Recently, our world witnessed major events that attracted a lot of attention towards the importance of automatic crowd scene analysis. For example, the COVID-19 breakout and public events require an automatic system to manage, count, secure, and track a crowd that shares the same area. However, analyzing crowd scenes is very challenging due to heavy occlusion, complex behaviors, and posture changes. This paper surveys deep learning-based methods for analyzing crowded scenes. The reviewed methods are categorized as (1) crowd counting and (2) crowd actions recognition. Moreover, crowd scene datasets are surveyed. In additional to the above surveys, this paper proposes an evaluation metric for crowd scene analysis methods. This metric estimates the difference between calculated crowed count and actual count in crowd scene videos.

One of the most important clinical examination tests is the blood test. In a clinical laboratory, counting different blood cells is important. Manual microscopic inspection is time-consuming and requires technical knowledge. Therefore, automatic medical diagnosis systems are required to help physicians to diagnose diseases in a fast and yet efficient way. Cell automatic classification has larger interest especially for clinics and laboratories; the most important step in automatic classification success is segmentation. This paper shows an efficient technique for automatic blood cell nuclei segmentation. This technique is relying on enhancing and filtering the gray scale image contrast. False objects are removed utilizing minimum segment size. 365 blood images were used to examine this segmentation technique. Quantitative analysis of the proposed segmentation technique on the blood image set gives 80.6% accuracy. In comparison to other techniques the proposed segmentation technique performance was found to be superior. The five normal white blood cells types were used for evaluation to compare isolated performance. Eosinophil was found to have the lowest segmentation accuracy which is 71.0% and Monocyte was the highest one with 85.9%. The blood images dataset and the source code are published on MATLAB file exchange website for comparison and re-production.

The COVID-19 pandemic has been deemed a global health pandemic. The early detection of COVID-19 is key to combating its outbreak and could help bring this pandemic to an end. One of the biggest challenges in combating COVID-19 is accurate testing for the disease. Utilizing the power of Convolutional Neural Networks (CNNs) to detect COVID-19 from chest X-ray images can help radiologists compare and validate their results with an automated system. In this paper, we propose a carefully designed network, dubbed CORONA-Net, that can accurately detect COVID-19 from chest X-ray images. CORONA-Net is divided into two phases: (1) The reinitialization phase and (2) the classification phase. In the reinitialization phase, the network consists of encoder and decoder networks. The objective of this phase is to train and initialize the encoder and decoder networks by a distribution that comes out of medical images. In the classification phase, the decoder network is removed from CORONA-Net, and the encoder network acts as a backbone network to fine-tune the classification phase based on the learned weights from the reinitialization phase. Extensive experiments were performed on a publicly available dataset, COVIDx, and the results show that CORONA-Net significantly outperforms the current state-of-the-art networks with an overall accuracy of 95.84%.

Among the non-invasive Colorectal cancer (CRC) screening approaches, Computed Tomography Colonography (CTC) and Virtual Colonoscopy (VC), are much more accurate. This work proposes an AI-based polyp detection framework for virtual colonoscopy (VC). Two main steps are addressed in this work: automatic segmentation to isolate the colon region from its background, and automatic polyp detection. Moreover, we evaluate the performance of the proposed framework on low-dose Computed Tomography (CT) scans. We build on our visualization approach, Fly-In (FI), which provides “filet”-like projections of the internal surface of the colon. The performance of the Fly-In approach confirms its ability with helping gastroenterologists, and it holds a great promise for combating CRC. In this work, these 2D projections of FI are fused with the 3D colon representation to generate new synthetic images. The synthetic images are used to train a RetinaNet model to detect polyps. The trained model has a $94\%$ f1-score and $97\%$ sensitivity. Furthermore, we study the effect of dose variation in CT scans on the performance of the the FI approach in polyp visualization. A simulation platform is developed for CTC visualization using FI, for regular CTC and low-dose CTC. This is accomplished using a novel AI restoration algorithm that enhances the Low-Dose CT images so that a 3D colon can be successfully reconstructed and visualized using the FI approach. Three senior board-certified radiologists evaluated the framework for the peak voltages of 30 KV, and the average relative sensitivities of the platform were $92\%$, whereas the 60 KV peak voltage produced average relative sensitivities of $99.5\%$.

Visual tracking is a difficult and challenging problem, for numerous reasons such as small object size, pose angle variations, occlusion, and camera motion. Object tracking has many real-world applications such as surveillance systems, moving organs in medical imaging, and robotics. Traditional tracking methods lack a recovery mechanism that can be used in situations when the tracked objects drift away from ground truth. In this paper, we propose a novel framework for tracking moving objects based on a composite framework and a reporter mechanism. The composite framework tracks moving objects using different trackers and produces pairs of forward/backward tracklets. A robustness score is then calculated for each tracker using its forward/backward tracklet pair to find the most reliable moving object trajectory. The reporter serves as the recovery mechanism to correct the moving object trajectory when the robustness score is very low, mainly using a combination of particle filter and template matching. The proposed framework can handle partial and heavy occlusions; moreover, the structure of the framework enables integration of other user-specific trackers. Extensive experiments on recent benchmarks show that the proposed framework outperforms other current state-of-the-art trackers due to its powerful trajectory analysis and recovery mechanism; the framework improved the area under the curve from 68% to 70.8% on OTB-100 benchmark.