1
|
Mercaldo F, Brunese L, Martinelli F, Santone A, Cesarelli M. Explainable Convolutional Neural Networks for Brain Cancer Detection and Localisation. SENSORS (BASEL, SWITZERLAND) 2023; 23:7614. [PMID: 37688069 PMCID: PMC10490676 DOI: 10.3390/s23177614] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 08/07/2023] [Accepted: 08/31/2023] [Indexed: 09/10/2023]
Abstract
Brain cancer is widely recognised as one of the most aggressive types of tumors. In fact, approximately 70% of patients diagnosed with this malignant cancer do not survive. In this paper, we propose a method aimed to detect and localise brain cancer, starting from the analysis of magnetic resonance images. The proposed method exploits deep learning, in particular convolutional neural networks and class activation mapping, in order to provide explainability by highlighting the areas of the medical image related to brain cancer (from the model point of view). We evaluate the proposed method with 3000 magnetic resonances using a free available dataset. The results we obtained are encouraging. We reach an accuracy ranging from 97.83% to 99.67% in brain cancer detection by exploiting four different models: VGG16, ResNet50, Alex_Net, and MobileNet, thus showing the effectiveness of the proposed method.
Collapse
Affiliation(s)
- Francesco Mercaldo
- Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, Italy; (L.B.); (A.S.)
- Institute for Informatics and Telematics, National Research Council of Italy, 56121 Pisa, Italy
| | - Luca Brunese
- Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, Italy; (L.B.); (A.S.)
| | - Fabio Martinelli
- Institute for Informatics and Telematics, National Research Council of Italy, 56121 Pisa, Italy
| | - Antonella Santone
- Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, Italy; (L.B.); (A.S.)
| | - Mario Cesarelli
- Department of Engineering, University of Sannio, 82100 Benevento, Italy;
| |
Collapse
|
2
|
Zhou Y. IYOLO-NL: An improved you only look once and none left object detector for real-time face mask detection. Heliyon 2023; 9:e19064. [PMID: 37636416 PMCID: PMC10457516 DOI: 10.1016/j.heliyon.2023.e19064] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Revised: 08/09/2023] [Accepted: 08/09/2023] [Indexed: 08/29/2023] Open
Abstract
Object detection is a fundamental task in computer vision that aims to locate and classify objects in images or videos. The one-stage You Only Look Once (YOLO) models are popular approaches to object detection. Real-time monitoring of mask wearing is necessary, especially for preventing the spread of the COVID-19 virus. While YOLO detectors facing challenges include improving the robustness of object detectors against occlusion, scale variation, handling false detection and false negative, and maintaining the balance between higher precision detection and faster inference time. In this study, a novel object detection model called Improved You Only Look Once and None Left (IYOLO-NL) based on YOLOv5 was proposed for real-time mask wearing detection. To fulfill the requirement of real-time detection, the lightweight IYOLO-NL was developed by using novel CSPNet-Ghost and SSPP bottleneck architecture. To prevent any missed correct results, IYOLO-NL integrates the proposed PANet-SC with a multi-level prediction scheme. To achieve high precision and handle sample allocation properly, the proposed global dynamic-k label assignment strategy was utilized in an anchor-free manner. A large dataset of face masks (FMD) was created, consisting of 6130 images, for use in conducting experiments on IYOLO-NL and other models. The experiment results show that IYOLO-NL surpasses other state-of-the-art (SOTA) methods and achieves 98.8% accuracy while maintaining 130 FPS.
Collapse
Affiliation(s)
- Yan Zhou
- Ocean College, Zhejiang University, Zhoushan, 316021, China
- State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, 310012, China
| |
Collapse
|
3
|
Real-Time Facemask Detection for Preventing COVID-19 Spread Using Transfer Learning Based Deep Neural Network. ELECTRONICS 2022. [DOI: 10.3390/electronics11142250] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
The COVID-19 pandemic disrupted people’s livelihoods and hindered global trade and transportation. During the COVID-19 pandemic, the World Health Organization mandated that masks be worn to protect against this deadly virus. Protecting one’s face with a mask has become the standard. Many public service providers will encourage clients to wear masks properly in the foreseeable future. On the other hand, monitoring the individuals while standing alone in one location is exhausting. This paper offers a solution based on deep learning for identifying masks worn over faces in public places to minimize the coronavirus community transmission. The main contribution of the proposed work is the development of a real-time system for determining whether the person on a webcam is wearing a mask or not. The ensemble method makes it easier to achieve high accuracy and makes considerable strides toward enhancing detection speed. In addition, the implementation of transfer learning on pretrained models and stringent testing on an objective dataset led to the development of a highly dependable and inexpensive solution. The findings provide validity to the application’s potential for use in real-world settings, contributing to the reduction in pandemic transmission. Compared to the existing methodologies, the proposed method delivers improved accuracy, specificity, precision, recall, and F-measure performance in three-class outputs. These metrics include accuracy, specificity, precision, and recall. An appropriate balance is kept between the number of necessary parameters and the time needed to conclude the various models.
