Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images
Open accessThe DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks (CNNs) are deep learning network architectures that have pushed forward the state-of-the-art in a range of computer vision applications and are increasingly popular in medical image analysis. However, training of CNNs is time-consuming and challenging. In medical image analysis tasks, the majority of training examples are easy to classify and therefore contribute little to the CNN learning process. In this paper, we propose a method to improve and speed-up the CNN training for medical image analysis tasks by dynamically selecting misclassified negative samples during training. Training samples are heuristically sampled based on classification by the current status of the CNN. Weights are assigned to the training samples and informative samples are more likely to be included in the next CNN training iteration. We evaluated and compared our proposed method by training a CNN with (SeS) and without (NSeS) the selective sampling method. We focus on the detection of hemorrhages in color fundus images. A decreased training time from 170 epochs to 60 epochs with an increased performance-on par with two human experts-was achieved with areas under the receiver operating characteristics curve of 0.894 and 0.972 on two data sets. The SeS CNN statistically outperformed the NSeS CNN on an independent test set.
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
“Twenty-five studies17,28,29,35,37,39,40,44–61 compared algorithm performance against healthcare professionals.”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [44]
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“Using multiple smaller sized layers with non-linear rectifications makes the CNN more discriminative and less parameters need to be optimized [30].”
BackgroundMethodImageNet 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 1×
“The CNN architecture used in this study consists of five convolutional layers followed by rectified linear units (ReLUs) [4] and spatial max-pooling.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
(2014) · Cited by 33,419
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×
“Additions such as the inclusion of drop-out [42] or batch normalization [43] could potentially further increase performance.”
BackgroundA decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Pilot experiments using MSRA weight initialization [3] showed an equal number of epochs required to train the SeS with similar end-performance on the test sets.”
MethodDeep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Cited by
Items 301–400 of 426
Shu, H., Yuan, Q., Pan, Y.-Z., Kong, W.-K., Feng, Y., Peng, C., Li, K., Nguyen, L.-M., Racharak, T., Xin, J.-Y., et al. (2026) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2026.1825518 · Cited by 6
“…AI into actual clinical workflows relies heavily on two complementary imaging modalities: Color Fundus (CF) photography for widespread 2D screening (Van Grinsven et al., 2016), and Optical Coherence Tomography Angiography (OCTA) for depth-resolved capillary visualization (Yoon et al., 2019).”
Dao, Q. T., Trinh, H., & Nguyen, V. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1585 · Cited by 4
Zhang, H., Kendall, W. Y., Jelly, E. T., & Wax, A. P. (2021) · Biomedical Optics Express · doi:10.1364/boe.430467 · Cited by 4
Chandrappa, K., & Shankar, K. K. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99481-1.00012-2 · Cited by 6
Software defined radio frequency sensing framework for Internet of Medical Things
Abuali, N. A., Khan, M. B., Ullah, F., Hayajneh, M., Ullah, H., & Mumtaz, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102106 · Cited by 7
Umapathy, L., Brown, T., Mushtaq, R., Greenhill, M. J., Lu, J., Martín, D. R., Altbach, M. I., & Bilgin, A. (2023) · Medical Physics · doi:10.1002/mp.16820 · Cited by 4
Malware Detection using Hybrid Autoencoder Approach for Better Security in Educational Institutions
Santoso, I., Heryadi, Y., Warnars, H. L. H. S., Wulandhari, L. A., Lukas, L., & Abdurachman, E. (2019) · IEEE International Conference on Teaching, Assessment, and Learning for Engineering · doi:10.1109/tale48000.2019.9225899 · Cited by 6
“Whereas the up-sampling layer is used to restore the dimensions that it should [42].”
BackgroundFast Training Methods and Their Experiments for Deep Learning CNN Models
Jiang, S., & Wang, S.-G. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9549817 · Cited by 4
“Data dropping or data sampling is another kind of drooping techniques to reduce the number of network input samples [17-19 , 21-24 21-24] or the dimensions of a sample [ 20].”
