Deep learning models require large amounts of annotated data, which are hard to obtain in the medical field, as the annotation process is laborious and depends on expert knowledge. This data scarcity hinders a model's ability to generalise effectively on unseen data, and recently, foundation models pretrained on large datasets have been proposed as a promising solution. RadiologyNET is a custom medical dataset that comprises 1,902,414 medical images covering various body parts and modalities of image acquisition. We used the RadiologyNET dataset to pretrain several popular architectures (ResNet18, ResNet34, ResNet50, VGG16, EfficientNetB3, EfficientNetB4, InceptionV3, DenseNet121, MobileNetV3Small and MobileNetV3Large). We compared the performance of ImageNet and RadiologyNET foundation models against training from randomly initialiased weights on several publicly available medical datasets: (i) Segmentation-LUng Nodule Analysis Challenge, (ii) Regression-RSNA Pediatric Bone Age Challenge, (iii) Binary classification-GRAZPEDWRI-DX and COVID-19 datasets, and (iv) Multiclass classification-Brain Tumor MRI dataset. Our results indicate that RadiologyNET-pretrained models generally perform similarly to ImageNet models, with some advantages in resource-limited settings. However, ImageNet-pretrained models showed competitive performance when fine-tuned on sufficient data. The impact of modality diversity on model performance was tested, with the results varying across tasks, highlighting the importance of aligning pretraining data with downstream applications. Based on our findings, we provide guidelines for using foundation models in medical applications and publicly release our RadiologyNET-pretrained models to support further research and development in the field. The models are available at https://github.com/AIlab-RITEH/RadiologyNET-TL-models .

The most common types of kidneys and liver cancer are renal cell carcinoma (RCC) and hepatic cell carcinoma (HCC), respectively. Accurate grading of these carcinomas is essential for determining the most appropriate treatment strategies, including surgery or pharmacological interventions. Traditional deep learning methods often struggle with the intricate and complex patterns seen in histopathology images of RCC and HCC, leading to inaccuracies in classification. To enhance the grading accuracy for liver and renal cell carcinoma, this research introduces a novel feature selection and fusion framework inspired by economic theories, incorporating attention mechanisms into three Convolutional Neural Network (CNN) architectures-MobileNetV2, DenseNet121, and InceptionV3-as foundational models. The attention mechanisms dynamically identify crucial image regions, leveraging each CNN's unique strengths. Additionally, a Gini-based feature selection method is implemented to prioritize the most discriminative features, and the extracted features from each network are optimally combined using a fusion technique modeled after a linear production function, maximizing each model's contribution to the final prediction. Experimental evaluations demonstrate that this proposed approach outperforms existing state-of-the-art models, achieving high accuracies of 93.04% for RCC and 98.24% for LCC. This underscores the method's robustness and effectiveness in accurately grading these types of cancers. The code of our method is publicly available in https://github.com/GHOSTCALL983/GRADE-CLASSIFICATION .

This paper presents a novel motion feature guided diffusion model for unpaired video-to-video translation (MFD-V2V), designed to synthesize dynamic, high-contrast cine cardiac magnetic resonance (CMR) from lower-contrast, artifact-prone displacement encoding with stimulated echoes (DENSE) CMR sequences. To achieve this, we first introduce a Latent Temporal Multi-Attention (LTMA) registration network that effectively learns more accurate and consistent cardiac motions from cine CMR image videos. A multi-level motion feature guided diffusion model, equipped with a specialized Spatio-Temporal Motion Encoder (STME) to extract fine-grained motion conditioning, is then developed to improve synthesis quality and fidelity. We evaluate our method, MFD-V2V, on a comprehensive cardiac dataset, demonstrating superior performance over the state-of-the-art in both quantitative metrics and qualitative assessments. Furthermore, we show the benefits of our synthesized cine CMRs improving downstream clinical and analytical tasks, underscoring the broader impact of our approach. Our code is publicly available at https://github.com/SwaksharDeb/MFD-V2V.

