Medical imaging is a vital diagnostic tool that provides detailed insights into human anatomy but faces challenges affecting its accuracy and efficiency. Advanced generative AI models offer promising solutions. Unlike previous reviews with a narrow focus, a comprehensive evaluation across techniques and modalities is necessary. This systematic review integrates the three state-of-the-art leading approaches, GANs, Diffusion Models, and Transformers, examining their applicability, methodologies, and clinical implications in improving medical image quality. Using the PRISMA framework, 63 studies from 989 were selected via Google Scholar and PubMed, focusing on GANs, Transformers, and Diffusion Models. Articles from ACM, IEEE Xplore, and Springer were analyzed. Generative AI techniques show promise in improving image resolution, reducing noise, and enhancing fidelity. GANs generate high-quality images, Transformers utilize global context, and Diffusion Models are effective in denoising and reconstruction. Challenges include high computational costs, limited dataset diversity, and issues with generalizability, with a focus on quantitative metrics over clinical applicability. This review highlights the transformative impact of GANs, Transformers, and Diffusion Models in advancing medical imaging. Future research must address computational and generalization challenges, emphasize open science, and validate these techniques in diverse clinical settings to unlock their full potential. These efforts could enhance diagnostic accuracy, lower costs, and improve patient outcome.

Information on deep learning (DL) tumor segmentation accuracy on a voxel and a structure level is essential for clinical introduction. In a previous study, a DL model was developed for oropharyngeal cancer (OPC) primary tumor (PT) segmentation in PET/CT images and voxel-level predicted probabilities (TPM) quantifying model certainty were introduced. This study extended the network to simultaneously generate TPMs for PT and pathologic lymph nodes (PL) and explored whether structure-level uncertainty in TPMs predicts segmentation model accuracy in an independent external cohort. We retrospectively gathered PET/CT images and manual delineations of gross tumor volume of the PT (GTVp) and PL (GTVln) of 407 OPC patients treated with (chemo)radiation in our institute. The HECKTOR 2022 challenge dataset served as external test set. The pre-existing architecture was modified for multi-label segmentation. Multiple models were trained, and the non-binarized ensemble average of TPMs was considered per patient. Segmentation accuracy was quantified by surface and aggregate DSC, model uncertainty by coefficient of variation (CV) of multiple predictions. Predicted GTVp and GTVln segmentations in the external test achieved 0.75 and 0.70 aggregate DSC. Patient-specific CV and surface DSC showed a significant correlation for both structures (-0.54 and -0.66 for GTVp and GTVln) in the external set, indicating significant calibration. Significant accuracy versus uncertainty calibration was achieved for TPMs in both internal and external test sets, indicating the potential use of quantified uncertainty from TPMs to identify cases with lower GTVp and GTVln segmentation accuracy, independently of the dataset.

This bibliometric analysis aims to explore scientific data on Artificial Intelligence (AI) and Head and Neck Cancer (HNC). AI-related HNC articles from the Web of Science Core Collection were searched. VosViewer and Biblioshiny/Bibiometrix for R Studio were used for data synthesis. This analysis covered key characteristics such as sources, authors, affiliations, countries, citations and top cited articles, keyword analysis, and trending topics. A total of 1,019 papers from 1995 to 2024 were included. Among them, 71.6% were original research articles, 7.6% were reviews, and 20.8% took other forms. The fifty most cited documents highlighted radiology as the most explored specialty, with an emphasis on deep learning models for segmentation. The publications have been increasing, with an annual growth rate of 94.4% after 2016. Among the 20 most productive countries, 14 are high-income economies. The keywords of strong citation revealed 2 main clusters: radiomics and radiotherapy. The most frequently keywords include machine learning, deep learning, artificial intelligence, and head and neck cancer, with recent emphasis on diagnosis, survival prediction, and histopathology. There has been an increase in the use of AI in HNC research since 2016 and indicated a notable disparity in publication quantity between high-income and low/middle-income countries. Future research should prioritize clinical validation and standardization to facilitate the integration of AI in HNC management, particularly in underrepresented regions.

