GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data
    MDPI AG ; 2021
    In:  Cancers Vol. 13, No. 7 ( 2021-03-30), p. 1590-
    Details
    In: Cancers, MDPI AG, Vol. 13, No. 7 ( 2021-03-30), p. 1590-
    Abstract: Deep learning requires a large amount of data to perform well. However, the field of medical image analysis suffers from a lack of sufficient data for training deep learning models. Moreover, medical images require manual labeling, usually provided by human annotators coming from various backgrounds. More importantly, the annotation process is time-consuming, expensive, and prone to errors. Transfer learning was introduced to reduce the need for the annotation process by transferring the deep learning models with knowledge from a previous task and then by fine-tuning them on a relatively small dataset of the current task. Most of the methods of medical image classification employ transfer learning from pretrained models, e.g., ImageNet, which has been proven to be ineffective. This is due to the mismatch in learned features between the natural image, e.g., ImageNet, and medical images. Additionally, it results in the utilization of deeply elaborated models. In this paper, we propose a novel transfer learning approach to overcome the previous drawbacks by means of training the deep learning model on large unlabeled medical image datasets and by next transferring the knowledge to train the deep learning model on the small amount of labeled medical images. Additionally, we propose a new deep convolutional neural network (DCNN) model that combines recent advancements in the field. We conducted several experiments on two challenging medical imaging scenarios dealing with skin and breast cancer classification tasks. According to the reported results, it has been empirically proven that the proposed approach can significantly improve the performance of both classification scenarios. In terms of skin cancer, the proposed model achieved an F1-score value of 89.09% when trained from scratch and 98.53% with the proposed approach. Secondly, it achieved an accuracy value of 85.29% and 97.51%, respectively, when trained from scratch and using the proposed approach in the case of the breast cancer scenario. Finally, we concluded that our method can possibly be applied to many medical imaging problems in which a substantial amount of unlabeled image data is available and the labeled image data is limited. Moreover, it can be utilized to improve the performance of medical imaging tasks in the same domain. To do so, we used the pretrained skin cancer model to train on feet skin to classify them into two classes—either normal or abnormal (diabetic foot ulcer (DFU)). It achieved an F1-score value of 86.0% when trained from scratch, 96.25% using transfer learning, and 99.25% using double-transfer learning.
    Type of Medium: Online Resource
    ISSN: 2072-6694
    URL: Article
    DOI: 10.3390/cancers13071590
    Language: English
    Publisher: MDPI AG
    Publication Date: 2021
    detail.hit.zdb_id: 2527080-1
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
    Springer Science and Business Media LLC ; 2021
    In:  Journal of Big Data Vol. 8, No. 1 ( 2021-03-31)
    Details
    In: Journal of Big Data, Springer Science and Business Media LLC, Vol. 8, No. 1 ( 2021-03-31)
    Abstract: In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.
    Type of Medium: Online Resource
    ISSN: 2196-1115
    URL: Article
    DOI: 10.1186/s40537-021-00444-8
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2021
    detail.hit.zdb_id: 2780218-8
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Table 9: Results of the proposed model with TL.
    PeerJ ; 2021
    In:  PeerJ Computer Science Vol. 7 ( 2021-09-28), p. e715-
    Details
    In: PeerJ Computer Science, PeerJ, Vol. 7 ( 2021-09-28), p. e715-
    Abstract: Transfer learning (TL) has been widely utilized to address the lack of training data for deep learning models. Specifically, one of the most popular uses of TL has been for the pre-trained models of the ImageNet dataset. Nevertheless, although these pre-trained models have shown an effective performance in several domains of application, those models may not offer significant benefits in all instances when dealing with medical imaging scenarios. Such models were designed to classify a thousand classes of natural images. There are fundamental differences between these models and those dealing with medical imaging tasks regarding learned features. Most medical imaging applications range from two to ten different classes, where we suspect that it would not be necessary to employ deeper learning models. This paper investigates such a hypothesis and develops an experimental study to examine the corresponding conclusions about this issue. The lightweight convolutional neural network (CNN) model and the pre-trained models have been evaluated using three different medical imaging datasets. We have trained the lightweight CNN model and the pre-trained models with two scenarios which are with a small number of images once and a large number of images once again. Surprisingly, it has been found that the lightweight model trained from scratch achieved a more competitive performance when compared to the pre-trained model. More importantly, the lightweight CNN model can be successfully trained and tested using basic computational tools and provide high-quality results, specifically when using medical imaging datasets.
