1
|
Wu N, Weng S, Xiao Q, Jiang H, Zhao Y, He Y. Rapid and accurate identification of bakanae pathogens carried by rice seeds based on hyperspectral imaging and deep transfer learning. Spectrochim Acta A Mol Biomol Spectrosc 2024; 311:123889. [PMID: 38340442 DOI: 10.1016/j.saa.2024.123889] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Revised: 01/09/2024] [Accepted: 01/10/2024] [Indexed: 02/12/2024]
Abstract
Bakanae disease is a common seed-borne disease of rice. Rapid and accurate detection of bakanae pathogens carried by rice seeds is essential for the health of rice germplasm resources and the safety of rice production. This study aims to propose a general framework for species identification of major bakanae pathogens carried by rice seeds based on hyperspectral imaging and deep transfer learning. Seven varieties of rice seeds and four kinds of bakanae pathogens were analyzed. One-dimensional deep convolution neural networks (DCNNs) were first constructed using complete datasets. They achieved accuracies larger than 96.5% on the testing sets of most datasets, exceeding the conventional SVM and PLS-DA models. Then the developed DCNNs were transferred to detect other complete training sets. Most of the deep transferred models achieved comparable or even better performance than the original DCNNs. Two smaller target training sets were further constructed by randomly selecting spectra from the complete training sets. As the size of the target training sets reduced, the accuracies of all models on the corresponding testing sets also decreased gradually. Visualization analysis were conducted using the t-distribution stochastic neighbor embedding (t-SNE) algorithm and a proposed gradient-weighted activation wavelength (Grad-AW) method. They all showed that deep transfer learning could utilize the representation patterns in the source datasets to improve the target tasks. The overall results indicated that the bakanae pathogens were all identified accurately under our proposed framework. Hyperspectral imaging combined with deep transfer learning provided a new idea for the quality detection of large-scale seeds in modern seed industry.
Collapse
Affiliation(s)
- Na Wu
- School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China
| | - Shizhuang Weng
- National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei, China
| | - Qinlin Xiao
- College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China
| | - Hubiao Jiang
- School of Plant Protection, Anhui Agricultural University, Hefei, China
| | - Yun Zhao
- School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China
| | - Yong He
- College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China.
| |
Collapse
|
2
|
Das Baksi K, Pokhrel V, Pudavar AE, Mande SS, Kuntal BK. BactInt: A domain driven transfer learning approach for extracting inter-bacterial associations from biomedical text. Comput Biol Chem 2024; 109:108012. [PMID: 38198963 DOI: 10.1016/j.compbiolchem.2023.108012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 12/15/2023] [Accepted: 12/30/2023] [Indexed: 01/12/2024]
Abstract
BACKGROUND The healthy as well as dysbiotic state of an ecosystem like human body is known to be influenced not only by the presence of the bacterial groups in it, but also with respect to the associations within themselves. Evidence reported in biomedical text serves as a reliable source for identifying and ascertaining such inter bacterial associations. However, the complexity of the reported text as well as the ever-increasing volume of information necessitates development of methods for automated and accurate extraction of such knowledge. METHODS A BioBERT (biomedical domain specific language model) based information extraction model for bacterial associations is presented that utilizes learning patterns from other publicly available datasets. Additionally, a specialized sentence corpus has been developed to significantly improve the prediction accuracy of the 'transfer learned' model using a fine-tuning approach. RESULTS The final model was seen to outperform all other variations (non-transfer learned and non-fine-tuned models) as well as models trained on BioGPT (a domain trained Generative Pre-trained Transformer). To further demonstrate the utility, a case study was performed using bacterial association network data obtained from experimental studies. CONCLUSION This study attempts to demonstrate the applicability of transfer learning in a niche field of life sciences where understanding of inter bacterial relationships is crucial to obtain meaningful insights in comprehending microbial community structures across different ecosystems. The study further discusses how such a model can be further improved by fine tuning using limited training data. The results presented and the datasets made available are expected to be a valuable addition in the field of medical informatics and bioinformatics.
Collapse
Affiliation(s)
| | - Vatsala Pokhrel
- TCS Research, Tata Consultancy Services Ltd, Pune 411057, India
| | | | | | - Bhusan K Kuntal
- TCS Research, Tata Consultancy Services Ltd, Pune 411057, India.
| |
Collapse
|
3
|
Wang H, Bardizbanian B, Zhu Z, Wang H, Dai C, Clancy EA. Evaluation of generic EMG-Torque models across two Upper-Limb joints. J Electromyogr Kinesiol 2024; 75:102864. [PMID: 38310768 DOI: 10.1016/j.jelekin.2024.102864] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Revised: 11/09/2023] [Accepted: 01/25/2024] [Indexed: 02/06/2024] Open
Abstract
Advanced single-use dynamic EMG-torque models require burdensome subject-specific calibration contractions and have historically been assumed to produce lower error than generic models (i.e., models that are identical across subjects and muscles). To investigate this assumption, we studied generic one degree of freedom (DoF) models derived from the ensemble median of subject-specific models, evaluated across subject, DoF and joint. We used elbow (N = 64) and hand-wrist (N = 9) datasets. Subject-specific elbow models performed statistically better [5.79 ± 1.89 %MVT (maximum voluntary torque) error] than generic elbow models (6.21 ± 1.85 %MVT error). However, there were no statistical differences between subject-specific vs. generic models within each hand-wrist DoF. Next, we evaluated generic models across joints. The best hand-wrist generic model had errors of 6.29 ± 1.85 %MVT when applied to the elbow. The elbow generic model had errors of 7.04 ± 2.29 %MVT when applied to the hand-wrist. The generic elbow model was statistically better in both joints, compared to the generic hand-wrist model. Finally, we tested Butterworth filter models (a simpler generic model), finding no statistical differences between optimum Butterworth and subject-specific models. Overall, generic models simplified EMG-torque training without substantive performance degradation and provided the possibility of transfer learning between joints.
Collapse
Affiliation(s)
- Haopeng Wang
- Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
| | - Berj Bardizbanian
- Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
| | - Ziling Zhu
- Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
| | - He Wang
- Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
| | - Chenyun Dai
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200241, China
| | - Edward A Clancy
- Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA.
| |
Collapse
|
4
|
Ng HW, Guan C. Subject-independent meta-learning framework towards optimal training of EEG-based classifiers. Neural Netw 2024; 172:106108. [PMID: 38219680 DOI: 10.1016/j.neunet.2024.106108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Revised: 11/13/2023] [Accepted: 01/05/2024] [Indexed: 01/16/2024]
Abstract
Advances in deep learning have shown great promise towards the application of performing high-accuracy Electroencephalography (EEG) signal classification in a variety of tasks. However, many EEG-based datasets are often plagued by the issue of high inter-subject signal variability. Robust deep learning models are notoriously difficult to train under such scenarios, often leading to subpar or widely varying performance across subjects under the leave-one-subject-out paradigm. Recently, the model agnostic meta-learning framework was introduced as a way to increase the model's ability to generalize towards new tasks. While the original framework focused on task-based meta-learning, this research aims to show that the meta-learning methodology can be modified towards subject-based signal classification while maintaining the same task objectives and achieve state-of-the-art performance. Namely, we propose the novel implementation of a few/zero-shot subject-independent meta-learning framework towards multi-class inner speech and binary class motor imagery classification. Compared to current subject-adaptive methods which utilize large number of labels from the target, the proposed framework shows its effectiveness in training zero-calibration and few-shot models for subject-independent EEG classification. The proposed few/zero-shot subject-independent meta-learning mechanism performs well on both small and large datasets and achieves robust, generalized performance across subjects. The results obtained shows a significant improvement over the current state-of-the-art, with the binary class motor imagery achieving 88.70% and the accuracy of multi-class inner speech achieving an average of 31.15%. Codes will be made available to public upon publication.
Collapse
Affiliation(s)
- Han Wei Ng
- Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore; AI Singapore, 3 Research Link, 117602, Singapore.
| | - Cuntai Guan
- Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore
| |
Collapse
|
5
|
Yengec-Tasdemir SB, Aydin Z, Akay E, Dogan S, Yilmaz B. An effective colorectal polyp classification for histopathological images based on supervised contrastive learning. Comput Biol Med 2024; 172:108267. [PMID: 38479197 DOI: 10.1016/j.compbiomed.2024.108267] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 03/06/2024] [Accepted: 03/06/2024] [Indexed: 03/26/2024]
Abstract
Early detection of colon adenomatous polyps is pivotal in reducing colon cancer risk. In this context, accurately distinguishing between adenomatous polyp subtypes, especially tubular and tubulovillous, from hyperplastic variants is crucial. This study introduces a cutting-edge computer-aided diagnosis system optimized for this task. Our system employs advanced Supervised Contrastive learning to ensure precise classification of colon histopathology images. Significantly, we have integrated the Big Transfer model, which has gained prominence for its exemplary adaptability to visual tasks in medical imaging. Our novel approach discerns between in-class and out-of-class images, thereby elevating its discriminatory power for polyp subtypes. We validated our system using two datasets: a specially curated one and the publicly accessible UniToPatho dataset. The results reveal that our model markedly surpasses traditional deep convolutional neural networks, registering classification accuracies of 87.1% and 70.3% for the custom and UniToPatho datasets, respectively. Such results emphasize the transformative potential of our model in polyp classification endeavors.
Collapse
Affiliation(s)
- Sena Busra Yengec-Tasdemir
- School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, BT39DT, United Kingdom.
| | - Zafer Aydin
- Department of Electrical and Computer Engineering, Abdullah Gul University, Kayseri, 38080, Turkey; Department of Computer Engineering, Abdullah Gul University, Kayseri, 38080, Turkey
| | - Ebru Akay
- Pathology Clinic, Kayseri City Hospital, Kayseri, 38080, Turkey
| | - Serkan Dogan
- Gastroenterology Clinic, Kayseri City Hospital, Kayseri, 38080, Turkey
| | - Bulent Yilmaz
- Department of Electrical and Computer Engineering, Abdullah Gul University, Kayseri, 38080, Turkey; Department of Electrical Engineering, Gulf University for Science and Technology, Mishref, 40005, Kuwait
| |
Collapse
|
6
|
Mwanga EP, Mchola IS, Makala FE, Mshani IH, Siria DJ, Mwinyi SH, Abbasi S, Seleman G, Mgaya JN, Jiménez MG, Wynne K, Sikulu-Lord MT, Selvaraj P, Okumu FO, Baldini F, Babayan SA. Rapid assessment of the blood-feeding histories of wild-caught malaria mosquitoes using mid-infrared spectroscopy and machine learning. Malar J 2024; 23:86. [PMID: 38532415 DOI: 10.1186/s12936-024-04915-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Accepted: 03/22/2024] [Indexed: 03/28/2024] Open
Abstract
BACKGROUND The degree to which Anopheles mosquitoes prefer biting humans over other vertebrate hosts, i.e. the human blood index (HBI), is a crucial parameter for assessing malaria transmission risk. However, existing techniques for identifying mosquito blood meals are demanding in terms of time and effort, involve costly reagents, and are prone to inaccuracies due to factors such as cross-reactivity with other antigens or partially digested blood meals in the mosquito gut. This study demonstrates the first field application of mid-infrared spectroscopy and machine learning (MIRS-ML), to rapidly assess the blood-feeding histories of malaria vectors, with direct comparison to PCR assays. METHODS AND RESULTS Female Anopheles funestus mosquitoes (N = 1854) were collected from rural Tanzania and desiccated then scanned with an attenuated total reflectance Fourier-transform Infrared (ATR-FTIR) spectrometer. Blood meals were confirmed by PCR, establishing the 'ground truth' for machine learning algorithms. Logistic regression and multi-layer perceptron classifiers were employed to identify blood meal sources, achieving accuracies of 88%-90%, respectively, as well as HBI estimates aligning well with the PCR-based standard HBI. CONCLUSIONS This research provides evidence of MIRS-ML effectiveness in classifying blood meals in wild Anopheles funestus, as a potential complementary surveillance tool in settings where conventional molecular techniques are impractical. The cost-effectiveness, simplicity, and scalability of MIRS-ML, along with its generalizability, outweigh minor gaps in HBI estimation. Since this approach has already been demonstrated for measuring other entomological and parasitological indicators of malaria, the validation in this study broadens its range of use cases, positioning it as an integrated system for estimating pathogen transmission risk and evaluating the impact of interventions.
Collapse
Affiliation(s)
- Emmanuel P Mwanga
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania.
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK.
| | - Idrisa S Mchola
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
| | - Faraja E Makala
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
| | - Issa H Mshani
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
| | - Doreen J Siria
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
| | - Sophia H Mwinyi
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
| | - Said Abbasi
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
| | - Godian Seleman
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
| | - Jacqueline N Mgaya
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
| | | | - Klaas Wynne
- School of Chemistry, University of Glasgow, Glasgow, G12 8QQ, UK
| | - Maggy T Sikulu-Lord
- Faculty of Science, School of the Environment, The University of Queensland, Brisbane, QLD, Australia
| | - Prashanth Selvaraj
- Institute for Disease Modelling, Bill and Melinda Gates Foundation, Seattle, USA
| | - Fredros O Okumu
- Environmental Health and Ecological Sciences Department, Ifakara Health Institute, Morogoro, Tanzania
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
- School of Public Health, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
- School of Life Science and Bioengineering, The Nelson Mandela African, Institution of Science and Technology, P. O. Box 447, Arusha, Tanzania
| | - Francesco Baldini
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
| | - Simon A Babayan
- School of Biodiversity, One Health and Veterinary Medicine, University of Glasgow, Glasgow, G12 8QQ, UK
| |
Collapse
|
7
|
Patel Y, Shah T, Dhar MK, Zhang T, Niezgoda J, Gopalakrishnan S, Yu Z. Integrated image and location analysis for wound classification: a deep learning approach. Sci Rep 2024; 14:7043. [PMID: 38528003 DOI: 10.1038/s41598-024-56626-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 03/08/2024] [Indexed: 03/27/2024] Open
Abstract
The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79-100% for Region of Interest (ROI) without location classifications, 73.98-100% for ROI with location classifications, and 78.10-100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts.
