Accurate prostate volume estimation is crucial for effective prostate disease management. Ultrasound (US) imaging, particularly transrectal ultrasound, offers a cost-effective and rapid assessment. However, US images often suffer from artifacts and poor contrast, making prostate volume estimation challenging. This review explores recent advancements in deep learning (DL) techniques for automatic prostate segmentation in US images as a primary step toward prostate volume estimation. We examine various DL architectures, including traditional U-Net modifications and innovative designs incorporating residual connections, multi-directional image data, and attention mechanisms. Additionally, we discuss pre-processing methods to enhance image quality, the integration of shape information, and strategies to improve the consistency and robustness of DL models. The effectiveness of these techniques is evaluated through metrics such as the Dice Similarity Coefficient, Jaccard Index, and Hausdorff Distance. The review highlights the potential of DL in improving prostate volume estimation accuracy and reducing clinical workload while also identifying areas for future research to enhance model performance and generalizability.

PurposeTraining and evaluation of the performance of a supervised deep-learning model for the segmentation of hepatic tumors from intraoperative US (iUS) images, with the purpose of improving the accuracy of tumor margin assessment during liver surgeries and the detection of lesions during colorectal surgeries.ApproachIn this retrospective study, a U-Net network was trained with the nnU-Net framework in different configurations for the segmentation of CRLM from iUS. The model was trained on B-mode intraoperative hepatic US images, hand-labeled by an expert clinician. The model was tested on an independent set of similar images. The average age of the study population was 61.9 ± 9.9 years. Ground truth for the test set was provided by a radiologist, and three extra delineation sets were used for the computation of inter-observer variability.ResultsThe presented model achieved a DSC of 0.84 (p=0.0037), which is comparable to the expert human raters scores. The model segmented hypoechoic and mixed lesions more accurately (DSC of 0.89 and 0.88, respectively) than hyper- and isoechoic ones (DSC of 0.70 and 0.60, respectively) only missing isoechoic or >20 mm in diameter (8% of the tumors) lesions. The inclusion of extra margins of probable tumor tissue around the lesions in the training ground truth resulted in lower DSCs of 0.75 (p=0.0022).ConclusionThe model can accurately segment hepatic tumors from iUS images and has the potential to speed up the resection margin definition during surgeries and the detection of lesion in screenings by automating iUS assessment.

Real-time segmentation of the liver parenchyma is a key requirement for computer-assisted guidance in minimally invasive liver surgery. However, existing methods are developed mainly on public cholecystectomy datasets and are therefore poorly representative of institution-specific acquisition conditions and of the appearance changes introduced by active liver resection. This study investigates public-to-private domain shift in real-time liver segmentation and proposes a SegFormer-B0-based boundary-guided framework that leverages anatomical liver contours and resection-induced boundaries to refine parenchyma segmentation. A surgery-specific augmentation strategy complements the framework by simulating intraoperative perturbations and generating synthetic resection-margin supervision when corresponding annotations are unavailable in the public training data. The method was evaluated on public laparoscopic data and private robot-assisted liver surgery data including both normal anatomy and active resection scenes. The proposed framework consistently outperformed the plain SegFormer-B0 baseline under both Public Training and combined Public + Private Training configurations. In the Public Training setting, the largest improvement was observed on NKI-Resection, where Dice increased from 0.71 to 0.87, while maintaining real-time inference at 75.50 FPS. A fixed library of ten manually annotated private resection images, drawn exclusively from the private training procedures, was used as a source of augmentation patches. Ablation results indicated complementary contributions from surgery-specific augmentation and resection-margin boundary modeling. These findings support boundary-guided refinement and targeted surgical augmentation as promising strategies for improving real-time liver segmentation under domain shift.

Accurate endoscope pose estimation and 3D tissue surface reconstruction significantly enhances monocular minimally invasive surgical procedures by enabling accurate navigation and improved spatial awareness. However, monocular endoscope pose estimation and tissue reconstruction face persistent challenges, including depth ambiguity, physiological tissue deformation, inconsistent endoscope motion, limited texture fidelity, and a restricted field of view. To overcome these limitations, a unified framework for monocular endoscopic tissue reconstruction that integrates scale-aware depth prediction with temporally-constrained perceptual refinement is presented. This framework incorporates a novel MAPIS-Depth module, which leverages Depth Pro for robust initialisation and Depth Anything for efficient per-frame depth prediction, in conjunction with L-BFGS-B optimisation, to generate pseudo-metric depth estimates. These estimates are temporally refined by computing pixel correspondences using RAFT and adaptively blending flow-warped frames based on LPIPS perceptual similarity, thereby reducing artefacts arising from physiological tissue deformation and motion. To ensure accurate registration of the synthesised pseudo-RGBD frames from MAPIS-Depth, a novel WEMA-RTDL module is integrated, optimising both rotation and translation. Finally, truncated signed distance function-based volumetric fusion and marching cubes are applied to extract a comprehensive 3D surface mesh. Evaluations on HEVD and SCARED, with ablation and comparative analyses, demonstrate the framework's robustness and superiority over state-of-the-art methods.

Accurate prostate volume estimation is crucial for effective prostate disease management. Ultrasound (US) imaging, particularly transrectal ultrasound, offers a cost-effective and rapid assessment. However, US images often suffer from artifacts and poor contrast, making prostate volume estimation challenging. This review explores recent advancements in deep learning (DL) techniques for automatic prostate segmentation in US images as a primary step for prostate volume estimation. We examine various DL architectures, including traditional U-Net modifications and innovative designs incorporating residual connections, multi-directional image data, and attention mechanisms. Additionally, we discuss pre-processing methods to enhance image quality, the integration of shape information, and strategies to improve the consistency and robustness of DL models. The effectiveness of these techniques is evaluated through metrics such as Dice Similarity Coefficient, Jaccard Index, and Hausdorff Distance. The review highlights the potential of DL in improving prostate volume estimation accuracy and reducing clinical workload, while also identifying areas for future research to enhance model performance and generalizability.