Hatem A. Rashwan

Armin Masoumian, Hatem A. Rashwan, Saddam Abdulwahab et al.

Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing of environment awareness. This work brings a new solution with a set of improvements, which increase the quantitative and qualitative understanding of depth maps compared to existing methods. Recently, a convolutional neural network (CNN) has demonstrated its extraordinary ability in estimating depth maps from monocular videos. However, traditional CNN does not support topological structure and they can work only on regular image regions with determined size and weights. On the other hand, graph convolutional networks (GCN) can handle the convolution on non-Euclidean data and it can be applied to irregular image regions within a topological structure. Therefore, in this work in order to preserve object geometric appearances and distributions, we aim at exploiting GCN for a self-supervised depth estimation model. Our model consists of two parallel auto-encoder networks: the first is an auto-encoder that will depend on ResNet-50 and extract the feature from the input image and on multi-scale GCN to estimate the depth map. In turn, the second network will be used to estimate the ego-motion vector (i.e., 3D pose) between two consecutive frames based on ResNet-18. Both the estimated 3D pose and depth map will be used for constructing a target image. A combination of loss functions related to photometric, projection, and smoothness is used to cope with bad depth prediction and preserve the discontinuities of the objects. In particular, our method provided comparable and promising results with a high prediction accuracy of 89% on the publicly KITTI and Make3D datasets along with a reduction of 40% in the number of trainable parameters compared to the state of the art solutions. The source code is publicly available at https://github.com/ArminMasoumian/GCNDepth.git

Muhammad Mursil, Hatem A. Rashwan, Luis Santos-Calderon et al.

Birth weight (BW) is a key indicator of neonatal health, with low birth weight (LBW) linked to increased mortality and morbidity. Early prediction of BW enables timely interventions; however, current methods like ultrasonography have limitations, including reduced accuracy before 20 weeks and operator dependent variability. Existing models often neglect nutritional and genetic influences, focusing mainly on physiological and lifestyle factors. This study presents an attention-based transformer model with a multi-encoder architecture for early (less than 12 weeks of gestation) BW prediction. Our model effectively integrates diverse maternal data such as physiological, lifestyle, nutritional, and genetic, addressing limitations seen in prior attention-based models such as TabNet. The model achieves a Mean Absolute Error (MAE) of 122 grams and an R-squared value of 0.94, demonstrating high predictive accuracy and interoperability with our in-house private dataset. Independent validation confirms generalizability (MAE: 105 grams, R-squared: 0.95) with the IEEE children dataset. To enhance clinical utility, predicted BW is classified into low and normal categories, achieving a sensitivity of 97.55% and a specificity of 94.48%, facilitating early risk stratification. Model interpretability is reinforced through feature importance and SHAP analyses, highlighting significant influences of maternal age, tobacco exposure, and vitamin B12 status, with genetic factors playing a secondary role. Our results emphasize the potential of advanced deep-learning models to improve early BW prediction, offering clinicians a robust, interpretable, and personalized tool for identifying pregnancies at risk and optimizing neonatal outcomes.

Saif Khalid, Hatem A. Rashwan, Saddam Abdulwahab et al.

The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called FGR-Net to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of 89% and an F1-score of 87%.

Eddardaa B. Loussaief, Mohammed Ayad, Domenc Puig et al.

The joint utilization of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating information from multiple data domains has shown promise in improving model generalizability and adaptability. However, this approach often demands substantial computational resources, hindering its practicality. In response, knowledge distillation (KD) has garnered attention as a solution. KD involves training light-weight models to emulate the behavior of more resource-intensive models, thereby mitigating the computational burden while maintaining performance. This paper addresses the pressing need to develop a lightweight and generalizable model for medical imaging segmentation that can effectively handle data integration challenges. Our proposed approach introduces a novel relation-based knowledge framework by seamlessly combining adaptive affinity-based and kernel-based distillation through a gram matrix that can capture the style representation across features. This methodology empowers the student model to accurately replicate the feature representations of the teacher model, facilitating robust performance even in the face of domain shift and data heterogeneity. To validate our innovative approach, we conducted experiments on publicly available multi-source prostate MRI data. The results demonstrate a significant enhancement in segmentation performance using lightweight networks. Notably, our method achieves this improvement while reducing both inference time and storage usage, rendering it a practical and efficient solution for real-time medical imaging segmentation.

