Synthetic Tumor Manipulation: With Radiomics Features

• URL: http://arxiv.org/abs/2311.02586v1
• Date: Sun, 5 Nov 2023 08:07:50 GMT
• Title: Synthetic Tumor Manipulation: With Radiomics Features
• Authors: Inye Na, Jonghun Kim, Hyunjin Park
• Abstract summary: RadiomicsFill is a synthetic tumor generator conditioned on radiomics features. Our model combines generative adversarial networks, radiomics-feature conditioning, and multi-task learning.
• Score: 3.6852491526879687
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce RadiomicsFill, a synthetic tumor generator conditioned on radiomics features, enabling detailed control and individual manipulation of tumor subregions. This conditioning leverages conventional high-dimensional features of the tumor (i.e., radiomics features) and thus is biologically well-grounded. Our model combines generative adversarial networks, radiomics-feature conditioning, and multi-task learning. Through experiments with glioma patients, RadiomicsFill demonstrated its capability to generate diverse, realistic tumors and its fine-tuning ability for specific radiomics features like 'Pixel Surface' and 'Shape Sphericity'. The ability of RadiomicsFill to generate an unlimited number of realistic synthetic tumors offers notable prospects for both advancing medical imaging research and potential clinical applications.

Related papers

• TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth [2.3743336223695057]
  Glioblastoma exhibits diverse, infiltrative, and patient-specific growth patterns that are only partially visible on routine MRI.<n>We present a biophysically-conditioned generative framework that synthesizes biologically realistic 3D brain MRI volumes from estimated, spatially continuous tumor-concentration fields.
  arXiv  Detail & Related papers  (2026-03-04T13:38:24Z)
• Tumor Synthesis conditioned on Radiomics [1.3521165953335823]
  We propose a tumor-generation model that utilizes radiomics features as generative conditions.<n>Our model employs a GAN-based model to generate tumor masks and a diffusion-based approach to generate tumor texture conditioned on radiomics features.<n>Our method allows the user to generate tumor images according to user-specified radiomics features such as size, shape, and texture at an arbitrary location.
  arXiv  Detail & Related papers  (2025-09-29T02:04:12Z)
• FreeTumor: Large-Scale Generative Tumor Synthesis in Computed Tomography Images for Improving Tumor Recognition [11.984311048958318]
  FreeTumor is an innovative Generative AI (GAI) framework to enable large-scale tumor synthesis for mitigating data scarcity. We create the largest training dataset for tumor synthesis and recognition by curating 161,310 publicly available Computed Tomography (CT) volumes. To validate the fidelity of synthetic tumors, we engaged 13 board-certified radiologists in a Visual Turing Test to discern between synthetic and real tumors.
  arXiv  Detail & Related papers  (2025-02-23T07:00:09Z)
• Analyzing Tumors by Synthesis [11.942932753828854]
  Tumor synthesis generates numerous tumor examples in medical images, aiding AI training for tumor detection and segmentation. This chapter reviews AI development on real and synthetic data. Case studies show that AI trained on synthetic tumors can achieve performance comparable to, or better than, AI only trained on real data.
  arXiv  Detail & Related papers  (2024-09-09T19:51:44Z)
• MGH Radiology Llama: A Llama 3 70B Model for Radiology [50.42811030970618]
  This paper presents an advanced radiology-focused large language model: MGH Radiology Llama. It is developed using the Llama 3 70B model, building upon previous domain-specific models like Radiology-GPT and Radiology-Llama2. Our evaluation, incorporating both traditional metrics and a GPT-4-based assessment, highlights the enhanced performance of this work over general-purpose LLMs.
  arXiv  Detail & Related papers  (2024-08-13T01:30:03Z)
• RadiomicsFill-Mammo: Synthetic Mammogram Mass Manipulation with Radiomics Features [3.0015555136149175]
  We present RadiomicsFill-Mammo, an innovative technique that generates realistic mammogram mass images mirroring specific radiomics attributes. Results indicate that RadiomicsFill-Mammo effectively generates diverse and realistic tumor images based on various radiomics conditions.
  arXiv  Detail & Related papers  (2024-07-08T07:33:52Z)
• Towards Generalizable Tumor Synthesis [48.45704270448412]
  Tumor synthesis enables the creation of artificial tumors in medical images, facilitating the training of AI models for tumor detection and segmentation. This paper made a progressive stride toward generalizable tumor synthesis by leveraging a critical observation. We have ascertained that generative AI models, e.g., Diffusion Models, can create realistic tumors generalized to a range of organs even when trained on a limited number of tumor examples from only one organ.
  arXiv  Detail & Related papers  (2024-02-29T18:57:39Z)
• ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data [115.0747462486285]
  ChatRadio-Valuer is a tailored model for automatic radiology report generation that learns generalizable representations. The clinical dataset utilized in this study encompasses a remarkable total of textbf332,673 observations. ChatRadio-Valuer consistently outperforms state-of-the-art models, especially ChatGPT (GPT-3.5-Turbo) and GPT-4 et al.
  arXiv  Detail & Related papers  (2023-10-08T17:23:17Z)
• Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction [0.5806504980491878]
  We present a novel end-to-end network capable of generating future tumor masks and realistic MRIs of how the tumor will look at any future time points. Our approach is based on cutting-edge diffusion probabilistic models and deep-segmentation neural networks.
  arXiv  Detail & Related papers  (2023-09-11T12:12:52Z)
• Radiology-Llama2: Best-in-Class Large Language Model for Radiology [71.27700230067168]
  This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning. Quantitative evaluations using ROUGE metrics on the MIMIC-CXR and OpenI datasets demonstrate that Radiology-Llama2 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-08-29T17:44:28Z)
• Radiology-GPT: A Large Language Model for Radiology [74.07944784968372]
  We introduce Radiology-GPT, a large language model for radiology. It demonstrates superior performance compared to general language models such as StableLM, Dolly and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication.
  arXiv  Detail & Related papers  (2023-06-14T17:57:24Z)
• Label-Free Liver Tumor Segmentation [10.851067782021902]
  We show that AI models can accurately segment liver tumors without the need for manual annotation by using synthetic tumors in CT scans. Our synthetic tumors have two intriguing advantages: realistic in shape and texture, which even medical professionals can confuse with real tumors. Our synthetic tumors can automatically generate many examples of small (or even tiny) synthetic tumors.
  arXiv  Detail & Related papers  (2023-03-27T01:22:12Z)
• Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection [52.93342510469636]
  Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers. Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR. To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation.
  arXiv  Detail & Related papers  (2022-07-19T16:38:48Z)
• Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study [55.78588835407174]
  We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. We present two networks, the Introspective Variational Autoencoder and the Style-Based GAN, that qualify for data augmentation in the medical field.
  arXiv  Detail & Related papers  (2020-06-24T18:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.