Collapse
Affiliation(s)
- Yash Patel
- Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA
| | - Tirth Shah
- Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA
| | - Mrinal Kanti Dhar
- Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA
| | - Taiyu Zhang
- Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA
| | - Jeffrey Niezgoda
- Advancing the Zenith of Healthcare (AZH) Wound and Vascular Center, Milwaukee, WI, USA
| | | | - Zeyun Yu
- Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA.
- Department of Biomedical Engineering, University of Wisconsin-Milwaukee, Milwaukee, WI, USA.
| |
Collapse
|
8
|
Sharkas M, Attallah O. Color-CADx: a deep learning approach for colorectal cancer classification through triple convolutional neural networks and discrete cosine transform. Sci Rep 2024; 14:6914. [PMID: 38519513 PMCID: PMC10959971 DOI: 10.1038/s41598-024-56820-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2022] [Accepted: 03/11/2024] [Indexed: 03/25/2024] Open
Abstract
Colorectal cancer (CRC) exhibits a significant death rate that consistently impacts human lives worldwide. Histopathological examination is the standard method for CRC diagnosis. However, it is complicated, time-consuming, and subjective. Computer-aided diagnostic (CAD) systems using digital pathology can help pathologists diagnose CRC faster and more accurately than manual histopathology examinations. Deep learning algorithms especially convolutional neural networks (CNNs) are advocated for diagnosis of CRC. Nevertheless, most previous CAD systems obtained features from one CNN, these features are of huge dimension. Also, they relied on spatial information only to achieve classification. In this paper, a CAD system is proposed called "Color-CADx" for CRC recognition. Different CNNs namely ResNet50, DenseNet201, and AlexNet are used for end-to-end classification at different training-testing ratios. Moreover, features are extracted from these CNNs and reduced using discrete cosine transform (DCT). DCT is also utilized to acquire spectral representation. Afterward, it is used to further select a reduced set of deep features. Furthermore, DCT coefficients obtained in the previous step are concatenated and the analysis of variance (ANOVA) feature selection approach is applied to choose significant features. Finally, machine learning classifiers are employed for CRC classification. Two publicly available datasets were investigated which are the NCT-CRC-HE-100 K dataset and the Kather_texture_2016_image_tiles dataset. The highest achieved accuracy reached 99.3% for the NCT-CRC-HE-100 K dataset and 96.8% for the Kather_texture_2016_image_tiles dataset. DCT and ANOVA have successfully lowered feature dimensionality thus reducing complexity. Color-CADx has demonstrated efficacy in terms of accuracy, as its performance surpasses that of the most recent advancements.
Collapse
Affiliation(s)
- Maha Sharkas
- Electronics and Communications Engineering Department, College of Engineering and Technology, Arab Academy for Science, Technology, and Maritime Transport, Alexandria, Egypt
| | - Omneya Attallah
- Electronics and Communications Engineering Department, College of Engineering and Technology, Arab Academy for Science, Technology, and Maritime Transport, Alexandria, Egypt.
- Wearables, Biosensing, and Biosignal Processing Laboratory, Arab Academy for Science, Technology and Maritime Transport, Alexandria, 21937, Egypt.
| |
Collapse
|
9
|
Li S, Meng X, Li R, Huang B, Wang X. NanoBERTa-ASP: predicting nanobody paratope based on a pretrained RoBERTa model. BMC Bioinformatics 2024; 25:122. [PMID: 38515052 PMCID: PMC10956323 DOI: 10.1186/s12859-024-05750-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 03/18/2024] [Indexed: 03/23/2024] Open
Abstract
BACKGROUND Nanobodies, also known as VHH or single-domain antibodies, are unique antibody fragments derived solely from heavy chains. They offer advantages of small molecules and conventional antibodies, making them promising therapeutics. The paratope is the specific region on an antibody that binds to an antigen. Paratope prediction involves the identification and characterization of the antigen-binding site on an antibody. This process is crucial for understanding the specificity and affinity of antibody-antigen interactions. Various computational methods and experimental approaches have been developed to predict and analyze paratopes, contributing to advancements in antibody engineering, drug development, and immunotherapy. However, existing predictive models trained on traditional antibodies may not be suitable for nanobodies. Additionally, the limited availability of nanobody datasets poses challenges in constructing accurate models. METHODS To address these challenges, we have developed a novel nanobody prediction model, named NanoBERTa-ASP (Antibody Specificity Prediction), which is specifically designed for predicting nanobody-antigen binding sites. The model adopts a training strategy more suitable for nanobodies, based on an advanced natural language processing (NLP) model called BERT (Bidirectional Encoder Representations from Transformers). To be more specific, the model utilizes a masked language modeling approach named RoBERTa (Robustly Optimized BERT Pretraining Approach) to learn the contextual information of the nanobody sequence and predict its binding site. RESULTS NanoBERTa-ASP achieved exceptional performance in predicting nanobody binding sites, outperforming existing methods, indicating its proficiency in capturing sequence information specific to nanobodies and accurately identifying their binding sites. Furthermore, NanoBERTa-ASP provides insights into the interaction mechanisms between nanobodies and antigens, contributing to a better understanding of nanobodies and facilitating the design and development of nanobodies with therapeutic potential. CONCLUSION NanoBERTa-ASP represents a significant advancement in nanobody paratope prediction. Its superior performance highlights the potential of deep learning approaches in nanobody research. By leveraging the increasing volume of nanobody data, NanoBERTa-ASP can further refine its predictions, enhance its performance, and contribute to the development of novel nanobody-based therapeutics. Github repository: https://github.com/WangLabforComputationalBiology/NanoBERTa-ASP.
Collapse
Affiliation(s)
- Shangru Li
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China
| | - Xiangpeng Meng
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China
| | - Rui Li
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China
| | - Bingding Huang
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China.
| | - Xin Wang
- College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China.
| |
Collapse
|
10
|
Zhang T, Wei D, Zhu M, Gu S, Zheng Y. Self-supervised learning for medical image data with anatomy-oriented imaging planes. Med Image Anal 2024; 94:103151. [PMID: 38527405 DOI: 10.1016/j.media.2024.103151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2023] [Revised: 12/29/2023] [Accepted: 03/20/2024] [Indexed: 03/27/2024]
Abstract
Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.
Collapse
Affiliation(s)
- Tianwei Zhang
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Dong Wei
- Jarvis Research Center, Tencent YouTu Lab, Shenzhen 518057, China
| | - Mengmeng Zhu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
| | - Shi Gu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
| | - Yefeng Zheng
- Jarvis Research Center, Tencent YouTu Lab, Shenzhen 518057, China
| |
Collapse
|
11
|
Dular L, Pernuš F, Špiclin Ž. Extensive T1-weighted MRI preprocessing improves generalizability of deep brain age prediction models. Comput Biol Med 2024; 173:108320. [PMID: 38531250 DOI: 10.1016/j.compbiomed.2024.108320] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Revised: 01/09/2024] [Accepted: 03/12/2024] [Indexed: 03/28/2024]
Abstract
Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI), representing a straightforward diagnostic biomarker of brain aging and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results across studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and evaluation protocols used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models from recent literature. Four preprocessing pipelines, which differed in terms of registration transform, grayscale correction, and software implementation, were evaluated. The results showed that the choice of software or preprocessing steps could significantly affect the prediction error, with a maximum increase of 0.75 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, using affine rather than rigid registration to brain atlas statistically significantly improved MAE. Models trained on 3D images with isotropic 1mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Our findings indicate that extensive T1w preprocessing improves MAE, especially when predicting on a new dataset. This runs counter to prevailing research literature, which suggests that models trained on minimally preprocessed T1w scans are better suited for age predictions on MRIs from unseen scanners. We demonstrate that, irrespective of the model or T1w preprocessing used during training, applying some form of offset correction is essential to enable the model's performance to generalize effectively on datasets from unseen sites, regardless of whether they have undergone the same or different T1w preprocessing as the training set.
Collapse
Affiliation(s)
- Lara Dular
- University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana 1000, Slovenia
| | - Franjo Pernuš
- University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana 1000, Slovenia
| | - Žiga Špiclin
- University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana 1000, Slovenia.
| |
Collapse
|
12
|
Zhao H, Qiu S, Bai M, Wang L, Wang Z. Toxicity prediction and classification of Gunqile-7 with small sample based on transfer learning method. Comput Biol Med 2024; 173:108348. [PMID: 38531249 DOI: 10.1016/j.compbiomed.2024.108348] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 03/10/2024] [Accepted: 03/17/2024] [Indexed: 03/28/2024]
Abstract
Drug-induced diseases are the most important component of iatrogenic disease. It is the duty of doctors to provide a reasonable and safe dose of medication. Gunqile-7 is a Mongolian medicine with analgesic and anti-inflammatory effects. As a foreign substance in the body, even with reasonable medication, it may produce varying degrees of adverse reactions or toxic side effects. Since the cost of collecting Gunqile-7 for pharmacological animal trials is high and the data sample is small, this paper employs transfer learning and data augmentation methods to study the toxicity of Gunqile-7. More specifically, to reduce the necessary number of training samples, the data augmentation approach is employed to extend the data set. Then, the transfer learning method and one-dimensional convolutional neural network are utilized to train the network. In addition, we use the support vector machine-recursive feature elimination method for feature selection to reduce features that have adverse effects on model predictions. Furthermore, due to the important role of the pre-trained model of transfer learning, we select a quantitative toxicity prediction model as the pre-trained model, which is consistent with the purpose of this paper. Lastly, the experimental results demonstrate the efficiency of the proposed method. Our method can improve accuracy by up to 9 percentage points compared to the method without transfer learning on a small sample set.
Collapse
Affiliation(s)
- Hongkai Zhao
- Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, China; School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China.
| | - Sen Qiu
- Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, China; School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China.
| | - Meirong Bai
- Key Laboratory of Ministry of Education of Mongolian Medicine RD Engineering, Inner Mongolia Minzu University, Tongliao 028000, China.
| | - Luyao Wang
- Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, China; School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China.
| | - Zhelong Wang
- Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, China; School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China.
| |
Collapse
|
13
|
Zhang J, Wang S, Jiang Z, Chen Z, Bai X. CD-Net: Cascaded 3D Dilated convolutional neural network for pneumonia lesion segmentation. Comput Biol Med 2024; 173:108311. [PMID: 38513395 DOI: 10.1016/j.compbiomed.2024.108311] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Revised: 02/22/2024] [Accepted: 03/12/2024] [Indexed: 03/23/2024]
Abstract
COVID-19 is a global pandemic that has caused significant global, social, and economic disruption. To effectively assist in screening and monitoring diagnosed cases, it is crucial to accurately segment lesions from Computer Tomography (CT) scans. Due to the lack of labeled data and the presence of redundant parameters in 3D CT, there are still significant challenges in diagnosing COVID-19 in related fields. To address the problem, we have developed a new model called the Cascaded 3D Dilated convolutional neural network (CD-Net) for directly processing CT volume data. To reduce memory consumption when cutting volume data into small patches, we initially design a cascade architecture in CD-Net to preserve global information. Then, we construct a Multi-scale Parallel Dilated Convolution (MPDC) block to aggregate features of different sizes and simultaneously reduce the parameters. Moreover, to alleviate the shortage of labeled data, we employ classical transfer learning, which requires only a small amount of data while achieving better performance. Experimental results conducted on the different public-available datasets verify that the proposed CD-Net has reduced the negative-positive ratio and outperformed other existing segmentation methods while requiring less data.
Collapse
Affiliation(s)
- Jinli Zhang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Shaomeng Wang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Zongli Jiang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Zhijie Chen
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Xiaolu Bai
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| |
Collapse
|
14
|
Wang Z, Wang R, Chu Y, Chen G, Lin T, Jiang R, Wang J. A method to assess industrial paraffin contamination levels in rice and its transferability analysis based on transfer component analysis. Food Chem 2024; 436:137682. [PMID: 37837682 DOI: 10.1016/j.foodchem.2023.137682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 09/19/2023] [Accepted: 10/04/2023] [Indexed: 10/16/2023]
Abstract
Accurate assessment of industrial paraffin contamination levels (IPCLs) in rice is critical for food safety. However, time-consuming and labor-intensive experiments to produce labels for targeted adulterated rice have hindered the development of IPCL estimation methods. In this paper, a transfer learning method (TCA-LSSVR) has been developed. The algorithm integrates transfer component analysis (TCA) with domain adaptive capabilities to produce accurate estimates. Rice from 7 different regions and 3 industrial paraffins were used to generate 4,680 samples from 9 datasets for benchmarking. The test results showed that the established algorithm achieved good estimation performance in various modelling strategies, and only 20 % of off-site samples were needed to supplement the source dataset, the average determination coefficient R2 reached 0.7045, the average RMSE reached 0.140 %, and the average RPD reached 2.023. This work highlights the prospect of rapidly developing a new generation of adulteration detection algorithms using only previous trial data.
