Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study
Open accessThe DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Increase the training time.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [87]
In the citing paper
“Add regularization.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [87]
In the citing paper
“Increase the depth (or width) of the model.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [87]
In the citing paper
“Expand the dataset with data augmentation or use transfer learning (explained in latter sections).”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [87]
In the citing paper
“Increase hyperparameters tuning.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [87]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 10×
“Hence, studying and designing a better network is necessary [35,39].”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 12×
“Krizhevsky et al. [30] developed the CNN further when they introduced the AlexNet network.”
InfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“For example, DCNN models trained on the ImageNet dataset [60], which comprises of natural images, are utilized to enhance the performance of the medical image classification task.”
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“The DCNN attained fast and excellent advancements in different attributes involving activation function [48], regularization strategies [49], and optimization techniques [50].”
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“These CNNs extract features via the convolutional layers and executes the classification tasks by the fully connected layers [37,40,41].”
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · cited 1×
“One of the most common techniques is data augmentation, where data is created virtually [63].”
Research works printed but not linked: 7
- Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
- Targ, S., Almeida, D., and Lyman, K. (2016). ResNet in ResNet: Generalizing residual architectures. arXiv.
- Larsson, G., Maire, M., and Shakhnarovich, G. (2016). FractalNet: Ultra-Deep Neural Networks Without Residuals. arXiv.
- Zhao, L., Wang, J., Li, X., Tu, Z., and Zeng, W. (2016). On the connection of deep fusion to ensembling. arXiv.
- Wang, J., Wei, Z., Zhang, T., and Zeng, W. (2016). Deeply-fused nets. arXiv.
- Combalia, M., Codella, N.C., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., and Puig, S. (2019). BCN20000: Dermoscopic lesions in the wild. arXiv.
- Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv.
Cited by
Items 101–200 of 264
Soliman, A., Chang, J. R., Etminani, K., Byttner, S., Davidsson, A., Martínez‐Sanchis, B., Camacho, V., Bauckneht, M., Stegeran, R., Ressner, M., et al. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02054-7 · Cited by 16
“The core of TL is to use the knowledge of pre-trained models on a source dataset, and fine-tune it for a target task on a different but related dataset [10, 11].”
BackgroundEnhancing cattle production and management through convolutional neural networks. A review
Ufitikirezi, J. D. D. M., Bumbálek, R., Zoubek, T., Bartoš, P., Havelka, Z., Kresan, J., Stehlík, R., Kuneš, R., Olšan, P., Strob, M., et al. (2024) · Czech Journal of Animal Science · doi:10.17221/124/2023-cjas · Cited by 15
Basu, S., Agarwal, R., & Srivastava, V. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103728 · Cited by 13
Detection of Skin Cancer: A Deep Learning Approach
Shafiullah, A., Faisal, F., Arnab, S. M. R., Badhon, R. H., Ali, S., Nishat, M. M., Ahmed, I., Muttaqi, M. R., Billah, M. A., Sadik, S. R., et al. (2023) · IEEE Smart World Congress (SWC) · doi:10.1109/swc57546.2023.10448820 · Cited by 12
Kormpos, C., Zantalis, F., Katsoulis, S., & Koulouras, G. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9050111 · Cited by 12
“Hyperparameter tuning is also a critical aspect of this process, as it optimizes the performance of the model for the specific task and dataset, ultimately enhancing its accuracy [16].”
Multiclassification of license plate based on deep convolution neural networks
Uthaib, M. A., & Croock, M. S. (2021) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v11i6.pp5266-5276 · Cited by 14
A bibliometric analysis of the advance of artificial intelligence in medicine
Andrade-Arenas, L., & Yactayo-Arias, C. (2024) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v14i3.pp3350-3361 · Cited by 16
Raina, D., Chandrashekhara, S. H., Voyles, R. M., Wachs, J. P., & Saha, S. K. (2024) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2024.3386919 · Cited by 14
“We also used the transfer learning approach during training, as the networks trained with natural images enhance performance in medical image analysis [48], [49].”