The identification of early micro-lesions and adjacent blood vessels in CT scans plays a pivotal role in the clinical diagnosis of pancreatic cancer, considering its aggressive nature and high fatality rate. Despite the widespread application of deep learning methods for this task, several challenges persist: (1) the complex background environment in abdominal CT scans complicates the accurate localization of potential micro-tumors; (2) the subtle contrast between micro-lesions within pancreatic tissue and the surrounding tissues makes it challenging for models to capture these features accurately; and (3) tumors that invade adjacent blood vessels pose significant barriers to surgical procedures. To address these challenges, we propose LUNETR (Language-Infused UNETR), an advanced multimodal encoder model that combines textual and image information for precise medical image segmentation. The integration of an autoencoding language model with cross-attention enabling our model to effectively leverage semantic associations between textual and image data, thereby facilitating precise localization of potential pancreatic micro-tumors. Additionally, we designed a Multi-scale Aggregation Attention (MSAA) module to comprehensively capture both spatial and channel characteristics of global multi-scale image data, enhancing the model's capacity to extract features from micro-lesions embedded within pancreatic tissue. Furthermore, in order to facilitate precise segmentation of pancreatic tumors and nearby blood vessels and address the scarcity of multimodal medical datasets, we collaborated with Zhuzhou Central Hospital to construct a multimodal dataset comprising CT images and corresponding pathology reports from 135 pancreatic cancer patients. Our experimental results surpass current state-of-the-art models, with the incorporation of the semantic encoder improving the average Dice score for pancreatic tumor segmentation by 2.23 %. For the Medical Segmentation Decathlon (MSD) liver and lung cancer datasets, our model achieved an average Dice score improvement of 4.31 % and 3.67 %, respectively, demonstrating the efficacy of the LUNETR.

Sparse-view Computed Tomography (CT) is an emerging protocol designed to reduce X-ray dose radiation in medical imaging. Reconstructions based on the traditional Filtered Back Projection algorithm suffer from severe artifacts due to sparse data. In contrast, Model-Based Iterative Reconstruction (MBIR) algorithms, though better at mitigating noise through regularization, are too computationally costly for clinical use. This paper introduces a novel technique, denoted as the Deep Guess acceleration scheme, using a trained neural network both to quicken the regularized MBIR and to enhance the reconstruction accuracy. We integrate state-of-the-art deep learning tools to initialize a clever starting guess for a proximal algorithm solving a non-convex model and thus computing a (mathematically) interpretable solution image in a few iterations. Experimental results on real and synthetic CT images demonstrate the Deep Guess effectiveness in (very) sparse tomographic protocols, where it overcomes its mere variational counterpart and many data-driven approaches at the state of the art. We also consider a ground truth-free implementation and test the robustness of the proposed framework to noise.

The choice of imaging modalities is essential in sarcoma management, as different techniques provide complementary information depending on tumor subtype and anatomical location. This narrative review examines the role of imaging in sarcoma characterization and treatment planning, particularly in the context of radiation therapy (RT). Magnetic resonance imaging (MRI) provides superior soft tissue contrast, enabling detailed assessment of tumor extent and peritumoral involvement. Computed tomography (CT) is particularly valuable for detecting osseous involvement, periosteal reactions, and calcifications, complementing MRI in sarcomas involving bone or calcified lesions. The combination of MRI and CT enhances tumor delineation, particularly for complex sites such as retroperitoneal and uterine sarcomas, where spatial relationships with adjacent organs are critical. In vascularized sarcomas, such as alveolar soft-part sarcomas, the integration of MRI with CT or MR angiography facilitates accurate mapping of tumor margins. Positron emission tomography with [18 F]-fluorodeoxyglucose ([18 F]-FDG PET) provides functional insights, identifying metabolically active regions within tumors to guide dose escalation. Although its role in routine staging is limited, [18 F]-FDG PET and emerging PET tracers offer promise for refining RT planning. Advances in artificial intelligence further enhance imaging precision, enabling more accurate contouring and treatment optimization. This review highlights how the integration of imaging modalities, tailored to specific sarcoma subtypes, supports precise RT delivery while minimizing damage to surrounding tissues. These strategies underline the importance of multidisciplinary approaches in improving sarcoma management and outcomes through multi-image-based RT planning.

Medical image registration plays a crucial role in medical imaging, with a wide range of clinical applications. In this context, brain MRI registration is commonly used in clinical practice for accurate diagnosis and treatment planning. In recent years, deep learning-based deformable registration methods have achieved remarkable results. However, existing methods have not been flexible and efficient in handling the feature relationships of anatomical structures at different levels when dealing with large deformations. To address this limitation, we propose a novel strategic integration registration network based on the pyramid structure. Our strategy mainly includes two aspects of integration: fusion of features at different scales, and integration of different neural network structures. Specifically, we design a CNN encoder and a Transformer decoder to efficiently extract and enhance both global and local features. Moreover, to overcome the error accumulation issue inherent in pyramid structures, we introduce progressive optimization iterations at the lowest scale for deformation field generation. This approach more efficiently handles the spatial relationships of images while improving accuracy. We conduct extensive evaluations across multiple brain MRI datasets, and experimental results show that our method outperforms other deep learning-based methods in terms of registration accuracy and robustness.