Collapse
Affiliation(s)
- Zhentao Wang
- College of Engineering, Northeast Agricultural University, Harbin 150030, China; Heilongjiang Provincial Key Laboratory of Modern Agricultural Equipment Technology in Northern Cold Regions, Harbin 150030, China
| | - Ruidong Wang
- College of Engineering, Northeast Agricultural University, Harbin 150030, China
| | - Yuhang Chu
- College of Engineering, Northeast Agricultural University, Harbin 150030, China; Heilongjiang Provincial Key Laboratory of Modern Agricultural Equipment Technology in Northern Cold Regions, Harbin 150030, China
| | - Guoqing Chen
- College of Engineering, Northeast Agricultural University, Harbin 150030, China; Heilongjiang Provincial Key Laboratory of Modern Agricultural Equipment Technology in Northern Cold Regions, Harbin 150030, China
| | - Tenghui Lin
- College of Engineering, Northeast Agricultural University, Harbin 150030, China
| | - Rui Jiang
- College of Engineering, Northeast Agricultural University, Harbin 150030, China
| | - Jinfeng Wang
- College of Engineering, Northeast Agricultural University, Harbin 150030, China; Heilongjiang Provincial Key Laboratory of Modern Agricultural Equipment Technology in Northern Cold Regions, Harbin 150030, China.
| |
Collapse
|
15
|
Gore S, Meche B, Shao D, Ginnett B, Zhou K, Azad RK. DiseaseNet: a transfer learning approach to noncommunicable disease classification. BMC Bioinformatics 2024; 25:107. [PMID: 38468193 PMCID: PMC10926612 DOI: 10.1186/s12859-024-05734-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Accepted: 03/06/2024] [Indexed: 03/13/2024] Open
Abstract
As noncommunicable diseases (NCDs) pose a significant global health burden, identifying effective diagnostic and predictive markers for these diseases is of paramount importance. Epigenetic modifications, such as DNA methylation, have emerged as potential indicators for NCDs. These have previously been exploited in other contexts within the framework of neural network models that capture complex relationships within the data. Applications of neural networks have led to significant breakthroughs in various biological or biomedical fields but these have not yet been effectively applied to NCD modeling. This is, in part, due to limited datasets that are not amenable to building of robust neural network models. In this work, we leveraged a neural network trained on one class of NCDs, cancer, as the basis for a transfer learning approach to non-cancer NCD modeling. Our results demonstrate promising performance of the model in predicting three NCDs, namely, arthritis, asthma, and schizophrenia, for the respective blood samples, with an overall accuracy (f-measure) of 94.5%. Furthermore, a concept based explanation method called Testing with Concept Activation Vectors (TCAV) was used to investigate the importance of the sample sources and understand how future training datasets for multiple NCD models may be improved. Our findings highlight the effectiveness of transfer learning in developing accurate diagnostic and predictive models for NCDs.
Collapse
Affiliation(s)
- Steven Gore
- Department of Biological Sciences and BioDiscovery Institute, University of North Texas, Denton, TX, USA
| | - Bailey Meche
- Department of Mathematics, University of Louisiana at Lafayette, Lafayette, LA, USA
| | - Danyang Shao
- Department of Biological Sciences and BioDiscovery Institute, University of North Texas, Denton, TX, USA
| | - Benjamin Ginnett
- Department of Engineering, Eastern Arizona College, Thatcher, AZ, USA
| | - Kelly Zhou
- Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA
| | - Rajeev K Azad
- Department of Biological Sciences and BioDiscovery Institute, University of North Texas, Denton, TX, USA.
| |
Collapse
|
16
|
Abad M, Casas-Roma J, Prados F. Generalizable disease detection using model ensemble on chest X-ray images. Sci Rep 2024; 14:5890. [PMID: 38467705 PMCID: PMC10928229 DOI: 10.1038/s41598-024-56171-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Accepted: 03/03/2024] [Indexed: 03/13/2024] Open
Abstract
In the realm of healthcare, the demand for swift and precise diagnostic tools has been steadily increasing. This study delves into a comprehensive performance analysis of three pre-trained convolutional neural network (CNN) architectures: ResNet50, DenseNet121, and Inception-ResNet-v2. To ensure the broad applicability of our approach, we curated a large-scale dataset comprising a diverse collection of chest X-ray images, that included both positive and negative cases of COVID-19. The models' performance was evaluated using separate datasets for internal validation (from the same source as the training images) and external validation (from different sources). Our examination uncovered a significant drop in network efficacy, registering a 10.66% reduction for ResNet50, a 36.33% decline for DenseNet121, and a 19.55% decrease for Inception-ResNet-v2 in terms of accuracy. Best results were obtained with DenseNet121 achieving the highest accuracy at 96.71% in internal validation and Inception-ResNet-v2 attaining 76.70% accuracy in external validation. Furthermore, we introduced a model ensemble approach aimed at improving network performance when making inferences on images from diverse sources beyond their training data. The proposed method uses uncertainty-based weighting by calculating the entropy in order to assign appropriate weights to the outputs of each network. Our results showcase the effectiveness of the ensemble method in enhancing accuracy up to 97.38% for internal validation and 81.18% for external validation, while maintaining a balanced ability to detect both positive and negative cases.
Collapse
Affiliation(s)
- Maider Abad
- Universitat Oberta de Catalunya, e-Health Center, Barcelona, Spain.
| | - Jordi Casas-Roma
- Universitat Oberta de Catalunya, e-Health Center, Barcelona, Spain
- Department of Computer Science, Universitat Autònoma de Barcelona (UAB), Bellaterra, Spain
- Computer Vision Center (CVC), Universitat Autònoma de Barcelona (UAB), Bellaterra, Spain
| | - Ferran Prados
- Universitat Oberta de Catalunya, e-Health Center, Barcelona, Spain
- Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Science, University College of London, London, WC1N 3BG, UK
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, WC1V 6LJ, UK
| |
Collapse
|
17
|
Chen J, Lu R, Jing B, Zhang H, Chen G, Shen D. One model, two brains: Automatic fetal brain extraction from MR images of twins. Comput Med Imaging Graph 2024; 112:102330. [PMID: 38262133 DOI: 10.1016/j.compmedimag.2024.102330] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 11/27/2023] [Accepted: 12/13/2023] [Indexed: 01/25/2024]
Abstract
Fetal brain extraction from magnetic resonance (MR) images is of great importance for both clinical applications and neuroscience studies. However, it is a challenging task, especially when dealing with twins, which are commonly existing in pregnancy. Currently, there is no brain extraction method dedicated to twins, raising significant demand to develop an effective twin fetal brain extraction method. To this end, we propose the first twin fetal brain extraction framework, which possesses three novel features. First, to narrow down the region of interest and preserve structural information between the two brains in twin fetal MR images, we take advantage of an advanced object detector to locate all the brains in twin fetal MR images at once. Second, we propose a Twin Fetal Brain Extraction Network (TFBE-Net) to further suppress insignificant features for segmenting brain regions. Finally, we propose a Two-step Training Strategy (TTS) to learn correlation features of the single fetal brain for further improving the performance of TFBE-Net. We validate the proposed framework on a twin fetal brain dataset. The experiments show that our framework achieves promising performance on both quantitative and qualitative evaluations, and outperforms state-of-the-art methods for fetal brain extraction.
Collapse
Affiliation(s)
- Jian Chen
- School of Electronic, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou, 350118, Fujian, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing, 100069, China
| | - Ranlin Lu
- School of Electronic, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou, 350118, Fujian, China
| | - Bin Jing
- Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Beijing, 100069, China; School of Biomedical Engineering, Capital Medical University, Beijing, 100069, China
| | - He Zhang
- Department of Radiology, Obstetrics and Gynecology Hospital, Fudan University, Shanghai, 200011, China
| | - Geng Chen
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China.
| | - Dinggang Shen
- School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai, 201210, China; Shanghai Clinical Research and Trial Center, Shanghai, 201210, China; Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 200230, China.
| |
Collapse
|
18
|
Li M, Li J, Song Z, Deng H, Xu J, Xu G, Liao W. EEGNet-based multi-source domain filter for BCI transfer learning. Med Biol Eng Comput 2024; 62:675-686. [PMID: 37982955 DOI: 10.1007/s11517-023-02967-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 11/06/2023] [Indexed: 11/21/2023]
Abstract
Deep learning has great potential on decoding EEG in brain-computer interface. While common deep learning algorithms cannot directly train models with data from multiple individuals because of the inter-individual differences in EEG. Collecting enough data for each subject to satisfy the training of deep learning would result in an increase in training cost. This study proposes a novel transfer learning, EEGNet-based multi-source domain filter for transfer learning (EEGNet-MDFTL), to reduce the amount of training data and improve the performance of BCI. The EEGNet-MDFTL uses bagging ensemble learning to learn domain-invariant features from the multi-source domain and utilizes model loss value to filter the multi-source domain. Compared with baseline methods, the accuracy of the EEGNet-MDFTL reaches 91.96%, higher than two state-of-the-art methods, which demonstrates source domain filter can select similar source domains to improve the accuracy of the model, and remains a high level even when the data amount is reduced to 1/8, proving that ensemble learning learns enough domain invariant features from the multi-source domain to make the model insensitive to data amount. The proposed EEGNet-MDFTL is effective in improving the decoding performance with a small amount of data, which is helpful to save the BCI training cost.
Collapse
Affiliation(s)
- Mengfan Li
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Science and Biomedical Engineering, Hebei University of Technology, Tianjin, China.
- Hebei Key Laboratory of Bioelectromagnetics and Neuroengineering, Tianjin, China.
- Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Tianjin, China.
| | - Jundi Li
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Science and Biomedical Engineering, Hebei University of Technology, Tianjin, China
- Hebei Key Laboratory of Bioelectromagnetics and Neuroengineering, Tianjin, China
- Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Tianjin, China
| | - Zhiyong Song
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Science and Biomedical Engineering, Hebei University of Technology, Tianjin, China
- Hebei Key Laboratory of Bioelectromagnetics and Neuroengineering, Tianjin, China
- Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Tianjin, China
| | - Haodong Deng
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Science and Biomedical Engineering, Hebei University of Technology, Tianjin, China
- Hebei Key Laboratory of Bioelectromagnetics and Neuroengineering, Tianjin, China
- Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Tianjin, China
| | - Jiaming Xu
- Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Guizhi Xu
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Science and Biomedical Engineering, Hebei University of Technology, Tianjin, China
- Hebei Key Laboratory of Bioelectromagnetics and Neuroengineering, Tianjin, China
- Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Tianjin, China
| | - Wenzhe Liao
- School of Artificial Intelligence, Hebei University of Technology, Tianjin, China
| |
Collapse
|
19
|
Wang T, Xu X, Pan H. Anti-noise transfer adversarial convolutions with adaptive threshold for rotating machine fault diagnosis. ISA Trans 2024; 146:175-185. [PMID: 38195293 DOI: 10.1016/j.isatra.2023.12.045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 12/31/2023] [Accepted: 12/31/2023] [Indexed: 01/11/2024]
Abstract
Fault diagnosis based on deep learning (DL) has been a research hotspot in recent years. However, the current neural networks are getting larger and larger, with more and more parameters and insufficient noise resistance, making it difficult to effectively apply these methods to real working conditions. To address these issues, we propose a novel deep learning method with fewer parameters and better noise resistance based on transfer adversarial subnetwork (TAS) and channel-wise thresholds (CWT), namely, anti-noise transfer adversarial convolutions (ANTAC). In the proposed method, the original data and feature vectors are mapped to reproducing kernel Hilbert space (RKHS) and processed by maximum mean discrepancy (MMD) and Wasserstein distance (WD), which makes the method more capable to distinguish the similar features without producing any additional training parameters. Furthermore, white Gaussian noise (WGN) and the soft thresholding method with CWT are used to reduce data noise and improve the robustness and noise resistance of the network. Finally, the superiority of the proposed method is validated through experiments on different datasets, network structures and the data with different SNRs. The results show that the proposed method has better feature discrimination ability, noise resistance, and fewer parameters compared with other methods. The highest accuracy of the proposed method is 99.90% on the test set.
Collapse
Affiliation(s)
- Tong Wang
- School of Mechanical Engineering, North University of China, Taiyuan 030051, China.
| | - Xin Xu
- School of Mechanical Engineering, North University of China, Taiyuan 030051, China.
| | - Hongxia Pan
- School of Mechanical Engineering, North University of China, Taiyuan 030051, China.
| |
Collapse
|
20
|
Tournois L, Hatsch D, Ludes B, Delabarde T. Automatic detection and identification of diatoms in complex background for suspected drowning cases through object detection models. Int J Legal Med 2024; 138:659-670. [PMID: 37804333 DOI: 10.1007/s00414-023-03096-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Accepted: 09/14/2023] [Indexed: 10/09/2023]
Abstract
The diagnosis of drowning is one of the most difficult tasks in forensic medicine. The diatom test is a complementary analysis method that may help the forensic pathologist in the diagnosis of drowning and the localization of the drowning site. This test consists in detecting or identifying diatoms, unicellular algae, in tissue and water samples. In order to observe diatoms under light microscopy, those samples may be digested by enzymes such as proteinase K. However, this digestion method may leave high amounts of debris, leading thus to a difficult detection and identification of diatoms. To the best of our knowledge, no model is proved to detect and identify accurately diatom species observed in highly complex backgrounds under light microscopy. Therefore, a novel method of model development for diatom detection and identification in a forensic context, based on sequential transfer learning of object detection models, is proposed in this article. The best resulting models are able to detect and identify up to 50 species of forensically relevant diatoms with an average precision and an average recall ranging from 0.7 to 1 depending on the concerned species. The models were developed by sequential transfer learning and globally outperformed those developed by traditional transfer learning. The best model of diatom species identification is expected to be used in routine at the Medicolegal Institute of Paris.
Collapse
Affiliation(s)
- Laurent Tournois
- UMR 8045 BABEL, Université Paris Cité, CNRS, 75012, Paris, France.