Armin Masoumian, Pezhman kazemi, Mohammad Chehreghani Montazer et al.

The inverted pendulum is a non-linear unbalanced system that needs to be controlled using motors to achieve stability and equilibrium. The inverted pendulum is constructed with Lego and using the Lego Mindstorm NXT, which is a programmable robot capable of completing many different functions. In this paper, an initial design of the inverted pendulum is proposed and the performance of different sensors, which are compatible with the Lego Mindstorm NXT was studied. Furthermore, the ability of computer vision to achieve the stability required to maintain the system is also investigated. The inverted pendulum is a conventional cart that can be controlled using a Fuzzy Logic controller that produces a self-tuning PID control for the cart to move on. The fuzzy logic and PID are simulated in MATLAB and Simulink, and the program for the robot is developed in the LabVIEW software.

Armin Masoumian, Pezhman kazemi, Mohammad Chehreghani Montazer et al.

The objective of this paper is to describe an approach to detect the slip and contact force in real-time feedback. In this novel approach, the DAVIS camera is used as a vision tactile sensor due to its fast process speed and high resolution. Two hundred experiments were performed on four objects with different shapes, sizes, weights, and materials to compare the accuracy and response of the Baxter robot grippers to avoid slipping. The advanced approach is validated by using a force-sensitive resistor (FSR402). The events captured with the DAVIS camera are processed with specific algorithms to provide feedback to the Baxter robot aiding it to detect the slip.

Armin Masoumian, David G. F. Marei, Saddam Abdulwahab et al.

Determining the distance between the objects in a scene and the camera sensor from 2D images is feasible by estimating depth images using stereo cameras or 3D cameras. The outcome of depth estimation is relative distances that can be used to calculate absolute distances to be applicable in reality. However, distance estimation is very challenging using 2D monocular cameras. This paper presents a deep learning framework that consists of two deep networks for depth estimation and object detection using a single image. Firstly, objects in the scene are detected and localized using the You Only Look Once (YOLOv5) network. In parallel, the estimated depth image is computed using a deep autoencoder network to detect the relative distances. The proposed object detection based YOLO was trained using a supervised learning technique, in turn, the network of depth estimation was self-supervised training. The presented distance estimation framework was evaluated on real images of outdoor scenes. The achieved results show that the proposed framework is promising and it yields an accuracy of 96% with RMSE of 0.203 of the correct absolute distance.

Farhan Akram, Vivek Kumar Singh, Hatem A. Rashwan et al.

In this paper, we propose an efficient blood vessel segmentation method for the eye fundus images using adversarial learning with multiscale features and kernel factorization. In the generator network of the adversarial framework, spatial pyramid pooling, kernel factorization and squeeze excitation block are employed to enhance the feature representation in spatial domain on different scales with reduced computational complexity. In turn, the discriminator network of the adversarial framework is formulated by combining convolutional layers with an additional squeeze excitation block to differentiate the generated segmentation mask from its respective ground truth. Before feeding the images to the network, we pre-processed them by using edge sharpening and Gaussian regularization to reach an optimized solution for vessel segmentation. The output of the trained model is post-processed using morphological operations to remove the small speckles of noise. The proposed method qualitatively and quantitatively outperforms state-of-the-art vessel segmentation methods using DRIVE and STARE datasets.

Vivek Kumar Singh, Hatem A. Rashwan, Mohamed Abdel-Nasser et al.

