Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference

A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods

The comprehensive integration of machine learning healthcare models within clinical practice remains suboptimal, notwithstanding the proliferation of high-performing solutions reported in the literature. A predominant factor hindering widespread adoption pertains to an insufficiency of evidence affirming the reliability of the aforementioned models. Recently, uncertainty quantification methods have been proposed as a potential solution to quantify the reliability of machine learning models and thus increase the interpretability and acceptability of the results. In this review, we offer a comprehensive overview of the prevailing methods proposed to quantify the uncertainty inherent in machine learning models developed for various medical image tasks. Contrary to earlier reviews that exclusively focused on probabilistic methods, this review also explores non-probabilistic approaches, thereby furnishing a more holistic survey of research pertaining to uncertainty quantification for machine learning models. Analysis of medical images with the summary and discussion on medical applications and the corresponding uncertainty evaluation protocols are presented, which focus on the specific challenges of uncertainty in medical image analysis. We also highlight some potential future research work at the end. Generally, this review aims to allow researchers from both clinical and technical backgrounds to gain a quick and yet in-depth understanding of the research in uncertainty quantification for medical image analysis machine learning models.

Neural orientation distribution fields for estimation and uncertainty quantification in diffusion MRI

Inferring brain connectivity and structure in-vivo requires accurate estimation of the orientation distribution function (ODF), which encodes key local tissue properties. However, estimating the ODF from diffusion MRI (dMRI) signals is a challenging inverse problem due to obstacles such as significant noise, high-dimensional parameter spaces, and sparse angular measurements. In this paper, we address these challenges by proposing a novel deep-learning based methodology for continuous estimation and uncertainty quantification of the spatially varying ODF field. We use a neural field (NF) to parameterize a random series representation of the latent ODFs, implicitly modeling the often ignored but valuable spatial correlation structures in the data, and thereby improving efficiency in sparse and noisy regimes. An analytic approximation to the posterior predictive distribution is derived which can be used to quantify the uncertainty in the ODF estimate at any spatial location, avoiding the need for expensive resampling-based approaches that are typically employed for this purpose. We present empirical evaluations on both synthetic and real in-vivo diffusion data, demonstrating the advantages of our method over existing approaches.

Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 * quantification using self-gated stack-of-radial MRI

PURPOSE

To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R2 * quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI.

METHODS

This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat-water and R2 * signal model. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. UP-Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R2 * in a testing dataset.

RESULTS

Compared with images reconstructed using compressed sensing (CS), UP-Net achieved structural similarity index >0.87 and normalized root mean squared error <0.18. Compared with reference quantitative maps generated using CS and graph-cut (GC) algorithms, UP-Net achieved low mean differences (MD) for liver PDFF (-0.36%) and R2 * (-0.37 s-1 ). Compared with breath-holding Cartesian MRI results, UP-Net achieved low MD for liver PDFF (0.53%) and R2 * (6.75 s-1 ). UP-Net uncertainty scores predicted absolute liver PDFF and R2 * errors with low MD of 0.27% and 0.12 s-1 compared to CS + GC results. The computational time for UP-Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice.

CONCLUSION

UP-Net rapidly calculates accurate liver PDFF and R2 * maps from self-gated free-breathing stack-of-radial MRI. The pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.

A deep network embedded with rough fuzzy discretization for OCT fundus image segmentation

The noise and redundant information are the main reasons for the performance bottleneck of medical image segmentation algorithms based on the deep learning. To this end, we propose a deep network embedded with rough fuzzy discretization (RFDDN) for OCT fundus image segmentation. Firstly, we establish the information decision table of OCT fundus image segmentation, and regard each category of segmentation region as a fuzzy set. Then, we use the fuzzy c-means clustering to get the membership degrees of pixels to each segmentation region. According to membership functions and the equivalence relation generated by the brightness attribute, we design the individual fitness function based on the rough fuzzy set, and use a genetic algorithm to search for the best breakpoints to discretize the features of OCT fundus images. Finally, we take the feature discretization based on the rough fuzzy set as the pre-module of the deep neural network, and introduce the deep supervised attention mechanism to obtain the important multi-scale information. We compare RFDDN with U-Net, ReLayNet, CE-Net, MultiResUNet, and ISCLNet on the two groups of 3D retinal OCT data. RFDDN is superior to the other five methods on all evaluation indicators. The results obtained by ISCLNet are the second only inferior to those obtained by RFDDN. DSC, sensitivity, and specificity of RFDDN are evenly 3.3%, 2.6%, and 7.1% higher than those of ISCLNet, respectively. HD95 and ASD of RFDDN are evenly 6.6% and 19.7% lower than those of ISCLNet, respectively. The experimental results show that our method can effectively eliminate the noise and redundant information in Oct fundus images, and greatly improve the accuracy of OCT fundus image segmentation while taking into account the interpretability and computational efficiency.