BackgroundElements of Medical Image Processing
Azadi, T. E., Janney, S. S., & Chakravarty, S. (2019) · Springer eBooks · doi:10.1007/978-981-13-3705-5_20 · Cited by 5
Deep Active Self-paced Learning for Biomedical Image Analysis
Wang, W., Feng, R., Liu, X., Lu, Y., Wang, Y., Guo, R., Lin, Z., Chen, T., Chen, D. Z., & Wu, J. (2019) · Intelligent systems reference library · doi:10.1007/978-3-030-32606-7_6 · Cited by 4
Medical image analysis of multiple myeloma based on convolutional neural network
Jin-xia, H., & Zhang, K. (2021) · Expert Systems · doi:10.1111/exsy.12810 · Cited by 5
“The neural network algorithm model used in this study mainly includes three modules: input layer, convolution pool and soft-max classifier (Grinsven et al., 2016; Tajbakhsh et al., 2016).”
MethodGhebrechristos, H., Alaghband, G., & Hwang, R. Y. (2017) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci.2017.286 · Cited by 4
“This is a form of in-training selective sampling used in [16] but we perform the subsampling as a preprocessing step.”
MethodInfluentialMamun, M. M. R. K., & Alouani, A. T. (2020) · Journal of Biomedical Engineering and Biosciences · doi:10.11159/jbeb.2020.001 · Cited by 5
Review on Detection and Classification of Diabetic Retinopathy using Fundus Images
Ikram, A., & Imran, A. (2023) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst60641.2023.10414197 · Cited by 3
“Hemorrhages were detected on images from the Messidor and Kaggle data sets with 84.8% sensitivity and 90.4% sensitivity, respectively [15].”
MethodInfluentialDeep learning for intracranial aneurysm segmentation using CT angiography
Zheng, H., Liu, X., Huang, Z., Ren, Y., Fu, B., Shi, T., Liu, L., Guo, Q., Tian, C., Liang, D., et al. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad6372 · Cited by 4
MT_Net: A Multi-Scale Framework Using the Transformer Block for Retina Layer Segmentation
Liu, E., He, X., Yue, J., Guan, Y., Yang, S., Zhang, L., Wang, A., Li, J., & Song, W. (2024) · Photonics · doi:10.3390/photonics11070607 · Cited by 3
Recognition of Diabetic Retinopathy Grades Based on Data Augmentation and Attention Mechanisms
Li, X., Wen, L., Du, F., Yang, L., & Wu, J. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23201 · Cited by 4
“…and devices, with color and contrast differences, this work improves contrast by Gaussian filtering, and applying the contrast enhancement method [7]: where I ce denotes the enhanced image, I denotes the original image, ∗ denotes convolution, and G ( x , y ; 𝜎 ) denotes the Gaussian filter with…”
Characterization of Errors in Deep Learning-Based Brain MRI Segmentation
Pai, A., Teng, Y.-C., Blair, J., Kallenberg, M., Dam, E. B., Sommer, S., Igel, C., & Nielsen, M. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-810408-8.00013-4 · Cited by 3
Fovea detection in optical coherence tomography using convolutional neural networks
Liefers, B. J., Venhuizen, F. G., Theelen, T., Hoyng, C. B., van Ginneken, B., & Sánchez, C. I. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2254301 · Cited by 3
Self-citationScreening und Management retinaler Erkrankungen mittels digitaler Medizin
Gerendas, B. S., Waldstein, S. M., & Schmidt-Erfurth, U. M. (2018) · Der Ophthalmologe · doi:10.1007/s00347-018-0752-7 · Cited by 3
Automated Microaneurysm Counts on Ultrawide Field Color and Fluorescein Angiography Images
Rageh, A., Ashraf, M., Fleming, A. D., & Silva, P. S. (2021) · Seminars in Ophthalmology · doi:10.1080/08820538.2021.1897852 · Cited by 3
Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G
Lim, W. X., & Chen, Z. (2024) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-024-03093-0 · Cited by 3
“Furthermore, noise removal filter such as Gaussian filtering is applied to smooth the images [18–21].”
