Semi-supervised learning for dose prediction in targeted radionuclide therapy: a synthetic data study

Objective. Accurate and personalized radiation dose estimation is crucial for effective targeted radionuclide therapy (TRT). Deep learning (DL) holds promise for this purpose. However, current DL-based dosimetry methods require large-scale supervised data, which is scarce in clinical practice. Approach. To address this challenge, we propose exploring semi-supervised learning (SSL) framework that leverages readily available pre-therapy positron emission tomography (PET) data, where only a small subset requires dose labels, to predict radiation doses, thereby reducing the dependency on extensive labeled datasets. In this study, traditional classification-based SSL approaches were adapted and extended in regression task specifically designed for dose prediction. To facilitate comprehensive testing and validation, we developed a synthetic dataset that simulates PET images and dose calculation using Monte Carlo simulations. Main results. In the experiment, several regression-adapted SSL methods were compared and evaluated under varying proportions of labeled data in the training set. The overall mean absolute percentage error of dose prediction remained between 9% and 11% across different organs, which achieved comparable performance than fully supervised ones. Significance. The preliminary experimental results demonstrated that the proposed SSL methods yield promising outcomes for organ-level dose prediction, particularly in scenarios where clinical data are not available in sufficient quantities.

• Publication year

  2026

• Venue

  Physics in Medicine and Biology

• Publication date

  2026-01-12

• Fields of study

  Medicine, Physics, Computer Science, Engineering

• Identifiers
  DOI 10.1088/1361-6560/ae36dfPMID 41525718
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Computational Nuclear Oncology Toward Precision Radiopharmaceutical Therapies: Ethical, Regulatory, and Socioeconomic Dimensions of Theranostic Digital Twins

  2025cited by this paper
• Deep transformer-based personalized dosimetry from SPECT/CT images: a hybrid approach for [177Lu]Lu-DOTATATE radiopharmaceutical therapy

  2024influential reference
• Pre-therapy PET-based voxel-wise dosimetry prediction by characterizing intra-organ heterogeneity in PSMA-directed radiopharmaceutical theranostics

  2024cited by this paper
• Multimodal radiotherapy dose prediction using a multi‐task deep learning model

  2024cited by this paper
• Deep semi-supervised regression via pseudo-label filtering and calibration

  2024cited by this paper
• PBPK-Adapted Deep Learning for Pretherapy Prediction of Voxelwise Dosimetry: In-Silico Proof of Concept

  2024cited by this paper
• Implementing Ac-225 labelled radiopharmaceuticals: practical considerations and (pre-)clinical perspectives

  2024cited by this paper
• MD-Dose: A diffusion model based on the Mamba for radiation dose prediction

  2024cited by this paper
• Single-Time-Point Imaging for Dosimetry After [177Lu]Lu-DOTATATE: Accuracy of Existing Methods and Novel Data-Driven Models for Reducing Sensitivity to Time-Point Selection

  2023cited by this paper
• Deep Learning-Based Feature Extraction from Whole-Body PET/CT Employing Maximum Intensity Projection Images: Preliminary Results of Lung Cancer Data

  2023cited by this paper
• Semi-supervised generative adversarial networks with spatial coevolution for enhanced image generation and classification

  2023influential reference
• DoseDiff: Distance-Aware Diffusion Model for Dose Prediction in Radiotherapy

  2023cited by this paper
• Fast Monte Carlo-Based Inverse Planning for Prostate Brachytherapy by Using Deep Learning

  2022cited by this paper
• MetaFormer Baselines for Vision

  2022cited by this paper
• Semi-supervised Vision Transformers at Scale

  2022cited by this paper
• Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation

  2022cited by this paper
• Generative Adversarial Networks

  2021influential reference
• Advanced Monte Carlo simulations of emission tomography imaging systems with GATE

  2021cited by this paper
• [68Ga]Ga-PSMA-11 PET imaging as a predictor for absorbed doses in organs at risk and small lesions in [177Lu]Lu-PSMA-617 treatment

  2021cited by this paper
• Denoising Diffusion Probabilistic Models

  2020cited by this paper
• Radiopharmaceutical therapy in cancer: clinical advances and challenges

  2020cited by this paper
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

  2020cited by this paper
• Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

  2020cited by this paper
• MixMatch: A Holistic Approach to Semi-Supervised Learning

  2019cited by this paper
• The effect of ligand amount, affinity and internalization on PSMA-targeted imaging and therapy: A simulation study using a PBPK model

  2019cited by this paper
• PyTorch: An Imperative Style, High-Performance Deep Learning Library

  2019influential reference
• Interpolation Consistency Training for Semi-Supervised Learning

  2019cited by this paper
• Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry

  2019cited by this paper
• Unsupervised Data Augmentation for Consistency Training

  2019cited by this paper
• Targeted Alpha Therapy, an Emerging Class of Cancer Agents: A Review

  2018cited by this paper
• CuPy : A NumPy-Compatible Library for NVIDIA GPU Calculations

  2017cited by this paper
• A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

  2017cited by this paper
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

  2017influential reference
• Whole-Body Voxel-Based Personalized Dosimetry: The Multiple Voxel S-Value Approach for Heterogeneous Media with Nonuniform Activity Distributions

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Temporal Ensembling for Semi-Supervised Learning

  2016cited by this paper
• U-Net: Convolutional Networks for Biomedical Image Segmentation

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015influential reference
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

  2013cited by this paper
• 4D XCAT phantom for multimodality imaging research.

  2010cited by this paper
• 4D XCAT phantom for multimodality imaging research.

  2010influential reference
• ImageNet: A large-scale hierarchical image database

  2009influential reference
• Effective Self-Training for Parsing

  2006cited by this paper
• Validation of a dose-point kernel convolution technique for internal dosimetry

  1995cited by this paper
• Maximum Likelihood Reconstruction for Emission Tomography

  1983cited by this paper

• No citing papers are available for this paper.