Search

Simple Summary: This paper presents a novel approach to produce virtual contrast enhanced (VCE) images for nasopharyngeal cancer (NPC) without the use of contrast agents, which carry certain risks. This model uses pixelwise gradient term to capture the shape and a GAN terms to capture the texture of the real contrast enhanced T1C images With similar accuracy to existing models, our method shows an advantage in reproducing texture closer to the realistic contrast-enhanced images. This results are tested by various measures, including mean absolute error (MAE), mean square error (MSE) and structural similarity index (SSIM) for similarity accuracy; total mean square variation per mean intensity (TMSVPMI), the total absolute vari-ation per mean intensity (TAVPMI), Tenengrad function per mean intensity (TFPMI) and variance function per mean intensity (VFPMI) Various variations of the model, including fine-tuning of the hyperparameters, normalization methods on the images and using single modality, have also been investigated to test the optimal performance. Background: The development of advanced computational models for medical imaging is crucial for improving diagnostic accuracy in healthcare. This paper introduces a novel approach for virtual contrast enhancement (VCE) in magnetic resonance imaging (MRI), particularly focusing on nasopharyngeal cancer (NPC). Methods: The proposed model, Pixelwise Gradient Model with GAN for Virtual Contrast Enhancement (PGMGVCE), makes use of pixelwise gradient methods with Generative Adversarial Networks (GANs) to enhance T1-weighted (T1-w) and T2-weighted (T2-w) MRI images. This approach combines the benefits of both modalities to simulate the effects of gadolinium-based contrast agents, thereby reducing associated risks. Various modifications of PGMGVCE, including changing hyperparameters, using normalization methods (z-score, Sigmoid and Tanh) and training the model with T1-w or T2-w images only, were tested to optimize the model's performance. Results: PGMGVCE demonstrated a similar accuracy to the existing model in terms of mean absolute error (MAE) (8.56 ± 0.45 for Li's model; 8.72 ± 0.48 for PGMGVCE), mean square error (MSE) (12.43 ± 0.67 for Li's model; 12.81 ± 0.73 for PGMGVCE) and structural similarity index (SSIM) (0.71 ± 0.08 for Li's model; 0.73 ± 0.12 for PGMGVCE). However, it showed improvements in texture representation, as indicated by total mean square variation per mean intensity (TMSVPMI) (0.124 ± 0.022 for ground truth; 0.079 ± 0.024 for Li's model; 0.120 ± 0.027 for PGMGVCE), total absolute variation per mean intensity (TAVPMI) (0.159 ± 0.031 for ground truth; 0.100 ± 0.032 for Li's model; 0.153 ± 0.029 for PGMGVCE), Tenengrad function per mean intensity (TFPMI) (1.222 ± 0.241 for ground truth; 0.981 ± 0.213 for Li's model; 1.194 ± 0.223 for PGMGVCE) and variance function per mean intensity (VFPMI) (0.0811 ± 0.005 for ground truth; 0.0667   ± 0.006 for Li's model; 0.0761   ± 0.006 for PGMGVCE). Conclusions: PGMGVCE presents an innovative and safe approach to VCE in MRI, demonstrating the power of deep learning in enhancing medical imaging. This model paves the way for more accurate and risk-free diagnostic tools in medical imaging. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we introduce a new technique for enhancing medical image diagnosis through transfer learning (TL). The approach addresses the issue of limited labelled images by pre-training deep learning models on similar medical images and then refining them with a small set of annotated medical images. Our method demonstrated excellent results in classifying the humerus and wrist, surpassing previous methods, and showing greater robustness in various experiments. Furthermore, we demonstrate the adaptability of the approach with a CT case, which showed improvements in the results. Medical image classification poses significant challenges in real-world scenarios. One major obstacle is the scarcity of labelled training data, which hampers the performance of image-classification algorithms and generalisation. Gathering sufficient labelled data is often difficult and time-consuming in the medical domain, but deep learning (DL) has shown remarkable performance, although it typically requires a large amount of labelled data to achieve optimal results. Transfer learning (TL) has played a pivotal role in reducing the time, cost, and need for a large number of labelled images. This paper presents a novel TL approach that aims to overcome