Improving breast mass classification by shared data with domain transformation using a generative adversarial network

BraNet: a mobil application for breast image classification based on deep learning algorithms

Mobile health apps are widely used for breast cancer detection using artificial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named "BraNet" for 2D breast imaging segmentation and classification using deep learning algorithms. During the phase off-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classification models. During phase online, the BraNet app was developed using the react native framework, offering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classification. This application operates on a client-server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader's agreement was assessed using the kappa coefficient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classification compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts' accuracy, with DM classification being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classification than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifications, nodules, mass, asymmetry, and dense breasts) and can affect the API accuracy model.

Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature

Background  Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. Purpose  To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods  The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. Results  A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. Conclusion  While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.

[Segmentation of Mass in Mammogram Using Gaze Search Patterns]

PURPOSE

It is very difficult for a radiologist to correctly detect small lesions and lesions hidden on dense breast tissue on a mammogram. Therefore, recently, computer-aided detection (CAD) systems have been widely used to assist radiologists in interpreting images. Thus, in this study, we aimed to segment mass on the mammogram with high accuracy by using focus images obtained from an eye-tracking device.

METHODS

We obtained focus images for two mammography expert radiologists and 19 mammography technologists on 8 abnormal and 8 normal mammograms published by the DDSM. Next, the auto-encoder, Pix2Pix, and UNIT learned the relationship between the actual mammogram and the focus image, and generated the focus image for the unknown mammogram. Finally, we segmented regions of mass on mammogram using the U-Net for each focus image generated by the auto-encoder, Pix2Pix, and UNIT.

RESULTS

The dice coefficient in the UNIT was 0.64±0.14. The dice coefficient in the UNIT was higher than that in the auto-encoder and Pix2Pix, and there was a statistically significant difference (p<0.05). The dice coefficient of the proposed method, which combines the focus images generated by the UNIT and the original mammogram, was 0.66±0.15, which is equivalent to the method using the original mammogram.

CONCLUSION

In the future, it will be necessary to increase the number of cases and further improve the segmentation.

Semi-Supervised Bladder Tissue Classification in Multi-Domain Endoscopic Images

OBJECTIVE

Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains.

METHOD

We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists.

CONCLUSION

The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists.

SIGNIFICANCE

This study shows the potential of using semi-supervised GAN-based bladder tissue classification when annotations are limited in multi-domain data.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis

Introduction

Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT).

Method

The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review.

Results

The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9.

Discussion

Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.

DF-dRVFL: A novel deep feature based classifier for breast mass classification

Amongst all types of cancer, breast cancer has become one of the most common cancers in the UK threatening millions of people's health. Early detection of breast cancer plays a key role in timely treatment for morbidity reduction. Compared to biopsy, which takes tissues from the lesion for further analysis, image-based methods are less time-consuming and pain-free though they are hampered by lower accuracy due to high false positivity rates. Nevertheless, mammography has become a standard screening method due to its high efficiency and low cost with promising performance. Breast mass, as the most palpable symptom of breast cancer, has received wide attention from the community. As a result, the past decades have witnessed the speeding development of computer-aided systems that are aimed at providing radiologists with useful tools for breast mass analysis based on mammograms. However, the main issues of these systems include low accuracy and require enough computational power on a large scale of datasets. To solve these issues, we developed a novel breast mass classification system called DF-dRVFL. On the public dataset DDSM with more than 3500 images, our best model based on deep random vector functional link network showed promising results through five-cross validation with an averaged AUC of 0.93 and an average accuracy of 81.71 % . Compared to sole deep learning based methods, average accuracy has increased by 0.38. Compared with the state-of-the-art methods, our method showed better performance considering the number of images for evaluation and the overall accuracy.

CheSS: Chest X-Ray Pre-trained Model via Self-supervised Contrastive Learning

Training deep learning models on medical images heavily depends on experts' expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fréchet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at https://github.com/mi2rl/CheSS .