Ultrasound contrast agents (UCAs) have been used as vascular reporters for the past 40 years. The ability to enhance vascular features in ultrasound images with engineered lipid-shelled microbubbles has enabled breakthroughs such as the detection of tissue perfusion or super-resolution imaging of the microvasculature. However, advances in the field of contrast-enhanced ultrasound are hindered by experimental variables that are difficult to control in a laboratory setting, such as complex vascular geometries, the lack of ground truth, and tissue nonlinearities. In addition, the demand for large datasets to train deep learning-based computational ultrasound imaging methods calls for the development of a simulation tool that can reproduce the physics of ultrasound wave interactions with tissues and microbubbles. Here, we introduce a physically realistic contrast-enhanced ultrasound simulator (PROTEUS) consisting of four interconnected modules that account for blood flow dynamics in segmented vascular geometries, intravascular microbubble trajectories, ultrasound wave propagation, and nonlinear microbubble scattering. The first part of this study describes the numerical methods that enabled this development. We demonstrate that PROTEUS can generate contrast-enhanced radio-frequency (RF) data in various vascular architectures across the range of medical ultrasound frequencies. PROTEUS offers a customizable framework to explore novel ideas in the field of contrast-enhanced ultrasound imaging. It is released as an open-source tool for the scientific community.

Accurate fetal birth weight (FBW) estimation is essential for optimizing delivery decisions and reducing perinatal mortality. However, clinical methods for FBW estimation are inefficient, operator-dependent, and challenging to apply in cases of complex fetal anatomy. Existing deep learning methods are based on 2D standard ultrasound (US) images or videos that lack spatial information, limiting their prediction accuracy. In this study, we propose the first method for directly estimating FBW from 3D fetal US volumes. Our approach integrates a multi-scale feature fusion network (MFFN) and a synthetic sample-based learning framework (SSLF). The MFFN effectively extracts and fuses multi-scale features under sparse supervision by incorporating channel attention, spatial attention, and a ranking-based loss function. SSLF generates synthetic samples by simply combining fetal head and abdomen data from different fetuses, utilizing semi-supervised learning to improve prediction performance. Experimental results demonstrate that our method achieves superior performance, with a mean absolute error of $166.4\pm155.9$ $g$ and a mean absolute percentage error of $5.1\pm4.6$%, outperforming existing methods and approaching the accuracy of a senior doctor. Code is available at: https://github.com/Qioy-i/EFW.

Unsupervised anomaly detection (UAD) is crucial in low-dose computed tomography (LDCT). Recent AI technologies, leveraging global features, have enabled effective UAD with minimal training data of normal patients. However, this approach, devoid of utilizing local features, exhibits vulnerability in detecting deep lesions within the lungs. In other words, while the conventional use of global features can achieve high specificity, it often comes with limited sensitivity. Developing a UAD AI model with high sensitivity is essential to prevent false negatives, especially in screening patients with diseases demonstrating high mortality rates. We have successfully pioneered a new LDCT UAD AI model that leverages local features, achieving a previously unattainable increase in sensitivity compared to global methods (17.5% improvement). Furthermore, by integrating this approach with conventional global-based techniques, we have successfully consolidated the advantages of each model - high sensitivity from the local model and high specificity from the global model - into a single, unified, trained model (17.6% and 33.5% improvement, respectively). Without the need for additional training, we anticipate achieving significant diagnostic efficacy in various LDCT applications, where both high sensitivity and specificity are essential, using our fixed model. Code is available at https://github.com/kskim-phd/Fusion-UADL.

Medical image segmentation is crucial for computer-aided diagnosis and treatment planning, directly influencing clinical decision-making. To enhance segmentation accuracy, existing methods typically fuse local, global, and various other features. However, these methods often ignore the negative impact of noise on the results during the feature fusion process. In contrast, certain regions of the human visual system, such as the inferotemporal cortex and parietal cortex, effectively suppress irrelevant noise while integrating multiple features-a capability lacking in current methods. To address this gap, we propose MS-Net, a medical image segmentation network inspired by human visual perception. MS-Net incorporates a multi-feature compression (MFC) module that mimics the human visual system's processing of complex images, first learning various feature types and subsequently filtering out irrelevant ones. Additionally, MS-Net features a segmentation refinement (SR) module that emulates how physicians segment lesions. This module initially performs coarse segmentation to capture the lesion's approximate location and shape, followed by a refinement step to achieve precise boundary delineation. Experimental results demonstrate that MS-Net not only attains state-of-the-art segmentation performance across three public datasets but also significantly reduces the number of parameters compared to existing models. Code is available at https://github.com/guangguangLi/MS-Net.