Bansal, N., & Vidyarthi, A. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10282-4 · Cited by 10
Leung, E. T. Y., Mei, X., Lee, B. K. M., Lam, K. K. W., Lee, C., Li, R., Ng, E. H. Y., Yeung, W. S. B., Yu, L., & Chiu, P. C. N. (2025) · Human Reproduction Open · doi:10.1093/hropen/hoaf024 · Cited by 11
“This approach is particularly useful in medical image analysis (Byra et al. , 2018; Alzubaidi et al. , 2020, 2021b) to address the limitations of sample availability and manual annotations, which can significantly improve classification accuracy and training efficiency without overfitting.”
Big transfer learning for automated skin cancer classification
Arkah, Z. M., Al-Dulaimi, D. S., & Khekan, A. R. (2021) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v23.i3.pp1611-1619 · Cited by 10
“The main issue with these methods is the shortage of training images [1], [7].”
ImSpect: Image-driven self-supervised learning for surgical margin evaluation with mass spectrometry
Connolly, L., Fooladgar, F., Jamzad, A., Kaufmann, M., Syeda, A., Ren, K. Y. M., Abolmaesumi, P., Rudan, J. F., McKay, D., Gabor Fichtinger, A., et al. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03106-1 · Cited by 9
“For example, convolutional neural network architectures such as AlexNet, VGG-Net, and ResNet have been successfully adapted to medicalimagingtasks[3].”
DoS Attack Detection in VANET using Transfer Learning Approach for BSM Data
Shahid, M. A., Jaekel, A., Zhang, N., & Allsopp, T. (2024) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc61514.2024.10592612 · Cited by 11
“TL has been used successfully in various application areas such as text classification [17], image classification [18] and medical imaging [19].”
MethodMulti-Modal Sensing for Propulsion Estimation in People Post-Stroke Across Speeds
Swaminathan, K., Choe, D. K., Kim, D., Barde, F., Baker, T. C., Wendel, N. C., Chin, A., Bergamo, G., Siviy, C., Lee, C., et al. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3577961 · Cited by 11
“…were only evident when using half of the individual-specific fine-tuning dataset ( ∼ 12 min instead of 24 min), suggesting that transfer learning is only helpful when there is limited data in the target domain, similar to prior uses of transfer learning for medical applications [71], [72].”
Deep Transfer Learning Optimization Techniques for Medical Image Classification: A Review
Kariuki, P., Gikunda, P., & Wandeto, J. (2023) · International Conference on Intelligent Computing and Machine Learning (2ICML) · doi:10.1109/2icml58251.2022.00013 · Cited by 9
“Thus, though transfer learning seems a better option for analyzing and classifying such images, models have to be optimized to ensure that they best fit the scenario at hand [44].”
BackgroundRani, S., Ahmad, T., Masood, S., & Saxena, C. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09005-x · Cited by 11
“CNN-based models, in particular, have Transfer Learning: By utilizing transfer learning [31, 32], model pre-training is employed to learn new samples effectively.”
MethodBWLM: A Balanced Weight Learning Mechanism for Long-Tailed Image Recognition
Fan, B., Ma, H., Liu, Y., & Yuan, X. (2024) · Applied Sciences · doi:10.3390/app14010454 · Cited by 10
Wu, Y., Iorga, M., Badhe, S., Zhang, J., Cantrell, D. R., Tanhehco, E. J., Szrama, N. P., Naidech, A. M., Drakopoulos, M., Hasan, S. T., et al. (2024) · Radiology Artificial Intelligence · doi:10.1148/ryai.230296 · Cited by 9
Self-citationAn Insight into Machine Learning Techniques for Cancer Detection
Chhillar, I., & Singh, A. (2023) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-023-00896-x · Cited by 9
Scalable quantum measurement error mitigation via conditional independence and transfer learning
Lee, C., & Park, D. K. (2023) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad1007 · Cited by 15
“This can be attributed to the use of a pre-trained model, enabling the creation of a simpler neural network with enhanced generalization capability [46, 47].”