the limitations and disadvantages of TL that are characteristic of an ImageNet dataset, which belongs to a different domain. Our proposed TL approach involves training DL models on numerous medical images that are similar to the target dataset. These models were then fine-tuned using a small set of annotated medical images to leverage the knowledge gained from the pre-training phase. We specifically focused on medical X-ray imaging scenarios that involve the humerus and wrist from the musculoskeletal radiographs (MURA) dataset. Both of these tasks face significant challenges regarding accurate classification. The models trained with the proposed TL were used to extract features and were subsequently fused to train several machine learning (ML) classifiers. We combined these diverse features to represent various relevant characteristics in a comprehensive way. Through extensive evaluation, our proposed TL and feature-fusion approach using ML classifiers achieved remarkable results. For the classification of the humerus, we achieved an accuracy of 87.85%, an F1-score of 87.63%, and a Cohen's Kappa coefficient of 75.69%. For wrist classification, our approach achieved an accuracy of 85.58%, an F1-score of 82.70%, and a Cohen's Kappa coefficient of 70.46%. The results demonstrated that the models trained using our proposed TL approach outperformed those trained with ImageNet TL. We employed visualisation techniques to further validate these findings, including a gradient-based class activation heat map (Grad-CAM) and locally interpretable model-independent explanations (LIME). These visualisation tools provided additional evidence to support the superior accuracy of models trained with our proposed TL approach compared to those trained with ImageNet TL. Furthermore, our proposed TL approach exhibited greater robustness in various experiments compared to ImageNet TL. Importantly, the proposed TL approach and the feature-fusion technique are not limited to specific tasks. They can be applied to various medical image applications, thus extending their utility and potential impact. To demonstrate the concept of reusability, a computed tomography (CT) case was adopted. The results obtained from the proposed method showed improvements. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we investigate the application of deep learning for classifying whole-slide images of cutaneous histopathological specimens into melanoma and non-melanoma. To do so, we used a total of 66 images (33 melanomas and 33 non-melanomas) to train models and evaluated them on 90 whole-slide images (40 melanomas and 50 non-melanomas). The best model achieved ROC–AUC at 0.821 for the whole-slide image level and 0.936 for the tile level. Although the histopathological diagnosis of cutaneous melanocytic lesions is fairly accurate and reliable among experienced surgical pathologists, it is not perfect in every case (especially melanoma). Microscopic examination–clinicopathological correlation is the gold standard for the definitive diagnosis of melanoma. Pathologists may encounter diagnostic controversies when melanoma closely mimics Spitz's nevus or blue nevus, exhibits amelanotic histopathology, or is in situ. It would be beneficial if diagnosing cutaneous melanocytic lesions can be automated by using deep learning, particularly when assisting surgical pathologists with their workloads. In this preliminary study, we investigated the application of deep learning for classifying cutaneous melanoma in whole-slide images (WSIs). We trained models via weakly supervised learning using a dataset of 66 WSIs (33 melanomas and 33 non-melanomas). We evaluated the models on a test set of 90 WSIs (40 melanomas and 50 non-melanomas), achieving ROC–AUC at 0.821 for the WSI level and 0.936 for the tile level by the best model. [ABSTRACT FROM AUTHOR]