Medical Images Segmentation for Lung Cancer Diagnosis Based on Deep Learning Architectures

Lung cancer presents one of the leading causes of mortalities for people around the world. Lung image analysis and segmentation are one of the primary steps used for early diagnosis of cancer. Handcrafted medical imaging segmentation presents a very time-consuming task for radiation oncologists. To address this problem, we propose in this work to develop a full and entire system used for early diagnosis of lung cancer in CT scan imaging. The proposed lung cancer diagnosis system is composed of two main parts: the first part is used for segmentation developed on top of the UNETR network, and the second part is a classification part used to classify the output segmentation part, either benign or malignant, developed on top of the self-supervised network. The proposed system presents a powerful tool for early diagnosing and combatting lung cancer using 3D-input CT scan data. Extensive experiments have been performed to contribute to better segmentation and classification results. Training and testing experiments have been performed using the Decathlon dataset. Experimental results have been conducted to new state-of-the-art performances: segmentation accuracy of 97.83%, and 98.77% as classification accuracy. The proposed system presents a new powerful tool to use for early diagnosing and combatting lung cancer using 3D-input CT scan data.

Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging

Despite technological and medical advances, the detection, interpretation, and treatment of cancer based on imaging data continue to pose significant challenges. These include inter-observer variability, class imbalance, dataset shifts, inter- and intra-tumour heterogeneity, malignancy determination, and treatment effect uncertainty. Given the recent advancements in image synthesis, Generative Adversarial Networks (GANs), and adversarial training, we assess the potential of these technologies to address a number of key challenges of cancer imaging. We categorise these challenges into (a) data scarcity and imbalance, (b) data access and privacy, (c) data annotation and segmentation, (d) cancer detection and diagnosis, and (e) tumour profiling, treatment planning and monitoring. Based on our analysis of 164 publications that apply adversarial training techniques in the context of cancer imaging, we highlight multiple underexplored solutions with research potential. We further contribute the Synthesis Study Trustworthiness Test (SynTRUST), a meta-analysis framework for assessing the validation rigour of medical image synthesis studies. SynTRUST is based on 26 concrete measures of thoroughness, reproducibility, usefulness, scalability, and tenability. Based on SynTRUST, we analyse 16 of the most promising cancer imaging challenge solutions and observe a high validation rigour in general, but also several desirable improvements. With this work, we strive to bridge the gap between the needs of the clinical cancer imaging community and the current and prospective research on data synthesis and adversarial networks in the artificial intelligence community.

A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning

This survey aims to identify commonly used methods, datasets, future trends, knowledge gaps, constraints, and limitations in the field to provide an overview of current solutions used in medical image analysis in parallel with the rapid developments in transfer learning (TL). Unlike previous studies, this survey grouped the last five years of current studies for the period between January 2017 and February 2021 according to different anatomical regions and detailed the modality, medical task, TL method, source data, target data, and public or private datasets used in medical imaging. Also, it provides readers with detailed information on technical challenges, opportunities, and future research trends. In this way, an overview of recent developments is provided to help researchers to select the most effective and efficient methods and access widely used and publicly available medical datasets, research gaps, and limitations of the available literature.

High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection

Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. However, high-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. Therefore, the sensitivity of mammography for breast cancer detection can be reduced by more than 20% in dense breasts. Additionally, extremely dense cases reported an increased risk of cancer compared to low-density breasts. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms (FFDM) as data augmentation during breast mass detection model training. To this end, a total of five cycle-consistent GAN (CycleGAN) models using three FFDM datasets were trained for low-to-high-density image translation in high-resolution mammograms. The training images were split by breast density BI-RADS categories, being BI-RADS A almost entirely fatty and BI-RADS D extremely dense breasts. Our results showed that the proposed data augmentation technique improved the sensitivity and precision of mass detection in models trained with small datasets and improved the domain generalization of the models trained with large databases. In addition, the clinical realism of the synthetic images was evaluated in a reader study involving two expert radiologists and one surgical oncologist.

