equipment is considerable. The scope of this work is to show the methodology used to develop a fast and low-cost system using images taken with a commercial camera to recover the height information of the road surface using Convolutional Neural Networks. Hence, the dataset was created ad hoc. Based on photometric theory, a closed black-box with four light sources positioned around the surface sample was built. The surface was provided with markers in order to link the ground truth measurements carried out with a laser profilometer and their corresponding intensity values. The proposed network was trained, validated and tested on the created dataset. Three loss functions where studied. The results showed the Binary Cross Entropy loss to be the most performing and the best overall on the reconstruction task. The methodology described in this study shows the feasibility of a low-cost system using commercial cameras based on Artificial Intelligence.
Collapse
Affiliation(s)
- Gonzalo de León
- Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy
- Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Université Gustave Eiffel, CEREMA, F-44344 Bouguenais, France
| | - Julien Cesbron
- Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Université Gustave Eiffel, CEREMA, F-44344 Bouguenais, France
| | - Philippe Klein
- Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Université Gustave Eiffel-Lyon, CEREMA, F-69675 Lyon, France
| | - Pietro Leandri
- Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy
| | - Massimo Losa
- Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy
| |
Collapse
|