Abstract Objective . High-resolution magnetic resonance imaging (MRI) can enhance lesion diagnosis, prognosis, and delineation. However, gradient power hardware limitations prohibit recording thin slices or sub-1 mm resolution. Furthermore, long scan time is not clinically acceptable. Conventional high-resolution images generated using statistical analytical methods include the limitation of capturing complex, high-dimensional image data with intricate patterns structures. This study aims to...

Abstract Purpose This study proposed an end-to-end unsupervised medical fusion generative adversarial network, MedFusionGAN, to fuse computed tomography (CT) and high-resolution isotropic 3D T1-Gd Magnetic resonance imaging (MRI) image sequences generate with CT bone structure MRI soft tissue contrast improve target delineation reduce the radiotherapy planning time. Methods We used a publicly available multicenter dataset (GLIS-RT, 230 patients) from Cancer Imaging Archive. To models...

Abstract Background 7 Tesla (7T) apparent diffusion coefficient (ADC) maps derived from diffusion‐weighted imaging (DWI) demonstrate improved image quality and spatial resolution over 3 (3T) ADC maps. However, 7T magnetic resonance (MRI) currently suffers limited clinical unavailability, higher cost, increased susceptibility to artifacts. Purpose To address these issues, we propose a hybrid CNN‐transformer model synthesize high‐resolution multimodal 3T MRI. Methods The Vision CNN‐Transformer...

<title>Abstract</title> Vision foundation models (VFMs) are pre-trained on extensive image datasets to learn general representations for diverse types of data. These can subsequently be fine-tuned specific downstream tasks, significantly boosting performance across a broad range applications. However, existing vision that claim applicable various clinical tasks mostly 3D computed tomography (CT), which benefits from the availability CT databases. Significant differences between and magnetic...

Abstract Background Endometriosis is one of the most common chronic diseases in women, with a prevalence up to 10%. The disease particularly affects women reproductive age. has significant impact on patient's quality life (QoL). In current study, we aimed evaluate role early diagnosis endometriosis patients’ QoL. Methods this longitudinal prospective 205 who were referred gynecology department Amir al-Mominin Hospital (Zabol-Iran) 2021 evaluated. Patients divided into two groups based time...

Abstract Background High‐resolution magnetic resonance imaging (MRI) with excellent soft‐tissue contrast is a valuable tool utilized for diagnosis and prognosis. However, MRI sequences long acquisition time are susceptible to motion artifacts, which can adversely affect the accuracy of post‐processing algorithms. Purpose This study proposes novel retrospective correction method named “motion artifact reduction using conditional diffusion probabilistic model” (MAR‐CDPM). The MAR‐CDPM aimed...

Purpose: To propose a self-supervised deep learning-based compressed sensing MRI (DL-based CS-MRI) method named "Adaptive Self-Supervised Consistency Guided Diffusion Model (ASSCGD)" to accelerate data acquisition without requiring fully sampled datasets. Materials and Methods: We used the fastMRI multi-coil brain axial T2-weighted (T2-w) dataset from 1,376 cases single-coil quantitative magnetization prepared 2 rapid gradient echoes (MP2RAGE) T1 maps 318 train test our model. Robustness...

The long acquisition time required for high-resolution Magnetic Resonance Imaging (MRI) leads to patient discomfort, increased likelihood of voluntary and involuntary movements, reduced throughput in imaging centers. This study proposed a novel method that leverages MRI physics incorporate data consistency during the training conditional diffusion probabilistic model, which we refer as consistency-guided model (DC-CDPM). aimed reconstruct contrast enhanced T1W from partially sampled data....

This study developed an unsupervised motion artifact reduction method for magnetic resonance imaging (MRI) images of patients with brain tumors. The proposed novel design uses multi-parametric multicenter contrast-enhanced T1W (ceT1W) and T2-FLAIR MRI images.

To investigate the impact of MRI patient-specific geometrical distortion (PSD) on quality Gamma Knife stereotactic radiosurgery (GK-SRS) plans vestibular schwannoma (VS) tumors.Three open access datasets including MPI-Leipzig Mind-Brain-Body (318 patients), slow event-related fMRI designs dataset (62 and VS (242 patients) were used. We used first two to train a 3D convolution network predict map third that then calculate correct PSD. GK-SRS evaluate dose distribution PSD-corrected images....

Abstract Background and Purpose. The world health organization recommended to incorporate gene information such as isocitrate dehydrogenase 1 (IDH1) mutation status improve prognosis, diagnosis, treatment of the central nervous system tumors. We proposed our Shuffle Residual Network (Shuffle-ResNet) predict IDH1 low grade glioma (LGG) tumors from multicenter anatomical magnetic resonance imaging (MRI) sequences including T2-w, T2-FLAIR, T1-w, T1-Gd. Methods Materials. used 105 patient's...

The aim of this study was to compare diffusion tensor imaging (DTI) isotropic map (p-map) with current radiographically (T2/T2-FLAIR) methods based on abnormal hyper-signal size and location glioblastoma tumor using a semi-automatic approach. Twenty-five patients biopsy-proved diagnosis participated in study. T2, T2-FLAIR images were acquired 1 week before radiotherapy. Hyper-signal regions DTI p-map segmented by means semi-automated segmentation. Manual segmentation used as ground truth....

Abstract Purpose This study proposed a novel retrospective motion reduction method named artifact unsupervised disentanglement generative adversarial network (MAUDGAN) that reduces the artifacts from brain images with tumors and metastases. The MAUDGAN was trained using mutlimodal multicenter 3D T1-Gd T2-fluid attenuated inversion recovery MRI images. Approach different levels were simulated in k -space for consisted of two generators, discriminators feature extractor networks constructed...

Dynamic Myocardial Positron Emission Tomography (PET) imaging is a valuable tool for evaluating myocardial uptake. However, extended acquisition time during the dynamic PET can be drawback, causing patient discomfort and potential motion artifacts. To address this challenge, we employed deep learning (DL) techniques to predict later frames using their initial ones. In study, used dataset of 350 patients who underwent 13N-ammonia scans train three DL models (U-Net, U-Net with self-attention...

Several Magnetic Resonance Imaging (MRI) sequences are acquired for diagnosis and treatment. MRI with excellent soft-tissue contrast is desired post-processing algorithms such as tumor segmentation. However, their performance markedly dropped due to the variation in medical imaging protocols or missing information. This study proposed a co-training deep learning algorithm segmenting vestibular schwannoma (VS) cancer. Our model was trained on both contrast-enhanced T1W (ceT1W) high-resolution...

Purpose: Apparent diffusion coefficient (ADC) maps derived from weighted (DWI) MRI provides functional measurements about the water molecules in tissues. However, DWI is time consuming and very susceptible to image artifacts, leading inaccurate ADC measurements. This study aims develop a deep learning framework synthesize multi-parametric MR images. Methods: We proposed multiparametric residual vision transformer model (MPR-ViT) that leverages long-range context of ViT layers along with...