Prostate cancer is a major health concern requiring accurate and accessible methods for early detection and risk stratification. Prostate volume (PV) is a key parameter in multivariate risk assessment, traditionally measured using transrectal ultrasound (TRUS). While TRUS provides precise measurements, its invasive nature affects patient comfort. Transabdominal ultrasound (TAUS) offers a non-invasive alternative but is limited by lower image quality and operator dependence. This study presents a deep-learning-based framework for automatic PV estimation using TAUS, aiming to improve non-invasive prostate cancer risk stratification. A dataset of TAUS videos from 100 patients (median age 67, 95-percentile range 55-81.2) was curated, with expert-delineated prostate boundaries and diameter calculations as ground truth. The framework integrates deep-learning models for prostate segmentation in both axial and sagittal planes, automatic diameter estimation, and PV calculation. Segmentation performance was evaluated using Dice correlation coefficient (%) and Hausdorff distance (mm), while volume estimation accuracy was assessed through volumetric error (mL). The axial model outperformed the sagittal model, achieving a Dice score of 0.76 ± 0.16 versus 0.68 ± 0.21, a Dice-MidPlane of 0.91 ± 0.06 versus 0.83. ± 0.10, and a Hausdorff distance of 6.21 ± 4.33 mm versus 7.93 ± 4.27 mm. The framework estimated PV with a mean volumetric error of -2.1 mL (95 % limits of agreement: -16.9 to 21.1 mL), resulting in a relative error smaller than 25 %. These findings highlight the potential of deep learning for accurate, non-invasive PV estimation, supporting improved prostate cancer risk assessment.

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.

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.