Data augmentation for medical imaging: A systematic literature review

Recent advances in Deep Learning have largely benefited from larger and more diverse training sets. However, collecting large datasets for medical imaging is still a challenge due to privacy concerns and labeling costs. Data augmentation makes it possible to greatly expand the amount and variety of data available for training without actually collecting new samples. Data augmentation techniques range from simple yet surprisingly effective transformations such as cropping, padding, and flipping, to complex generative models. Depending on the nature of the input and the visual task, different data augmentation strategies are likely to perform differently. For this reason, it is conceivable that medical imaging requires specific augmentation strategies that generate plausible data samples and enable effective regularization of deep neural networks. Data augmentation can also be used to augment specific classes that are underrepresented in the training set, e.g., to generate artificial lesions. The goal of this systematic literature review is to investigate which data augmentation strategies are used in the medical domain and how they affect the performance of clinical tasks such as classification, segmentation, and lesion detection. To this end, a comprehensive analysis of more than 300 articles published in recent years (2018-2022) was conducted. The results highlight the effectiveness of data augmentation across organs, modalities, tasks, and dataset sizes, and suggest potential avenues for future research.

An integrated framework for breast mass classification and diagnosis using stacked ensemble of residual neural networks

A computer-aided diagnosis (CAD) system requires automated stages of tumor detection, segmentation, and classification that are integrated sequentially into one framework to assist the radiologists with a final diagnosis decision. In this paper, we introduce the final step of breast mass classification and diagnosis using a stacked ensemble of residual neural network (ResNet) models (i.e. ResNet50V2, ResNet101V2, and ResNet152V2). The work presents the task of classifying the detected and segmented breast masses into malignant or benign, and diagnosing the Breast Imaging Reporting and Data System (BI-RADS) assessment category with a score from 2 to 6 and the shape as oval, round, lobulated, or irregular. The proposed methodology was evaluated on two publicly available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Comparative experiments were conducted on the individual models and an average ensemble of models with an XGBoost classifier. Qualitative and quantitative results show that the proposed model achieved better performance for (1) Pathology classification with an accuracy of 95.13%, 99.20%, and 95.88%; (2) BI-RADS category classification with an accuracy of 85.38%, 99%, and 96.08% respectively on CBIS-DDSM, INbreast, and the private dataset; and (3) shape classification with 90.02% on the CBIS-DDSM dataset. Our results demonstrate that our proposed integrated framework could benefit from all automated stages to outperform the latest deep learning methodologies.

Image Augmentation Techniques for Mammogram Analysis

Research in the medical imaging field using deep learning approaches has become progressively contingent. Scientific findings reveal that supervised deep learning methods' performance heavily depends on training set size, which expert radiologists must manually annotate. The latter is quite a tiring and time-consuming task. Therefore, most of the freely accessible biomedical image datasets are small-sized. Furthermore, it is challenging to have big-sized medical image datasets due to privacy and legal issues. Consequently, not a small number of supervised deep learning models are prone to overfitting and cannot produce generalized output. One of the most popular methods to mitigate the issue above goes under the name of data augmentation. This technique helps increase training set size by utilizing various transformations and has been publicized to improve the model performance when tested on new data. This article surveyed different data augmentation techniques employed on mammogram images. The article aims to provide insights into basic and deep learning-based augmentation techniques.

Generative Adversarial Networks in Medical Image augmentation: A review

OBJECT

With the development of deep learning, the number of training samples for medical image-based diagnosis and treatment models is increasing. Generative Adversarial Networks (GANs) have attracted attention in medical image processing due to their excellent image generation capabilities and have been widely used in data augmentation. In this paper, a comprehensive and systematic review and analysis of medical image augmentation work are carried out, and its research status and development prospects are reviewed.

METHOD

This paper reviews 105 medical image augmentation related papers, which mainly collected by ELSEVIER, IEEE Xplore, and Springer from 2018 to 2021. We counted these papers according to the parts of the organs corresponding to the images, and sorted out the medical image datasets that appeared in them, the loss function in model training, and the quantitative evaluation metrics of image augmentation. At the same time, we briefly introduce the literature collected in three journals and three conferences that have received attention in medical image processing.

