Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

Automated assessment of cardiac pathologies on cardiac MRI using T1-mapping and late gadolinium phase sensitive inversion recovery sequences with deep learning

BACKGROUND

A deep learning (DL) model that automatically detects cardiac pathologies on cardiac MRI may help streamline the diagnostic workflow. To develop a DL model to detect cardiac pathologies on cardiac MRI T1-mapping and late gadolinium phase sensitive inversion recovery (PSIR) sequences were used.

METHODS

Subjects in this study were either diagnosed with cardiac pathology (n = 137) including acute and chronic myocardial infarction, myocarditis, dilated cardiomyopathy, and hypertrophic cardiomyopathy or classified as normal (n = 63). Cardiac MR imaging included T1-mapping and PSIR sequences. Subjects were split 65/15/20% for training, validation, and hold-out testing. The DL models were based on an ImageNet pretrained DenseNet-161 and implemented using PyTorch and fastai. Data augmentation with random rotation and mixup was applied. Categorical cross entropy was used as the loss function with a cyclic learning rate (1e-3). DL models for both sequences were developed separately using similar training parameters. The final model was chosen based on its performance on the validation set. Gradient-weighted class activation maps (Grad-CAMs) visualized the decision-making process of the DL model.

RESULTS

The DL model achieved a sensitivity, specificity, and accuracy of 100%, 38%, and 88% on PSIR images and 78%, 54%, and 70% on T1-mapping images. Grad-CAMs demonstrated that the DL model focused its attention on myocardium and cardiac pathology when evaluating MR images.

CONCLUSIONS

The developed DL models were able to reliably detect cardiac pathologies on cardiac MR images. The diagnostic performance of T1 mapping alone is particularly of note since it does not require a contrast agent and can be acquired quickly.

Learning with limited annotations: A survey on deep semi-supervised learning for medical image segmentation

Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly difficult and costly to obtain, especially in the medical imaging domain where only experts can provide reliable and accurate annotations. Semi-supervised learning has emerged as an appealing strategy and been widely applied to medical image segmentation tasks to train deep models with limited annotations. In this paper, we present a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarize both the technical novelties and empirical results. Furthermore, we analyze and discuss the limitations and several unsolved problems of existing approaches. We hope this review can inspire the research community to explore solutions to this challenge and further advance the field of medical image segmentation.

Segmentation of cardiac infarction in delayed-enhancement MRI using probability map and transformers-based neural networks

BACKGROUND AND OBJECTIVE

Automatic segmentation of myocardial infarction is of great clinical interest for the quantitative evaluation of myocardial infarction (MI). Late Gadolinium Enhancement cardiac MRI (LGE-MRI) is commonly used in clinical practice to quantify MI, which is crucial for clinical diagnosis and treatment of cardiac diseases. However, the segmentation of infarcted tissue in LGE-MRI is highly challenging due to its high anisotropy and inhomogeneities.

METHODS

The innovative aspect of our work lies in the utilization of a probability map of the healthy myocardium to guide the localization of infarction, as well as the combination of 2D U-Net and U-Net transformers to achieve the final segmentation. Instead of employing a binary segmentation map, we propose using a probability map of the normal myocardium, obtained through a dedicated 2D U-Net. To leverage spatial information, we employ a U-Net transformers network where we incorporate the probability map into the original image as an additional input. Then, To address the limitations of U-Net in segmenting accurately the contours, we introduce an adapted loss function.

RESULTS

Our method has been evaluated on the 2020 MICCAI EMIDEC challenge dataset, yielding competitive results. Specifically, we achieved a Dice score of 92.94% for the myocardium and 92.36% for the infarction. These outcomes highlight the competitiveness of our approach.

CONCLUSION

In the case of the infarction class, our proposed method outperforms state-of-the-art techniques across all metrics evaluated in the challenge, establishing its superior performance in infarction segmentation. This study further reinforces the importance of integrating a contour loss into the segmentation process.

Pixel-wise statistical analysis of myocardial injury in STEMI patients with delayed enhancement MRI

Objectives

Myocardial injury assessment from delayed enhancement magnetic resonance images is routinely limited to global descriptors such as size and transmurality. Statistical tools from computational anatomy can drastically improve this characterization, and refine the assessment of therapeutic procedures aiming at infarct size reduction. Based on these techniques, we propose a new characterization of myocardial injury up to the pixel resolution. We demonstrate it on the imaging data from the Minimalist Immediate Mechanical Intervention randomized clinical trial (MIMI: NCT01360242), which aimed at comparing immediate and delayed stenting in acute ST-Elevation Myocardial Infarction (STEMI) patients.

Methods

We analyzed 123 patients from the MIMI trial (62 ± 12 years, 98 male, 65 immediate 58 delayed stenting). Early and late enhancement images were transported onto a common geometry using techniques inspired by statistical atlases, allowing pixel-wise comparisons across population subgroups. A practical visualization of lesion patterns against specific clinical and therapeutic characteristics was also proposed using state-of-the-art dimensionality reduction.

Results

Infarct patterns were roughly comparable between the two treatments across the whole myocardium. Subtle but significant local differences were observed for the LCX and RCA territories with higher transmurality for delayed stenting at lateral and inferior/inferoseptal locations, respectively (15% and 23% of myocardial locations with a p-value <0.05, mainly in these regions). In contrast, global measurements were comparable for all territories (no statistically significant differences for all-except-one measurements before standardization / for all after standardization), although immediate stenting resulted in more subjects without reperfusion injury.

Conclusion

Our approach substantially empowers the analysis of lesion patterns with standardized comparisons up to the pixel resolution, and may reveal subtle differences not accessible with global observations. On the MIMI trial data as illustrative case, it confirmed its general conclusions regarding the lack of benefit of delayed stenting, but revealed subgroups differences thanks to the standardized and finer analysis scale.

Qureshi A, Li J, Mahmood T. On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

Uncertainty-guided mutual consistency learning for semi-supervised medical image segmentation

Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring expert-examined annotations and takes the advantage of unlabeled data which is much easier to acquire. Although consistency learning has been proven to be an effective approach by enforcing an invariance of predictions under different distributions, existing approaches cannot make full use of region-level shape constraint and boundary-level distance information from unlabeled data. In this paper, we propose a novel uncertainty-guided mutual consistency learning framework to effectively exploit unlabeled data by integrating intra-task consistency learning from up-to-date predictions for self-ensembling and cross-task consistency learning from task-level regularization to exploit geometric shape information. The framework is guided by the estimated segmentation uncertainty of models to select out relatively certain predictions for consistency learning, so as to effectively exploit more reliable information from unlabeled data. Experiments on two publicly available benchmark datasets showed that: (1) Our proposed method can achieve significant performance improvement by leveraging unlabeled data, with up to 4.13% and 9.82% in Dice coefficient compared to supervised baseline on left atrium segmentation and brain tumor segmentation, respectively. (2) Compared with other semi-supervised segmentation methods, our proposed method achieve better segmentation performance under the same backbone network and task settings on both datasets, demonstrating the effectiveness and robustness of our method and potential transferability for other medical image segmentation tasks.