BackgroundKyung, S., Jang, M., Park, S., Yoon, H. M., Hong, G.-S., & Kim, N. (2024) · Scientific Reports · doi:10.1038/s41598-024-58163-y · Cited by 8
“The batch sizes of upstream and downstream tasks were 60 and 20.”
BackgroundCassidy, B., McBride, C., Kendrick, C., Reeves, N. D., Pappachan, J. M., Fernandez, C. J., Chacko, E., Brüngel, R., Friedrich, C. M., Alotaibi, M. S., et al. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110172 · Cited by 10
Low-Cost Probabilistic 3D Denoising with Applications for Ultra-Low-Radiation Computed Tomography
Horenko, I., Pospíšil, L., Vecchi, E., Albrecht, S., Gerber, A., Rehbock, B., Stroh, A., & Gerber, S. (2022) · Journal of Imaging · doi:10.3390/jimaging8060156 · Cited by 8
A Concise Review on Deep Learning for Musculoskeletal X-ray Images
Alammar, Z., Alzubaidi, L., Zhang, J., Santamaría, J., Li, Y., & Gu, Y. (2022) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta56598.2022.10034618 · Cited by 9
“This technique was applied for colored images in different medical health issues such as DFU (diabetic foot ulcer) [4], [2].”
BackgroundMethodSelf-citationAguirre-Arango, J. C., Álvarez-Meza, A. M., & Castellanos-Dominguez, G. (2023) · Computation · doi:10.3390/computation11060113 · Cited by 9
“Nevertheless, choosing an appropriate and representative pre-trained model is crucial to avoid suboptimal results and potential bias [34,35].”
BackgroundContrastive learning meets transfer learning: a case study in medical image analysis
Lu, Y., Jha, A., Deng, R., & Huo, Y. (2022) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2610990 · Cited by 10
“Some studies presented that the value of transfer learning is limited [1,22] , while a more recent work [19] demonstrated that pretraining at a larger scale is a key to performance gains.”
BackgroundGadAllah, M. T., Mohamed, A. E. A., Hefnawy, A. A., Zidan, H. E., El‐Banby, G. M., & Badawy, S. M. (2023) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa58542.2023.10217585 · Cited by 8
Convolution Neural Networks for Disease Prediction: Applications and Challenges
Mushtaq, S., & Singh, O. (2024) · Scalable Computing Practice and Experience · doi:10.12694/scpe.v25i1.2097 · Cited by 8
Freezing partial source representations matters for image inpainting under limited data
Zhang, Y., Yang, M., Xiao, T., Wang, Z., & Chi, Z. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108072 · Cited by 8
Cáceres, M. P., Gauvin, A., Dumais, F., & Iorio‐Morin, C. (2024) · World Neurosurgery · doi:10.1016/j.wneu.2024.06.026 · Cited by 4
An overview of computer—aided medical image classification
Boafo, Y. G. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19558-1 · Cited by 8
“This allows the pre-trained model to extract features from the new dataset effectively and efficiently[80].”
Transfer Learning in Natural Language Processing
Joseph, S., Parthi, A. G., Maruthavanan, D., Jayaram, V., Veerapaneni, P. K., & Parlapalli, V. (2024) · International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact64819.2024.10912895 · Cited by 11
Employment of Pre-trained Deep Learning Models for Date Classification: A Comparative Study
Al-Sabaawi, A., Hasan, R. I., Fadhel, M. A., Al-Shamma, O., & Alzubaidi, L. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-71187-0_17 · Cited by 7
Self-citationMathieu, A., Ajana, S., Korobelnik, J., Goff, M. L., Gontier, B., Rougier, M., Delcourt, C., & Delyfer, M. (2024) · Acta Ophthalmologica · doi:10.1111/aos.16660 · Cited by 7
“To advance DL in AMD and ophthalmology in general, it is crucial to establish larger and more comprehensive datasets (Alzubaidi et al., 2020, 2021).”