Simple Summary: The glaziovianin A derivative gatastatin, presented as a γ-tubulin-specific inhibitor, could represent a viable chemotherapeutic strategy to solve the specificity issues associated with targeting α and β tubulin. Since gatastatin's specificity for γ tubulin has not been confirmed by an in silico analysis or verified experimentally by other groups, we undertook finding a molecular-level elucidation of the binding mode of gatastatin and comparing its predicted binding affinity values for both α-β and γ tubulin. We believe that our paper opens the possibility for the rational design of a long-sought candidate drug with desired specificity and selectivity for γ tubulin. Given its critical role in cell mitosis, the tubulin γ chain represents a viable chemotherapeutic target to solve the specificity issues associated with targeting α and β tubulin. Since γ tubulin is overexpressed in glioblastoma multiforme (GBM) and some breast lesions, the glaziovianin A derivative gatastatin, presented as a γ-tubulin-specific inhibitor, could yield a successful therapeutic strategy. The present work aims to identify the binding sites and modes of gatastatin and its derivatives through molecular-docking simulations. Computational binding free energy predictions were compared to experimental microscale thermophoresis assay results. The computational simulations did not reveal a strong preference toward γ tubulin, suggesting that further derivatization may be needed to increase its specificity. [ABSTRACT FROM AUTHOR]

Simple Summary: As computer performance continues to grow at more affordable costs, mathematical modelling and in silico experimentation begin to play a larger role in understanding cancer evolution. The aim of our work is to formulate a control strategy for the Adaptive Cellular Therapy (ACT) that can fully eradicates the Chronic Myelogenous Leukemia (CML) cells population in a mathematical model describing interactions between naive T cells, effector T cells and CML cancer cells in the circulatory blood system. Mathematical analysis and numerical simulations allow us to conclude that it is possible to design a personalized administration protocol for the ACT in the form of a pulse train with asymmetrical waves and a fixed amplitude to achieve complete CML cancer cells eradication. The amplitude of the impulse on which the treatment is applied is given by an arithmetical combination of the parameters of the system with at least a duty cycle of 45 min/day. This paper is devoted to exploring personalized applications of cellular immunotherapy as a control strategy for the treatment of chronic myelogenous leukemia described by a dynamical system of three first-order ordinary differential equations. The latter was achieved by applying both the Localization of Compact Invariant Sets and Lyapunov's stability theory. Combination of these two approaches allows us to establish sufficient conditions on the immunotherapy treatment parameter to ensure the complete eradication of the leukemia cancer cells. These conditions are given in terms of the system parameters and by performing several in silico experimentations, we formulated a protocol for the therapy application that completely eradicates the leukemia cancer cells population for different initial tumour concentrations. The formulated protocol does not dangerously increase the effector T cells population. Further, complete eradication is considered when solutions go below a finite critical value below which cancer cells cannot longer persist; i.e., one cancer cell. Numerical simulations are consistent with our analytical results. [ABSTRACT FROM AUTHOR]

This paper describes a method to reconstruct bendable superficial hyperthermia applicators for routine clinical patient-specific treatment planning. The reconstruction uses a CT scan with a flexible silicone dummy applicator positioned on the patient. The curvature was approximated by two second-degree polynomial functions. A realistic treatment series was mimicked using a standard Alderson radiation therapy phantom and a treatment planning model was reconstructed from a CT scan. The variation among treatment curvatures was compared to the modelled curvature. The mathematical approximation of the applicator curvature was validated for this phantom experiment, as well as for clinical treatments. The average maximum variation among the successive mimicked sessions was 3.67 ± 0.69 mm (range 2.98–4.60 mm). The maximum deviation between the treatment curvature and the modelled curvature was 4.35 mm. Comparing the treatment and approximated curvature yielded a maximum deviation between 2.98 mm and 4.12 mm. For clinical treatments the maximum deviation of the treatment and approximated curvature varied between 0.48 mm and 1.98 mm. These results allow adequate reconstruction of bendable hyperthermia applicators for treatment planning, which can further improve treatment quality, for example by optimizing the water bolus temperature for patient-specific tumor depths. Predictive parameters for hyperthermia treatment outcome can easily be evaluated and compared for various input parameters. [ABSTRACT FROM AUTHOR]