Akogo, D., & Palmer, X. (2019) · Lecture notes in networks and systems · doi:10.1007/978-3-030-12385-7_13 · Cited by 4
Deep Learning-Based Diabetic Retinopathy Detection: A Survey
Jebran, P. M., & Banu, S. (2021) · International Journal of Organizational and Collective Intelligence · doi:10.4018/ijoci.2021070103 · Cited by 3
Diabetic Rethinopathy Phase Identification with Deep Features
Taşpınar, Y. S. (2022) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco55406.2022.9797136 · Cited by 4
Topology-Aware Learning for Semi-supervised Cross-domain Retinal Artery/Vein Classification
Liu, H., Xie, J., Liu, Y., Hao, H., Guo, L., Zhang, J., & Zhao, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23473-6_4 · Cited by 3
Rogers, H., de la Iglesia, B., Zebin, T., Cielniak, G., & Magri, B. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10142-0 · Cited by 6
“The selective sampling method proposed by [28] aids in haemorrhage detection by dynamically selecting misclassified negative samples during training.”
DR-ConvNeXt: DR classification method for reconstructing ConvNeXt model structure
Song, P., & Wu, Y. J. (2025) · Journal of X-Ray Science and Technology · doi:10.1177/08953996241311190 · Cited by 2
“In this study, the color-correction algorithm proposed by Grinsven 24 is employed, which effectively adjusts the colors of DR fundus images, even in the presence of varying background colors and brightness levels.”
Problem‐Oriented Strategy for Diabetic Retinopathy Identification
Hadef, M., Boulahia, S. Y., & Amamra, A. (2025) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.70216 · Cited by 2
“There are other works that targeted specific lesions for diagnosing diabetic retinopathy, such as changes in blood vessels [49–52] or microaneurysms [53, 54].”
Machine learning and digital images of porous materials: from rock to the human brain
Sahimi, A., & Sahimi, M. (2026) · Frontiers of Physics · doi:10.3389/fphy.2025.1742403 · Cited by 2
Dash, A. K., & Mohapatra, P. (2020) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-7998-5071-7.ch006 · Cited by 2
A comprehensive survey on computer-aided diagnostic systems in diabetic retinopathy screening
Tavakoli, M., & Kelley, P. (2021) · Institute of Physics eBooks · doi:10.1088/978-0-7503-2060-3ch12 · Cited by 2
“[112] Patches based selective sampling End-to-end HE detection Kaggle, MESSIDOR AUC=0.”
BackgroundMethodInfluentialSegmentation for Retinal Blood Vessels Using Channel Attention U-Net and Pix2Pix
Polowczyk, A., Polowczyk, A., Wiltos, K., & Woźniak, M. (2025) · doi:10.1109/cihmcompanion65205.2025.11002693 · Cited by 2
“A technique has been proposed in [1] that relies on enhanced contrast using a Gaussian filter.”
Improving Spatial Context in CNNs for Semantic Medical Image Segmentation
Mesbah, R., McCane, B., Mills, S. J., & Robins, A. V. (2017) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2017.15 · Cited by 2
“Unlike [21, 24, 27] in which multiple parallel CNN architectures are engaged in a single expensive training phase, our approach is based on only one trained encoder-decoder architecture.”
BackgroundMethodMitral Valve Abnormality Detection Using Deep Learning Approach in PLAX view in TTE
Chandra, V. (2020) · International Journal of Emerging Trends in Engineering Research · doi:10.30534/ijeter/2020/67842020 · Cited by 2
Multi-class segmentation of Diabetic Retinopathy lesions: effects of metrics, improvements and loss
Furtado, P. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00219 · Cited by 2
“[7], Quellec et al. [8] (exudates, hemorrhages and microaneurysms), Haloi et al. [9], van Grinsven et al. [10], Orlando et al. [11] and Shan et al. [12] (microaneurysms, hemorrhages or both).”
BackgroundCaramihale, T., Popescu, D., & Ichim, L. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68548-9_68 · Cited by 2
Adjei, P. E., Nunoo‐Mensah, H., Kobia‐Acquah, E., & Akowuah, E. K. (2018) · Middle East Conference on Biomedical Engineering · doi:10.1109/mecbme.2018.8402434 · Cited by 2
“The method also requires heavy computing power and memory [14].”
MethodYin, W., Hu, Y., Yi, S., & He, J. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab0a90 · Cited by 2
“…(Adam) (Kingma et al 2014) with learning rate of 0.001, beta_1 of 0.9, beta_2 of 0.999 and epsilon of 1 × 10 − 8 , minimizing a cost function C defined as follows (Grinsven et al 2016): where y is the predicted probability score, x is the mark and m is the total number of samples in one mini-batch.”