BackgroundJindal, M., & Singh, B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110583 · Cited by 8
Banarase, S. D. S. S. J. (2024) · Journal of Electrical Systems · doi:10.52783/jes.1748 · Cited by 6
“The incorporation of Transfer Learning enables [12-13] the transfer of knowledge gained from a pre-trained model to the specific task of papaya leaf disease detection.”
MethodSharma, P., Thilakarathna, I., & Fennell, A. Y. (2024) · Frontiers in Plant Science · doi:10.3389/fpls.2024.1409821 · Cited by 6
Reis, S. S., Coelho, L. P., Sousa, M. C., Neto, M., Silva, M., & Sequeira, M. (2025) · Applied Sciences · doi:10.3390/app15158321 · Cited by 7
Çakmakçı, C., Magalhães, D. R., Pacor, V. R., de Almeida, D. H. S., Çakmakçı, Y., Dalga, S., Szabó, C., María, G. A., & Titto, C. G. (2023) · Applied Animal Behaviour Science · doi:10.1016/j.applanim.2023.106060 · Cited by 6
Domain and label efficient approach for diabetic retinopathy severity detection
Ohri, K., & Kumar, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16908-3 · Cited by 7
Real-Time Sickle Cell Anemia Diagnosis Based Hardware Accelerator
Fadhel, M. A., Al-Shamma, O., Alzubaidi, L., & Oleiwi, S. R. (2020) · Communications in Computer and Information Science · doi:10.1007/978-3-030-55340-1_14 · Cited by 5
Self-citationComparative Study of Non-Iterative Fine-Tuning Strategies in Mosquito Larvae Image Classification
Lesmana, I. P. D., Rohmah, E. A., Zahra, S. F., Subekti, S., Purnama, I. K. E., & Purnomo, M. H. (2024) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim64038.2024.10882660 · Cited by 5
“However, this approach may not consistently yield high precision when there is a significant discrepancy between the source and target domains [18].”
Berrones-Reyes, M. C., Aguilar, M. A. S., & Castillo-Olea, C. (2023) · Applied Sciences · doi:10.3390/app13179639 · Cited by 6
“One of the main issues attached to medical applications for deep learning is that there is usually a limited number of annotated data, where the problem of overfitting arises [24].”
BackgroundWang, W., Zhao, X., Jia, Y., & Xu, J. (2024) · PLoS ONE · doi:10.1371/journal.pone.0297578 · Cited by 7
Ensemble of Vision Transformers and CNNs for Accurate Diabetic Foot Ulcer Classification
Pagadala, A. A., Silas, S., & Joy, E. (2024) · International Conference on Cognitive Robotics and Intelligent Systems (ICC-ROBINS) · doi:10.1109/icc-robins60238.2024.10533993 · Cited by 5
“The dataset [6, 17, 18] consists of 2 classes namely Abnormal (Ulcer) and Normal (Healthy skin) with 512 and 512 and 543 images respectively.”
BackgroundMencattini, A., Tocci, T., Nuccetelli, M., Pieri, M., Bernardini, S., & Martinelli, E. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.103030 · Cited by 8
Breast Cancer Detection with MobileNetV2 and Explainable AI
Sumaiyya, S., Shyamala, G., Latha, N. R., & Pallavi, G. (2024) · International Conference on Sustainable Expert Systems (ICSES) · doi:10.1109/icses63445.2024.10763178 · Cited by 6
“By reusing a model pre-trained on a large, general dataset, such as ImageNet, and fine-tuning it for specific medical imaging tasks, TL reduces the need for vast amounts of task-specific data and computational resources [4][5].”
Ningrum, A. P., Winarno, S., & Praskatama, V. (2024) · Journal of Applied Computer Science and Technology · doi:10.52158/jacost.v5i2.1002 · Cited by 5
“Transfer learning dalam CNN adalah teknik di mana model yang sebelumnya telah dilatih menggunakan dataset besar, seperti ImageNet digunakan kembali untuk menyelesaikan tugas pada dataset yang berbeda jumlah data yang lebih sedikit [24].”