- BioSilicium, Riom, France.
| | | | - Bertrand Ludes
- UMR 8045 BABEL, Université Paris Cité, CNRS, 75012, Paris, France
- Institut Médico-Légal de Paris, Paris, France
| | - Tania Delabarde
- UMR 8045 BABEL, Université Paris Cité, CNRS, 75012, Paris, France
- Institut Médico-Légal de Paris, Paris, France
| |
Collapse
|
21
|
Zhang Y, Shangguan C, Zhang X, Ma J, He J, Jia M, Chen N. Computer-Aided Diagnosis of Complications After Liver Transplantation Based on Transfer Learning. Interdiscip Sci 2024; 16:123-140. [PMID: 37875773 DOI: 10.1007/s12539-023-00588-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Revised: 09/20/2023] [Accepted: 09/22/2023] [Indexed: 10/26/2023]
Abstract
Liver transplantation is one of the most effective treatments for acute liver failure, cirrhosis, and even liver cancer. The prediction of postoperative complications is of great significance for liver transplantation. However, the existing prediction methods based on traditional machine learning are often unavailable or unreliable due to the insufficient amount of real liver transplantation data. Therefore, we propose a new framework to increase the accuracy of computer-aided diagnosis of complications after liver transplantation with transfer learning, which can handle small-scale but high-dimensional data problems. Furthermore, since data samples are often high dimensional in the real world, capturing key features that influence postoperative complications can help make the correct diagnosis for patients. So, we also introduce the SHapley Additive exPlanation (SHAP) method into our framework for exploring the key features of postoperative complications. We used data obtained from 425 patients with 456 features in our experiments. Experimental results show that our approach outperforms all compared baseline methods in predicting postoperative complications. In our work, the average precision, the mean recall, and the mean F1 score reach 91.22%, 91.70%, and 91.18%, respectively.
Collapse
Affiliation(s)
- Ying Zhang
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China.
| | - Chenyuan Shangguan
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China
| | - Xuena Zhang
- Department of Anesthesiology Medicine, Beijing Chaoyang Hospital, Capital Medical University, Beijing, 100069, China
| | - Jialin Ma
- Tianjin Zhuoman Technology Co., Ltd., Tianjin, 300000, China
| | - Jiyuan He
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China
| | - Meng Jia
- School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China
| | - Na Chen
- Hebei Vocational College of Rail Transportation, Shijiazhuang, 050051, China
| |
Collapse
|
22
|
Zhang R, Guo H, Xu Z, Hu Y, Chen M, Zhang L. MGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition. Brain Res Bull 2024; 208:110901. [PMID: 38355058 DOI: 10.1016/j.brainresbull.2024.110901] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 12/31/2023] [Accepted: 02/11/2024] [Indexed: 02/16/2024]
Abstract
Currently, most models rarely consider the negative transfer problem in the research field of cross-subject EEG emotion recognition. To solve this problem, this paper proposes a semi-supervised domain adaptive algorithm based on few labeled samples of target subject, which called multi-domain geodesic flow kernel dynamic distribution alignment (MGFKD). It consists of three modules: 1) GFK common feature extractor: projects the feature distribution of source and target subjects to the Grassmann manifold space, and obtains the latent common features of the two feature distributions through GFK method. 2) Source domain selector: obtains pseudo-labels of the target subject through weak classifier, finds "golden source subjects" by using few known labels of target subjects. 3) Label corrector: uses a dynamic distribution balance strategy to correct the pseudo-labels of the target subject. We conducted comparison experiments on the SEED and SEED-IV datasets, and the results show that MGFKD outperforms unsupervised and semi-supervised domain adaptation algorithms, achieving an average accuracy of 87.51±7.68% and 68.79±8.25% on the SEED and SEED-IV datasets with only one labeled sample per video for target subject. Especially when the number of source domains is set as 6 and the number of known labels is set as 5, the accuracy increase to 90.20±7.57% and 69.99±7.38%, respectively. The above results prove that our proposed algorithm can efficiently and quickly improve the cross-subject EEG emotion classification performance. Since it only need a small number of labeled samples of new subjects, making it has strong application value in future EEG-based emotion recognition applications.
Collapse
Affiliation(s)
- Rui Zhang
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China
| | - Huifeng Guo
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China
| | - Zongxin Xu
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China
| | - Yuxia Hu
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China
| | - Mingming Chen
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China
| | - Lipeng Zhang
- Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China.
| |
Collapse
|
23
|
Yao Z, Li F, Xie W, Chen J, Wu J, Zhan Y, Wu X, Wang Z, Zhang G. DeepSF-4mC: A deep learning model for predicting DNA cytosine 4mC methylation sites leveraging sequence features. Comput Biol Med 2024; 171:108166. [PMID: 38382385 DOI: 10.1016/j.compbiomed.2024.108166] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2023] [Revised: 02/15/2024] [Accepted: 02/15/2024] [Indexed: 02/23/2024]
Abstract
N4-methylcytosine (4mC) is a DNA modification involving the addition of a methyl group to the fourth nitrogen atom of the cytosine base. This modification may influence gene regulation, providing potential insights into gene control mechanisms. Traditional laboratory methods for detecting 4mC DNA methylation have limitations, but the rise of artificial intelligence has introduced efficient computational strategies for 4mC site prediction. Despite this progress, challenges persist in terms of model performance and interpretability. To tackle these challenges, we propose DeepSF-4mC, a deep learning model specifically designed for predicting DNA cytosine 4mC methylation sites by leveraging sequence features. Our approach incorporates multiple encoding techniques to enhance prediction accuracy, increase model stability, and reduce the computational resources needed. Leveraging transfer learning, we harness existing models to enhance performance through learned representations or fine-tuning. Ensemble learning techniques combine predictions from multiple models, boosting robustness and accuracy. This research contributes to DNA methylation analysis and lays the groundwork for understanding 4mC's multifaceted role in biological processes. The web server for DeepSF-4mC is accessible at: http://deepsf-4mc.top/and the original code can be found at: https://github.com/754131799/DeepSF-4mC.
Collapse
Affiliation(s)
- Zhaomin Yao
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Fei Li
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Weiming Xie
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Jiaming Chen
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Jiezhang Wu
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Ying Zhan
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Xiaodan Wu
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China
| | - Zhiguo Wang
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China.
| | - Guoxu Zhang
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China.
| |
Collapse
|
24
|
Yu W, Xu N, Huang N, Chen H. Bridging the gap: Geometry-centric discriminative manifold distribution alignment for enhanced classification in colorectal cancer imaging. Comput Biol Med 2024; 170:107998. [PMID: 38266468 DOI: 10.1016/j.compbiomed.2024.107998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 12/19/2023] [Accepted: 01/13/2024] [Indexed: 01/26/2024]
Abstract
The early detection of colorectal cancer (CRC) through medical image analysis is a pivotal concern in healthcare, with the potential to significantly reduce mortality rates. Current Domain Adaptation (DA) methods strive to mitigate the discrepancies between different imaging modalities that are critical in identifying CRC, yet they often fall short in addressing the complexity of cancer's presentation within these images. These conventional techniques typically overlook the intricate geometrical structures and the local variations within the data, leading to suboptimal diagnostic performance. This study introduces an innovative application of the Discriminative Manifold Distribution Alignment (DMDA) method, which is specifically engineered to enhance the medical image diagnosis of colorectal cancer. DMDA transcends traditional DA approaches by focusing on both local and global distribution alignments and by intricately learning the intrinsic geometrical characteristics present in manifold space. This is achieved without depending on the potentially misleading pseudo-labels, a common pitfall in existing methodologies. Our implementation of DMDA on three distinct datasets, involving several unique DA tasks, has consistently demonstrated superior classification accuracy and computational efficiency. The method adeptly captures the complex morphological and textural nuances of CRC lesions, leading to a significant leap in domain adaptation technology. DMDA's ability to reconcile global and local distributional disparities, coupled with its manifold-based geometrical structure learning, signals a paradigm shift in medical imaging analysis. The results obtained are not only promising in terms of advancing domain adaptation theory but also in their practical implications, offering the prospect of substantially improved diagnostic accuracy and faster clinical workflows. This heralds a transformative approach in personalized oncology care, aligning with the pressing need for early and accurate CRC detection.
Collapse
Affiliation(s)
- Weiwei Yu
- Department of Gastroenterology, Wenzhou TCM Hospital of Zhejiang Chinese Medical University, Wenzhou, Zhejiang, 325000, China.
| | - Nuo Xu
- Department of Medical Oncology, Wenzhou TCM Hospital of Zhejiang Chinese Medical University, Wenzhou, Zhejiang, 325000, China.
| | - Nuanhui Huang
- Department of Medical Oncology, Wenzhou TCM Hospital of Zhejiang Chinese Medical University, Wenzhou, Zhejiang, 325000, China.
| | - Houliang Chen
- Department of Medical Oncology, Wenzhou TCM Hospital of Zhejiang Chinese Medical University, Wenzhou, Zhejiang, 325000, China.
| |
Collapse
|
25
|
Chiu YW, Tung CW, Wang CC. Multitask learning for predicting pulmonary absorption of chemicals. Food Chem Toxicol 2024; 185:114453. [PMID: 38244667 DOI: 10.1016/j.fct.2024.114453] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 12/31/2023] [Accepted: 01/11/2024] [Indexed: 01/22/2024]
Abstract
Pulmonary absorption is an important route for drug delivery and chemical exposure. To streamline the chemical assessment process for the reduction of animal experiments, several animal-free models were developed for pulmonary absorption research. While Calu-3 and Caco-2 cells and their derived computational models were used in estimating pulmonary permeability, the ex vivo isolated perfused lung (IPL) models are considered more clinically relevant measurements. However, the IPL experiments are resource-consuming making it infeasible for the large-scale screening of potential inhaled toxicants and drugs. In silico models are desirable for estimating pulmonary absorption. This study presented a novel machine learning method that employed an extratrees-based multitask learning approach to predict the IPL absorption rate constant (kaIPL) of various chemicals. The shared permeability knowledge was extracted by simultaneously learning three relevant tasks of Caco-2 and Calu-3 cell permeability and IPL absorption rate. Seven informative physicochemical descriptors were identified. A rigorous evaluation of the developed prediction model showed good performance with a high correlation between predictions and observations (r = 0.84) in the independent test dataset. Two case studies of inhalation drugs and respiratory sensitizers revealed the potential application of this model, which may serve as a valuable tool for predicting pulmonary absorption of chemicals.
Collapse
Affiliation(s)
- Yu-Wen Chiu
- Department and Institute of Veterinary Medicine, School of Veterinary Medicine, National Taiwan University, Taipei, 106, Taiwan
| | - Chun-Wei Tung
- Institute of Biotechnology and Pharmaceutical Research, National Health Research Institutes, Miaoli County, 350, Taiwan.
| | - Chia-Chi Wang
- Department and Institute of Veterinary Medicine, School of Veterinary Medicine, National Taiwan University, Taipei, 106, Taiwan.
| |
Collapse
|
26
|
Matsumoto S, Nakahara Y, Yonezawa T, Nakamura Y, Tanabe M, Higashi M, Shiraishi J. Development of an individual display optimization system based on deep convolutional neural network transition learning for somatostatin receptor scintigraphy. Radiol Phys Technol 2024; 17:195-206. [PMID: 38165579 DOI: 10.1007/s12194-023-00766-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 11/13/2023] [Accepted: 11/26/2023] [Indexed: 01/04/2024]
Abstract
Somatostatin receptor scintigraphy (SRS) is an essential examination for the diagnosis of neuroendocrine tumors (NETs). This study developed a method to individually optimize the display of whole-body SRS images using a deep convolutional neural network (DCNN) reconstructed by transfer learning of a DCNN constructed using Gallium-67 (67Ga) images. The initial DCNN was constructed using U-Net to optimize the display of 67Ga images (493 cases/986 images), and a DCNN with transposed weight coefficients was reconstructed for the optimization of whole-body SRS images (133 cases/266 images). A DCNN was constructed for each observer using reference display conditions estimated in advance. Furthermore, to eliminate information loss in the original image, a grayscale linear process is performed based on the DCNN output image to obtain the final linearly corrected DCNN (LcDCNN) image. To verify the usefulness of the proposed method, an observer study using a paired-comparison method was conducted on the original, reference, and LcDCNN images of 15 cases with 30 images. The paired comparison method showed that in most cases (29/30), the LcDCNN images were significantly superior to the original images in terms of display conditions. When comparing the LcDCNN and reference images, the number of LcDCNN and reference images that were superior to each other in the display condition was 17 and 13, respectively, and in both cases, 6 of these images showed statistically significant differences. The optimized SRS images obtained using the proposed method, while reflecting the observer's preference, were superior to the conventional manually adjusted images.
Collapse
Affiliation(s)
- Shun Matsumoto
- Division of Radiology, Yamaguchi University Hospital, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan.
