A survey on deep learning applied to medical images: from simple artificial neural networks to generative models

Celard, Pedro; Iglesias, Eva; Sorribes-Fdez, J. M.; Romero, R.; Vieira, A. Seara; Borrajo, Lourdes

doi:10.1007/s00521-022-07953-4

Cited by 65 publications

(32 citation statements)

References 150 publications

(171 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL algorithms are data driven for feature extraction and can automatically obtain deep and specific feature representations based on learning from numerous samples. Moreover, an end-to-end approach allows these algorithms to adapt to the specific medical task requirements [48]. Additionally, DL algorithms can solve with high-dimensional data due to multiple techniques such as the loss function, optimizer, and hidden layers.…”

Section: Discussionmentioning

confidence: 99%

Identification of Asymptomatic COVID-19 Patients on Chest CT Images Using Transformer-Based or Convolutional Neural Network–Based Deep Learning Models

et al. 2023

View full text Add to dashboard Cite

Novel coronavirus disease 2019 (COVID-19) has rapidly spread throughout the world; however, it is difficult for clinicians to make early diagnoses. This study is to evaluate the feasibility of using deep learning (DL) models to identify asymptomatic COVID-19 patients based on chest CT images. In this retrospective study, six DL models (Xception, NASNet, ResNet, EfficientNet, ViT, and Swin), based on convolutional neural networks (CNNs) or transformer architectures, were trained to identify asymptomatic patients with COVID-19 on chest CT images. Data from Yangzhou were randomly split into a training set (n = 2140) and an internal-validation set (n = 360). Data from Suzhou was the external-test set (n = 200). Model performance was assessed by the metrics accuracy, recall, and specificity and was compared with the assessments of two radiologists. A total of 2700 chest CT images were collected in this study. In the validation dataset, the Swin model achieved the highest accuracy of 0.994, followed by the EfficientNet model (0.954). The recall and the precision of the Swin model were 0.989 and 1.000, respectively. In the test dataset, the Swin model was still the best and achieved the highest accuracy (0.980). All the DL models performed remarkably better than the two experts. Last, the time on the test set diagnosis spent by two experts—42 min, 17 s (junior); and 29 min, 43 s (senior)—was significantly higher than those of the DL models (all below 2 min). This study evaluated the feasibility of multiple DL models in distinguishing asymptomatic patients with COVID-19 from healthy subjects on chest CT images. It found that a transformer-based model, the Swin model, performed best.

show abstract

Section: Discussionmentioning

confidence: 99%

Identification of Asymptomatic COVID-19 Patients on Chest CT Images Using Transformer-Based or Convolutional Neural Network–Based Deep Learning Models

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Adding a vector of features derived from an OCT image, along with the noise input, the discriminator's task was to find the similarity index between the real and fake images and assign false images to its input labels. Conditioning was accomplished by feeding one hot vector into the input of the generator [33]. A highlevel exhibit of our cGAN is presented in Figure 2.…”

Section: Medical Images Augmentation Using Gansmentioning

confidence: 99%

GANs-Based Intracoronary Optical Coherence Tomography Image Augmentation for Improved Plaques Characterization Using Deep Neural Networks

Zafar

Sharif

2023

Optics

View full text Add to dashboard Cite

Data augmentation using generative adversarial networks (GANs) is vital in the creation of new instances that include imaging modality tasks for improved deep learning classification. In this study, conditional generative adversarial networks (cGANs) were used on a dataset of OCT (Optical Coherence Tomography)-acquired images of coronary atrial plaques for synthetic data creation for the first time, and further validated using deep learning architecture. A new OCT images dataset of 51 patients marked by three professionals was created and programmed. We used cGANs to synthetically populate the coronary aerial plaques dataset by factors of 5×, 10×, 50× and 100× from a limited original dataset to enhance its volume and diversification. The loss functions for the generator and the discriminator were set up to generate perfect aliases. The augmented OCT dataset was then used in the training phase of the leading AlexNet architecture. We used cGANs to create synthetic images and envisaged the impact of the ratio of real data to synthetic data on classification accuracy. We illustrated through experiments that augmenting real images with synthetic images by a factor of 50× during training helped improve the test accuracy of the classification architecture for label prediction by 15.8%. Further, we performed training time assessments against a number of iterations to identify optimum time efficiency. Automated plaques detection was found to be in conformity with clinical results using our proposed class conditioning GAN architecture.

show abstract

“…Unfortunately, deep features require a lot of data, 3 which is generally not available in bulk for biomedical images. To combat this, the medical imaging community has started using deep learning model through the utilization of data augmentation as a use case of generative adversarial network (GAN), 4 generative modeling, 5 fast computational framework for optimization, 5 etc. GANs generate image randomly, 6 which may not always be useful.…”

Section: Introductionmentioning

confidence: 99%

Conditional generative adversarial network based multi-task learning framework for breast lesion segmentation of ultrasound images

Datta,

Haque

2024

J. Electron. Imag.

View full text Add to dashboard Cite

The conditional generative adversarial network (cGAN) is widely used in image-toimage translation for natural images by implementing supervised learning loss in the GAN framework. It has also been extended to biomedical images for image segmentation. However, during the training phase, it lacks proper guidance for smooth convergence, and the model requires a large dataset, which is often unavailable for biomedical images. To address this limitation, we integrated a multi-task learning technique using a cGAN-based adversarial framework for lesion segmentation in ultrasound (US) breast images. Our proposition defines an auxiliary task of finding the mask similarity score between the input US image and the ground-truth segmentation mask, which is trained on features extracted from the available data for the segmentation task. This learning methodology is imposed within a cGAN framework to boost the original segmentation task of the generator and guide it through the auxiliary task. The proposed method shows improved convergence and stability compared to the core adversarial network, and its performance has been assessed on different datasets and model architectures, demonstrating significant improvement over the baseline.

show abstract

A survey on deep learning applied to medical images: from simple artificial neural networks to generative models

Cited by 65 publications

References 150 publications

Identification of Asymptomatic COVID-19 Patients on Chest CT Images Using Transformer-Based or Convolutional Neural Network–Based Deep Learning Models

Identification of Asymptomatic COVID-19 Patients on Chest CT Images Using Transformer-Based or Convolutional Neural Network–Based Deep Learning Models

GANs-Based Intracoronary Optical Coherence Tomography Image Augmentation for Improved Plaques Characterization Using Deep Neural Networks

Conditional generative adversarial network based multi-task learning framework for breast lesion segmentation of ultrasound images

Contact Info

Product

Resources

About