Singh, D. K., Mehta, M. A., Müller, H., & Holzinger, A. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.10.037 · Cited by 7
“…abnormality in soft organs, such as the gallbladder [3,8,9,12,15 – 18, 33, 34] , thyroid thyroid gland [ In recent years, transfer learning [38,39] using pre-trained models has grown faster due to the following advantages offered by them: 1) automatic learning and extraction of relevant…”
Thyroid Cancer Classification using Transfer Learning
Nugroho, H. A., & Frannita, E. L. (2021) · doi:10.1109/ic2se52832.2021.9791905 · Cited by 5
Gan, T., Jin, Z., Yu, L., Liang, X. H., Zhang, H., & Ye, X. (2023) · Scientific Reports · doi:10.1038/s41598-023-49057-6 · Cited by 6
“Although the distribution of natural images and medical images is quite different, multiple studies 29–31 have proved that this paradigm can improve model performance in various task settings.”
Silicosis Detection Using Extended Transfer Learning Model
Sharma, G. K., Harjule, P., Agarwal, B., & Kumar, R. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-53085-2_10 · Cited by 5
Saim, M., & Feroui, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20140-y · Cited by 6
“However, the accuracy of DL models relies heavily on the quantity and quality of training data, which poses challenges within the medical domain [8, 9].”
Transfer Learning Approach for Indoor Localization with Small Datasets
Yoon, J., Oh, J., & Kim, S. (2023) · Remote Sensing · doi:10.3390/rs15082122 · Cited by 6
Hou, Y., & Navarro‐Cía, M. (2023) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ace4cf · Cited by 6
Deep Learning Perspectives for Prediction of Diabetic Foot Ulcers
Sharma, A., Kaushal, A., Dogra, K., & Mohana, R. (2023) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-6684-9823-1.ch006 · Cited by 5
Raina, D., Dawange, A., Bandha, T., Kaur, A., Wasekar, R., Verma, K., Verma, S., & Dhingra, K. (2024) · Journal of Knowledge Learning and Science Technology · doi:10.60087/jklst.v3.n4.p200 · Cited by 7
Application of Deep Learning Autoencoders as Features Extractor of Diabetic Foot Ulcer Images
Alatrany, A. S., Hussain, A. J., Alatrany, S. S. J., & Al-Jumaily, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13832-4_11 · Cited by 8
Encoder–decoder semantic segmentation models for pressure wound images
Eldem, H., Ülker, E., & Işıklı, O. Y. (2022) · The Imaging Science Journal · doi:10.1080/13682199.2022.2163531 · Cited by 5
“Transfer learning can obtain highly accurate model from a small training data set [74 – 77].”
MethodXu, J., Zhuang, S., He, Y., Wang, H., Zhuang, Z., & Zeng, H. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.103966 · Cited by 4
Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle
Magotra, A., & Kim, J. (2021) · Symmetry · doi:10.3390/sym13081344 · Cited by 5
“With large amounts of data, machine learning algorithms do well [86].”
BackgroundAccelerated muscle mass estimation from CT images through transfer learning
Yoon, S., Kim, T., Jung, Y. K., & Kim, Y.-H. (2024) · BMC Medical Imaging · doi:10.1186/s12880-024-01449-4 · Cited by 4
“In [43], transfer learning was performed with both identical and non-identical domain data respectively for the diabetic foot ulcer (DFU) classification task.”
MethodKaushik, P., & Sharma, P. (2024) · International Conference on Innovative Sustainable Computational Technologies (CISCT) · doi:10.1109/cisct62494.2024.11134194 · Cited by 4
Ismaila, L., Rasti, P., Bernard, F., Labriffe, M., Meneï, P., Minassian, A. T., Rousseau, D., & Lemée, J.-M. (2022) · Applied Sciences · doi:10.3390/app12146925 · Cited by 11
“While largely used in computer vision, transfer learning is still actively investigated (especially in the medical domain [9,10]).”