BackgroundInfluentialA meta-fusion RCNN network for endoscopic visual bladder lesions intelligent detection
Lin, J., Pan, Y., Xu, J., Bao, Y., & Hui, Z. (2022) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2022.102138 · Cited by 3
CNN and Fuzzy logic based hybrid approach for lung cancer detection and report generation
Bandopadhyay, S., & Phadke, A. C. (2022) · International Interdisciplinary Humanitarian Conference for Sustainability (IIHC) · doi:10.1109/iihc55949.2022.10060729 · Cited by 2
End-to-end learning via a convolutional neural network for cancer cell line classification
Akogo, D., & Palmer, X. (2019) · Journal of Industry-University Collaboration · doi:10.1108/jiuc-02-2019-002 · Cited by 2
Application of Deep Learning in Medical Image Processing - A Comprehensive Review
Aruna, G. (2020) · IJARCCE · doi:10.17148/ijarcce.2020.9622 · Cited by 2
Guo, W., Liu, X., Ma, Y., & Zhang, R. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210213 · Cited by 2
A new deep model based on part pooling for medical image classification
Li, X., Guo, Z., Zhang, S., & Guo, X. (2021) · IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) · doi:10.1109/aiid51893.2021.9456464 · Cited by 2
“We conduct experiments on two benchmarks, Chest X-Ray Images (CXI) [16] and APTOS2019-Blindness-Detection (ABD) [12].”
BackgroundMethodAn Efficient System for Grading Diabetic Retinopathy by Detecting the Location of Lesions
Ramasubramanian, B., Hemanand, D., Kavinkumar, K., & Manjula, M. M. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-99-1431-9_57 · Cited by 1
Cao, L., & Pan, K. (2023) · International Conference on Advances in Artificial Intelligence and Applications (AAIA) · doi:10.1145/3603273.3637854 · Cited by 1
“In the last few years, as deep learning technology has continued to evolve, CNNs have shown exceptional results in the field of medical imaging [4-8].”
BackgroundLi, Z., Huang, J., Chen, J., Jin, Z., Jiang, H., Ding, L., Zhang, T., Sun, W., Lu, R., Zhang, Q., et al. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1444136 · Cited by 4
Detection of Brain Haemorrhage Using Convolutional Neural Network
Mahesh Prasanna, K., Venkatesh, G., Navaneetha, K., Naveena, N., Mary, F. S., & Subramanian, B. (2025) · International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI) · doi:10.1109/ic3ecsbhi63591.2025.10991259 · Cited by 1
Exploring AI-assisted techniques for diabetic retinopathy detection: a comprehensive review
Ahmad, I., Singh, V. P., & Gore, M. M. (2025) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-025-00647-6 · Cited by 1
“An improved and fast method of training a CNN using selective data sampling was intro - duced by Van Grinsven et al. (2016) to detect HEMs in the color fundus image.”
Image-text guided fundus vessel segmentation via attention mechanism and gated residual learning
Xu, J., Liu, Q., Shen, J., Tan, R., Tian, S., Chi, W., & Yang, W. (2025) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2025.1710343 · Cited by 1
Deep Learning-Driven Framework for Diabetic Retinopathy Diagnosis and Virtual Ophthalmic Support
Sathar, G., Sunanda, N., Mounika, G., Shailaja, K., Krishna, K. V., & Sikkakoli, A. K. (2025) · International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) · doi:10.1109/icicnis66685.2025.11315582 · Cited by 1
Clinically Aligned AI for Diabetic Retinopathy: Interpretable Grading Based on Lesion Segmentation
Hezil, N., Bouridane, A., Hamoudi, R., Deriche, M. A., & Harrag, F. (2026) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.70286 · Cited by 1
Bittner, S.-J., Barz, M., & Sonntag, D. (2026) · Frontiers in Big Data · doi:10.3389/fdata.2026.1676922 · Cited by 1
“For example, studies have been able to detect specific pathologies in fundus images, such as exudates (Benzamin and Chakraborty, 2018) or hemorrhage (Grinsven et al., 2016).”