This paper proposes an efficient solution for tumor segmentation and classification in breast ultrasound (BUS) images. We propose to add an atrous convolution layer to the conditional generative adversarial network (cGAN) segmentation model to learn tumor features at different resolutions of BUS images. To automatically re-balance the relative impact of each of the highest level encoded features, we also propose to add a channel-wise weighting block in the network. In addition, the SSIM and L1-norm loss with the typical adversarial loss are used as a loss function to train the model. Our model outperforms the state-of-the-art segmentation models in terms of the Dice and IoU metrics, achieving top scores of 93.76% and 88.82%, respectively. In the classification stage, we show that few statistics features extracted from the shape of the boundaries of the predicted masks can properly discriminate between benign and malignant tumors with an accuracy of 85%$

Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Farhan Akram et al.

The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based image segmentation models, such as FCN. Therefore, SLSNet can be used for practical dermoscopic applications.

Mohamed Chafik Bakkay, Sylvie Chambon, Hatem A. Rashwan et al.

This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM classifier is trained with a multi-scale descriptor, Histogram Of Curviness Saliency (HCS). This descriptor is robust to illumination changes and is able to detect and to describe the external and the internal contours of the target insect in multi-scale. The proposed classification method can be trained with a small set of images. Quantitative evaluations show that the proposed method is able to classify insects with higher accuracy (rate of 95.8%) than the state-of-the art approaches.

Vivek Kumar Singh, Hatem A. Rashwan, Santiago Romani et al.

Mammogram inspection in search of breast tumors is a tough assignment that radiologists must carry out frequently. Therefore, image analysis methods are needed for the detection and delineation of breast masses, which portray crucial morphological information that will support reliable diagnosis. In this paper, we proposed a conditional Generative Adversarial Network (cGAN) devised to segment a breast mass within a region of interest (ROI) in a mammogram. The generative network learns to recognize the breast mass area and to create the binary mask that outlines the breast mass. In turn, the adversarial network learns to distinguish between real (ground truth) and synthetic segmentations, thus enforcing the generative network to create binary masks as realistic as possible. The cGAN works well even when the number of training samples are limited. Therefore, the proposed method outperforms several state-of-the-art approaches. This hypothesis is corroborated by diverse experiments performed on two datasets, the public INbreast and a private in-house dataset. The proposed segmentation model provides a high Dice coefficient and Intersection over Union (IoU) of 94% and 87%, respectively. In addition, a shape descriptor based on a Convolutional Neural Network (CNN) is proposed to classify the generated masks into four mass shapes: irregular, lobular, oval and round. The proposed shape descriptor was trained on Digital Database for Screening Mammography (DDSM) yielding an overall accuracy of 80%, which outperforms the current state-of-the-art.

Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Estefania Talavera et al.

First-person (wearable) camera continually captures unscripted interactions of the camera user with objects, people, and scenes reflecting his personal and relational tendencies. One of the preferences of people is their interaction with food events. The regulation of food intake and its duration has a great importance to protect against diseases. Consequently, this work aims to develop a smart model that is able to determine the recurrences of a person on food places during a day. This model is based on a deep end-to-end model for automatic food places recognition by analyzing egocentric photo-streams. In this paper, we apply multi-scale Atrous convolution networks to extract the key features related to food places of the input images. The proposed model is evaluated on an in-house private dataset called "EgoFoodPlaces". Experimental results shows promising results of food places classification recognition in egocentric photo-streams.

Vivek Kumar Singh, Hatem A. Rashwan, Adel Saleh et al.

In this paper, an optic disc and cup segmentation method is proposed using U-Net followed by a multi-scale feature matching network. The proposed method targets task 2 of the REFUGE challenge 2018. In order to solve the segmentation problem of task 2, we firstly crop the input image using single shot multibox detector (SSD). The cropped image is then passed to an encoder-decoder network with skip connections also known as generator. Afterwards, both the ground truth and generated images are fed to a convolution neural network (CNN) to extract their multi-level features. A dice loss function is then used to match the features of the two images by minimizing the error at each layer. The aggregation of error from each layer is back-propagated through the generator network to enforce it to generate a segmented image closer to the ground truth. The CNN network improves the performance of the generator network without increasing the complexity of the model.