Collapse
|
4
|
Wang Z, Sun W, Zhu Q, Shi P. Face Mask-Wearing Detection Model Based on Loss Function and Attention Mechanism. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:2452291. [PMID: 35865498 PMCID: PMC9296297 DOI: 10.1155/2022/2452291] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 06/15/2022] [Indexed: 11/17/2022]
Abstract
Face mask-wearing detection is of great significance for safety protection during the epidemic. Aiming at the problem of low detection accuracy due to the problems of occlusion, complex illumination, and density in mask-wearing detection, this paper proposes a neural network model based on the loss function and attention mechanism for mask-wearing detection in complex environments. Based on YOLOv5s, we first introduce an attention mechanism in the feature fusion process to improve feature utilization, study the effect of different attention mechanisms (CBAM, SE, and CA) on improving deep network models, and then explore the influence of different bounding box loss functions (GIoU, CIoU, and DIoU) on mask-wearing recognition. CIoU is used as the frame regression loss function to improve the positioning accuracy. By collecting 7,958 mask-wearing images and a large number of images of people without masks as a dataset and using YOLOv5s as the benchmark model, the mAP of the model proposed in the paper reached 90.96% on the validation set, which is significantly better than the traditional deep learning method. Mask-wearing detection is carried out in a real environment, and the experimental results of the proposed method can meet the daily detection requirements.
Collapse
Affiliation(s)
- Zhong Wang
- School of Computer Science and Technology, Hefei Normal University, Hefei 230601, China
| | - Wu Sun
- School of Computer Science and Technology, Hefei Normal University, Hefei 230601, China
| | - Qiang Zhu
- School of Computer Science and Technology, Hefei Normal University, Hefei 230601, China
| | - Peibei Shi
- School of Computer Science and Technology, Hefei Normal University, Hefei 230601, China
| |
Collapse
|
5
|
Mar-Cupido R, García V, Rivera G, Sánchez JS. Deep transfer learning for the recognition of types of face masks as a core measure to prevent the transmission of COVID-19. Appl Soft Comput 2022; 125:109207. [PMID: 35765303 PMCID: PMC9222491 DOI: 10.1016/j.asoc.2022.109207] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2021] [Revised: 05/31/2022] [Accepted: 06/19/2022] [Indexed: 11/21/2022]
Abstract
The use of face masks in public places has emerged as one of the most effective non-pharmaceutical measures to lower the spread of COVID-19 infection. This has led to the development of several detection systems for identifying people who do not wear a face mask. However, not all face masks or coverings are equally effective in preventing virus transmission or illness caused by viruses and therefore, it appears important for those systems to incorporate the ability to distinguish between the different types of face masks. This paper implements four pre-trained deep transfer learning models (NasNetMobile, MobileNetv2, ResNet101v2, and ResNet152v2) to classify images based on the type of face mask (KN95, N95, surgical and cloth) worn by people. Experimental results indicate that the deep residual networks (ResNet101v2 and ResNet152v2) provide the best performance with the highest accuracy and the lowest loss.
Collapse
Affiliation(s)
- Ricardo Mar-Cupido
- División Multidisciplinaria en Ciudad Universitaria, Universidad Autónoma de Ciudad Juárez, Av. José de Jesús Delgado 18100, Ciudad Juárez, Chihuahua, Mexico
| | - Vicente García
- División Multidisciplinaria en Ciudad Universitaria, Universidad Autónoma de Ciudad Juárez, Av. José de Jesús Delgado 18100, Ciudad Juárez, Chihuahua, Mexico
| | - Gilberto Rivera
- División Multidisciplinaria en Ciudad Universitaria, Universidad Autónoma de Ciudad Juárez, Av. José de Jesús Delgado 18100, Ciudad Juárez, Chihuahua, Mexico
| | - J Salvador Sánchez
- Institute of New Imaging Technologies, Department of Computer Languages and Systems, Universitat Jaume I, Av. de Vicent Sos Baynat, s/n 12071 Castelló de la Plana, Spain
| |
Collapse
|
6
|
Azouji N, Sami A, Taheri M. EfficientMask-Net for face authentication in the era of COVID-19 pandemic. SIGNAL, IMAGE AND VIDEO PROCESSING 2022; 16:1991-1999. [PMID: 35469317 PMCID: PMC9022166 DOI: 10.1007/s11760-022-02160-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/04/2021] [Revised: 11/20/2021] [Accepted: 01/21/2022] [Indexed: 06/14/2023]
Abstract
Today, we are facing the COVID-19 pandemic. Accordingly, properly wearing face masks has become vital as an effective way to prevent the rapid spread of COVID-19. This research develops an Efficient Mask-Net method for low-power devices, such as mobile and embedding models with low-memory requirements. The method identifies face mask-wearing conditions in two different schemes: I. Correctly Face Mask (CFM), Incorrectly Face Mask (IFM), and Not Face Mask (NFM) wearing; II. Uncovered Chin IFM, Uncovered Nose IFM, and Uncovered Nose and Mouth IFM. The proposed method can also be helpful to unmask the face for face authentication based on unconstrained 2D facial images in the wild. In this study, deep convolutional neural networks (CNNs) were employed as feature extractors. Then, deep features were fed to a recently proposed large margin piecewise linear (LMPL) classifier. In the experimental study, lightweight and very powerful mobile implementation of CNN models were evaluated, where the novel "EffientNetb0" deep feature extractor with LMPL classifier outperformed well-known end-to-end CNN models, as well as conventional image classification methods. It achieved high accuracies of 99.53 and 99.64% in fulfilling the two mentioned tasks, respectively.
Collapse
Affiliation(s)
- Neda Azouji
- Department of Computer Science and Engineering and IT, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
| | - Ashkan Sami
- Department of Computer Science and Engineering and IT, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
| | - Mohammad Taheri
- Department of Computer Science and Engineering and IT, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
| |
Collapse
|
7
|
Bakken S. Biomedical and health informatics continue to contribute to COVID-19 pandemic solutions and beyond. J Am Med Inform Assoc 2021; 28:1361-1362. [PMID: 34261133 PMCID: PMC8279786 DOI: 10.1093/jamia/ocab130] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Suzanne Bakken
- School of Nursing, Department of Biomedical Informatics, and Data Science Institute, Columbia University, New York, New York, USA
| |
Collapse
|