Convolutional Model with Classification through Izhikevich Neuron
Luna-Álvarez, A., Mújica‐Vargas, D., & Mejía-Lavalle, M. (2019) · Research in Computing Science · doi:10.13053/rcs-148-10-6 · Cited by 2
“One way to reduce time is to reduce the training data, a related paper is [4] in which it is proposed to make a selection of representative data with heuristic values granted by human experts, this method decrease the training time without affecting the performance of the neural network.”
MethodProgressive Transmission of Medical Images via a Bank of Generative Adversarial Networks
Chang, C., Wang, X., Horng, J.-H., & Echizen, I. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/9917545 · Cited by 2
Root Canal Therapy Evaluation Based on Rule Embedded Neural Networks
Zhou, Y., & Zhang, H. (2021) · International Conference on Intelligent Computing, Automation and Applications (ICAA) · doi:10.1109/icaa53760.2021.00136 · Cited by 1
“In literature [12], fast-CNN was used to conduct selective sampling of data and was finally successfully applied in detection in color images.”
MethodForward Kinematic Analysis of 6-R Industrial Robot Using Active Sampled Neural Network Regressor
Kesaba, P., & Choudhury, B. B. (2022) · International Journal of Software Innovation · doi:10.4018/ijsi.297921 · Cited by 1
Yang, B., Zhao, S., Ye, K., & Zhang, R. (2021) · doi:10.1145/3507548.3507612 · Cited by 1
“Preprocessing method in [24] is performed to enhance details, exploit random rotation (0 to 270 degrees), random horizontal or vertical flip and random horizontal.”
MethodSathananthavathi, V., & Indumathi, G. (2022) · IETE Journal of Research · doi:10.1080/03772063.2022.2098181 · Cited by 1
Approaches for Detection of Diabetic Retinopathy: A Review
Bhoopal, S., Mahesh, K. R., & Chethan, H. K. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-19-3035-5_16 · Cited by 1
Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing
Banupriya, V., & Anusuya, S. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.038696 · Cited by 1
Brain Hemorrhage Detection Using AI
M, F. T. J. (2023) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem24760 · Cited by 1
Patient Outcomes Through Machine Learning: A Review Of Data Management Strategies In Healthcare
Uddin, M. M. (2024) · Innovatech Engineering Journal · doi:10.70937/jnes.v1i01.33 · Cited by 4
A neural-network based approach for exudates evaluation in retinal images
Caramihale, T., Popescu, D., & Ichim, L. (2017) · International Symposium on Advanced Topics in Electrical Engineering · doi:10.1109/atee.2017.7905107 · Cited by 1
“Different researches have presented approaches for diabetic retinopathy detection or evaluation in retinal images [1-10].”
BackgroundIdiopathic Interstitial Pneumonias Medical Image Detection Using Deep Learning Techniques: A Survey
Sun, Z., & He, S. (2019) · ACM Southeast Regional Conference (ACMSE) · doi:10.1145/3299815.3314425 · Cited by 2
“Currently, no curriculum learning method for pulmonary nodule detection has been found, but the training set selection method for retinal imaging hemorrhage detection mentioned in [27] can be similar to that applied to pulmonary nodule detection.”
MethodDiabetic retinopathy and maculopathy lesions
Al-Diri, B., Calivá, F., Chudzik, P., Ometto, G., & Habib, M. (2019) · Elsevier eBooks · doi:10.1016/b978-0-08-102816-2.00012-5 · Cited by 1
Segmentation of Diabetic Retinopathy Lesions: The Common Fallacy and Evaluation of Real Segmenters
Furtado, P. (2020) · Open Journal of Medical Imaging · doi:10.4236/ojmi.2020.104016 · Cited by 1
“Van Grinsen [12] hemorrhages 79% (1 FPI, 8 px center) 89% (10 FPI) 87% (10 FPI)”
BackgroundInfluentialDetailed Analysis of Semantic Segmentation of Diabetic Retinopathy Lesions
Furtado, P. (2020) · Cited by 1
Deep Learning Performance on Medical Image, Data and Signals
Erdoğmuş, P. (2019) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis.02.01.541366 · Cited by 2
Fu, J., Li, L., Yan, Y., & Ma, F. (2021) · PubMed Central · doi:10.13201/j.issn.2096-7993.2021.05.019 · Cited by 1
Mitral Valve Abnormality Detection by fully end to end with Deep Neural Network
Chandra, V., Singh, V. K., Sarkar, P. G., & cardiology, R. (2020) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.c5372.029320 · Cited by 1
“Detection of systolic and [15] diastolic movement in cin-MRI of heart.”