- Graduate School of Health Sciences, Kumamoto University, 4-24-1 Kuhonji, Kumamoto, 862-0976, Japan.
| | - Yuki Nakahara
- Division of Radiology, Yamaguchi University Hospital, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan
| | - Teppei Yonezawa
- Division of Radiology, Yamaguchi University Hospital, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan
| | - Yuto Nakamura
- Division of Radiology, Yamaguchi University Hospital, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan
| | - Masahiro Tanabe
- Department of Radiology, Yamaguchi University School of Medicine, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan
| | - Mayumi Higashi
- Department of Radiology, Yamaguchi University School of Medicine, 1-1-1 Minamikogushi, Yamaguchi, 755-8505, Japan
| | - Junji Shiraishi
- Faculty of Life Sciences, Kumamoto University, 4-24-1 Kuhonji, Kumamoto, 862-0976, Japan
| |
Collapse
|
27
|
Tian R, Lu G, Tang S, Sang L, Ma H, Qian W, Yang W. Benign and malignant classification of breast tumor ultrasound images using conventional radiomics and transfer learning features: A multicenter retrospective study. Med Eng Phys 2024; 125:104117. [PMID: 38508797 DOI: 10.1016/j.medengphy.2024.104117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2023] [Revised: 01/25/2024] [Accepted: 02/13/2024] [Indexed: 03/22/2024]
Abstract
This study aims to establish an effective benign and malignant classification model for breast tumor ultrasound images by using conventional radiomics and transfer learning features. We collaborated with a local hospital and collected a base dataset (Dataset A) consisting of 1050 cases of single lesion 2D ultrasound images from patients, with a total of 593 benign and 357 malignant tumor cases. The experimental approach comprises three main parts: conventional radiomics, transfer learning, and feature fusion. Furthermore, we assessed the model's generalizability by utilizing multicenter data obtained from Datasets B and C. The results from conventional radiomics indicated that the SVM classifier achieved the highest balanced accuracy of 0.791, while XGBoost obtained the highest AUC of 0.854. For transfer learning, we extracted deep features from ResNet50, Inception-v3, DenseNet121, MNASNet, and MobileNet. Among these models, MNASNet, with 640-dimensional deep features, yielded the optimal performance, with a balanced accuracy of 0.866, AUC of 0.937, sensitivity of 0.819, and specificity of 0.913. In the feature fusion phase, we trained SVM, ExtraTrees, XGBoost, and LightGBM with early fusion features and evaluated them with weighted voting. This approach achieved the highest balanced accuracy of 0.964 and AUC of 0.981. Combining conventional radiomics and transfer learning features demonstrated clear advantages over using individual features for breast tumor ultrasound image classification. This automated diagnostic model can ease patient burden and provide additional diagnostic support to radiologists. The performance of this model encourages future prospective research in this domain.
Collapse
Affiliation(s)
- Ronghui Tian
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Guoxiu Lu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Department of Nuclear Medicine, General Hospital of Northern Theatre Command, Shenyang, China
| | - Shiting Tang
- Department of Orthopedics, Joint Surgery and Sports Medicine, The First Hospital of China Medical University, Shenyang, China
| | - Liang Sang
- Department of Ultrasound, The First Hospital of China Medical University, Shenyang, China
| | - He Ma
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Wei Qian
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Wei Yang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer, Hospital & Institute, Shenyang, China.
| |
Collapse
|
28
|
Li F, Zhang J, Li K, Peng Y, Zhang H, Xu Y, Yu Y, Zhang Y, Liu Z, Wang Y, Huang L, Zhou F. GANSamples-ac4C: Enhancing ac4C site prediction via generative adversarial networks and transfer learning. Anal Biochem 2024; 689:115495. [PMID: 38431142 DOI: 10.1016/j.ab.2024.115495] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2023] [Revised: 02/18/2024] [Accepted: 02/22/2024] [Indexed: 03/05/2024]
Abstract
RNA modification, N4-acetylcytidine (ac4C), is enzymatically catalyzed by N-acetyltransferase 10 (NAT10) and plays an essential role across tRNA, rRNA, and mRNA. It influences various cellular functions, including mRNA stability and rRNA biosynthesis. Wet-lab detection of ac4C modification sites is highly resource-intensive and costly. Therefore, various machine learning and deep learning techniques have been employed for computational detection of ac4C modification sites. The known ac4C modification sites are limited for training an accurate and stable prediction model. This study introduces GANSamples-ac4C, a novel framework that synergizes transfer learning and generative adversarial network (GAN) to generate synthetic RNA sequences to train a better ac4C modification site prediction model. Comparative analysis reveals that GANSamples-ac4C outperforms existing state-of-the-art methods in identifying ac4C sites. Moreover, our result underscores the potential of synthetic data in mitigating the issue of data scarcity for biological sequence prediction tasks. Another major advantage of GANSamples-ac4C is its interpretable decision logic. Multi-faceted interpretability analyses detect key regions in the ac4C sequences influencing the discriminating decision between positive and negative samples, a pronounced enrichment of G in this region, and ac4C-associated motifs. These findings may offer novel insights for ac4C research. The GANSamples-ac4C framework and its source code are publicly accessible at http://www.healthinformaticslab.org/supp/.
Collapse
Affiliation(s)
- Fei Li
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Jiale Zhang
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Kewei Li
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China.
| | - Yu Peng
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Haotian Zhang
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Yiping Xu
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Yue Yu
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Yuteng Zhang
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Zewen Liu
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, Guizhou, China
| | - Ying Wang
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Lan Huang
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Fengfeng Zhou
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, and College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China; College of Software, Jilin University, Changchun, Jilin, 130012, China.
| |
Collapse
|
29
|
S S, Dharani Devi G, V R, Jeyalakshmi J. Privacy-Preserving Breast Cancer Classification: A Federated Transfer Learning Approach. J Imaging Inform Med 2024:10.1007/s10278-024-01035-8. [PMID: 38424280 DOI: 10.1007/s10278-024-01035-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Revised: 01/11/2024] [Accepted: 01/30/2024] [Indexed: 03/02/2024]
Abstract
Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22 s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment.
Collapse
Affiliation(s)
- Selvakanmani S
- Department of Information Technology, R.M.K Engineering College, Chennai, Tamil Nadu, India.
| | - G Dharani Devi
- Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India
| | - Rekha V
- Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai, Tamil Nadu, India
| | - J Jeyalakshmi
- Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidhyapeetham, Chennai, India
| |
Collapse
|
30
|
Jakkaladiki SP, Maly F. Integrating hybrid transfer learning with attention-enhanced deep learning models to improve breast cancer diagnosis. PeerJ Comput Sci 2024; 10:e1850. [PMID: 38435578 PMCID: PMC10909230 DOI: 10.7717/peerj-cs.1850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Accepted: 01/10/2024] [Indexed: 03/05/2024]
Abstract
Cancer, with its high fatality rate, instills fear in countless individuals worldwide. However, effective diagnosis and treatment can often lead to a successful cure. Computer-assisted diagnostics, especially in the context of deep learning, have become prominent methods for primary screening of various diseases, including cancer. Deep learning, an artificial intelligence technique that enables computers to reason like humans, has recently gained significant attention. This study focuses on training a deep neural network to predict breast cancer. With the advancements in medical imaging technologies such as X-ray, magnetic resonance imaging (MRI), and computed tomography (CT) scans, deep learning has become essential in analyzing and managing extensive image datasets. The objective of this research is to propose a deep-learning model for the identification and categorization of breast tumors. The system's performance was evaluated using the breast cancer identification (BreakHis) classification datasets from the Kaggle repository and the Wisconsin Breast Cancer Dataset (WBC) from the UCI repository. The study's findings demonstrated an impressive accuracy rate of 100%, surpassing other state-of-the-art approaches. The suggested model was thoroughly evaluated using F1-score, recall, precision, and accuracy metrics on the WBC dataset. Training, validation, and testing were conducted using pre-processed datasets, leading to remarkable results of 99.8% recall rate, 99.06% F1-score, and 100% accuracy rate on the BreakHis dataset. Similarly, on the WBC dataset, the model achieved a 99% accuracy rate, a 98.7% recall rate, and a 99.03% F1-score. These outcomes highlight the potential of deep learning models in accurately diagnosing breast cancer. Based on our research, it is evident that the proposed system outperforms existing approaches in this field.
Collapse
Affiliation(s)
- Sudha Prathyusha Jakkaladiki
- Faculty of Informatics and Management, University of Hradec Králové, Hradec Kralove, Hradec Kralove, Czech Republic
| | - Filip Maly
- Faculty of Informatics and Management, University of Hradec Králové, Hradec Kralove, Hradec Kralove, Czech Republic
| |
Collapse
|
31
|
Ergun H. Wood identification based on macroscopic images using deep and transfer learning approaches. PeerJ 2024; 12:e17021. [PMID: 38436000 PMCID: PMC10908261 DOI: 10.7717/peerj.17021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Accepted: 02/06/2024] [Indexed: 03/05/2024] Open
Abstract
Identifying forest types is vital for evaluating the ecological, economic, and social benefits provided by forests, and for protecting, managing, and sustaining them. Although traditionally based on expert observation, recent developments have increased the use of technologies such as artificial intelligence (AI). The use of advanced methods such as deep learning will make forest species recognition faster and easier. In this study, the deep network models RestNet18, GoogLeNet, VGG19, Inceptionv3, MobileNetv2, DenseNet201, InceptionResNetv2, EfficientNet and ShuffleNet, which were pre-trained with ImageNet dataset, were adapted to a new dataset. In this adaptation, transfer learning method is used. These models have different architectures that allow a wide range of performance evaluation. The performance of the model was evaluated by accuracy, recall, precision, F1-score, specificity and Matthews correlation coefficient. ShuffleNet was proposed as a lightweight network model that achieves high performance with low computational power and resource requirements. This model was an efficient model with an accuracy close to other models with customisation. This study reveals that deep network models are an effective tool in the field of forest species recognition. This study makes an important contribution to the conservation and management of forests.
Collapse
Affiliation(s)
- Halime Ergun
- Department of Computer Engineering, Seydişehir Ahmet Cengiz Faculty of Engineering, Necmettin Erbakan University, Konya, Turkey
| |
Collapse
|
32
|
Pare JR, Gjesteby LA, Tonelli M, Leo MM, Muruganandan KM, Choudhary G, Brattain LJ. Transfer Learning-Based B-Line Assessment of Lung Ultrasound for Acute Heart Failure. Ultrasound Med Biol 2024:S0301-5629(24)00103-0. [PMID: 38423896 DOI: 10.1016/j.ultrasmedbio.2024.02.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 01/30/2024] [Accepted: 02/08/2024] [Indexed: 03/02/2024]
Abstract
OBJECTIVE B-lines assessed by lung ultrasound (LUS) outperform physical exam, chest radiograph, and biomarkers for the associated diagnosis of acute heart failure (AHF) in the emergent setting. The use of LUS is however limited to trained professionals and suffers from interpretation variability. The objective was to utilize transfer learning to create an AI-enabled software that can aid novice users to automate LUS B-line interpretation. METHODS Data from an observational AHF LUS study provided standardized cine clips for AI model development and evaluation. A total of 49,952 LUS frames from 30 patients were hand scored and trained on a convolutional neural network (CNN) to interpret B-lines at the frame level. A random independent evaluation set of 476 LUS clips from 60 unique patients assessed model performance. The AI models scored the clips on both a binary and ordinal 0-4 multiclass assessment. RESULTS A multiclassification AI algorithm had the best performance at the binary level when applied to the independent evaluation set, AUC of 0.967 (95% CI 0.965-0.970) for detecting pathologic conditions. When compared to expert blinded reviewer, the 0-4 multiclassification AI algorithm scale had a reported linear weighted kappa of 0.839 (95% CI 0.804-0.871). CONCLUSIONS The multiclassification AI algorithm is a robust and well performing model at both binary and ordinal multiclass B-line evaluation. This algorithm has the potential to be integrated into clinical workflows to assist users with quantitative and objective B-line assessment for evaluation of AHF.
Collapse
Affiliation(s)
- Joseph R Pare
- Alpert Medical School of Brown University, Providence, RI, USA; Lifespan, Providence, RI, USA; Providence VA Medical Center, Providence, RI, USA; Boston University, Boston, MA, USA.
| | - Lars A Gjesteby
- Human Health & Performance Systems Group, MIT Lincoln Laboratory, Lexington, MA, USA
| | | | | | | | - Gaurav Choudhary
- Alpert Medical School of Brown University, Providence, RI, USA; Lifespan, Providence, RI, USA; Providence VA Medical Center, Providence, RI, USA
| | - Laura J Brattain
- Human Health & Performance Systems Group, MIT Lincoln Laboratory, Lexington, MA, USA
| |
Collapse
|
33
|
Shafik W, Tufail A, De Silva Liyanage C, Apong RAAHM. Using transfer learning-based plant disease classification and detection for sustainable agriculture. BMC Plant Biol 2024; 24:136. [PMID: 38408925 PMCID: PMC10895770 DOI: 10.1186/s12870-024-04825-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Accepted: 02/15/2024] [Indexed: 02/28/2024]
Abstract
Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's "Zero Hunger," "Climate Action," and "Responsible Consumption and Production" sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.
Collapse
Affiliation(s)
- Wasswa Shafik
- School of Digital Science, Universiti Brunei Darussalam, Tungku Link, Gadong, BE1410, Brunei
| | - Ali Tufail
- School of Digital Science, Universiti Brunei Darussalam, Tungku Link, Gadong, BE1410, Brunei.
| | | | | |
Collapse
|
34
|
Lilhore UK, Dalal S, Varshney N, Sharma YK, Rao KBVB, Rao VVRM, Alroobaea R, Simaiya S, Margala M, Chakrabarti P. Prevalence and risk factors analysis of postpartum depression at early stage using hybrid deep learning model. Sci Rep 2024; 14:4533. [PMID: 38402249 PMCID: PMC10894236 DOI: 10.1038/s41598-024-54927-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Accepted: 02/18/2024] [Indexed: 02/26/2024] Open
Abstract
Postpartum Depression Disorder (PPDD) is a prevalent mental health condition and results in severe depression and suicide attempts in the social community. Prompt actions are crucial in tackling PPDD, which requires a quick recognition and accurate analysis of the probability factors associated with this condition. This concern requires attention. The primary aim of our research is to investigate the feasibility of anticipating an individual's mental state by categorizing individuals with depression from those without depression using a dataset consisting of text along with audio recordings from patients diagnosed with PPDD. This research proposes a hybrid PPDD framework that combines Improved Bi-directional Long Short-Term Memory (IBi-LSTM) with Transfer Learning (TL) based on two Convolutional Neural Network (CNN) architectures, respectively CNN-text and CNN audio. In the proposed model, the CNN section efficiently utilizes TL to obtain crucial knowledge from text and audio characteristics, whereas the improved Bi-LSTM module combines written material and sound data to obtain intricate chronological interpersonal relationships. The proposed model incorporates an attention technique to augment the effectiveness of the Bi-LSTM scheme. An experimental analysis is conducted on the PPDD online textual and speech audio dataset collected from UCI. It includes textual features such as age, women's health tracks, medical histories, demographic information, daily life metrics, psychological evaluations, and 'speech records' of PPDD patients. Data pre-processing is applied to maintain the data integrity and achieve reliable model performance. The proposed model demonstrates a great performance in better precision, recall, accuracy, and F1-score over existing deep learning models, including VGG-16, Base-CNN, and CNN-LSTM. These metrics indicate the model's ability to differentiate among women at risk of PPDD vs. non-PPDD. In addition, the feature importance analysis demonstrates that specific risk factors substantially impact the prediction of PPDD. The findings of this research establish a basis for improved precision and promptness in assessing the risk of PPDD, which may ultimately result in earlier implementation of interventions and the establishment of support networks for women who are susceptible to PPDD.
