Content-based Image Retrieval for Breast Ultrasound Images using Convolutional Autoencoders: A Feasibility Study

Daoud, Mohammad I.; Saleh, Amro; Hababeh, Ismail; Alazrai, Rami

doi:10.1109/biosmart.2019.8734190

Cited by 15 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features bring benefits to CBHIR, such as ignoring the noise in WSIs that might be noticeable due to the scanners. Also, they can reduce the demand for annotated images for training an FE, which is expensive and time-consuming [40,41].…”

Section: Feature Extractormentioning

confidence: 99%

See 1 more Smart Citation

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Tabatabaei,

Pérez Bueno,

Colomer

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14% increase), compared to working with the original images.

show abstract

Section: Feature Extractormentioning

confidence: 99%

“…In this paper, at this stage, the welltrained CAE extracts the features of the images of the validation and training sets. These feature vectors are subsequently indexed and saved as the features of the database for the searching process [41].…”

Section: Searchingmentioning

confidence: 99%

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Tabatabaei,

Pérez Bueno,

Colomer

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A similar procedure based on measuring the similarity of the latent features from different input data has been applied on different state-of-the-art techniques, such as contrastive learning [77][78][79] or content-based image retrieval (CBIR) [80][81][82]. In contrastive learning tasks, an encoder network followed by a projection head is trained to differentiate between positive and negative samples, being positive samples the augmented version of a query (or samples with the same label in the case of supervised contrastive [77]), and negative samples the entire remainder of the batch.…”

Section: Static Prototypesmentioning

confidence: 99%

“…At this point, several contributions are proposed in a novel framework for glaucoma grading. The method based on static prototypes was conducted for the first time by inferring the weights (φ → Θ) of class-based prediction networks, instead of auto-encoders, as in the case of CBIR-based studies [80][81][82], or architectures intended to discern between positive and negative classes, as in the contrastive learning works [77][78][79]. Notwithstanding, the main novelties related to the prototypical environment were introduced in the dynamic approximation.…”

Section: About the Ablation Experimentsmentioning

confidence: 99%

Circumpapillary OCT-focused hybrid learning for glaucoma grading using tailored prototypical neural networks

García

Amor

Colomer

et al. 2021

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

“…Recently, several US denoising techniques based on deep learning have been widely used, such as Convolutional Neural Networks (CNN) [11,12,13,14], Generative Adversarial Networks (GANs) [15,16,17], and Autoencoders (AEs) [18,19], which can recover the original dataset and make it noisefree with better robustness and precision [20]. Deep learning methods have obtained better results in medical imaging in comparison with previous methods such as Wavelet, Wiener, Gaussian [21], Multi-Layer perceptron [22], Dictionary Learning [23], Least Square, Bilateral Filter, Non-Local Mean [24].…”

mentioning

confidence: 99%

Ultrasound breast images denoising using generative adversarial networks (GANs)

Jiménez-Gaona,

Rodríguez-Alvarez,

Escudero

et al. 2024

IDA

View full text Add to dashboard Cite

INTRODUCTION: Ultrasound in conjunction with mammography imaging, plays a vital role in the early detection and diagnosis of breast cancer. However, speckle noise affects medical ultrasound images and degrades visual radiological interpretation. Speckle carries information about the interactions of the ultrasound pulse with the tissue microstructure, which generally causes several difficulties in identifying malignant and benign regions. The application of deep learning in image denoising has gained more attention in recent years. OBJECTIVES: The main objective of this work is to reduce speckle noise while preserving features and details in breast ultrasound images using GAN models. METHODS: We proposed two GANs models (Conditional GAN and Wasserstein GAN) for speckle-denoising public breast ultrasound databases: BUSI, DATASET A, AND UDIAT (DATASET B). The Conditional GAN model was trained using the Unet architecture, and the WGAN model was trained using the Resnet architecture. The image quality results in both algorithms were measured by Peak Signal to Noise Ratio (PSNR, 35–40 dB) and Structural Similarity Index (SSIM, 0.90–0.95) standard values. RESULTS: The experimental analysis clearly shows that the Conditional GAN model achieves better breast ultrasound despeckling performance over the datasets in terms of PSNR = 38.18 dB and SSIM = 0.96 with respect to the WGAN model (PSNR = 33.0068 dB and SSIM = 0.91) on the small ultrasound training datasets. CONCLUSIONS: The observed performance differences between CGAN and WGAN will help to better implement new tasks in a computer-aided detection/diagnosis (CAD) system. In future work, these data can be used as CAD input training for image classification, reducing overfitting and improving the performance and accuracy of deep convolutional algorithms.

show abstract

Content-based Image Retrieval for Breast Ultrasound Images using Convolutional Autoencoders: A Feasibility Study

Cited by 15 publications

References 15 publications

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Circumpapillary OCT-focused hybrid learning for glaucoma grading using tailored prototypical neural networks

Ultrasound breast images denoising using generative adversarial networks (GANs)

Contact Info

Product

Resources

About