SegAE: Unsupervised white matter lesion segmentation from brain MRIs using a CNN autoencoder

Exploring approaches to tackle cross-domain challenges in brain medical image segmentation: a systematic review

Introduction

Brain medical image segmentation is a critical task in medical image processing, playing a significant role in the prediction and diagnosis of diseases such as stroke, Alzheimer's disease, and brain tumors. However, substantial distribution discrepancies among datasets from different sources arise due to the large inter-site discrepancy among different scanners, imaging protocols, and populations. This leads to cross-domain problems in practical applications. In recent years, numerous studies have been conducted to address the cross-domain problem in brain image segmentation.

Methods

This review adheres to the standards of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) for data processing and analysis. We retrieved relevant papers from PubMed, Web of Science, and IEEE databases from January 2018 to December 2023, extracting information about the medical domain, imaging modalities, methods for addressing cross-domain issues, experimental designs, and datasets from the selected papers. Moreover, we compared the performance of methods in stroke lesion segmentation, white matter segmentation and brain tumor segmentation.

Results

A total of 71 studies were included and analyzed in this review. The methods for tackling the cross-domain problem include Transfer Learning, Normalization, Unsupervised Learning, Transformer models, and Convolutional Neural Networks (CNNs). On the ATLAS dataset, domain-adaptive methods showed an overall improvement of ~3 percent in stroke lesion segmentation tasks compared to non-adaptive methods. However, given the diversity of datasets and experimental methodologies in current studies based on the methods for white matter segmentation tasks in MICCAI 2017 and those for brain tumor segmentation tasks in BraTS, it is challenging to intuitively compare the strengths and weaknesses of these methods.

Conclusion

Although various techniques have been applied to address the cross-domain problem in brain image segmentation, there is currently a lack of unified dataset collections and experimental standards. For instance, many studies are still based on n-fold cross-validation, while methods directly based on cross-validation across sites or datasets are relatively scarce. Furthermore, due to the diverse types of medical images in the field of brain segmentation, it is not straightforward to make simple and intuitive comparisons of performance. These challenges need to be addressed in future research.

Semisupervised white matter hyperintensities segmentation on MRI

This study proposed a semisupervised loss function named level-set loss (LSLoss) for cerebral white matter hyperintensities (WMHs) segmentation on fluid-attenuated inversion recovery images. The training procedure did not require manually labeled WMH masks. Our image preprocessing steps included biased field correction, skull stripping, and white matter segmentation. With the proposed LSLoss, we trained a V-Net using the MRI images from both local and public databases. Local databases were the small vessel disease cohort (HKU-SVD, n = 360) and the multiple sclerosis cohort (HKU-MS, n = 20) from our institutional imaging center. Public databases were the Medical Image Computing Computer-assisted Intervention (MICCAI) WMH challenge database (MICCAI-WMH, n = 60) and the normal control cohort of the Alzheimer's Disease Neuroimaging Initiative database (ADNI-CN, n = 15). We achieved an overall dice similarity coefficient (DSC) of 0.81 on the HKU-SVD testing set (n = 20), DSC = 0.77 on the HKU-MS testing set (n = 5), and DSC = 0.78 on MICCAI-WMH testing set (n = 30). The segmentation results obtained by our semisupervised V-Net were comparable with the supervised methods and outperformed the unsupervised methods in the literature.

Deep learning based unpaired image-to-image translation applications for medical physics: a systematic review

Purpose. There is a growing number of publications on the application of unpaired image-to-image (I2I) translation in medical imaging. However, a systematic review covering the current state of this topic for medical physicists is lacking. The aim of this article is to provide a comprehensive review of current challenges and opportunities for medical physicists and engineers to apply I2I translation in practice.Methods and materials. The PubMed electronic database was searched using terms referring to unpaired (unsupervised), I2I translation, and medical imaging. This review has been reported in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. From each full-text article, we extracted information extracted regarding technical and clinical applications of methods, Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) study type, performance of algorithm and accessibility of source code and pre-trained models.Results. Among 461 unique records, 55 full-text articles were included in the review. The major technical applications described in the selected literature are segmentation (26 studies), unpaired domain adaptation (18 studies), and denoising (8 studies). In terms of clinical applications, unpaired I2I translation has been used for automatic contouring of regions of interest in MRI, CT, x-ray and ultrasound images, fast MRI or low dose CT imaging, CT or MRI only based radiotherapy planning, etc Only 5 studies validated their models using an independent test set and none were externally validated by independent researchers. Finally, 12 articles published their source code and only one study published their pre-trained models.Conclusion. I2I translation of medical images offers a range of valuable applications for medical physicists. However, the scarcity of external validation studies of I2I models and the shortage of publicly available pre-trained models limits the immediate applicability of the proposed methods in practice.