    Type of Medium: Online Resource
    ISSN: 2376-5992
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    URL: Article
    DOI: 10.7717/peerj-cs.715
    DOI: 10.7717/peerj-cs.715/fig-1
    DOI: 10.7717/peerj-cs.715/fig-2
    DOI: 10.7717/peerj-cs.715/fig-3
    DOI: 10.7717/peerj-cs.715/fig-4
    DOI: 10.7717/peerj-cs.715/fig-5
    DOI: 10.7717/peerj-cs.715/fig-6
    DOI: 10.7717/peerj-cs.715/fig-7
    DOI: 10.7717/peerj-cs.715/fig-8
    DOI: 10.7717/peerj-cs.715/fig-9
    DOI: 10.7717/peerj-cs.715/fig-10
    DOI: 10.7717/peerj-cs.715/fig-11
    DOI: 10.7717/peerj-cs.715/fig-12
    DOI: 10.7717/peerj-cs.715/fig-13
    DOI: 10.7717/peerj-cs.715/fig-14
    DOI: 10.7717/peerj-cs.715/table-1
    DOI: 10.7717/peerj-cs.715/table-2
    DOI: 10.7717/peerj-cs.715/table-3
    DOI: 10.7717/peerj-cs.715/table-4
    DOI: 10.7717/peerj-cs.715/table-5
    DOI: 10.7717/peerj-cs.715/table-6
    DOI: 10.7717/peerj-cs.715/table-7
    DOI: 10.7717/peerj-cs.715/table-8
    DOI: 10.7717/peerj-cs.715/table-9
    Language: English
    Publisher: PeerJ
    Publication Date: 2021
    detail.hit.zdb_id: 2868384-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Statistical accuracy analysis of different detecting algorithms for surveillance system in smart city
    Institute of Advanced Engineering and Science ; 2020
    In:  Indonesian Journal of Electrical Engineering and Computer Science Vol. 18, No. 2 ( 2020-05-01), p. 979-
    Details
    In: Indonesian Journal of Electrical Engineering and Computer Science, Institute of Advanced Engineering and Science, Vol. 18, No. 2 ( 2020-05-01), p. 979-
    Abstract: 〈 span 〉 Several detecting algorithms are developed for real-time surveillance systems in the smart cities. The most popular algorithms due to its accuracy are: Temporal Differencing, Background Subtraction, and Gaussian Mixture Models. Selecting of which algorithm is the best to be used, based on accuracy, is a good choise, but is not the best. Statistical accuracy anlysis tests are required for achieving a confident decision. This paper presents further analysis of the accuracy by employing four parameters: false recognition, unrecognized, true recognition, and total fragmentation ratios. The results proof that no algorithm is selected as the perfect or suitable for all applications based on the total fragmentation ratio, whereas both false recognition ratio and unrecognized ratio parameters have a significant impact. The mlti-way Analysis of Variate (so-called K-way ANONVA) is used for proofing the results based on SPSS statistics. 〈 /span 〉
    Type of Medium: Online Resource
    ISSN: 2502-4760 , 2502-4752
    URL: Issue
    URL: Article
    DOI: 10.11591/ijeecs.v18.i2
    DOI: 10.11591/ijeecs.v18.i2.pp979-986
    Language: Unknown
    Publisher: Institute of Advanced Engineering and Science
    Publication Date: 2020
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    نهج إحصائي جديد للحصول على أفضل شريحة رؤية في تسلسل الرنين المغناطيسي لأورام الدماغ
    College of Science for Women, University of Baghdad ; 2024
    In:  Baghdad Science Journal ( 2024-04-20)
    Details
    In: Baghdad Science Journal, College of Science for Women, University of Baghdad, ( 2024-04-20)
    Abstract: Early diagnosis of brain tumor enhances the possibility of patients being cured. With the progress of the use of artificial intelligence in the medical field, the detection of brain tumors has become one of the researchers’ interests. Obtaining which slice in the MRI sequence gives the best visibility of the tumor is still a challenge. This paper introduced a novel statistical approach to extracting the tumor from the patient's MRI scan (sequence). Initially, the probability mass function (PMF) was computed for each image in the sequence. Then, the Kullback-Leibler divergence technique was applied to determine the tumor image(s) that diverged from the respective healthy ones. The best tumor visibility slice was determined using the root mean square error metric. In addition, a clustering approach was applied to segment the tumor images. The vector quantization (VQ) method was utilized for grouping the images into 16 different clusters, while a reverse VQ technique was employed to produce two-tone images. Finally, a 2D Teager operator was used to detect the edges for tumor demarcation. A private dataset of twenty MRI scans (sequences) was used for testing and evaluating the system.