RESULT

First, we summarize the advantages of various augmentation models, loss functions, and evaluation metrics. Researchers can use this information as a reference when designing augmentation tasks. Second, we explore the relationship between augmented models and the amount of the training set, and tease out the role that augmented models may play when the quality of the training set is limited. Third, the statistical number of papers shows that the development momentum of this research field remains strong. Furthermore, we discuss the existing limitations of this type of model and suggest possible research directions.

CONCLUSION

We discuss GAN-based medical image augmentation work in detail. This method effectively alleviates the challenge of limited training samples for medical image diagnosis and treatment models. It is hoped that this review will benefit researchers interested in this field.

Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network

Purpose: The purpose of this study was to develop and evaluate lung cancer segmentation with a pretrained model and transfer learning. The pretrained model was constructed from an artificial dataset generated using a generative adversarial network (GAN).

Materials and Methods: Three public datasets containing images of lung nodules/lung cancers were used: LUNA16 dataset, Decathlon lung dataset, and NSCLC radiogenomics. The LUNA16 dataset was used to generate an artificial dataset for lung cancer segmentation with the help of the GAN and 3D graph cut. Pretrained models were then constructed from the artificial dataset. Subsequently, the main segmentation model was constructed from the pretrained models and the Decathlon lung dataset. Finally, the NSCLC radiogenomics dataset was used to evaluate the main segmentation model. The Dice similarity coefficient (DSC) was used as a metric to evaluate the segmentation performance.

Results: The mean DSC for the NSCLC radiogenomics dataset improved overall when using the pretrained models. At maximum, the mean DSC was 0.09 higher with the pretrained model than that without it.

Conclusion: The proposed method comprising an artificial dataset and a pretrained model can improve lung cancer segmentation as confirmed in terms of the DSC metric. Moreover, the construction of the artificial dataset for the segmentation using the GAN and 3D graph cut was found to be feasible.

A review of medical image data augmentation techniques for deep learning applications

Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.

Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification

BACKGROUND AND OBJECTIVE

The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images.

METHODS

A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method.

RESULTS

The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods.

CONCLUSION

The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Deep learning (DL) has been successfully applied to the diagnosis of ophthalmic diseases. However, rare diseases are commonly neglected due to insufficient data. Here, we demonstrate that few-shot learning (FSL) using a generative adversarial network (GAN) can improve the applicability of DL in the optical coherence tomography (OCT) diagnosis of rare diseases. Four major classes with a large number of datasets and five rare disease classes with a few-shot dataset are included in this study. Before training the classifier, we constructed GAN models to generate pathological OCT images of each rare disease from normal OCT images. The Inception-v3 architecture was trained using an augmented training dataset, and the final model was validated using an independent test dataset. The synthetic images helped in the extraction of the characteristic features of each rare disease. The proposed DL model demonstrated a significant improvement in the accuracy of the OCT diagnosis of rare retinal diseases and outperformed the traditional DL models, Siamese network, and prototypical network. By increasing the accuracy of diagnosing rare retinal diseases through FSL, clinicians can avoid neglecting rare diseases with DL assistance, thereby reducing diagnosis delay and patient burden.

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection, metallic surface defect detection, disaster prediction, etc., are inevitable. The performance of computer vision algorithms can significantly deteriorate when the training dataset is imbalanced. In recent years, Generative Adversarial Neural Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image data. It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets. In this paper, we examine the most recent developments of GANs based techniques for addressing imbalance problems in image data. The real-world challenges and implementations of synthetic image generation based on GANs are extensively covered in this survey. Our survey first introduces various imbalance problems in computer vision tasks and its existing solutions, and then examines key concepts such as deep generative image models and GANs. After that, we propose a taxonomy to summarize GANs based techniques for addressing imbalance problems in computer vision tasks into three major categories: 1. Image level imbalances in classification, 2. object level imbalances in object detection and 3. pixel level imbalances in segmentation tasks. We elaborate the imbalance problems of each group, and provide GANs based solutions in each group. Readers will understand how GANs based techniques can handle the problem of imbalances and boost performance of the computer vision algorithms.

