Artificial intelligence (AI) is one of the most promising approaches to health innovation. The use of AI in image recognition considerably extends findings beyond the constraints of human sight. The application of AI in medical imaging, which relies on picture interpretation, is beneficial for automatic diagnosis. Diagnostic radiology is evolving from a subjective perceptual talent to a more objective science thanks to AI. Automatic object detection in medical images is an essential AI technology in medicine. The problem of detecting brain tumors at an early stage is well advanced with convolutional neural network (CNN) and deep learning algorithms (DLA). The problem is that those algorithms require a training phase with a big database of more than 500 images and time-consuming with a complex computational and expensive infrastructure. This study proposes a classical automatic segmentation method for detecting brain tumors in the early stage using MRI images. It is based on a multilevel thresholding technique on a harmony search algorithm (HSO); the algorithm was developed to suit MRI brain segmentation, and parameters selection was optimized for the purpose. Multiple thresholds, based on the variance and entropy functions, break the histogram into multiple portions, and different colors are associated with each portion. To eliminate the tiny arias supposed as noise and detect brain tumors, morphological operations followed by a connected component analysis are utilized after segmentation. The brain tumor detection performance is judged using performance parameters such as Accuracy, Dice Coefficient, and Jaccard index. The results are compared to those acquired manually by experts in the field. The results were further compared with different CNN and DLA approaches using Brain Images dataset called the “BraTS 2017 challenge”. The average Dice Index was used as a performance measure for the comparison. The results of the proposed approach were found to be competitive in accuracy to those obtained by CNN and DLA methods and much better in terms of execution time, computational complexity, and data management.

This study introduces a novel deep-learning methodology that is customized to automatically diagnose Alzheimer’s disease (AD) through the analysis of MRI datasets. The process of diagnosing AD via the visual examination of magnetic resonance imaging (MRI) presents considerable challenges. The visual diagnosis of mild to very mild stages of AD is challenging due to the MRI similarities observed between a brain that is aging normally and one that has AD. The detection of AD with extreme precision is critical during its early stages. Deep-learning techniques have recently been shown to be significantly more effective than human detection in identifying various stages of AD, enabling early-stage diagnosis. The aim of this research is to develop a deep-learning approach that utilizes pre-trained convolutional neural networks (CNNs) to accurately detect the severity levels of AD, particularly in situations where the quantity and quality of available datasets are limited. In this approach, the AD dataset is preprocessed via a refined image processing module prior to the training phase. The proposed method was compared to two well-known deep-learning algorithms (VGG16 and ResNet50) using four Kaggle AD datasets: one for the normal stage of the disease and three for the mild, very mild, and moderate stages, respectively. This allowed us to evaluate the effectiveness of the classification results. The three models were compared using six performance metrics. The results achieved with our approach indicate an overall detection accuracy of 99.3%, which is superior to the other existing models.

Gold nanoparticles (GNPs) are used in proton therapy radio-sensitizers to help increase the dose of radiation to targeted tumors by the emission of secondary electrons. Thus, this study aimed to investigate the link between secondary electron yields produced from a nanoshell of GNPs and dose absorption according to the distance from the center of the nanoparticles by using a Monte Carlo model. Microscopic evaluation was performed by modeling the interactions of secondary electrons in a phase-space file (PSF), where the number of emitted electrons was calculated within a spherical GNP of 15 nm along with the absorbed dose near it. Then, the Geant4-DNA physics list was used to facilitate the tracking of low-energy electrons down to an energy below 50 eV in water. The results show a remarkable change in the number of secondary electrons, which can be compared at concentrations less than and greater than 5 mg/mL, with increased secondary electron production exhibited around NPs within a distance of 10–100 nm from the surface of all nanospheres. It was found that there was a steep dose enhancement drop-off up to a factor of dose enhancement factor (DFE) ≤ 1 within a short distance of 100 nm from the surface of the GNPs, which revealed that the dose enhancement existed locally at nanometer distances from the GNPs. Overall, our results indicate that the physical interactions of protons with GNP clusters should not be considered as being directly responsible for the radio-sensitization effect, but should be regarded as playing a major role in NP properties and concentrations, which has a subsequent impact on local dose enhancement.

The development of sensor technology enables the creation of DNA-based biosensors for biomedical applications. Herein, a quartz tuning fork (QTF) sensing system was employed as a transducer for biomedical applications to address indirect DNA damage associated with gold nanoparticles (GNPs) and enhance the effectiveness of low-dose gamma radiation in radiation therapy. The experiment included two stages, namely during and after irradiation exposure; shift frequencies (Δf) were measured for 20 min in each stage. During the irradiation stage, the QTF response to DNA damage was investigated in a deionized aqueous solution with and without 100 nm GNPs at different concentrations (5, 10, 15, and 20 µg/mL). Upon exposure to gamma radiation for 20 min at a dose rate of 2.4 µGy/min, the ratio of Δf/ΔT indicates increased fork displacement frequencies with or without GNPs. Additionally, DNA damage associated with high and low GNP concentrations was evaluated using the change in the resonance frequency of the QTF. The results indicate that GNPs at 15 and 10 µg/mL were associated with high damage-enhancement ratios, while saturation occurred at 20 µg/mL. At 15 µg/mL, significant radiotherapy enhancement occurred compared to that at 10 µg/mL at 10 min after exposure. In the post-irradiation stage, the frequency considerably differed between 15 and 10 µg/mL. Finally, these results significantly depart from the experimental predictions in the post-radiation stage. They exhibited no appreciable direct effect on DNA repair owing to the absence of an environment that promotes DNA repair following irradiation. However, these findings demonstrate the potential of enhancing damage by combining GNP-mediated radiation sensitization and biosensor technology. Thus, QTF is recommended as a reliable measure of DNA damage to investigate the dose enhancement effect at various GNP concentrations.

Nanomedicine targeted drug delivery is one of the emerging techniques for diagnosis and treatment of complex diseases. Medical image processing of High-Resolution Magnetic Resonance Imaging (HR-MRI), when combined with iron oxide nanoparticles (IO-NPs), provides a precious tool to monitor diagnosis and treatment processes. The challenge is to detect the nanoparticles inside the HR-MRI images. This is due to the low resolution of the images and the small size of the nanoparticles. In this paper, we study the drug delivery efficiency using a mouse with an inflamed calf, with IO-NPs attached to the therapeutic drug and injected into the mouse's eye. Our aim is to know how much of the drug injected will reach the inflamed region of the calf. A high-resolution MRI system was used to take images of the inflamed calf region. Knowing that iron oxide has a strong magnetic intensity on MRI images, image processing techniques were used to identify the location and quantity of IO-NPs attached to the drug. By knowing the location and quantity of IO-NPs we can estimate the quantity of drug delivered to the region of interest. In our project, K-mean algorithm, an automatic clustering algorithm was used to detect the iron oxide NPs in the MRI images. This then extracts them from the 3D model of the femoral region of interest. Extraction of NPs permits an estimation of the number of NPs clustered in the region and furthermore estimates the quantity of the drug delivered to the region of interest. The results obtained of nanoparticle detection and extraction seem to be a promising way to estimate the amount of delivered drug to a targeted area.