A joint ventricle and WMH segmentation from MRI for evaluation of healthy and pathological changes in the aging brain

Age-related changes in brain structure include atrophy of the brain parenchyma and white matter changes of presumed vascular origin. Enlargement of the ventricles may occur due to atrophy or impaired cerebrospinal fluid (CSF) circulation. The co-occurrence of these changes in neurodegenerative diseases and in aging brains often requires investigators to take both into account when studying the brain, however, automated segmentation of enlarged ventricles and white matter hyperintensities (WMHs) can be a challenging task. Here, we present a hybrid multi-atlas segmentation and convolutional autoencoder approach for joint ventricle parcellation and WMH segmentation from magnetic resonance images (MRIs). Our fully automated approach uses a convolutional autoencoder to generate a standardized image of grey matter, white matter, CSF, and WMHs, which, in conjunction with labels generated by a multi-atlas segmentation approach, is then fed into a convolutional neural network to parcellate the ventricular system. Hence, our approach does not depend on manually delineated training data for new data sets. The segmentation pipeline was validated on both healthy elderly subjects and subjects with normal pressure hydrocephalus using ground truth manual labels and compared with state-of-the-art segmentation methods. We then applied the method to a cohort of 2401 elderly brains to investigate associations of ventricle volume and WMH load with various demographics and clinical biomarkers, using a multiple regression model. Our results indicate that the ventricle volume and WMH load are both highly variable in a cohort of elderly subjects and there is an independent association between the two, which highlights the importance of taking both the possibility of enlarged ventricles and WMHs into account when studying the aging brain.

Intelligent Algorithm-Based Coronary Angiography Characteristics of Acute Non-ST-Segment Elevation Myocardial Infarction Patients with Different Genders

OBJECTIVE

This study was aimed at comparing the characteristics of coronary angiography based on intelligent algorithm in patients with acute non-ST-segment elevation myocardial infarction (NSTEMI) of different genders.

METHODS

Eighty patients were selected to segment the coronary angiogram using the convolutional neural network (CNN) algorithm, the input layer of the CNN was used to receive the image dataset, and three-dimensional data were input during semantic segmentation to achieve automatic segmentation of the target features. Segmentation results were quantitatively assessed by accuracy (Acc), sensitivity (Se), specificity (Sp), and Dice coefficient (Dice). The characteristics of coronary angiography were compared between the two groups.

RESULTS

The CNN algorithm had good segmentation effect, complete vessel extraction, and little noise, and Acc, Se, Sp, and Dice were 90.32%, 93.39%, 91.25%, and 89.75%, respectively. The proportion of diabetes mellitus was higher in female patients with NSTEMI (68.8%) than that in male patients (46.3%); the proportion of the left main coronary artery (LM) and left anterior descending artery (LAD) was lower in the female group (7.5%, 41.3%) than that in the male group (13.8%, 81.3%), and the difference between the two groups was statistically significant (P < 0.05).

CONCLUSION

The CNN algorithm achieves accurate extraction of vessels from coronary angiographic images, and women with diabetes and hyperlipidemia are more likely to have NSTEMI than men, especially the elderly.

Brain Tumor Segmentation Using Graph Coloring Approach in Magnetic Resonance Images

It is important to have an accurate and reliable brain tumor segmentation for cancer diagnosis and treatment planning. There are few unsupervised approaches for brain tumor segmentation. In this paper, a new unsupervised approach based on graph coloring for brain tumor segmentation is introduced. In this study, a graph coloring approach is used for brain tumor segmentation. For this aim, each pixel of brain image assumed as a node of graph and difference between brightness of a couple of pixels considered as edge. This method was applied on T1-enhanced magnetic resonance images of low-grade and high-grade patients. Since a rigid graph was needed for graph coloring, edges must be divided into existing or nonexisting edge using a threshold. The value of this threshold has affected the accuracy of image segmentation, so the choice of the optimal threshold was important. The optimal value for this threshold was 0.42 of maximum value of difference of brightness between pixels that caused the 83.62% of correlation accuracy. The results showed that graph coloring approach can be a reliable unsupervised approach for brain tumor segmentation. This approach, as an unsupervised approach, shows better accuracy in comparison with neural networks and neuro-fuzzy networks. However, as a limitation, the accuracy of this approach is dependent on the threshold of edges.

Diagnosis and Treatment Effect of Convolutional Neural Network-Based Magnetic Resonance Image Features on Severe Stroke and Mental State

