Triplet-constraint Transformer with Multi-scale Refinement for Dose Prediction in Radiotherapy
Radiotherapy is a primary treatment for cancers with the aim of applying sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs). Convolutional neural networks (CNNs) have automated the radiotherapy plan-making by predicting the dose maps. However, current CNN-based methods ignore the remarkable dose difference in the dose map, i.e., high dose value in the interior PTV while low value in the exterior PTV, leading to a suboptimal prediction. In this paper, we propose a triplet-constraint transformer (TCtrans) with multi-scale refinement to predict the high-quality dose distribution. Concretely, a novel PTV-guided triplet constraint is designed to refine dose feature representations in the interior and exterior PTV by utilizing the explicit geometry of PTV. Furthermore, we introduce a multi-scale refinement (MSR) module to effectively fulfill the triplet constraint in different decoding layers with multiple scales. Besides, a transformer encoder is devised to learn the important global dosimetric knowledge. Experiments on a clinical cervical cancer dataset demonstrate the superiority of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
TripletSimilar Papers 제목 키워드 기반
Knowledge Graph Refinement based on Triplet BERT-Networks
Knowledge graph embedding techniques are widely used for knowledge graph refinement tasks such as graph completion and triple classification. These techniques aim at embedding the entities and relations of a Knowledge Gr…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsRelation+3Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation
Scene graph generation is a pivotal task in computer vision, focusing on comprehensive identification of visual relation tuples embedded within images. The advancement of methods involving triplets has sought to enha…
Graph GenerationRelationScene Graph GenerationTripletAdvanced Machine Learning Approaches for Enhancing Person Re-Identification Performance
Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearan…
Unsupervised Domain AdaptationPerson Re-IdentificationDomain GeneralizationContrastive LearningTriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
Salient object detection is the pixel-level dense prediction task which can highlight the prominent object in the scene. Recently U-Net framework is widely used, and continuous convolution and pooling operations generate…
DecoderObjectobject-detectionObject Detection+3RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
Preference-learning methods for machine translation (MT), such as Direct Preference Optimization (DPO), have shown strong gains but typically rely on large, carefully curated preference triplets and often struggle to gen…
Reinforcement LearningMachine Translation