    Type of Medium: Online Resource
    ISSN: 2411-7986 , 2078-8665
    URL: Issue
    URL: Article
    DOI: 10.21123/bsj.2024.21.11
    DOI: 10.21123/bsj.2024.9311
    Language: English
    Publisher: College of Science for Women, University of Baghdad
    Publication Date: 2024
    detail.hit.zdb_id: 2727652-1
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study
    MDPI AG ; 2020
    In:  Applied Sciences Vol. 10, No. 13 ( 2020-06-29), p. 4523-
    Details
    In: Applied Sciences, MDPI AG, Vol. 10, No. 13 ( 2020-06-29), p. 4523-
    Abstract: One of the main challenges of employing deep learning models in the field of medicine is a lack of training data due to difficulty in collecting and labeling data, which needs to be performed by experts. To overcome this drawback, transfer learning (TL) has been utilized to solve several medical imaging tasks using pre-trained state-of-the-art models from the ImageNet dataset. However, there are primary divergences in data features, sizes, and task characteristics between the natural image classification and the targeted medical imaging tasks. Therefore, TL can slightly improve performance if the source domain is completely different from the target domain. In this paper, we explore the benefit of TL from the same and different domains of the target tasks. To do so, we designed a deep convolutional neural network (DCNN) model that integrates three ideas including traditional and parallel convolutional layers and residual connections along with global average pooling. We trained the proposed model against several scenarios. We utilized the same and different domain TL with the diabetic foot ulcer (DFU) classification task and with the animal classification task. We have empirically shown that the source of TL from the same domain can significantly improve the performance considering a reduced number of images in the same domain of the target dataset. The proposed model with the DFU dataset achieved F1-score value of 86.6% when trained from scratch, 89.4% with TL from a different domain of the targeted dataset, and 97.6% with TL from the same domain of the targeted dataset.
    Type of Medium: Online Resource
    ISSN: 2076-3417
    URL: Article
    DOI: 10.3390/app10134523
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2704225-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model
    MDPI AG ; 2020
    In:  Electronics Vol. 9, No. 3 ( 2020-03-06), p. 445-
    Details
    In: Electronics, MDPI AG, Vol. 9, No. 3 ( 2020-03-06), p. 445-
    Abstract: Breast cancer is a significant factor in female mortality. An early cancer diagnosis leads to a reduction in the breast cancer death rate. With the help of a computer-aided diagnosis system, the efficiency increased, and the cost was reduced for the cancer diagnosis. Traditional breast cancer classification techniques are based on handcrafted features techniques, and their performance relies upon the chosen features. They also are very sensitive to different sizes and complex shapes. However, histopathological breast cancer images are very complex in shape. Currently, deep learning models have become an alternative solution for diagnosis, and have overcome the drawbacks of classical classification techniques. Although deep learning has performed well in various tasks of computer vision and pattern recognition, it still has some challenges. One of the main challenges is the lack of training data. To address this challenge and optimize the performance, we have utilized a transfer learning technique which is where the deep learning models train on a task, and then fine-tune the models for another task. We have employed transfer learning in two ways: Training our proposed model first on the same domain dataset, then on the target dataset, and training our model on a different domain dataset, then on the target dataset. We have empirically proven that the same domain transfer learning optimized the performance. Our hybrid model of parallel convolutional layers and residual links is utilized to classify hematoxylin–eosin-stained breast biopsy images into four classes: invasive carcinoma, in-situ carcinoma, benign tumor and normal tissue. To reduce the effect of overfitting, we have augmented the images with different image processing techniques. The proposed model achieved state-of-the-art performance, and it outperformed the latest methods by achieving a patch-wise classification accuracy of 90.5%, and an image-wise classification accuracy of 97.4% on the validation set. Moreover, we have achieved an image-wise classification accuracy of 96.1% on the test set of the microscopy ICIAR-2018 dataset.