BackgroundImageNet pre-training and two-step transfer learning in chromosome image classification
Chen, T., Xie, C., Zhang, W., Li, Y., Ke, W., Li, T., Huang, X., & Li, K. (2026) · Scientific Reports · doi:10.1038/s41598-026-38662-w · Cited by 3
“Alzubaidi et al. 18 used general skin images as an intermediate domain for diabetic foot ulcer classification.”
Pereira, B. P., Antoine, C., de Barros, A. O. D. S., Pacífico, L. D. C., Pijeira, M. S. O., Rossi, A. M., Ricci‐Júnior, E., Alencar, L. M. R., & Santos‐Oliveira, R. (2023) · Bioengineering · doi:10.3390/bioengineering10020238 · Cited by 3
“Medical imaging plays a key role in the early diagnosis, monitoring of medical treatments, and therapeutic response assessment [1,2].”
BackgroundThe New Landscape of Diagnostic Imaging with the Incorporation of Computer Vision
Cossio, M. (2023) · Artificial intelligence · doi:10.5772/intechopen.110133 · Cited by 3
Mulyono, S., Sadyah, N. A. C., Subroto, I. M. I., Haviana, S. F. C., Poetro, B. S. W., Syaifuddin, N. M., Sulaiman, N. S., & Yacob, A. (2023) · Proceeding of the Electrical Engineering Computer Science and Informatics · doi:10.1109/eecsi59885.2023.10295901 · Cited by 3
Kidney Abnormalities Prediction in Ultrasound Images using Transfer Learning Approach
Mangayarkarasi, T., & Jamal, D. N. (2023) · International Conference on Advances in Computational Intelligence and Communication (ICACIC) · doi:10.1109/icacic59454.2023.10435333 · Cited by 3
“In [1] authors-Laith Alzubaidi and Mohammed A. Fadhel presented an application of Transfer learning for the diagnosis of Diabetic Foot Ulcer.”
BackgroundConnecting Autonomous Engineering Domains with the Shared Language of Deep Neural Networks
Bale, A. S., Rajani, M., Taj, N., Selva Agnes, S., Amala, G. S., & Lal, K. (2024) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla59606.2024.10531318 · Cited by 14
A medical image classification method based on self‐regularized adversarial learning
Fan, Z., Zhang, X., Ruan, S., Thorstad, W. L., Gay, H. A., Song, P., Wang, X., & Li, H. (2024) · Medical Physics · doi:10.1002/mp.17320 · Cited by 3
Hybrid Deep Learning-Based Enhanced Occlusion Segmentation in PICU Patient Monitoring
Munoz, M. F., Hoang, V. H., Le, T.-D., Jouvet, P. A., & Noumeir, R. (2024) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2024.3503499 · Cited by 5
Review of Deep Learning: Architectures, Applications and Challenges
Sirmorya, A., Chaudhari, M., & Balasinor, S. (2022) · International Journal of Computer Applications · doi:10.5120/ijca2022922164 · Cited by 3
Klasifikasikan Jenis Cacat Kulit Menggunakan SMOTE-GoogLeNet
Prananda, A. R., Frannita, E. L., Pramitaningrum, E., Hidayat, A., Setiawan, W. B., & Purwaningsih, N. (2024) · JITU Journal Informatic Technology And Communication · doi:10.36596/jitu.v8i1.1341 · Cited by 3
Domain Adaptation in Medical Imaging: Evaluating the Effectiveness of Transfer Learning
Eva, A. A., Jim, J. R., Rahman, A., Bhuiyan, H., & Kabir, M. M. (2024) · Studies in big data · doi:10.1007/978-981-97-3966-0_1 · Cited by 3
Implementing a Hardware Accelerator to Enhance the Recognition Performance of the Fruit Mature
Fadhel, M. A., & Al-Shamma, O. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-33-6966-5_5 · Cited by 3
Self-citationSelf-supervised Pretraining for Covid-19 and Other Pneumonia Detection from Chest X-ray Images
Hao, Y., Wang, Y., & Wang, X. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-89698-0_102 · Cited by 3
Evaluation of cancer outcome assessment using MRI: A review of deep-learning methods
Mazaheri, Y., Thakur, S. B., Bitencourt, A. G. V., Gullo, R. L., Hötker, A. M., Bates, . D. B., & Akın, O. (2022) · BJR|Open · doi:10.1259/bjro.20210072 · Cited by 3
Diagnosing Coronavirus (COVID-19) Using Various Deep Learning Models: A Comparative Study
Al-Shamma, O., Fadhel, M. A., Alzubaidi, L., Farhan, L., & Al‐Amidie, M. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-71187-0_110 · Cited by 3
Self-citationConditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy LabelsPreprint
Dufumier, B., Gori, P., Victor, J., Grigis, A., & Duchesnay, É. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.05643 · Cited by 13
“Traditional transfer learning from natural images has been applied to several medical applications [1, 27], hypothesizing that features can be re-used or fine-tuned on the downstream tasks [35].”