Post-operative glioblastoma multiforme segmentation with uncertainty estimation

Segmentation of post-operative glioblastoma multiforme (GBM) is essential for the planning of Tumor Treating Fields (TTFields) treatment and other clinical applications. Recent methods developed for pre-operative GBM segmentation perform poorly on post-operative GBM MRI scans. In this paper we present a method for the segmentation of GBM in post-operative patients. Our method incorporates an ensemble of segmentation networks and the Kullback–Leibler divergence agreement score in the objective function to estimate the prediction label uncertainty and cope with noisy labels and inter-observer variability. Moreover, our method integrates the surgery type and computes non-tumorous tissue delineation to automatically segment the tumor. We trained and validated our method on a dataset of 340 enhanced T1 MRI scans of patients that were treated with TTFields (270 scans for train and 70 scans for test). For validation, we developed a tool that uses the uncertainty map along with the segmentation result. Our tool allows visualization and fast editing of the tissues to improve the results dependent on user preference. Three physicians reviewed and graded our segmentation and editing tool on 12 different MRI scans. The validation set average (SD) Dice scores were 0.81 (0.11), 0.71 (0.24), 0.64 (0.25), and 0.68 (0.19) for whole-tumor, resection, necrotic-core, and enhancing-tissue, respectively. The physicians rated 72% of the segmented GBMs acceptable for treatment planning or better. Another 22% can be edited manually in a reasonable time to achieve a clinically acceptable result. According to these results, the proposed method for GBM segmentation can be integrated into TTFields treatment planning software in order to shorten the planning process. To conclude, we have extended a state-of-the-art pre-operative GBM segmentation method with surgery-type, anatomical information, and uncertainty visualization to facilitate a clinically viable segmentation of post-operative GBM for TTFields treatment planning.

DGRUnit: Dual graph reasoning unit for brain tumor segmentation

Many fully automatic segmentation models have been created to solve the difficulty of brain tumor segmentation, thanks to the rapid growth of deep learning. However, few approaches focus on the long-range relationships and contextual interdependence in multimodal Magnetic Resonance (MR) images. In this paper, we propose a novel approach for brain tumor segmentation called the dual graph reasoning unit (DGRUnit). Two parallel graph reasoning modules are included in our proposed method: a spatial reasoning module and a channel reasoning module. The spatial reasoning module models the long-range spatial dependencies between distinct regions in an image using a graph convolutional network (GCN). The channel reasoning module uses a graph attention network (GAT) to model the rich contextual interdependencies between different channels with similar semantic representations. Our experimental results clearly demonstrate the superior performance of the proposed DGRUnit. The ablation study shows the flexibility and generalizability of our model, which can be easily integrated into a wide range of neural networks and further improve them. When compared to several state-of-the-art methods, experimental results show that the proposed approach significantly improves both visual inspection and quantitative metrics for brain tumor segmentation tasks.

Dementia-related user-based collaborative filtering for imputing missing data and generating a reliability scale on clinical test scores

Medical doctors may struggle to diagnose dementia, particularly when clinical test scores are missing or incorrect. In case of any doubts, both morphometrics and demographics are crucial when examining dementia in medicine. This study aims to impute and verify clinical test scores with brain MRI analysis and additional demographics, thereby proposing a decision support system that improves diagnosis and prognosis in an easy-to-understand manner. Therefore, we impute the missing clinical test score values by unsupervised dementia-related user-based collaborative filtering to minimize errors. By analyzing succession rates, we propose a reliability scale that can be utilized for the consistency of existing clinical test scores. The complete base of 816 ADNI1-screening samples was processed, and a hybrid set of 603 features was handled. Moreover, the detailed parameters in use, such as the best neighborhood and input features were evaluated for further comparative analysis. Overall, certain collaborative filtering configurations outperformed alternative state-of-the-art imputation techniques. The imputation system and reliability scale based on the proposed methodology are promising for supporting the clinical tests.