BackgroundAutomated Recognition of Diabetic Retinopathy using Machine Learning Techniques
(2019) · International Journal of Recent Technology and Engineering (IJRTE) · doi:10.35940/ijrte.d1121.1284s219 · Cited by 1
A multi-scale gated network for retinal hemorrhage detection
Xia, H., Rao, Z., & Zhou, Z. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03476-6 · Cited by 1
“While works in [28] [29] adopted one stage method to directly detect hemorrhage lesions, which is more convenient by using the loss for supervision.”
MethodBoosted Training of Convolutional Neural Networks for Multi-Class SegmentationPreprint
Berger, L. U., Hyde, E., Gibb, M., Pavithran, N., Kelly, G., Mumtaz, F., & Sebastien Ourselin, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.05974 · Cited by 1
“Also in [7] a selective sampling method on negative samples was used to improve the training of a CNN for hemorrhage detection in 2D fungus images.”
MethodPoint-of-Care Diabetic Retinopathy Diagnosis: A Standalone Mobile Application ApproachPreprint
Hagos, M. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04066 · Cited by 6
“[61] Patches based selective sampling End-to-end Kaggle [30] SN=84.”
Retinal Lesion Segmentation Using Transfer Learning with an Encoder-Decoder CNN
Ortiz-Feregrino, R., Tovar-Arriaga, S., Ortega, C. P., & Takacs, A. (2017) · Revista Mexicana de Ingeniería Biomédica · doi:10.17488/rmib.43.2.4 · Cited by 1
Intasam, A., Piyawattanametha, N., Promworn, Y., Jiranantanakorn, T., Thawornwanchai, S., Thanasitthichai, S., Khwayotha, S., Juhong, A., & Piyawattanametha, W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4635895 · Cited by 1
Ordóñez, P. F. (2017) · DigitalCommons - Kennesaw State University (Kennesaw State University)
M.tech, D. O. C., & Bhatti, E. (2018) · International Journal of Advanced Research in Computer Science · doi:10.26483/ijarcs.v9i1.5368
Fundus image analysis for automatic screening of ophthalmic pathologies.
Granero, A. C. (2018) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/99745
“In (Grinsven et al., 2016) a method to improve and speed-up the CNN training for medical image analysis tasks is proposed.”
MethodMargin-Based Sample Filtering for Image Classification Using Convolutional Neural Networks
Kaplanoglou, P. I., & Diamantaras, K. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451592 · Cited by 1
“The relative works of [19] [20] [21] [22], aim to reduce the amount of data used during training, and thus training time, but are not evaluated on larger image datasets that contain noisy examples.”
BackgroundAutomatic Detection and Evaluation of Hard Exudates Based on Deep Bayesian Learning
Wu, Y., Jin, W., & Cai, Z. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483887
Keras based CNN Model for Disease Extraction in Ultrasound Image
Cho, Y. (2018) · Journal of Digital Contents Society · doi:10.9728/dcs.2018.19.10.1975
Correction to: Towards a Glaucoma Risk Index Based on Simulated Hemodynamics from Fundus Images
Orlando, J. I., Barbosa‐Breda, J., Keer, K. V., Blaschko, M. B., Blanco, P. J., & Bulant, C. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00934-2_106
Image processing methods for computer-aided screening for disease
Valverde, J. J. G. (2018) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.52589 · Cited by 1
Deep Learning Based Pain Treatment
Jaiswal, T., & Jaiswal, S. (2019) · International Journal of Trend in Scientific Research and Development · doi:10.31142/ijtsrd23639
Sparsely Activated Networks: A new method for decomposing and compressing dataPreprint
Bizopoulos, P. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00400 · Cited by 2
“[88] Mark JJP van Grinsven, Bram van Ginneken, Carel B Hoyng, Thomas Thee-”
BackgroundUGLRnet: A Classification Model for Upper Gastrointestinal Lesion Image
Shuang, F., Wu, Z., & Fan, W. (2019) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis46139.2019.8940329
“At present, Convolutional Neural Network has made good progress in the fields of blood cell classification [3], early diagnosis of oral cancer [4], detection of eyeground hemorrhage [5], classification of liver lesions [6], diagnosis of breast cancer [7].”