Diabetic foot ulcer classification using an enhanced coordinate attention integrated ConvNext model
Anbarasi, L. J., Neeraja, R., Geetha, S., Vidhya, R., Ravi, V., & Dhanya, D. (2026) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-025-01692-1 · Cited by 2
“The dataset includes 1055 images of two types: Normal and DFU images [41–43 ] where 512 DFU images and 543 normal images.”
Domain adaptation and computer vision approaches for robust detection of jellyfish in aquaculture
Folkman, L., Pitt, K. A., Strickland, J. K., Smark, A., Johnston, C., Albinsson, M. E., Huynh, C., & Stantić, B. (2026) · Aquaculture International · doi:10.1007/s10499-025-02420-y · Cited by 2
“…domain adaptation approach, which after pre-training on a dataset of common objects, continues pre-training on broad, out-of-domain jellyfish data, and finally fine-tunes the model on the target-domain (aquaculture) data is a highly effective strategy (Alzubaidi et al. 2020; Reed et al. 2022).”
Salur, M. U. (2026) · Applied Sciences · doi:10.3390/app16041993 · Cited by 3
An AI-driven framework for diabetic foot ulcer classification, segmentation, and depth estimation
Debnath, S., Velladurai, D. W., Renukadevi, M. N., Shreenidhi, H. S., Kishore, J., & Singh, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-52864-2 · Cited by 2
“The dataset was subsequently partitioned into training, validation, and testing sets 46–48 .”
Akhund, S. A., Qazi, S., Mazhar, M. A., Shaikh, A. A., Atif, E., Shaikh, A., Shaibah, H., Musa, M. K., N.Qazi, S., Khan, M. A., et al. (2026) · Medical Education Online · doi:10.1080/10872981.2026.2684837 · Cited by 3
“…documents a related pattern: model robustness decreases when inputs fall outside the distributions represented in the training data, a finding established across transfer learning architectures [34,35], providing an explanatory framework for LLM failures on non-standard or unfamiliar visual inputs.”
NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks
Roychowdhury, S. (2023) · Information · doi:10.3390/info14060333 · Cited by 5
MixUp Brain-Cortical Augmentations in Self-supervised Learning
Ambroise, C., Frouin, V., Dufumier, B., Duchesnay, É., & Grigis, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44858-4_10 · Cited by 3
An Approach to Recognize Efficient Deep Learning Model for Pattern Recognition
Kaur, A., & Kapoor, M. (2024) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito61523.2024.10522108 · Cited by 2
Damit, D. S. A., Sulaiman, S. N., Osman, M. K., Karim, N. K. A., Razali, N. F., & Marzuki, M. I. F. (2024) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa60979.2024.10525595 · Cited by 2
Diabetes Foot Ulcer Detection Using Inception V3 Deep Learning Technique
Geeitha, S., Aravinth., S., Rishikesh, K. G., Nishanth, J., & Renuka, P. (2024) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs60874.2024.10717009 · Cited by 2
“For an accurate comparison, we downsized all photos to 224 × 224 pixels, matching the input resolution of the SoTA technique on the data [22].”