The purpose of this paper is to explore the impact of magnetic resonance imaging (MRI) image features based on convolutional neural network (CNN) algorithm and conditional random field on the diagnosis and mental state of patients with severe stroke. 208 patients with severe stroke who all received MRI examination were recruited as the research objects. According to cerebral small vascular disease (CSVD) score, the patients were divided into CSVD 0∼4 groups. The patients who completed the three-month follow-up were classified into cognitive impairment group (124 cases) and the noncognitive impairment group (84 cases) according to the cut-off point of the Montreal cognitive assessment (MOCA) scale score of 26. A novel image segmentation algorithm was proposed based on U-shaped fully CNN (U-Net) and conditional random field, which was compared with the fully CNN (FCN) algorithm and U-Net algorithm, and was applied to the MRI segmentation training of patients with severe stroke. It was found that the average symmetric surface distance (ASSD) (3.13 ± 1.35), Hoffman distance (HD) (28.71 ± 9.05), Dice coefficient (0.78 ± 1.35), accuracy (0.74 ± 0.11), and sensitivity (0.85 ± 0.13) of the proposed algorithm were superior to those of FCN algorithm and U-Net algorithm. There were significant differences in the MOCA scores among the five groups of patients from CSVD 0 to CSVD 4 in the three time periods (0, 1, and 3 months) (P < 0.05). Differences in cerebral microhemorrhage (CMB), perivascular space (PVS), and number of cavities, Fazekas, and total CSVD scores between the two groups were significant (P < 0.05). Multivariate regression found that the number of PVS, white matter hyperintensity (WMH) Fazekas, and total CSVD score were independent factors of cognitive impairment. In short, MRI images based on deep learning image segmentation algorithm had good application value for clinical diagnosis and treatment of stroke and can effectively improve the detection effect of brain domain characteristics and psychological state of patients after stroke.

An anomaly detection approach to identify chronic brain infarcts on MRI

The performance of current machine learning methods to detect heterogeneous pathology is limited by the quantity and quality of pathology in medical images. A possible solution is anomaly detection; an approach that can detect all abnormalities by learning how 'normal' tissue looks like. In this work, we propose an anomaly detection method using a neural network architecture for the detection of chronic brain infarcts on brain MR images. The neural network was trained to learn the visual appearance of normal appearing brains of 697 patients. We evaluated its performance on the detection of chronic brain infarcts in 225 patients, which were previously labeled. Our proposed method detected 374 chronic brain infarcts (68% of the total amount of brain infarcts) which represented 97.5% of the total infarct volume. Additionally, 26 new brain infarcts were identified that were originally missed by the radiologist during radiological reading. Our proposed method also detected white matter hyperintensities, anomalous calcifications, and imaging artefacts. This work shows that anomaly detection is a powerful approach for the detection of multiple brain abnormalities, and can potentially be used to improve the radiological workflow efficiency by guiding radiologists to brain anomalies which otherwise remain unnoticed.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Identification of White Matter Lesions in Patients With Acute Ischemic Lesions Using U-net

Background: White matter lesions (WML) have been proved to be significantly associated with many brain diseases. Precise evaluation of burden of WML at early stage could provide insights in the prognosis and assist in intervention. However, acute ischemic lesions (AIL) exhibit hyperintensities on FLAIR images either, and are detected by diffusion weighted imaging (DWI). It is challenging to identify and segment WML in the patients with WML and AIL. Convolutional neural network (CNN) based architecture has been validated as an efficient tool for automatic segmentation. This study aimed to evaluate the performance of U-net in evaluation of WML in the patients with WML and AIL.

Methods: A total of 208 cases from Chinese Atherosclerosis Risk Evaluation (CARE II) study were recruited in the present study. All subjects underwent imaging of FLAIR and DWI on 3.0 Tesla scanners. The contours of WML delineated by the observer and its scores rated by the observer were considered as gold standard. Among all 208 cases, 108 were randomly selected as train set, and the remaining 100 cases were used as test set. The performance of lesion segmentation toolbox (LST) and three U-net models were evaluated on three levels: pixel, lesion, and subject levels. The performance of all methods in WML identification and segmentation was also evaluated among the cases with different lesion volumes and between the cases with and without AIL.

Results: All U-net models outperformed LST on pixel, lesion, and subject levels, while no differences were found among three U-net models. All segmentation methods performed best in the cases with WML volume (WMLV) > 20 ml but worst in those with WMLV < 5 ml. In addition, all methods showed similar performance between the cases with and without AIL. The scores determined by U-net exhibited a strong correlation with the gold standard (all Spearman correlation coefficients >0.89, ICCs >0.88, p-values <0.001).

Conclusion: U-net performs well on identification and segmentation of WML in the patients with WML and AIL. The performance of U-net is validated by a dataset of multicenter study. Our results indicate that U-net has an advantage in assessing the burden of WML in the patients suffered from both WML and AIL.

Common misconceptions, hidden biases and modern challenges of dMRI tractography

The human brain is a complex and organized network, where the connection between regions is not achieved with single axons crisscrossing each other but rather millions of densely packed and well-ordered axons. Reconstruction from diffusion MRI tractography is only an attempt to capture the full complexity of this network, at the macroscale. This review provides an overview of the misconceptions, biases and pitfalls present in structural white matter bundle and connectome reconstruction using tractography. The goal is not to discourage readers, but rather to inform them of the limitations present in the methods used by researchers in the field in order to focus on what they can do and promote proper interpretations of their results. It also provides a list of open problems that could be solved in future research projects for the next generation of PhD students.