Capturing rich multi-scale features is essential to address complex variations in medical image segmentation. Multiple hybrid networks have been developed to integrate the complementary benefits of convolutional neural networks (CNN) and Transformers. However, existing methods may suffer from either huge computational cost required by the complicated networks or unsatisfied performance of lighter networks. How to give full play to the advantages of both convolution and self-attention and design networks that are both effective and efficient still remains an unsolved problem. In this work, we propose a robust lightweight multi-stage hybrid architecture, named Multi-stage Aggregation Transformer version 2 (MA-TransformerV2), to extract multi-scale features with progressive aggregations for accurate segmentation of highly variable medical images at a low computational cost. Specifically, lightweight Trans blocks and lightweight CNN blocks are parallelly introduced into the dual-branch encoder module in each stage, and then a vector quantization block is incorporated at the bottleneck to discretizes the features and discard the redundance. This design not only enhances the representation capabilities and computational efficiency of the model, but also makes the model interpretable. Extensive experimental results on public datasets show that our method outperforms state-of-the-art methods, including CNN-based, Transformer-based, advanced hybrid CNN-Transformer-based models, and several lightweight models, in terms of both segmentation accuracy and model capacity. Code will be made publicly available at https://github.com/zjmiaprojects/MATransformerV2.

Surface-based analysis of the cerebral cortex is ubiquitous in human neuroimaging with MRI. It is crucial for tasks like cortical registration, parcellation, and thickness estimation. Traditionally, such analyses require high-resolution, isotropic scans with good gray-white matter contrast, typically a T1-weighted scan with 1 mm resolution. This requirement precludes application of these techniques to most MRI scans acquired for clinical purposes, since they are often anisotropic and lack the required T1-weighted contrast. To overcome this limitation and enable large-scale neuroimaging studies using vast amounts of existing clinical data, we introduce recon-all-clinical, a novel methodology for cortical reconstruction, registration, parcellation, and thickness estimation for clinical brain MRI scans of any resolution and contrast. Our approach employs a hybrid analysis method that combines a convolutional neural network (CNN) trained with domain randomization to predict signed distance functions (SDFs), and classical geometry processing for accurate surface placement while maintaining topological and geometric constraints. The method does not require retraining for different acquisitions, thus simplifying the analysis of heterogeneous clinical datasets. We evaluated recon-all-clinical on multiple public datasets like ADNI, HCP, AIBL, OASIS and including a large clinical dataset of over 9,500 scans. The results indicate that our method produces geometrically precise cortical reconstructions across different MRI contrasts and resolutions, consistently achieving high accuracy in parcellation. Cortical thickness estimates are precise enough to capture aging effects, independently of MRI contrast, even though accuracy varies with slice thickness. Our method is publicly available at https://surfer.nmr.mgh.harvard.edu/fswiki/recon-all-clinical, enabling researchers to perform detailed cortical analysis on the huge amounts of already existing clinical MRI scans. This advancement may be particularly valuable for studying rare diseases and underrepresented populations where research-grade MRI data is scarce.

Since the outbreak of the COVID-19 pandemic in 2019, medical imaging has emerged as a primary modality for diagnosing COVID-19 pneumonia. In clinical settings, the segmentation of lung infections from computed tomography images enables rapid and accurate quantification and diagnosis of COVID-19. Segmentation of COVID-19 infections in the lungs poses a formidable challenge, primarily due to the indistinct boundaries and limited contrast presented by ground glass opacity manifestations. Moreover, the confounding similarity among infiltrates, lung tissues, and lung walls further complicates this segmentation task. To address these challenges, this paper introduces a novel deep network architecture, called CAD-Unet, for segmenting COVID-19 lung infections. In this architecture, capsule networks are incorporated into the existing Unet framework. Capsule networks represent a novel type of network architecture that differs from traditional convolutional neural networks. They utilize vectors for information transfer among capsules, facilitating the extraction of intricate lesion spatial information. Additionally, we design a capsule encoder path and establish a coupling path between the unet encoder and the capsule encoder. This design maximizes the complementary advantages of both network structures while achieving efficient information fusion. Finally, extensive experiments are conducted on four publicly available datasets, encompassing binary segmentation tasks and multi-class segmentation tasks. The experimental results demonstrate the superior segmentation performance of the proposed model. The code has been released at: https://github.com/AmanoTooko-jie/CAD-Unet.