Vision-Language Models for Automated 3D PET/CT Report Generation

arXiv — cs.CVWednesday, November 26, 2025 at 5:00:00 AM
  • A new framework named PETRG-3D has been proposed for automated 3D PET/CT report generation, addressing the growing need for efficient reporting in oncology due to a shortage of trained specialists. This model utilizes a dual-branch architecture to separately encode PET and CT volumes while incorporating style-adaptive prompts to standardize reporting across different hospitals.
  • The development of PETRG-3D is significant as it aims to reduce clinical workload and enhance the accuracy of PET/CT reports, which are crucial for effective patient management in oncology. By automating this process, healthcare providers can allocate resources more efficiently and improve patient outcomes.
  • This advancement reflects a broader trend in medical imaging where artificial intelligence is increasingly utilized to enhance diagnostic processes. Similar innovations in areas such as MRI synthesis and CT reconstruction highlight the ongoing efforts to improve imaging accuracy and reduce the burden on healthcare professionals, ultimately aiming for better patient care.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstruction
PositiveArtificial Intelligence
A recent study has introduced a semantic distribution-guided reconstruction framework that leverages a vision-language foundation model to improve undersampled MRI reconstruction. This approach encodes both the reconstructed images and auxiliary information into high-level semantic features, enhancing the quality of MRI images, particularly for knee and brain datasets.
Multi Head Attention Enhanced Inception v3 for Cardiomegaly Detection
PositiveArtificial Intelligence
A new approach utilizing multi-head attention and the Inception v3 model has been developed for the automatic detection of cardiomegaly through X-ray images. This method integrates deep learning tools and attention mechanisms, enhancing the accuracy and efficiency of diagnosing cardiovascular diseases by leveraging a robust data collection phase and preprocessing techniques to improve image quality.
LiMT: A Multi-task Liver Image Benchmark Dataset
PositiveArtificial Intelligence
A new multi-task liver image benchmark dataset, named LiMT, has been introduced to enhance computer-aided diagnosis (CAD) technology for liver lesions. This dataset supports liver and tumor segmentation, multi-label lesion classification, and lesion detection using arterial phase-enhanced computed tomography (CT) from 150 cases, including various liver diseases and normal instances.
Blind Adaptive Local Denoising for CEST Imaging
PositiveArtificial Intelligence
A new method called Blind Adaptive Local Denoising (BALD) has been proposed to enhance Chemical Exchange Saturation Transfer (CEST) MRI imaging by addressing the challenges of spatially varying noise and complex imaging protocols that affect data accuracy. BALD utilizes the self-similar nature of CEST data to stabilize noise distributions without prior knowledge of noise characteristics.
MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
PositiveArtificial Intelligence
MTBBench has been introduced as a new benchmark designed to simulate decision-making in Molecular Tumor Boards (MTBs), addressing the limitations of existing evaluations that focus on unimodal question-answering. This benchmark incorporates multimodal and longitudinal oncology questions, validated by clinicians through a co-developed application.
Detection of brain network abnormalities by graph invariants in Alzheimer’s disease using MRI images
NeutralArtificial Intelligence
A recent study published in Nature — Machine Learning has identified brain network abnormalities in Alzheimer's disease through the application of graph invariants using MRI images. This innovative approach enhances the understanding of the disease's impact on brain connectivity and structure.
Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
PositiveArtificial Intelligence
A new study introduces Upstream Probabilistic Meta-Imputation (UPMI) as a novel strategy for classifying pediatric pancreatitis, a complex inflammatory condition. This method leverages machine learning techniques to enhance diagnostic accuracy by utilizing a low-dimensional meta-feature space, addressing challenges posed by limited sample sizes and the intricacies of multimodal imaging.
From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesis
PositiveArtificial Intelligence
A new framework called Tumor Fabrication (TF) has been proposed for synthesizing 3D brain tumors from healthy MRI scans, addressing the challenge of limited annotated tumor data. This two-stage process includes a coarse synthesis followed by refinement using a generative model, enabling the creation of large volumes of paired synthetic data for improved tumor segmentation.