Attribute-guided image generation of three-dimensional computed tomography images of lung nodules using a generative adversarial network

PURPOSE

To develop and evaluate a three-dimensional (3D) generative model of computed tomography (CT) images of lung nodules using a generative adversarial network (GAN). To guide the GAN, lung nodule size was used.

MATERIALS AND METHODS

A public CT dataset of lung nodules was used, from where 1182 lung nodules were obtained. Our proposed GAN model used masked 3D CT images and nodule size information to generate images. To evaluate the generated CT images, two radiologists visually evaluated whether the CT images with lung nodule were true or generated, and the diagnostic ability was evaluated using receiver-operating characteristic analysis and area under the curves (AUC). Then, two models for classifying nodule size into five categories were trained, one using the true and the other using the generated CT images of lung nodules. Using true CT images, the classification accuracy of the sizes of the true lung nodules was calculated for the two classification models.

RESULTS

The sensitivity, specificity, and AUC of the two radiologists were respectively as follows: radiologist 1: 81.3%, 37.7%, and 0.592; radiologist 2: 77.1%, 30.2%, and 0.597. For categorization of nodule size, the mean accuracy of the classification model constructed with true CT images was 85% (range 83.2-86.1%), and that with generated CT images was 85% (range 82.2-88.1%).

CONCLUSIONS

Our results show that it was possible to generate 3D CT images of lung nodules that could be used to construct a classification model of lung nodule size without true CT images.

Toward automated severe pharyngitis detection with smartphone camera using deep learning networks

PURPOSE

Severe pharyngitis is frequently associated with inflammations caused by streptococcal pharyngitis, which can cause immune-mediated and post-infectious complications. The recent global pandemic of coronavirus disease (COVID-19) encourages the use of telemedicine for patients with respiratory symptoms. This study, therefore, purposes automated detection of severe pharyngitis using a deep learning framework with self-taken throat images.

METHODS

A dataset composed of two classes of 131 throat images with pharyngitis and 208 normal throat images was collected. Before the training classifier, we constructed a cycle consistency generative adversarial network (CycleGAN) to augment the training dataset. The ResNet50, Inception-v3, and MobileNet-v2 architectures were trained with transfer learning and validated using a randomly selected test dataset. The performance of the models was evaluated based on the accuracy and area under the receiver operating characteristic curve (ROC-AUC).

RESULTS

The CycleGAN-based synthetic images reflected the pragmatic characteristic features of pharyngitis. Using the synthetic throat images, the deep learning model demonstrated a significant improvement in the accuracy of the pharyngitis diagnosis. ResNet50 with GAN-based augmentation showed the best ROC-AUC of 0.988 for pharyngitis detection in the test dataset. In the 4-fold cross-validation using the ResNet50, the highest detection accuracy and ROC-AUC achieved were 95.3% and 0.992, respectively.

CONCLUSION

The deep learning model for smartphone-based pharyngitis screening allows fast identification of severe pharyngitis with a potential of the timely diagnosis of pharyngitis. In the recent pandemic of COVID-19, this framework will help patients with upper respiratory symptoms to improve convenience in diagnosis and reduce transmission.

Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net

Combinations of data augmentation methods and deep learning architectures for automatic pancreas segmentation on CT images are proposed and evaluated. Images from a public CT dataset of pancreas segmentation were used to evaluate the models. Baseline U-net and deep U-net were chosen for the deep learning models of pancreas segmentation. Methods of data augmentation included conventional methods, mixup, and random image cropping and patching (RICAP). Ten combinations of the deep learning models and the data augmentation methods were evaluated. Four-fold cross validation was performed to train and evaluate these models with data augmentation methods. The dice similarity coefficient (DSC) was calculated between automatic segmentation results and manually annotated labels and these were visually assessed by two radiologists. The performance of the deep U-net was better than that of the baseline U-net with mean DSC of 0.703–0.789 and 0.686–0.748, respectively. In both baseline U-net and deep U-net, the methods with data augmentation performed better than methods with no data augmentation, and mixup and RICAP were more useful than the conventional method. The best mean DSC was obtained using a combination of deep U-net, mixup, and RICAP, and the two radiologists scored the results from this model as good or perfect in 76 and 74 of the 82 cases.