Multimodality is often necessary for improving object segmentation tasks, especially in the case of multilabel tasks, such as tumor segmentation, which is crucial for clinical diagnosis and treatment planning. However, a major challenge in utilizing multimodality with deep learning remains: the limited availability of annotated training data, primarily due to the time-consuming acquisition process and the necessity for expert annotations. Although deep learning has significantly advanced many tasks in medical imaging, conventional augmentation techniques are often insufficient due to the inherent complexity of volumetric medical data. To address this problem, we propose an innovative slice-based latent diffusion architecture for the generation of 3D multi-modal images and their corresponding multi-label masks. Our approach enables the simultaneous generation of the image and mask in a slice-by-slice fashion, leveraging a positional encoding and a Latent Aggregation module to maintain spatial coherence and capture slice sequentiality. This method effectively reduces the computational complexity and memory demands typically associated with diffusion models. Additionally, we condition our architecture on tumor characteristics to generate a diverse array of tumor variations and enhance texture using a refining module that acts like a super-resolution mechanism, mitigating the inherent blurriness caused by data scarcity in the autoencoder. We evaluate the effectiveness of our synthesized volumes using the BRATS2021 dataset to segment the tumor with three tissue labels and compare them with other state-of-the-art diffusion models through a downstream segmentation task, demonstrating the superior performance and efficiency of our method. While our primary application is tumor segmentation, this method can be readily adapted to other modalities. Code is available here : https://github.com/Arksyd96/multi-modal-mri-and-mask-synthesis-with-conditional-slice-based-ldm.

Accurate segmentation of three-dimensional (3D) clinical medical images is critical for the diagnosis and treatment of spinal diseases. However, the complexity of spinal anatomy and the inherent uncertainties of current imaging technologies pose significant challenges for the semantic segmentation of spinal images. Although convolutional neural networks (CNNs) and Transformer-based models have achieved remarkable progress in spinal segmentation, their limitations in modeling long-range dependencies hinder further improvements in segmentation accuracy. To address these challenges, we propose a novel framework, SpineMamba, which incorporates a residual visual Mamba layer capable of effectively capturing and modeling the deep semantic features and long-range spatial dependencies in 3D spinal data. To further enhance the structural semantic understanding of the vertebrae, we also propose a novel spinal shape prior module that captures specific anatomical information about the spine from medical images, significantly enhancing the model's ability to extract structural semantic information of the vertebrae. Extensive comparative and ablation experiments across three datasets demonstrate that SpineMamba outperforms existing state-of-the-art models. On two computed tomography (CT) datasets, the average Dice similarity coefficients achieved are 94.40±4% and 88.28±3%, respectively, while on a magnetic resonance (MR) dataset, the model achieves a Dice score of 86.95±10%. Notably, SpineMamba surpasses the widely recognized nnU-Net in segmentation accuracy, with a maximum improvement of 3.63 percentage points. These results highlight the precision, robustness, and exceptional generalization capability of SpineMamba.

Approximately 20-30 % of patients with acute ischemic stroke due to lacunar infarction experience early neurological deterioration (END) within the first three days after onset, leading to disability or more severe sequelae. Hemodynamic perfusion deficits may play a crucial role in END, causing growth in the infarcted area and functional impairments, and even poor long-term prognosis. Therefore, it is vitally important to predict which patients may be at risk of perfusion deficits to initiate treatment and close monitoring early, preparing for potential reperfusion. Our goal is to utilize radiomic features from magnetic resonance imaging (MRI) and machine learning techniques to develop a predictive model for hypoperfusion. During January 2011 to December 2020, a retrospective collection of 92 patients with lacunar stroke was conducted, who underwent MRI within 48 h, had clinical laboratory values, follow-up prognosis records, and advanced perfusion image to confirm the presence of hypoperfusion. Using the initial MRI of these patients, radiomics features were extracted and selected from Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient (ADC), and Fluid Attenuated Inversion Recovery (FLAIR) sequences. The data was divided into an 80 % training set and a 20 % testing set, and a hypoperfusion prediction model was developed using machine learning. Tthe model trained on DWI + FLAIR sequence showed superior performance with an accuracy of 84.1 %, AUC 0.92, recall 79.5 %, specificity 87.8 %, precision 83.8 %, and F1 score 81.2. Statistically significant clinical factors between patients with and without hypoperfusion included the NIHSS scores and the size of the lacunar infarction. Combining these two features with the top seven weighted radiomics features from DWI + FLAIR sequence, a total of nine features were used to develop a new prediction model through machine learning. This model in test set achieved an accuracy of 88.9 %, AUC 0.91, recall 87.5 %, specificity 90.0 %, precision 87.5 %, and F1 score 87.5. Utilizing radiomics techniques on DWI and FLAIR sequences from MRI of patients with lacunar stroke, it is possible to predict the presence of hypoperfusion, necessitating close monitoring to prevent the deterioration of clinical symptoms. Incorporating stroke volume and NIHSS scores into the prediction model enhances its performance. Future studies of a larger scale are required to validate these findings.