    Type of Medium: Online Resource
    ISSN: 2079-9292
    URL: Article
    DOI: 10.3390/electronics9030445
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2662127-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    Deep Learning Models for Classification of Red Blood Cells in Microscopy Images to Aid in Sickle Cell Anemia Diagnosis
    MDPI AG ; 2020
    In:  Electronics Vol. 9, No. 3 ( 2020-03-04), p. 427-
    Details
    In: Electronics, MDPI AG, Vol. 9, No. 3 ( 2020-03-04), p. 427-
    Abstract: Sickle cell anemia, which is also called sickle cell disease (SCD), is a hematological disorder that causes occlusion in blood vessels, leading to hurtful episodes and even death. The key function of red blood cells (erythrocytes) is to supply all the parts of the human body with oxygen. Red blood cells (RBCs) form a crescent or sickle shape when sickle cell anemia affects them. This abnormal shape makes it difficult for sickle cells to move through the bloodstream, hence decreasing the oxygen flow. The precise classification of RBCs is the first step toward accurate diagnosis, which aids in evaluating the danger level of sickle cell anemia. The manual classification methods of erythrocytes require immense time, and it is possible that errors may be made throughout the classification stage. Traditional computer-aided techniques, which have been employed for erythrocyte classification, are based on handcrafted features techniques, and their performance relies on the selected features. They also are very sensitive to different sizes, colors, and complex shapes. However, microscopy images of erythrocytes are very complex in shape with different sizes. To this end, this research proposes lightweight deep learning models that classify the erythrocytes into three classes: circular (normal), elongated (sickle cells), and other blood content. These models are different in the number of layers and learnable filters. The available datasets of red blood cells with sickle cell disease are very small for training deep learning models. Therefore, addressing the lack of training data is the main aim of this paper. To tackle this issue and optimize the performance, the transfer learning technique is utilized. Transfer learning does not significantly affect performance on medical image tasks when the source domain is completely different from the target domain. In some cases, it can degrade the performance. Hence, we have applied the same domain transfer learning, unlike other methods that used the ImageNet dataset for transfer learning. To minimize the overfitting effect, we have utilized several data augmentation techniques. Our model obtained state-of-the-art performance and outperformed the latest methods by achieving an accuracy of 99.54% with our model and 99.98% with our model plus a multiclass SVM classifier on the erythrocytesIDB dataset and 98.87% on the collected dataset.
    Type of Medium: Online Resource
    ISSN: 2079-9292
    URL: Article
    DOI: 10.3390/electronics9030427
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2662127-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification
    MDPI AG ; 2022
    In:  Applied Sciences Vol. 12, No. 5 ( 2022-03-02), p. 2605-
    Details
    In: Applied Sciences, MDPI AG, Vol. 12, No. 5 ( 2022-03-02), p. 2605-
    Abstract: In the last decade, there has been a surge of interest in addressing complex Computer Vision (CV) problems in the field of face recognition (FR). In particular, one of the most difficult ones is based on the accurate determination of the ethnicity of mankind. In this regard, a new classification method using Machine Learning (ML) tools is proposed in this paper. Specifically, a new Deep Learning (DL) approach based on a Deep Convolutional Neural Network (DCNN) model is developed, which outperforms a reliable determination of the ethnicity of people based on their facial features. However, it is necessary to make use of specialized high-performance computing (HPC) hardware to build a workable DCNN-based FR system due to the low computation power given by the current central processing units (CPUs). Recently, the latter approach has increased the efficiency of the network in terms of power usage and execution time. Then, the usage of field-programmable gate arrays (FPGAs) was considered in this work. The performance of the new DCNN-based FR method using FPGA was compared against that using graphics processing units (GPUs). The experimental results considered an image dataset composed of 3141 photographs of citizens from three distinct countries. To our knowledge, this is the first image collection gathered specifically to address the ethnicity identification problem. Additionally, the ethnicity dataset was made publicly available as a novel contribution to this work. Finally, the experimental results proved the high performance provided by the proposed DCNN model using FPGAs, achieving an accuracy level of 96.9 percent and an F1 score of 94.6 percent while using a reasonable amount of energy and hardware resources.
    Type of Medium: Online Resource
    ISSN: 2076-3417
    URL: Article
    DOI: 10.3390/app12052605
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2704225-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 10
    Online Resource
    Online Resource
    DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network
    Springer Science and Business Media LLC ; 2020
    In:  Multimedia Tools and Applications Vol. 79, No. 21-22 ( 2020-6), p. 15655-15677
    Details
    In: Multimedia Tools and Applications, Springer Science and Business Media LLC, Vol. 79, No. 21-22 ( 2020-6), p. 15655-15677
    Type of Medium: Online Resource
    ISSN: 1380-7501 , 1573-7721
    URL: Article
    DOI: 10.1007/s11042-019-07820-w
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2020
    detail.hit.zdb_id: 1287642-2
    detail.hit.zdb_id: 1479928-5
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...