Embedding expertise knowledge into inverse treatment planning for low‐dose‐rate brachytherapy of hepatic malignancies

Zhu, Jianjun; Wang, Cheng; Teng, Sitong; Lü, Jian; Lyu, P; Zhang, P.; Xu, Jun; Lu, Ligong; Teng, Gao‐Jun

doi:10.1002/mp.16627

Cited by 4 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paramount considerations for ensuring the safety and efficacy of such interventions lie in the accurate segmentation and differentiation of patient anatomy, which constitutes fundamental prerequisites for procedural planning and intra-operative guidance. This imperative underscores the explicit delineation of three cardinal anatomical domains [3]: firstly, the avoidance organs (AVO), characterized by the skeletal structures, mandate meticulous circumvention by instrument or needle trajectories en route to the designated targets; secondly, the liver parenchyma itself emerges as the principal organs at risk (OAR) during the phases of tumor access and treatment delivery, underscoring the essentiality of precise delineation to prevent unintended harm; and lastly, the gross target volume (GTV)-liver tumors prescribes target boundaries and volume, thereby serving as the crucial locus for diagnostic sampling or therapeutic ablation. Given the implications of these delineations, the formulation of an advanced and efficient segmentation framework emerges as a research imperative.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

Lyu,

Liu,

Lin

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Precise liver tumors and associated organ segmentation hold immense value for surgical and radiological intervention, enabling anatomical localization for pre-operative planning and intra-operative guidance. Modern deep learning models for medical image segmentation have evolved from convolution neural networks to transformer architectures, significantly boosting global context understanding. However, accurate delineation especially of hepatic lesions remains an enduring challenge due to models’ predominant focus solely on spatial feature extraction failing to adequately characterize complex medical anatomies. Moreover, the relative paucity of expertly annotated medical imaging data restricts model exposure to diverse pathological presentations. In this paper, we present a three-phrased cascaded segmentation framework featuring an X-Fuse model that synergistically integrates spatial and frequency domain’s complementary information in dual encoders to enrich latent feature representation. To enhance model generalizability, building upon X Fuse topology and taking advantage of additional unlabeled pathological data, our proposed integration of curriculum pseudo-labeling with Jensen-Shannon variance-based uncertainty rectification promotes optimized pseudo-supervision in the context of semi-supervised learning. We further introduce a tumor-focus augmentation technique including training-free copy-paste and knowledge-based synthesis that show efficacy in simplicity, contributing to the substantial elevation of model adaptability on diverse lesional morphologies. Extensive experiments and modular evaluations on a holdout test set demonstrate that our methods significantly outperform existing state-of-the-art segmentation models in both supervised and semi-supervised settings, as measured by the Dice similarity coefficient, achieving superior delineation of bones (95.42%), liver (96.26%), and liver tumors (89.53%) with 16.41% increase comparing to V-Net on supervised-only and augmented-absent scenario. Our method marks a significant step toward the realization of more reliable and robust AI-assisted diagnostic tools for liver tumor intervention. We have made the codes publicly available.

show abstract

Section: Introductionmentioning

confidence: 99%