Bi-parametric prostate MR image synthesis using pathology and
sequence-conditioned stable diffusion
- URL: http://arxiv.org/abs/2303.02094v1
- Date: Fri, 3 Mar 2023 17:24:39 GMT
- Title: Bi-parametric prostate MR image synthesis using pathology and
sequence-conditioned stable diffusion
- Authors: Shaheer U. Saeed, Tom Syer, Wen Yan, Qianye Yang, Mark Emberton,
Shonit Punwani, Matthew J. Clarkson, Dean C. Barratt, Yipeng Hu
- Abstract summary: We propose an image synthesis mechanism for multi-sequence prostate MR images conditioned on text.
We generate paired bi-parametric images conditioned on images conditioned on paired data.
We validate our method using 2D image slices from real suspected prostate cancer patients.
- Score: 3.290987481767681
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose an image synthesis mechanism for multi-sequence prostate MR images
conditioned on text, to control lesion presence and sequence, as well as to
generate paired bi-parametric images conditioned on images e.g. for generating
diffusion-weighted MR from T2-weighted MR for paired data, which are two
challenging tasks in pathological image synthesis. Our proposed mechanism
utilises and builds upon the recent stable diffusion model by proposing
image-based conditioning for paired data generation. We validate our method
using 2D image slices from real suspected prostate cancer patients. The realism
of the synthesised images is validated by means of a blind expert evaluation
for identifying real versus fake images, where a radiologist with 4 years
experience reading urological MR only achieves 59.4% accuracy across all tested
sequences (where chance is 50%). For the first time, we evaluate the realism of
the generated pathology by blind expert identification of the presence of
suspected lesions, where we find that the clinician performs similarly for both
real and synthesised images, with a 2.9 percentage point difference in lesion
identification accuracy between real and synthesised images, demonstrating the
potentials in radiological training purposes. Furthermore, we also show that a
machine learning model, trained for lesion identification, shows better
performance (76.2% vs 70.4%, statistically significant improvement) when
trained with real data augmented by synthesised data as opposed to training
with only real images, demonstrating usefulness for model training.
Related papers
- On Sensitivity and Robustness of Normalization Schemes to Input
Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input.
DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases.
We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
arXiv Detail & Related papers (2023-06-23T03:09:03Z) - Medical Diffusion -- Denoising Diffusion Probabilistic Models for 3D
Medical Image Generation [0.6486409713123691]
We show that diffusion probabilistic models can synthesize high quality medical imaging data.
We provide quantitative measurements of their performance through a reader study with two medical experts.
We demonstrate that synthetic images can be used in a self-supervised pre-training and improve the performance of breast segmentation models when data is scarce.
arXiv Detail & Related papers (2022-11-07T08:37:48Z) - Automated SSIM Regression for Detection and Quantification of Motion
Artefacts in Brain MR Images [54.739076152240024]
Motion artefacts in magnetic resonance brain images are a crucial issue.
The assessment of MR image quality is fundamental before proceeding with the clinical diagnosis.
An automated image quality assessment based on the structural similarity index (SSIM) regression has been proposed here.
arXiv Detail & Related papers (2022-06-14T10:16:54Z) - Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis [68.5287824124996]
We present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images.
We apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem.
Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
arXiv Detail & Related papers (2022-03-29T08:41:17Z) - Texture Characterization of Histopathologic Images Using Ecological
Diversity Measures and Discrete Wavelet Transform [82.53597363161228]
This paper proposes a method for characterizing texture across histopathologic images with a considerable success rate.
It is possible to quantify the intrinsic properties of such images with promising accuracy on two HI datasets.
arXiv Detail & Related papers (2022-02-27T02:19:09Z) - Malignancy Prediction and Lesion Identification from Clinical
Dermatological Images [65.1629311281062]
We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images.
We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
arXiv Detail & Related papers (2021-04-02T20:52:05Z) - Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware
Generative Adversarial Networks [5.3580471186206005]
We trained a generative adversarial network (GAN) to generate synthetic MR knee images conditioned on various acquisition parameters.
In a Turing test, two experts mislabeled 40.5% of real and synthetic MR images, demonstrating that the image quality of the generated synthetic and real MR images is comparable.
arXiv Detail & Related papers (2021-02-17T11:39:36Z) - Advancing diagnostic performance and clinical usability of neural
networks via adversarial training and dual batch normalization [2.1699022621790736]
We let six radiologists rate the interpretability of saliency maps in datasets of X-rays, computed tomography, and magnetic resonance imaging scans.
We found that the accuracy of adversarially trained models was equal to standard models when sufficiently large datasets and dual batch norm training were used.
arXiv Detail & Related papers (2020-11-25T20:41:01Z) - Synthetic Sample Selection via Reinforcement Learning [8.099072894865802]
We propose a reinforcement learning based synthetic sample selection method that learns to choose synthetic images containing reliable and informative features.
In experiments on a cervical dataset and a lymph node dataset, the image classification performance is improved by 8.1% and 2.3%, respectively.
arXiv Detail & Related papers (2020-08-26T01:34:19Z) - Improved Slice-wise Tumour Detection in Brain MRIs by Computing
Dissimilarities between Latent Representations [68.8204255655161]
Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods.
We have proposed a slice-wise semi-supervised method for tumour detection based on the computation of a dissimilarity function in the latent space of a Variational AutoEncoder.
We show that by training the models on higher resolution images and by improving the quality of the reconstructions, we obtain results which are comparable with different baselines.
arXiv Detail & Related papers (2020-07-24T14:02:09Z)
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.