Collapse
Affiliation(s)
- Umesh Kumar Lilhore
- Department of Computer Science & Engineering, Chandigarh University Gharuan Mohali, Gharuan, 140413, Punjab, India.
| | - Surjeet Dalal
- Amity School of Engineering and Technology, Amity University Haryana, Panchgaon, Haryana, India
| | - Neeraj Varshney
- Department of Computer Engineering and Applications GLA University, Mathura, India
| | - Yogesh Kumar Sharma
- Department of Computer Science & Engineering, Koneru Lakshmaiah Education Foundation, Greenfield, Vaddeswaram, Guntur, Andhra Pradesh, India
| | - K B V Brahma Rao
- Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur, Andhra Pradesh, India
| | - V V R Maheswara Rao
- Dept. of Computer Science and Engineering, Shri Vishnu Engineering College for Women (A), Bhimavaram, Andhra Pradesh, India, 534202
| | - Roobaea Alroobaea
- Department of Computer Science, College of Computers and Information Technology, Taif University, P. O. Box 11099, 21944, Taif, Saudi Arabia
| | - Sarita Simaiya
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | - Martin Margala
- School of Computing and Informatics, University of Louisiana, Lafayette, USA
| | - Prasun Chakrabarti
- Department of Computer Science and Engineering, Sir Padampat Singhania University, Udaipur, 313601, Rajasthan, India
| |
Collapse
|
35
|
Dong Q, Wang S, Miao Y, Luo H, Weng Z, Yu L. Novel antimicrobial peptides against Cutibacterium acnes designed by deep learning. Sci Rep 2024; 14:4529. [PMID: 38402320 PMCID: PMC10894229 DOI: 10.1038/s41598-024-55205-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 02/21/2024] [Indexed: 02/26/2024] Open
Abstract
The increasing prevalence of antibiotic resistance in Cutibacterium acnes (C. acnes) requires the search for alternative therapeutic strategies. Antimicrobial peptides (AMPs) offer a promising avenue for the development of new treatments targeting C. acnes. In this study, to design peptides with the specific inhibitory activity against C. acnes, we employed a deep learning pipeline with generators and classifiers, using transfer learning and pretrained protein embeddings, trained on publicly available data. To enhance the training data specific to C. acnes inhibition, we constructed a phylogenetic tree. A panel of 42 novel generated linear peptides was then synthesized and experimentally evaluated for their antimicrobial selectivity and activity. Five of them demonstrated their high potency and selectivity against C. acnes with MIC of 2-4 µg/mL. Our findings highlight the potential of these designed peptides as promising candidates for anti-acne therapeutics and demonstrate the power of computational approaches for the rational design of targeted antimicrobial peptides.
Collapse
Affiliation(s)
- Qichang Dong
- Shanghai MetaNovas Biotech Co., Ltd, Shanghai, 200120, China
| | - Shaohua Wang
- Shanghai MetaNovas Biotech Co., Ltd, Shanghai, 200120, China
| | - Ying Miao
- College of Biological Science and Engineering, Fuzhou University, Fuzhou, 350108, China
| | - Heng Luo
- Shanghai MetaNovas Biotech Co., Ltd, Shanghai, 200120, China
| | - Zuquan Weng
- College of Biological Science and Engineering, Fuzhou University, Fuzhou, 350108, China
| | - Lun Yu
- Metanovas Biotech Inc., Foster City, 94404, USA.
| |
Collapse
|
36
|
Tian R, Lu G, Zhao N, Qian W, Ma H, Yang W. Constructing the Optimal Classification Model for Benign and Malignant Breast Tumors Based on Multifeature Analysis from Multimodal Images. J Imaging Inform Med 2024:10.1007/s10278-024-01036-7. [PMID: 38381383 DOI: 10.1007/s10278-024-01036-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Revised: 01/28/2024] [Accepted: 02/02/2024] [Indexed: 02/22/2024]
Abstract
The purpose of this study was to fuse conventional radiomic and deep features from digital breast tomosynthesis craniocaudal projection (DBT-CC) and ultrasound (US) images to establish a multimodal benign-malignant classification model and evaluate its clinical value. Data were obtained from a total of 487 patients at three centers, each of whom underwent DBT-CC and US examinations. A total of 322 patients from dataset 1 were used to construct the model, while 165 patients from datasets 2 and 3 formed the prospective testing cohort. Two radiologists with 10-20 years of work experience and three sonographers with 12-20 years of work experience semiautomatically segmented the lesions using ITK-SNAP software while considering the surrounding tissue. For the experiments, we extracted conventional radiomic and deep features from tumors from DBT-CCs and US images using PyRadiomics and Inception-v3. Additionally, we extracted conventional radiomic features from four peritumoral layers around the tumors via DBT-CC and US images. Features were fused separately from the intratumoral and peritumoral regions. For the models, we tested the SVM, KNN, decision tree, RF, XGBoost, and LightGBM classifiers. Early fusion and late fusion (ensemble and stacking) strategies were employed for feature fusion. Using the SVM classifier, stacking fusion of deep features and three peritumoral radiomic features from tumors in DBT-CC and US images achieved the optimal performance, with an accuracy and AUC of 0.953 and 0.959 [CI: 0.886-0.996], a sensitivity and specificity of 0.952 [CI: 0.888-0.992] and 0.955 [0.868-0.985], and a precision of 0.976. The experimental results indicate that the fusion model of deep features and peritumoral radiomic features from tumors in DBT-CC and US images shows promise in differentiating benign and malignant breast tumors.
Collapse
Affiliation(s)
- Ronghui Tian
- College of Medicine and Biological Information Engineering, Northeastern University, No. 195 Chuangxin Road, Hunnan District, Shenyang, 110819, Liaoning Province, China
| | - Guoxiu Lu
- College of Medicine and Biological Information Engineering, Northeastern University, No. 195 Chuangxin Road, Hunnan District, Shenyang, 110819, Liaoning Province, China
- Department of Nuclear Medicine, General Hospital of Northern Theatre Command, No. 83 Wenhua Road, Shenhe District, Shenyang, 110016, Liaoning Province, China
| | - Nannan Zhao
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, No. 44 Xiaoheyan Road, Dadong District, Shenyang, 110042, Liaoning Province, China
| | - Wei Qian
- College of Medicine and Biological Information Engineering, Northeastern University, No. 195 Chuangxin Road, Hunnan District, Shenyang, 110819, Liaoning Province, China
| | - He Ma
- College of Medicine and Biological Information Engineering, Northeastern University, No. 195 Chuangxin Road, Hunnan District, Shenyang, 110819, Liaoning Province, China
| | - Wei Yang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, No. 44 Xiaoheyan Road, Dadong District, Shenyang, 110042, Liaoning Province, China.
| |
Collapse
|
37
|
Kumar Lilhore U, Simaiya S, Sharma YK, Kaswan KS, Rao KBVB, Rao VVRM, Baliyan A, Bijalwan A, Alroobaea R. A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization. Sci Rep 2024; 14:4299. [PMID: 38383520 PMCID: PMC10881962 DOI: 10.1038/s41598-024-54212-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 02/09/2024] [Indexed: 02/23/2024] Open
Abstract
Skin cancer is a frequently occurring and possibly deadly disease that necessitates prompt and precise diagnosis in order to ensure efficacious treatment. This paper introduces an innovative approach for accurately identifying skin cancer by utilizing Convolution Neural Network architecture and optimizing hyperparameters. The proposed approach aims to increase the precision and efficacy of skin cancer recognition and consequently enhance patients' experiences. This investigation aims to tackle various significant challenges in skin cancer recognition, encompassing feature extraction, model architecture design, and optimizing hyperparameters. The proposed model utilizes advanced deep-learning methodologies to extract complex features and patterns from skin cancer images. We enhance the learning procedure of deep learning by integrating Standard U-Net and Improved MobileNet-V3 with optimization techniques, allowing the model to differentiate malignant and benign skin cancers. Also substituted the crossed-entropy loss function of the Mobilenet-v3 mathematical framework with a bias loss function to enhance the accuracy. The model's squeeze and excitation component was replaced with the practical channel attention component to achieve parameter reduction. Integrating cross-layer connections among Mobile modules has been proposed to leverage synthetic features effectively. The dilated convolutions were incorporated into the model to enhance the receptive field. The optimization of hyperparameters is of utmost importance in improving the efficiency of deep learning models. To fine-tune the model's hyperparameter, we employ sophisticated optimization methods such as the Bayesian optimization method using pre-trained CNN architecture MobileNet-V3. The proposed model is compared with existing models, i.e., MobileNet, VGG-16, MobileNet-V2, Resnet-152v2 and VGG-19 on the "HAM-10000 Melanoma Skin Cancer dataset". The empirical findings illustrate that the proposed optimized hybrid MobileNet-V3 model outperforms existing skin cancer detection and segmentation techniques based on high precision of 97.84%, sensitivity of 96.35%, accuracy of 98.86% and specificity of 97.32%. The enhanced performance of this research resulted in timelier and more precise diagnoses, potentially contributing to life-saving outcomes and mitigating healthcare expenditures.
Collapse
Affiliation(s)
- Umesh Kumar Lilhore
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | - Sarita Simaiya
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | - Yogesh Kumar Sharma
- Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfield, Vaddeswaram, Guntur, AP, India
| | - Kuldeep Singh Kaswan
- School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India
| | - K B V Brahma Rao
- Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfield, Vaddeswaram, Guntur, AP, India
| | - V V R Maheswara Rao
- Departmentt of Computer Science and Engineering, Shri Vishnu Engineering College for Women (A), Bhimavaram, India
| | - Anupam Baliyan
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | | | - Roobaea Alroobaea
- Department of Computer Science, College of Computers and Information Technology, Taif University, P. O. Box 11099, 21944, Taif, Saudi Arabia
| |
Collapse
|
38
|
Loeffler HH, He J, Tibo A, Janet JP, Voronov A, Mervin LH, Engkvist O. Reinvent 4: Modern AI-driven generative molecule design. J Cheminform 2024; 16:20. [PMID: 38383444 PMCID: PMC10882833 DOI: 10.1186/s13321-024-00812-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2023] [Accepted: 02/09/2024] [Indexed: 02/23/2024] Open
Abstract
REINVENT 4 is a modern open-source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within the general machine learning optimization algorithms, transfer learning, reinforcement learning and curriculum learning. REINVENT 4 enables and facilitates de novo design, R-group replacement, library design, linker design, scaffold hopping and molecule optimization. This contribution gives an overview of the software and describes its design. Algorithms and their applications are discussed in detail. REINVENT 4 is a command line tool which reads a user configuration in either TOML or JSON format. The aim of this release is to provide reference implementations for some of the most common algorithms in AI based molecule generation. An additional goal with the release is to create a framework for education and future innovation in AI based molecular design. The software is available from https://github.com/MolecularAI/REINVENT4 and released under the permissive Apache 2.0 license. Scientific contribution. The software provides an open-source reference implementation for generative molecular design where the software is also being used in production to support in-house drug discovery projects. The publication of the most common machine learning algorithms in one code and full documentation thereof will increase transparency of AI and foster innovation, collaboration and education.
Collapse
Affiliation(s)
- Hannes H Loeffler
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden.
| | - Jiazhen He
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden
| | - Alessandro Tibo
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden
| | - Jon Paul Janet
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden
| | - Alexey Voronov
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden
| | - Lewis H Mervin
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK
| | - Ola Engkvist
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden
| |
Collapse
|
39
|
Perkgoz C. Identifying optical microscope images of CVD-grown two-dimensional MoS 2 by convolutional neural networks and transfer learning. PeerJ Comput Sci 2024; 10:e1885. [PMID: 38435565 PMCID: PMC10909165 DOI: 10.7717/peerj-cs.1885] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 01/29/2024] [Indexed: 03/05/2024]
Abstract
Background In Complementary Metal-Oxide Semiconductor (CMOS) technology, scaling down has been a key strategy to improve chip performance and reduce power losses. However, challenges such as sub-threshold leakage and gate leakage, resulting from short-channel effects, contribute to an increase in distributed static power. Two-dimensional transition metal dichalcogenides (2D TMDs) emerge as potential solutions, serving as channel materials with steep sub-threshold swings and lower power consumption. However, the production and development of these 2-dimensional materials require some time-consuming tasks. In order to employ them in different fields, including chip technology, it is crucial to ensure that their production meets the required standards of quality and uniformity; in this context, deep learning techniques show significant potential. Methods This research introduces a transfer learning-based deep convolutional neural network (CNN) to classify chemical vapor deposition (CVD) grown molybdenum disulfide (MoS2) flakes based on their uniformity or the occurrence of defects affecting electronic properties. Acquiring and labeling a sufficient number of microscope images for CNN training may not be realistic. To address this challenge, artificial images were generated using Fresnel equations to pre-train the CNN. Subsequently, accuracy was improved through fine-tuning with a limited set of real images. Results The proposed transfer learning-based CNN method significantly improved all measurement metrics with respect to the ordinary CNNs. The initial CNN, trained with limited data and without transfer learning, achieved 68% average accuracy for binary classification. Through transfer learning and artificial images, the same CNN achieved 85% average accuracy, demonstrating an average increase of approximately 17%. While this study specifically focuses on MoS2 structures, the same methodology can be extended to other 2-dimensional materials by simply incorporating their specific parameters when generating artificial images.