Bone age assessment using general use convolutional neural networks
Pinheiro, G., Magalhães, L., & Guevara, M. A. (2019) · International Conference on Graphics and Interaction (ICGI) · doi:10.1109/icgi47575.2019.8955014
“…good results when applied to medical imaging analysis tasks, such as detection of brain lesions [20], [21], detection of retina anomalies [22], [23], detection and 978-1-7281-6378-9/19/$31.00 ©2019 IEEE classification of pathological lesions masses in mammograms [24]–[27], detection of…”
InfluentialError feedback sampling for CNN training in upper gastrointestinal diseases classification
Wang, Y., Feng, H., & Fan, W. (2019) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis46139.2019.9043428
“Therefore, in order to reduce unnecessary efforts on redundant samples and train more error-prone samples [5], we further proposed the error feedback sampling method on the basis of random sampling.”
BackgroundInfluentialBakhtiariziabari, M., & Ghafoorian, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59861-7_52
Explainable Deep Learning for Referable Diabetic Retinopathy
Chetoui, M., Couturier, A., & Akhloufi, M. A. (2020) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece47787.2020.9255773
“[9] presented a CNN with 9 layers inspired by OxfordNet [4] to detect hemorrhage on fundus images.”
MethodNeuromorphic machine learning for audio processing : from bio-inspiration to biomedical applications
Acharya, J. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/142608 · Cited by 2
Robust Localization of Retinal Lesions via Weakly-supervised Learning
Zhao, R., Li, Q., & You, J. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413100
Signal Detection in Satellite‐Ground IoT Link Based on Blind Neural Network
Guan, Q., & Wu, S. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/5547989 · Cited by 1
Deep CNN Architecture for Respiratory Sound Classification
Zachariah, S. C., & Bindhu, P. (2021) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-1385
Analysis Paper on Different Algorithm, Dataset and Devices Used for Fundus Images
Arora, P., & Singh, B. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-3660-8_4
Zhao, H., Peng, H., Gao, Z., & Zheng, S. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534118
“• Good performance of the presented method has been verified by a large number of experiments on standard datasets and 3 detection tasks, along with comparisons against several state-of-the-arts, e.g. [13], [20], [21], [42].”
BackgroundMethodInfluentialRetracted: Evaluation of RCNN parameters for Senile dementia diagnosis using ADNI dataset
Balne, S., & Elumalai, A. (2021) · International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT) · doi:10.1109/rteict52294.2021.9573969
“Many diseases may be detected using scanned and X-Ray records [1], but analysing vast amounts of data for the human brain (or) by hand is a time-consuming operation.”
BackgroundRetracted
Metadata
- Authors
- van Grinsven, M. J. J. P., van Ginneken, B., Hoyng, C. B., Theelen, T., & Sanchez, C. I.
- Affiliations
- Radboud University Medical Center (NL)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2016-05
- Volume
- 35
- Issue
- 5
- Pages
- 1273-1284
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2344912502
- Cited by
- 426
- References
- 51
- Citations by year
- 2026: 7 · 2025: 13 · 2024: 27 · 2023: 41 · 2022: 49 · 2021: 70 · 2020: 57 · 2019: 68 · 2018: 50 · 2017: 38 · 2016: 6
- FWCI
- 46.88
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- Radboud Repository (Radboud University) (submittedVersion)
- Radboud Repository (Radboud University) (submittedVersion, other-oa)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- convolutional neural network training, training efficiency, sample weighting, hemorrhage detection, color fundus images, medical image analysis, training time reduction
- MeSH terms
- Machine Learning, Fundus Oculi, Humans, Image Interpretation, Computer-Assisted, Retinal Hemorrhage, Databases, Factual, Neural Networks, Computer
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.