FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis

• URL: http://arxiv.org/abs/2406.01264v1
• Date: Mon, 3 Jun 2024 12:27:29 GMT
• Title: FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis
• Authors: Linshan Wu, Jiaxin Zhuang, Xuefeng Ni, Hao Chen,
• Abstract summary: FreeTumor is a robust solution for robust tumor synthesis and segmentation. It uses adversarial training strategy to leverage large-scale and diversified unlabeled data in synthesis training. In FreeTumor, we investigate the data scaling law in tumor segmentation by scaling up the dataset to 11k cases.
• Score: 7.064154713491736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI-driven tumor analysis has garnered increasing attention in healthcare. However, its progress is significantly hindered by the lack of annotated tumor cases, which requires radiologists to invest a lot of effort in collecting and annotation. In this paper, we introduce a highly practical solution for robust tumor synthesis and segmentation, termed FreeTumor, which refers to annotation-free synthetic tumors and our desire to free patients that suffering from tumors. Instead of pursuing sophisticated technical synthesis modules, we aim to design a simple yet effective tumor synthesis paradigm to unleash the power of large-scale data. Specifically, FreeTumor advances existing methods mainly from three aspects: (1) Existing methods only leverage small-scale labeled data for synthesis training, which limits their ability to generalize well on unseen data from different sources. To this end, we introduce the adversarial training strategy to leverage large-scale and diversified unlabeled data in synthesis training, significantly improving tumor synthesis. (2) Existing methods largely ignored the negative impact of low-quality synthetic tumors in segmentation training. Thus, we employ an adversarial-based discriminator to automatically filter out the low-quality synthetic tumors, which effectively alleviates their negative impact. (3) Existing methods only used hundreds of cases in tumor segmentation. In FreeTumor, we investigate the data scaling law in tumor segmentation by scaling up the dataset to 11k cases. Extensive experiments demonstrate the superiority of FreeTumor, e.g., on three tumor segmentation benchmarks, average $+8.9\%$ DSC over the baseline that only using real tumors and $+6.6\%$ DSC over the state-of-the-art tumor synthesis method. Code will be available.

Related papers

• 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)
• Optimizing Synthetic Data for Enhanced Pancreatic Tumor Segmentation [1.6321136843816972]
  This study critically evaluates the limitations of existing generative-AI based frameworks for pancreatic tumor segmentation. We conduct a series of experiments to investigate the impact of synthetic textittumor size and textitboundary definition precision on model performance. Our findings demonstrate that: (1) strategically selecting a combination of synthetic tumor sizes is crucial for optimal segmentation outcomes, and (2) generating synthetic tumors with precise boundaries significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-07-27T15:38:07Z)
• Improving Breast Cancer Grade Prediction with Multiparametric MRI Created Using Optimized Synthetic Correlated Diffusion Imaging [71.91773485443125]
  Grading plays a vital role in breast cancer treatment planning. The current tumor grading method involves extracting tissue from patients, leading to stress, discomfort, and high medical costs. This paper examines using optimized CDI$s$ to improve breast cancer grade prediction.
  arXiv  Detail & Related papers  (2024-05-13T15:48:26Z)
• From Pixel to Cancer: Cellular Automata in Computed Tomography [12.524228287083888]
  Tumor synthesis seeks to create artificial tumors in medical images. This paper establishes a set of generic rules to simulate tumor development. We integrate the tumor state into the original computed tomography (CT) images to generate synthetic tumors across different organs.
  arXiv  Detail & Related papers  (2024-03-11T06:46:31Z)
• 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)
• Prediction of brain tumor recurrence location based on multi-modal fusion and nonlinear correlation learning [55.789874096142285]
  We present a deep learning-based brain tumor recurrence location prediction network. We first train a multi-modal brain tumor segmentation network on the public dataset BraTS 2021. Then, the pre-trained encoder is transferred to our private dataset for extracting the rich semantic features. Two decoders are constructed to jointly segment the present brain tumor and predict its future tumor recurrence location.
  arXiv  Detail & Related papers  (2023-04-11T02:45:38Z)
• 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)
• Synthetic Tumors Make AI Segment Tumors Better [10.851067782021902]
  We develop a novel strategy to generate synthetic tumors. The tumors are realistic in shape and texture, which even medical professionals can confuse with real tumors. Our synthetic tumors have the potential to improve the success rate of small tumor detection.
  arXiv  Detail & Related papers  (2022-10-26T16:45:19Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)
• Triplet Contrastive Learning for Brain Tumor Classification [99.07846518148494]
  We present a novel approach of directly learning deep embeddings for brain tumor types, which can be used for downstream tasks such as classification. We evaluate our method on an extensive brain tumor dataset which consists of 27 different tumor classes, out of which 13 are defined as rare.
  arXiv  Detail & Related papers  (2021-08-08T11:26:34Z)
• Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
  We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
  arXiv  Detail & Related papers  (2020-02-03T22:25:01Z)

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.