Collapse
Affiliation(s)
- Cahit Perkgoz
- Department of Computer Engineering, Eskisehir Technical University, Eskişehir, Turkey
| |
Collapse
|
40
|
Reyes D, Sánchez J. Performance of convolutional neural networks for the classification of brain tumors using magnetic resonance imaging. Heliyon 2024; 10:e25468. [PMID: 38352765 PMCID: PMC10862681 DOI: 10.1016/j.heliyon.2024.e25468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Revised: 11/09/2023] [Accepted: 01/27/2024] [Indexed: 02/16/2024] Open
Abstract
Brain tumors are a diverse group of neoplasms that are challenging to detect and classify due to their varying characteristics. Deep learning techniques have proven to be effective in tumor classification. However, there is a lack of studies that compare these techniques using a common methodology. This work aims to analyze the performance of convolutional neural networks in the classification of brain tumors. We propose a network consisting of a few convolutional layers, batch normalization, and max-pooling. Then, we explore recent deep architectures, such as VGG, ResNet, EfficientNet, or ConvNeXt. The study relies on two magnetic resonance imaging datasets with over 3000 images of three types of tumors -gliomas, meningiomas, and pituitary tumors-, as well as images without tumors. We determine the optimal hyperparameters of the networks using the training and validation sets. The training and test sets are used to assess the performance of the models from different perspectives, including training from scratch, data augmentation, transfer learning, and fine-tuning. The experiments are performed using the TensorFlow and Keras libraries in Python. We compare the accuracy of the models and analyze their complexity based on the capacity of the networks, their training times, and image throughput. Several networks achieve high accuracy rates on both datasets, with the best model achieving 98.7% accuracy, which is on par with state-of-the-art methods. The average precision for each type of tumor is 94.3% for gliomas, 93.8% for meningiomas, 97.9% for pituitary tumors, and 95.3% for images without tumors. VGG is the largest model with over 171 million parameters, whereas MobileNet and EfficientNetB0 are the smallest ones with 3.2 and 5.9 million parameters, respectively. These two neural networks are also the fastest to train with 23.7 and 25.4 seconds per epoch, respectively. On the other hand, ConvNext is the slowest model with 58.2 seconds per epoch. Our custom model obtained the highest image throughput with 234.37 images per second, followed by MobileNet with 226 images per second. ConvNext obtained the smallest throughput with 97.35 images per second. ResNet, MobileNet, and EfficientNet are the most accurate networks, with MobileNet and EfficientNet demonstrating superior performance in terms of complexity. Most models achieve the best accuracy using transfer learning followed by a fine-tuning step. However, data augmentation does not contribute to increasing the accuracy of the models in general.
Collapse
Affiliation(s)
- Daniel Reyes
- Dr. Stetter ITQ S.L.U., Parque Científico Tecnológico, Las Palmas de Gran Canaria, 35017, Spain
- Department of Computer Science, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, 35017, Spain
| | - Javier Sánchez
- Department of Computer Science, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, 35017, Spain
| |
Collapse
|
41
|
Maurya A, Stanley RJ, Aradhyula HY, Lama N, Nambisan AK, Patel G, Saeed D, Swinfard S, Smith C, Jagannathan S, Hagerty JR, Stoecker WV. Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features. J Imaging Inform Med 2024:10.1007/s10278-024-00969-3. [PMID: 38332404 DOI: 10.1007/s10278-024-00969-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Revised: 09/22/2023] [Accepted: 10/27/2023] [Indexed: 02/10/2024]
Abstract
In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel "fusion" technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.
Collapse
Affiliation(s)
- Akanksha Maurya
- Missouri University of Science &Technology, Rolla, MO, 65209, USA
| | - R Joe Stanley
- Missouri University of Science &Technology, Rolla, MO, 65209, USA.
| | | | - Norsang Lama
- Missouri University of Science &Technology, Rolla, MO, 65209, USA
| | - Anand K Nambisan
- Missouri University of Science &Technology, Rolla, MO, 65209, USA
| | | | | | | | - Colin Smith
- A.T. Still University of Health Sciences, Kirksville, MO, USA
| | | | | | | |
Collapse
|
42
|
Rhomberg T, Trivik-Barrientos F, Hakim A, Raabe A, Murek M. Applied deep learning in neurosurgery: identifying cerebrospinal fluid (CSF) shunt systems in hydrocephalus patients. Acta Neurochir (Wien) 2024; 166:69. [PMID: 38321344 PMCID: PMC10847194 DOI: 10.1007/s00701-024-05940-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2023] [Accepted: 11/27/2023] [Indexed: 02/08/2024]
Abstract
BACKGROUND Over the recent decades, the number of different manufacturers and models of cerebrospinal fluid shunt valves constantly increased. Proper identification of shunt valves on X-ray images is crucial to neurosurgeons and radiologists to derive further details of a specific shunt valve, such as opening pressure settings and MR scanning conditions. The main aim of this study is to evaluate the feasibility of an AI-assisted shunt valve detection system. METHODS The dataset used contains 2070 anonymized images of ten different, commonly used shunt valve types. All images were acquired from skull X-rays or scout CT-images. The images were randomly split into a 80% training and 20% validation set. An implementation in Python with the FastAi library was used to train a convolutional neural network (CNN) using a transfer learning method on a pre-trained model. RESULTS Overall, our model achieved an F1-score of 99% to predict the correct shunt valve model. F1-scores for individual shunt valves ranged from 92% for the Sophysa Sophy Mini SM8 to 100% for several other models. CONCLUSION This technology has the potential to automatically detect different shunt valve models in a fast and precise way and may facilitate the identification of an unknown shunt valve on X-ray or CT scout images. The deep learning model we developed could be integrated into PACS systems or standalone mobile applications to enhance clinical workflows.
Collapse
Affiliation(s)
- Thomas Rhomberg
- Department of Neurosurgery, Inselspital, University Hospital Bern, Bern, Switzerland.
- Department of Neurosurgery and Neurorestoration, Klinikum Klagenfurt Am Wörthersee, Klagenfurt, Austria.
| | | | - Arsany Hakim
- Department of Neuroradiology, Inselspital, University Hospital Bern, Bern, Switzerland
| | - Andreas Raabe
- Department of Neurosurgery, Inselspital, University Hospital Bern, Bern, Switzerland
| | - Michael Murek
- Department of Neurosurgery, Inselspital, University Hospital Bern, Bern, Switzerland
| |
Collapse
|
43
|
Chilukoti SV, Shan L, Tida VS, Maida AS, Hei X. A reliable diabetic retinopathy grading via transfer learning and ensemble learning with quadratic weighted kappa metric. BMC Med Inform Decis Mak 2024; 24:37. [PMID: 38321416 DOI: 10.1186/s12911-024-02446-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2022] [Accepted: 01/29/2024] [Indexed: 02/08/2024] Open
Abstract
The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for doctors to identify them. Therefore, numerous predictive models based on machine learning (ML) and deep learning (DL) have been developed to determine all stages of DR. However, existing DR classification models cannot classify every DR stage or use a computationally heavy approach. Common metrics such as accuracy, F1 score, precision, recall, and AUC-ROC score are not reliable for assessing DR grading. This is because they do not account for two key factors: the severity of the discrepancy between the assigned and predicted grades and the ordered nature of the DR grading scale. This research proposes computationally efficient ensemble methods for the classification of DR. These methods leverage pre-trained model weights, reducing training time and resource requirements. In addition, data augmentation techniques are used to address data limitations, improve features, and improve generalization. This combination offers a promising approach for accurate and robust DR grading. In particular, we take advantage of transfer learning using models trained on DR data and employ CLAHE for image enhancement and Gaussian blur for noise reduction. We propose a three-layer classifier that incorporates dropout and ReLU activation. This design aims to minimize overfitting while effectively extracting features and assigning DR grades. We prioritize the Quadratic Weighted Kappa (QWK) metric due to its sensitivity to label discrepancies, which is crucial for an accurate diagnosis of DR. This combined approach achieves state-of-the-art QWK scores (0.901, 0.967 and 0.944) in the Eyepacs, Aptos, and Messidor datasets.
Collapse
Affiliation(s)
- Sai Venkatesh Chilukoti
- School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, 70503, LA, USA
| | - Liqun Shan
- School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, 70503, LA, USA
| | - Vijay Srinivas Tida
- Department of Computer Science, College of Saint Benedict and Saint John's University, St. Joseph, MN, 56374, USA
| | - Anthony S Maida
- School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, 70503, LA, USA
| | - Xiali Hei
- School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, 70503, LA, USA.
| |
Collapse
|
44
|
Ghosh S, Mitra P. MaTPIP: A deep-learning architecture with eXplainable AI for sequence-driven, feature mixed protein-protein interaction prediction. Comput Methods Programs Biomed 2024; 244:107955. [PMID: 38064959 DOI: 10.1016/j.cmpb.2023.107955] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 11/09/2023] [Accepted: 11/26/2023] [Indexed: 01/26/2024]
Abstract
BACKGROUND AND OBJECTIVE Protein-protein interaction (PPI) is a vital process in all living cells, controlling essential cell functions such as cell cycle regulation, signal transduction, and metabolic processes with broad applications that include antibody therapeutics, vaccines, and drug discovery. The problem of sequence-based PPI prediction has been a long-standing issue in computational biology. METHODS We introduce MaTPIP, a cutting-edge deep-learning framework for predicting PPI. MaTPIP stands out due to its innovative design, fusing pre-trained Protein Language Model (PLM)-based features with manually curated protein sequence attributes, emphasizing the part-whole relationship by incorporating two-dimensional granular part (amino-acid) level features and one-dimensional whole-level (protein) features. What sets MaTPIP apart is its ability to integrate these features across three different input terminals seamlessly. MatPIP also includes a distinctive configuration of Convolutional Neural Network (CNN) with Transformer components for concurrent utilization of CNN and sequential characteristics in each iteration and a one-dimensional to two-dimensional converter followed by a unified embedding. The statistical significance of this classifier is validated using McNemar's test. RESULTS MaTPIP outperformed the existing methods on both the Human PPI benchmark and cross-species PPI testing datasets, demonstrating its immense generalization capability for PPI prediction. We used seven diverse datasets with varying PPI target class distributions. Notably, within the novel PPI scenario, the most challenging category for Human PPI Benchmark, MaTPIP improves the existing state-of-the-art score from 74.1% to 78.6% (measured in Area under ROC Curve), from 23.2% to 32.8% (in average precision) and from 4.9% to 9.5% (in precision at 3% recall) for 50%, 10% and 0.3% target class distributions, respectively. In cross-species PPI evaluation, hybrid MaTPIP establishes a new benchmark score (measured in Area Under precision-recall curve) of 81.1% from the previous 60.9% for Mouse, 80.9% from 56.2% for Fly, 78.1% from 55.9% for Worm, 59.9% from 41.7% for Yeast, and 66.2% from 58.8% for E.coli. Our eXplainable AI-based assessment reveals an average contribution of different feature families per prediction on these datasets. CONCLUSIONS MaTPIP mixes manually curated features with the feature extracted from the pre-trained PLM to predict sequence-based protein-protein association. Furthermore, MaTPIP demonstrates strong generalization capabilities for cross-species PPI predictions.
Collapse
Affiliation(s)
- Shubhrangshu Ghosh
- Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, West Bengal, India; TCS Research, Tata Consultancy Services Limited, Kolkata, West Bengal, India
| | - Pralay Mitra
- Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, West Bengal, India.
| |
Collapse
|
45
|
Darvishi-Bayazi MJ, Ghaemi MS, Lesort T, Arefin MR, Faubert J, Rish I. Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning. Comput Biol Med 2024; 169:107893. [PMID: 38183700 DOI: 10.1016/j.compbiomed.2023.107893] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 11/28/2023] [Accepted: 12/20/2023] [Indexed: 01/08/2024]
Abstract
Pathology diagnosis based on EEG signals and decoding brain activity holds immense importance in understanding neurological disorders. With the advancement of artificial intelligence methods and machine learning techniques, the potential for accurate data-driven diagnoses and effective treatments has grown significantly. However, applying machine learning algorithms to real-world datasets presents diverse challenges at multiple levels. The scarcity of labeled data, especially in low regime scenarios with limited availability of real patient cohorts due to high costs of recruitment, underscores the vital deployment of scaling and transfer learning techniques. In this study, we explore a real-world pathology classification task to highlight the effectiveness of data and model scaling and cross-dataset knowledge transfer. As such, we observe varying performance improvements through data scaling, indicating the need for careful evaluation and labeling. Additionally, we identify the challenges of possible negative transfer and emphasize the significance of some key components to overcome distribution shifts and potential spurious correlations and achieve positive transfer. We see improvement in the performance of the target model on the target (NMT) datasets by using the knowledge from the source dataset (TUAB) when a low amount of labeled data was available. Our findings demonstrated that a small and generic model (e.g. ShallowNet) performs well on a single dataset, however, a larger model (e.g. TCN) performs better in transfer learning when leveraging a larger and more diverse dataset.
