Bilinear Pooling for Thyroid Nodule Classification in Ultrasound Imaging

Aboudi, Noura; Khachnaoui, Hajer; Moussa, Olfa Ben; Khlifa, Nawrès

doi:10.1007/s13369-023-07674-3

Cited by 7 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TL is a powerful technique in DL that leverages the knowledge acquired by pre-trained CNN models like AlexNet, VGG, ResNet, and Inception. These models are trained on extensive datasets and excel at extracting important features from images [18][19][20][21][22]. By employing TL, we can take advantage of these pre-trained models' ability to recognize common patterns and structures in images, even for different tasks.…”

Section: Transfer Learning Techniquementioning

confidence: 99%

“…The Bilinear CNN (BCNN) architecture has gained significant attention in computer vision for its ability to capture spatial interactions between features, making it effective in tasks like image classification and object recognition [21][22]. BCNN utilizes bilinear pooling as a key component, combining the output vectors of two separate CNN architectures through an outer product function.…”

Section: Bilinear Cnn Model Descriptionmentioning

confidence: 99%

“…These models were initially trained on the extensive ImageNet dataset, enabling them to learn valuable generic image features. Additionally, we explored two variations of BCNN architectures by combining the aforementioned pre-trained models: BCNN (VGG − 16)2 and BCNN (Inception − v3) 2[21][22]. Furthermore, we developed a custom CNN model tailored specifically to address our research problem.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Postoperative Visual Acuity in Rhegmatogenous Retinal Detachment Using OCT Images

Hosni,

Khachnaoui,

Zgolli

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Deep Learning (DL) methods, such as Convolution Neural Networks (CNNs), have shown great potential in diagnosing complex diseases. Among these diseases, Rhegmatogenous Retinal Detachment (RRD) stands out as a critical condition necessitating precise diagnosis and postoperative Visual Acuity (VA) prediction. This research introduces a DL-based Computer-Aided Diagnosis (CAD) system that utilizes Optical Coherence Tomography (OCT) images for both the diagnosis of RRD and the prediction of postoperative VA. The CAD system utilizes DL techniques and a diverse dataset, including OCT images of patients with RRD from the Hedi Raies Ophthalmology Institute of Tunis and a large public dataset of normal subjects OCT. Preprocessing steps, such as image cropping, enhancement, denoising, and resizing, are applied to the tomographic images. Data oversampling and augmentation techniques address class imbalance and improve the dataset by generating additional samples. Various DL models, including pre-trained CNN models (VGG-16, Inception-V3, Inception-ResNet-V2), Bilinear (BCNN) (BCNN (VGG − 16) 2 and BCNN (Inception − V3) 2 ), and a custom CNN architecture, are implemented for RRD diagnosis and postoperative VA prediction. The experimental outcomes demonstrate the effectiveness of the proposed CAD system in accurately diagnosing RRD and predicting postoperative VA. The system achieves high accuracy, with 99.87% for diagnosing RRD and 98.06% for predicting postoperative VA using the BCNN (VGG − 16) 2 model. The developed CAD system represents a significant advancement in the field of RRD and postoperative VA prediction. By combining DL and OCT imaging, the system provides automated and accurate diagnosis, showing potential in improving patient care and treatment decisions.

show abstract