Md. Mostafa Kamal Sarker, Mohammed Jabreel, Hatem A. Rashwan et al.

Diversity of food and its attributes represents the culinary habits of peoples from different countries. Thus, this paper addresses the problem of identifying food culture of people around the world and its flavor by classifying two main food attributes, cuisine and flavor. A deep learning model based on multi-scale convotuional networks is proposed for extracting more accurate features from input images. The aggregation of multi-scale convolution layers with different kernel size is also used for weighting the features results from different scales. In addition, a joint loss function based on Negative Log Likelihood (NLL) is used to fit the model probability to multi labeled classes for multi-modal classification task. Furthermore, this work provides a new dataset for food attributes, so-called Yummly48K, extracted from the popular food website, Yummly. Our model is assessed on the constructed Yummly48K dataset. The experimental results show that our proposed method yields 65% and 62% average F1 score on validation and test set which outperforming the state-of-the-art models.

Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Farhan Akram et al.

Skin lesion segmentation (SLS) in dermoscopic images is a crucial task for automated diagnosis of melanoma. In this paper, we present a robust deep learning SLS model, so-called SLSDeep, which is represented as an encoder-decoder network. The encoder network is constructed by dilated residual layers, in turn, a pyramid pooling network followed by three convolution layers is used for the decoder. Unlike the traditional methods employing a cross-entropy loss, we investigated a loss function by combining both Negative Log Likelihood (NLL) and End Point Error (EPE) to accurately segment the melanoma regions with sharp boundaries. The robustness of the proposed model was evaluated on two public databases: ISBI 2016 and 2017 for skin lesion analysis towards melanoma detection challenge. The proposed model outperforms the state-of-the-art methods in terms of segmentation accuracy. Moreover, it is capable to segment more than $100$ images of size 384x384 per second on a recent GPU.

Vivek Kumar Singh, Santiago Romani, Hatem A. Rashwan et al.

This paper proposes a novel approach based on conditional Generative Adversarial Networks (cGAN) for breast mass segmentation in mammography. We hypothesized that the cGAN structure is well-suited to accurately outline the mass area, especially when the training data is limited. The generative network learns intrinsic features of tumors while the adversarial network enforces segmentations to be similar to the ground truth. Experiments performed on dozens of malignant tumors extracted from the public DDSM dataset and from our in-house private dataset confirm our hypothesis with very high Dice coefficient and Jaccard index (>94% and >89%, respectively) outperforming the scores obtained by other state-of-the-art approaches. Furthermore, in order to detect portray significant morphological features of the segmented tumor, a specific Convolutional Neural Network (CNN) have also been designed for classifying the segmented tumor areas into four types (irregular, lobular, oval and round), which provides an overall accuracy about 72% with the DDSM dataset.

Hatem A. Rashwan, Sylvie Chambon, Pierre Gurdjos et al.

In the context of 2D/3D registration, this paper introduces an approach that allows to match features detected in two different modalities: photographs and 3D models, by using a common 2D reprensentation. More precisely, 2D images are matched with a set of depth images, representing the 3D model. After introducing the concept of curvilinear saliency, related to curvature estimation, we propose a new ridge and valley detector for depth images rendered from 3D model. A variant of this detector is adapted to photographs, in particular by applying it in multi-scale and by combining this feature detector with the principle of focus curves. Finally, a registration algorithm for determining the correct viewpoint of the 3D model and thus the pose is proposed. It is based on using histogram of gradients features adapted to the features manipulated in 2D and in 3D, and the introduction of repeatability scores. The results presented highlight the quality of the features detected, in term of repeatability, and also the interest of the approach for registration and pose estimation.