RECORD
Synthetic Tumor Manipulation: With Radiomics Features
Image and Video Processing · Submitted 5 Nov 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We introduce RadiomicsFill, a synthetic tumor generator conditioned on radiomics features, enabling detailed control and individual manipulation of tumor subregions. | contribution 0.99 | 0.92 | 0.20 | asserted 1.00 |
| s1 | This conditioning leverages conventional high-dimensional features of the tumor (i.e., radiomics features) and thus is biologically well-grounded. | method 0.59 | 0.36 | 0.06 | asserted 1.00 |
| s2 | Our model combines generative adversarial networks, radiomics-feature conditioning, and multi-task learning. | method 0.99 | 0.81 | 0.05 | asserted 1.00 |
| s3 | 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'. | result 1.00 | 0.96 | 0.25 | asserted 1.00 |
| s4 | 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. | interpretation 0.95 | 0.32 | 0.66 | hedged possibility 0.62 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Uses data or values from 1 paper
-
For our experiments and evaluations, we utilized the Brain Tumor Segmentation (BraTS) 2021 training data [ref] , which offers glioma datasets with three types of tumor masks (i.e., necrotic, enhancing tumor, and edema).
The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification · Dataset · 1.00
Cites as background 1 paper
-
Recent research trends aim to overcome this challenge through the generation of synthetic data using generative models such as generative adversarial networks (GANs) and diffusion [ref] .
Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models · Introduction · 0.86
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.