Collapse
Affiliation(s)
- Mohammad-Javad Darvishi-Bayazi
- Mila, Québec AI Institute, Montréal, QC, Canada; Faubert Lab, Montréal, QC, Canada; Université de Montréal, Montréal, QC, Canada.
| | | | - Timothee Lesort
- Mila, Québec AI Institute, Montréal, QC, Canada; Université de Montréal, Montréal, QC, Canada
| | - Md Rifat Arefin
- Mila, Québec AI Institute, Montréal, QC, Canada; Université de Montréal, Montréal, QC, Canada
| | - Jocelyn Faubert
- Faubert Lab, Montréal, QC, Canada; Université de Montréal, Montréal, QC, Canada
| | - Irina Rish
- Mila, Québec AI Institute, Montréal, QC, Canada; Université de Montréal, Montréal, QC, Canada
| |
Collapse
|
46
|
Kumar S, Kumar H, Kumar G, Singh SP, Bijalwan A, Diwakar M. A methodical exploration of imaging modalities from dataset to detection through machine learning paradigms in prominent lung disease diagnosis: a review. BMC Med Imaging 2024; 24:30. [PMID: 38302883 PMCID: PMC10832080 DOI: 10.1186/s12880-024-01192-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2023] [Accepted: 01/03/2024] [Indexed: 02/03/2024] Open
Abstract
BACKGROUND Lung diseases, both infectious and non-infectious, are the most prevalent cause of mortality overall in the world. Medical research has identified pneumonia, lung cancer, and Corona Virus Disease 2019 (COVID-19) as prominent lung diseases prioritized over others. Imaging modalities, including X-rays, computer tomography (CT) scans, magnetic resonance imaging (MRIs), positron emission tomography (PET) scans, and others, are primarily employed in medical assessments because they provide computed data that can be utilized as input datasets for computer-assisted diagnostic systems. Imaging datasets are used to develop and evaluate machine learning (ML) methods to analyze and predict prominent lung diseases. OBJECTIVE This review analyzes ML paradigms, imaging modalities' utilization, and recent developments for prominent lung diseases. Furthermore, the research also explores various datasets available publically that are being used for prominent lung diseases. METHODS The well-known databases of academic studies that have been subjected to peer review, namely ScienceDirect, arXiv, IEEE Xplore, MDPI, and many more, were used for the search of relevant articles. Applied keywords and combinations used to search procedures with primary considerations for review, such as pneumonia, lung cancer, COVID-19, various imaging modalities, ML, convolutional neural networks (CNNs), transfer learning, and ensemble learning. RESULTS This research finding indicates that X-ray datasets are preferred for detecting pneumonia, while CT scan datasets are predominantly favored for detecting lung cancer. Furthermore, in COVID-19 detection, X-ray datasets are prioritized over CT scan datasets. The analysis reveals that X-rays and CT scans have surpassed all other imaging techniques. It has been observed that using CNNs yields a high degree of accuracy and practicability in identifying prominent lung diseases. Transfer learning and ensemble learning are complementary techniques to CNNs to facilitate analysis. Furthermore, accuracy is the most favored metric for assessment.
Collapse
Affiliation(s)
- Sunil Kumar
- Department of Computer Engineering, J. C. Bose University of Science and Technology, YMCA, Faridabad, India
- Department of Information Technology, School of Engineering and Technology (UIET), CSJM University, Kanpur, India
| | - Harish Kumar
- Department of Computer Engineering, J. C. Bose University of Science and Technology, YMCA, Faridabad, India
| | - Gyanendra Kumar
- Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India
| | | | - Anchit Bijalwan
- Faculty of Electrical and Computer Engineering, Arba Minch University, Arba Minch, Ethiopia.
| | - Manoj Diwakar
- Department of Computer Science and Engineering, Graphic Era Deemed to Be University, Dehradun, India
| |
Collapse
|
47
|
Li J, Jiang P, An Q, Wang GG, Kong HF. Medical image identification methods: A review. Comput Biol Med 2024; 169:107777. [PMID: 38104516 DOI: 10.1016/j.compbiomed.2023.107777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 10/30/2023] [Accepted: 11/28/2023] [Indexed: 12/19/2023]
Abstract
The identification of medical images is an essential task in computer-aided diagnosis, medical image retrieval and mining. Medical image data mainly include electronic health record data and gene information data, etc. Although intelligent imaging provided a good scheme for medical image analysis over traditional methods that rely on the handcrafted features, it remains challenging due to the diversity of imaging modalities and clinical pathologies. Many medical image identification methods provide a good scheme for medical image analysis. The concepts pertinent of methods, such as the machine learning, deep learning, convolutional neural networks, transfer learning, and other image processing technologies for medical image are analyzed and summarized in this paper. We reviewed these recent studies to provide a comprehensive overview of applying these methods in various medical image analysis tasks, such as object detection, image classification, image registration, segmentation, and other tasks. Especially, we emphasized the latest progress and contributions of different methods in medical image analysis, which are summarized base on different application scenarios, including classification, segmentation, detection, and image registration. In addition, the applications of different methods are summarized in different application area, such as pulmonary, brain, digital pathology, brain, skin, lung, renal, breast, neuromyelitis, vertebrae, and musculoskeletal, etc. Critical discussion of open challenges and directions for future research are finally summarized. Especially, excellent algorithms in computer vision, natural language processing, and unmanned driving will be applied to medical image recognition in the future.
Collapse
Affiliation(s)
- Juan Li
- School of Information Engineering, Wuhan Business University, Wuhan, 430056, China; School of Artificial Intelligence, Wuchang University of Technology, Wuhan, 430223, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China
| | - Pan Jiang
- School of Information Engineering, Wuhan Business University, Wuhan, 430056, China
| | - Qing An
- School of Artificial Intelligence, Wuchang University of Technology, Wuhan, 430223, China
| | - Gai-Ge Wang
- School of Computer Science and Technology, Ocean University of China, Qingdao, 266100, China.
| | - Hua-Feng Kong
- School of Information Engineering, Wuhan Business University, Wuhan, 430056, China.
| |
Collapse
|
48
|
Tian W, Zhang Z, Bouffard D, Wu H, Xin K, Gu X, Liao Z. Enhancing interpretability and generalizability of deep learning-based emulator in three-dimensional lake hydrodynamics using Koopman operator and transfer learning: Demonstrated on the example of lake Zurich. Water Res 2024; 249:120996. [PMID: 38103441 DOI: 10.1016/j.watres.2023.120996] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 11/02/2023] [Accepted: 12/07/2023] [Indexed: 12/19/2023]
Abstract
Three-dimensional lake hydrodynamic model is a powerful tool widely used to assess hydrological condition changes of lake. However, its computational cost becomes problematic when forecasting the state of large lakes or using high-resolution simulation in small-to-medium size lakes. One possible solution is to employ a data-driven emulator, such as a deep learning (DL) based emulator, to replace the original model for fast computing. However, existing DL-based emulators are often black-box and data-dependent models, causing poor interpretability and generalizability in practical applications. In this study, a data-driven emulator is established using deep neural network (DNN) to replace the original model for fast computing of three-dimensional lake hydrodynamics. Then, the Koopman operator and transfer learning (TL) are employed to enhance the interpretability and generalizability of the emulator. Finally, the generalizability of DL-based emulators is comprehensively analyzed through linear regression and correlation analysis. These methods are tested against an existing hydrodynamic model of Lake Zurich (Switzerland) whose data was provided by an open-source web-based platform called Meteolakes/Alplakes. According to the results, (1) The DLEDMD offers better interpretability than DNN because its Koopman operator reveals the linear structure behind the hydrodynamics; (2) The generalization of the DL-based emulators in three-dimensional lake hydrodynamics are influenced by the similarity between the training and testing data; (3) TL effectively improves the generalizability of the DL-based emulators.
Collapse
Affiliation(s)
- Wenchong Tian
- College of Environmental Science and Engineering, Tongji University, 200092 Shanghai, China; Key Laboratory of Yangtze River Water Environment, Ministry of Education, Tongji University, 200092 Shanghai, China; Key Laboratory of Urban Water Supply, Water Saving and Water Environment Governance in the Yangtze River Delta of Ministry of Water Resources, Shanghai 200092, P.R. China
| | - Zhiyu Zhang
- College of Environmental Science and Engineering, Tongji University, 200092 Shanghai, China; Key Laboratory of Yangtze River Water Environment, Ministry of Education, Tongji University, 200092 Shanghai, China
| | - Damien Bouffard
- Eawag, Swiss Federal Institute of Aquatic Science and Technology, Surface Waters Research and Management, 6047 Kastanienbaum, Switzerland; Faculty of Geosciences and Environment, Institute of Earth Surface Dynamics, University of Lausanne, Geopolis, Mouline, CH-1015 Lausanne, Switzerland
| | - Hao Wu
- School of Mathematical Sciences, Institute of Natural Sciences, and MOE-LSC, Shanghai Jiao Tong University, Shanghai, China; School of Mathematical Sciences, Tongji University, Shanghai, China
| | - Kunlun Xin
- College of Environmental Science and Engineering, Tongji University, 200092 Shanghai, China
| | - Xianyong Gu
- National Engineering Research Center of Dredging Technology and Equipment Co., Ltd., 201208 Shanghai, China
| | - Zhenliang Liao
- College of Environmental Science and Engineering, Tongji University, 200092 Shanghai, China; Key Laboratory of Yangtze River Water Environment, Ministry of Education, Tongji University, 200092 Shanghai, China.
| |
Collapse
|
49
|
Bao Z, Huang Z, Gou J, Du L, Liu K, Zhou J, Chen Y. Teacher-student complementary sample contrastive distillation. Neural Netw 2024; 170:176-189. [PMID: 37989039 DOI: 10.1016/j.neunet.2023.11.036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Revised: 09/08/2023] [Accepted: 11/15/2023] [Indexed: 11/23/2023]
Abstract
Knowledge distillation (KD) is a widely adopted model compression technique for improving the performance of compact student models, by utilizing the "dark knowledge" of a large teacher model. However, previous studies have not adequately investigated the effectiveness of supervision from the teacher model, and overconfident predictions in the student model may degrade its performance. In this work, we propose a novel framework, Teacher-Student Complementary Sample Contrastive Distillation (TSCSCD), that alleviate these challenges. TSCSCD consists of three key components: Contrastive Sample Hardness (CSH), Supervision Signal Correction (SSC), and Student Self-Learning (SSL). Specifically, CSH evaluates the teacher's supervision for each sample by comparing the predictions of two compact models, one distilled from the teacher and the other trained from scratch. SSC corrects weak supervision according to CSH, while SSL employs integrated learning among multi-classifiers to regularize overconfident predictions. Extensive experiments on four real-world datasets demonstrate that TSCSCD outperforms recent state-of-the-art knowledge distillation techniques.
Collapse
Affiliation(s)
- Zhiqiang Bao
- School of Computer Science, South China Normal University, South China Normal University, Guangzhou, 510631, Guangdong, China
| | - Zhenhua Huang
- School of Computer Science, South China Normal University, South China Normal University, Guangzhou, 510631, Guangdong, China.
| | - Jianping Gou
- College of Computer and Information Science, College of Software, Southwest University, Chongqing, 400715, Chongqing, China
| | - Lan Du
- Faculty of Information Technology, Monash University, Melbourne, VIC 3800, Victoria, Australia
| | - Kang Liu
- School of Computer Science, South China Normal University, South China Normal University, Guangzhou, 510631, Guangdong, China
| | - Jingtao Zhou
- School of Computer Science, South China Normal University, South China Normal University, Guangzhou, 510631, Guangdong, China
| | - Yunwen Chen
- Research and Development Department, DataGrand Inc., Shanghai, 201203, China
| |
Collapse
|
50
|
Yadav N, Sorek-Hamer M, Von Pohle M, Asanjan AA, Sahasrabhojanee A, Suel E, E Arku R, Lingenfelter V, Brauer M, Ezzati M, Oza N, Ganguly AR. Using deep transfer learning and satellite imagery to estimate urban air quality in data-poor regions. Environ Pollut 2024; 342:122914. [PMID: 38000726 PMCID: PMC7615387 DOI: 10.1016/j.envpol.2023.122914] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 11/08/2023] [Accepted: 11/09/2023] [Indexed: 11/26/2023]
Abstract
Urban air pollution is a critical public health challenge in low-and-middle-income countries (LMICs). At the same time, LMICs tend to be data-poor, lacking adequate infrastructure to monitor air quality (AQ). As LMICs undergo rapid urbanization, the socio-economic burden of poor AQ will be immense. Here we present a globally scalable two-step deep learning (DL) based approach for AQ estimation in LMIC cities that mitigates the need for extensive AQ infrastructure on the ground. We train a DL model that can map satellite imagery to AQ in high-income countries (HICs) with sufficient ground data, and then adapt the model to learn meaningful AQ estimates in LMIC cities using transfer learning. The trained model can explain up to 54% of the variation in the AQ distribution of the target LMIC city without the need for target labels. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned and adapted from two HIC cities, specifically Los Angeles and New York.
Collapse
Affiliation(s)
- Nishant Yadav
- Sustainability and Data Sciences Laboratory, Northeastern University, Boston, USA; University Space Research Association (USRA), Mountain View, USA.
| | - Meytar Sorek-Hamer
- University Space Research Association (USRA), Mountain View, USA; NASA Ames Research Center, Moffett Field, USA
| | - Michael Von Pohle
- University Space Research Association (USRA), Mountain View, USA; NASA Ames Research Center, Moffett Field, USA
| | - Ata Akbari Asanjan
- University Space Research Association (USRA), Mountain View, USA; NASA Ames Research Center, Moffett Field, USA
| | - Adwait Sahasrabhojanee
- University Space Research Association (USRA), Mountain View, USA; NASA Ames Research Center, Moffett Field, USA
| | | | | | - Violet Lingenfelter
- Sustainability and Data Sciences Laboratory, Northeastern University, Boston, USA; University Space Research Association (USRA), Mountain View, USA
| | | | | | - Nikunj Oza
- NASA Ames Research Center, Moffett Field, USA
| | - Auroop R Ganguly
- Sustainability and Data Sciences Laboratory, Northeastern University, Boston, USA; Pacific Northwest National Laboratory (PNNL), Richland, USA; The Institute for Experiential AI, Northeastern University, Boston, USA
| |
Collapse
|