Deep learning-based medical image-to-mesh reconstruction has rapidly evolved, enabling the transformation of medical imaging data into three-dimensional mesh models that are critical in computational medicine and in silico trials for advancing our understanding of disease mechanisms, and diagnostic and therapeutic techniques in modern medicine. This survey systematically categorizes existing approaches into four main categories: template models, statistical models, generative models, and implicit models. Each category is analysed in detail, examining their methodological foundations, strengths, limitations, and applicability to different anatomical structures and imaging modalities. We provide an extensive evaluation of these methods across various anatomical applications, from cardiac imaging to neurological studies, supported by quantitative comparisons using standard metrics. Additionally, we compile and analyse major public datasets available for medical mesh reconstruction tasks and discuss commonly used evaluation metrics and loss functions. The survey identifies current challenges in the field, including requirements for topological correctness, geometric accuracy, and multi-modality integration. Finally, we present promising future research directions in this domain. This systematic review aims to serve as a comprehensive reference for researchers and practitioners in medical image analysis and computational medicine.

Ultrasound (US) imaging plays a crucial role in diagnosing heart and pelvic diseases, where sonographers tend to evaluate dynamic motion and structure. However, the scarcity of US videos for rare cases limitstraining opportunities for novice sonographers and deep learning models, hindering detection rates and clinical diagnostic applications. US video synthesis is a promising solution to this issue. Nevertheless, accurately imitating the intricate motion of the anatomy while preserving image fidelity presents asignificant challenge. In this work, we propose OnUVS, a novel online feature-decoupling framework for high-fidelity US video synthesis. First, to simulate realistic motion, we incorporate keypoints into anatomical learning through a weakly supervised training approach, which enhances motion representation and minimizes the need for fully annotated data. Second, we implement a dual-decoder generator that effectively balances content and textural features of generated frames, significantly enhancing the image fidelity of US videos. Third, a multi-scale discriminator further refines the sharpness and fine details, ensuring high-fidelity video synthesis. Fourth, an online learning strategy is designed to smooth coherence between frames by constraining the keypoint trajectories during inference. Validation on echocardiographic and pelvic floor US datasets demonstrates that OnUVS outperforms existing methods, achieving a 22.08% improvement in motion consistency (FVD) and 25.04% in image fidelity (FID).

Generating virtual organ populations that capture sufficient variability while remaining plausible is essential to conduct in silico trials (ISTs) of medical devices. However, not all anatomical shapes of interest are always available for each individual in a population. The imaging examinations and modalities used can vary between subjects depending on their individualized clinical pathways. Different imaging modalities may have various fields of view and are sensitive to signals from other tissues/organs, or both. Hence, missing/partially overlapping anatomical information is often available across individuals. We introduce a generative shape model for multipart anatomical structures, learnable from sets of unpaired datasets, i.e., where each substructure in the shape assembly comes from datasets with missing or partially overlapping substructures from disjoint subjects of the same population. The proposed generative model can synthesize complete multipart shape assemblies coined virtual chimeras (VCs). We applied this framework to build VCs from databases of whole-heart shape assemblies that each contribute samples for heart substructures. Specifically, we propose a graph neural network-based generative shape compositional framework, which comprises two components, a part-aware generative shape model that captures the variability in shape observed for each structure of interest in the training population and a spatial composition network that assembles/composes the structures synthesized by the former into multipart shape assemblies (i.e., VCs). We also propose a novel self-supervised learning scheme that enables the spatial composition network to be trained with partially overlapping data and weak labels. We trained and validated our approach using shapes of cardiac structures derived from cardiac magnetic resonance (MR) images in the UK Biobank (UKBB). When trained with complete and partially overlapping data, our approach significantly outperforms a principal component analysis (PCA)-based shape model (trained with complete data) in terms of generalizability and specificity. This demonstrates the superiority of the proposed method, as the synthesized cardiac virtual populations are more plausible and capture a greater degree of shape variability than those generated by the PCA-based shape model.

Fetal cortical plate segmentation is essential in quantitative analysis of fetal brain maturation and cortical folding. Manual segmentation of the cortical plate, or manual refinement of automatic segmentations is tedious and time-consuming. Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation. To reduce the burden of manual refinement of segmentations, we have developed a new and powerful deep learning segmentation method. Our method exploits new deep attentive modules with mixed kernel convolutions within a fully convolutional neural network architecture that utilizes deep supervision and residual connections. We evaluated our method quantitatively based on several performance measures and expert evaluations. Results show that our method outperforms several state-of-the-art deep models for segmentation, as well as a state-of-the-art multi-atlas segmentation technique. We achieved average Dice similarity coefficient of 0.87, average Hausdorff distance of 0.96 mm, and average symmetric surface difference of 0.28 mm on reconstructed fetal brain MRI scans of fetuses scanned in the gestational age range of 16 to 39 weeks (28.6± 5.3). With a computation time of less than 1 minute per fetal brain, our method can facilitate and accelerate large-scale studies on normal and altered fetal brain cortical maturation and folding.

Accurate standard plane (SP) localization is the fundamental step for prenatal ultrasound (US) diagnosis. Typically, dozens of US SPs are collected to determine the clinical diagnosis. 2D US has to perform scanning for each SP, which is time-consuming and operator-dependent. While 3D US containing multiple SPs in one shot has the inherent advantages of less user-dependency and more efficiency. Automatically locating SP in 3D US is very challenging due to the huge search space and large fetal posture variations. Our previous study proposed a deep reinforcement learning (RL) framework with an alignment module and active termination to localize SPs in 3D US automatically. However, termination of agent search in RL is important and affects the practical deployment. In this study, we enhance our previous RL framework with a newly designed adaptive dynamic termination to enable an early stop for the agent searching, saving at most 67% inference time, thus boosting the accuracy and efficiency of the RL framework at the same time. Besides, we validate the effectiveness and generalizability of our algorithm extensively on our in-house multi-organ datasets containing 433 fetal brain volumes, 519 fetal abdomen volumes, and 683 uterus volumes. Our approach achieves localization error of 2.52mm/10.26°, 2.48mm/10.39°, 2.02mm/10.48°, 2.00mm/14.57°, 2.61mm/9.71°, 3.09mm/9.58°, 1.49mm/7.54°for the transcerebellar, transventricular, transthalamic planes in fetal brain, abdominal plane in fetal abdomen, and mid-sagittal, transverse and coronal planes in uterus, respectively. Experimental results show that our method is general and has the potential to improve the efficiency and standardization of US scanning.

Automatic prostate segmentation in transrectal ultrasound (TRUS) images is of essential importance for image-guided prostate interventions and treatment planning. However, developing such automatic solutions remains very challenging due to the missing/ambiguous boundary and inhomogeneous intensity distribution of the prostate in TRUS, as well as the large variability in prostate shapes. This paper develops a novel 3D deep neural network equipped with attention modules for better prostate segmentation in TRUS by fully exploiting the complementary information encoded in different layers of the convolutional neural network (CNN). Our attention module utilizes the attention mechanism to selectively leverage the multi-level features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers. Experimental results on challenging 3D TRUS volumes show that our method attains satisfactory segmentation performance. The proposed attention mechanism is a general strategy to aggregate multi-level deep features and has the potential to be used for other medical image segmentation tasks. The code is publicly available at https://github.com/wulalago/DAF3D.