MethodCina, A., Haschtmann, D., Damopoulos, D., Gerber, N., Loibl, M., Fekete, T. F., Kleinstück, F. S., & Galbusera, F. (2023) · Brain and Spine · doi:10.1016/j.bas.2023.102738 · Cited by 2
“Transfer learning from ImageNet (Deng et al., 2009) to the medical domain involves using knowledge gained from a large dataset of general images (ImageNet) to improve the performance of deep learning models on medical tasks (Alzubaidi et al., 2020).”
BackgroundCNN Models Using Chest X-Ray Images for COVID-19 Detection: A Survey
Mellal, N., & Zaidi, S. (2023) · Revue d intelligence artificielle · doi:10.18280/ria.370621 · Cited by 3
“Traditional, parallel convolutional layers, and residual connections are three ideas integrated in the developed model DCNN (deep convolutional neural network) [18].”
BackgroundGastric Ulcer Detection in Endoscopic Images Using MobileNetV3-Small
Ataxonovich, K. T., qizi, S. N. Q., & Ochilov, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-53827-8_21 · Cited by 2
Prananda, A. R., & Frannita, E. L. (2023) · Jurnal Ecotipe (Electronic Control Telecommunication Information and Power Engineering) · doi:10.33019/jurnalecotipe.v10i2.4329 · Cited by 2
Brain Tumor Segmentation Using Two-Stage Convolutional Neural Network for Federated Evaluation
Pawar, K., Zhong, S., Chen, Z., & Egan, G. F. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09002-8_43 · Cited by 2
Saint‐Esteven, A. L. G., Motisi, L., Balermpas, P., & Tanadini‐Lang, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27420-6_9 · Cited by 2
Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A SurveyPreprint
Kariuki, P., Gikunda, P., & Wandeto, J. (2023) · doi:10.36227/techrxiv.22638937.v1 · Cited by 3
Ferdinand, V. A., Nawir, V., Henry, G. E., & Cenggoro, T. W. (2024) · International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE) · doi:10.1109/icitisee63424.2024.10730252 · Cited by 1
“Alzubaidi et al. [14] observed how transfer learning affects the overall performance of diabetic foot ulcer classification on various scenarios.”
BackgroundMethodXu, L., Zhang, X., Zhang, X., Wu, T., Yu, H., Du, W., Chen, Z., & Chen, N. (2025) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2025.104532 · Cited by 1
A Deep Learning Approach for Classification of Dog Skin Diseases
Pal, P., & Saini, M. (2025) · International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS) · doi:10.1109/iccams65118.2025.11234587 · Cited by 1
“These techniques are useful, but can be slow and are used for clinicians' level of experience [4].”
Metadata
- Authors
- Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J., Santamaría, J., Duan, Y., & R. Oleiwi, S.
- Affiliations
- Queensland University of Technology (AU)
- University of Information Technology and Communications (IQ)
- Universidad de Jaén (ES)
- University of Missouri (US)
- Nursing College, Muthanna University, Muthanna 76218, Iraq
- Corresponding author
- Alzubaidi, Laith
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2020-06-29
- Volume
- 10
- Issue
- 13
- Pages
- 4523
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W3038835370
- Cited by
- 258
- References
- 62
- Citations by year
- 2026: 27 · 2025: 30 · 2024: 59 · 2023: 54 · 2022: 49 · 2021: 34 · 2020: 5
- FWCI
- 13.95
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- QUT ePrints (Queensland University of Technology) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- transfer learning, diagnostic imaging, diabetic foot ulcer classification, domain shift, ImageNet pre-trained models, convolutional neural networks, skip connections, global average pooling, limited training data, animal image classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.