Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture

Machine learning fusion for glioma tumor detection

The early detection of brain tumors is very important for treating them and improving the quality of life for patients. Through advanced imaging techniques, doctors can now make more informed decisions. This paper introduces a framework for a tumor detection system capable of grading gliomas. The system's implementation begins with the acquisition and analysis of brain magnetic resonance images. Key features indicative of tumors and gliomas are extracted and classified as independent components. A deep learning model is then employed to categorize these gliomas. The proposed model classifies gliomas into three primary categories: meningioma, pituitary, and glioma. Performance evaluation demonstrates a high level of accuracy (99.21%), specificity (98.3%), and sensitivity (97.83%). Further research and validation are essential to refine the system and ensure its clinical applicability. The development of accurate and efficient tumor detection systems holds significant promise for enhancing patient care and improving survival rates.

Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches

Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.

A Deep Learning-based Pipeline for Segmenting the Cerebral Cortex Laminar Structure in Histology Images

Characterizing the anatomical structure and connectivity between cortical regions is a critical step towards understanding the information processing properties of the brain and will help provide insight into the nature of neurological disorders. A key feature of the mammalian cerebral cortex is its laminar structure. Identifying these layers in neuroimaging data is important for understanding their global structure and to help understand the connectivity patterns of neurons in the brain. We studied Nissl-stained and myelin-stained slice images of the brain of the common marmoset (Callithrix jacchus), which is a new world monkey that is becoming increasingly popular in the neuroscience community as an object of study. We present a novel computational framework that first acquired the cortical labels using AI-based tools followed by a trained deep learning model to segment cerebral cortical layers. We obtained a Euclidean distance of 1274.750 ± 156.400 μ m for the cortical labels acquisition, which was in the acceptable range by computing the half Euclidean distance of the average cortex thickness ( 1800.630 μ m ). We compared our cortical layer segmentation pipeline with the pipeline proposed by Wagstyl et al. (PLoS biology, 18(4), e3000678 2020) adapted to 2D data. We obtained a better mean95 th percentile Hausdorff distance (95HD) of  92.150 μ m . Whereas a mean 95HD of  94.170 μ m was obtained from Wagstyl et al. We also compared our pipeline's performance against theirs using their dataset (the BigBrain dataset). The results also showed better segmentation quality, 85.318 % Jaccard Index acquired from our pipeline, while 83.000 % was stated in their paper.

Prediction of prognosis in glioblastoma with radiomics features extracted by synthetic MRI images using cycle-consistent GAN

To propose a style transfer model for multi-contrast magnetic resonance imaging (MRI) images with a cycle-consistent generative adversarial network (CycleGAN) and evaluate the image quality and prognosis prediction performance for glioblastoma (GBM) patients from the extracted radiomics features. Style transfer models of T1 weighted MRI image (T1w) to T2 weighted MRI image (T2w) and T2w to T1w with CycleGAN were constructed using the BraTS dataset. The style transfer model was validated with the Cancer Genome Atlas Glioblastoma Multiforme (TCGA-GBM) dataset. Moreover, imaging features were extracted from real and synthesized images. These features were transformed to rad-scores by the least absolute shrinkage and selection operator (LASSO)-Cox regression. The prognosis performance was estimated by the Kaplan-Meier method. For the accuracy of the image quality of the real and synthesized MRI images, the MI, RMSE, PSNR, and SSIM were 0.991 ± 2.10 × 10 - 4 , 2.79 ± 0.16, 40.16 ± 0.38, and 0.995 ± 2.11 × 10 - 4 , for T2w, and .992 ± 2.63 × 10 - 4 , 2.49 ± 6.89 × 10 - 2 , 40.51 ± 0.22, and 0.993 ± 3.40 × 10 - 4 for T1w, respectively. The survival time had a significant difference between good and poor prognosis groups for both real and synthesized T2w (p < 0.05). However, the survival time had no significant difference between good and poor prognosis groups for both real and synthesized T1w. On the other hand, there was no significant difference between the real and synthesized T2w in both good and poor prognoses. The results of T1w were similar in the point that there was no significant difference between the real and synthesized T1w. It was found that the synthesized image could be used for prognosis prediction. The proposed prognostic model using CycleGAN could reduce the cost and time of image scanning, leading to a promotion to build the patient's outcome prediction with multi-contrast images.

Improved robustness for deep learning-based segmentation of multi-center myocardial perfusion cardiovascular MRI datasets using data-adaptive uncertainty-guided space-time analysis

BACKGROUND

Fully automatic analysis of myocardial perfusion cardiovascular magnetic resonance imaging datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge.

METHODS

Datasets from three medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed data-adaptive uncertainty-guided space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).

RESULTS

The proposed DAUGS analysis approach performed similarly to the established approach on the inD (Dice score for the testing subset of inD: 0.896 ± 0.050 vs 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the exDs (Dice for exD-1: 0.885 ± 0.040 vs 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs the established approach (4.3% vs 17.1%, p < 0.0005).

CONCLUSION

The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location, or scanner vendor.

Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis

Background

Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge.

Methods

Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.).

Results

The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005).

Conclusions

The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.

Whole Spine Segmentation Using Object Detection and Semantic Segmentation

OBJECTIVE

Virtual and augmented reality have enjoyed increased attention in spine surgery. Preoperative planning, pedicle screw placement, and surgical training are among the most studied use cases. Identifying osseous structures is a key aspect of navigating a 3-dimensional virtual reconstruction. To automate the otherwise time-consuming process of labeling vertebrae on each slice individually, we propose a fully automated pipeline that automates segmentation on computed tomography (CT) and which can form the basis for further virtual or augmented reality application and radiomic analysis.

METHODS

Based on a large public dataset of annotated vertebral CT scans, we first trained a YOLOv8m (You-Only-Look-Once algorithm, Version 8 and size medium) to detect each vertebra individually. On the then cropped images, a 2D-U-Net was developed and externally validated on 2 different public datasets.

RESULTS

Two hundred fourteen CT scans (cervical, thoracic, or lumbar spine) were used for model training, and 40 scans were used for external validation. Vertebra recognition achieved a mAP50 (mean average precision with Jaccard threshold of 0.5) of over 0.84, and the segmentation algorithm attained a mean Dice score of 0.75 ± 0.14 at internal, 0.77 ± 0.12 and 0.82 ± 0.14 at external validation, respectively.

CONCLUSION

We propose a 2-stage approach consisting of single vertebra labeling by an object detection algorithm followed by semantic segmentation. In our externally validated pilot study, we demonstrate robust performance for our object detection network in identifying individual vertebrae, as well as for our segmentation model in precisely delineating the bony structures.

Intra- and Inter-expert Validation of an Automatic Segmentation Method for Fluid Regions Associated with Central Serous Chorioretinopathy in OCT Images

Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of 0.868 ± 0.056 in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method.

M-DDC: MRI based demyelinative diseases classification with U-Net segmentation and convolutional network

Childhood demyelinative diseases classification (DDC) with brain magnetic resonance imaging (MRI) is crucial to clinical diagnosis. But few attentions have been paid to DDC in the past. How to accurately differentiate pediatric-onset neuromyelitis optica spectrum disorder (NMOSD) from acute disseminated encephalomyelitis (ADEM) based on MRI is challenging in DDC. In this paper, a novel architecture M-DDC based on joint U-Net segmentation network and deep convolutional network is developed. The U-Net segmentation can provide pixel-level structure information, that helps the lesion areas location and size estimation. The classification branch in DDC can detect the regions of interest inside MRIs, including the white matter regions where lesions appear. The performance of the proposed method is evaluated on MRIs of 201 subjects recorded from the Children's Hospital of Zhejiang University School of Medicine. The comparisons show that the proposed DDC achieves the highest accuracy of 99.19% and dice of 71.1% for ADEM and NMOSD classification and segmentation, respectively.

Deep learning techniques for isointense infant brain tissue segmentation: a systematic literature review

Introduction

To improve comprehension of initial brain growth in wellness along with sickness, it is essential to precisely segment child brain magnetic resonance imaging (MRI) into white matter (WM) and gray matter (GM), along with cerebrospinal fluid (CSF). Nonetheless, in the isointense phase (6-8 months of age), the inborn myelination and development activities, WM along with GM display alike stages of intensity in both T1-weighted and T2-weighted MRI, making tissue segmentation extremely difficult.

Methods

The comprehensive review of studies related to isointense brain MRI segmentation approaches is highlighted in this publication. The main aim and contribution of this study is to aid researchers by providing a thorough review to make their search for isointense brain MRI segmentation easier. The systematic literature review is performed from four points of reference: (1) review of studies concerning isointense brain MRI segmentation; (2) research contribution and future works and limitations; (3) frequently applied evaluation metrics and datasets; (4) findings of this studies.

Results and discussion

The systemic review is performed on studies that were published in the period of 2012 to 2022. A total of 19 primary studies of isointense brain MRI segmentation were selected to report the research question stated in this review.

Paving the path toward multi-omics approaches in the diagnostic challenges faced in thyroid pathology

INTRODUCTION

Despite advancements in diagnostic methods, the classification of indeterminate thyroid nodules still poses diagnostic challenges not only in pre-surgical evaluation but even after histological evaluation of surgical specimens. Proteomics, aided by mass spectrometry and integrated with artificial intelligence and machine learning algorithms, shows great promise in identifying diagnostic markers for thyroid lesions.

AREAS COVERED

This review provides in-depth exploration of how proteomics has contributed to the understanding of thyroid pathology. It discusses the technical advancements related to immunohistochemistry, genetic and proteomic techniques, such as mass spectrometry, which have greatly improved sensitivity and spatial resolution up to single-cell level. These improvements allowed the identification of specific protein signatures associated with different types of thyroid lesions.

EXPERT COMMENTARY

Among all the proteomics approaches, spatial proteomics stands out due to its unique ability to capture the spatial context of proteins in both cytological and tissue thyroid samples. The integration of multi-layers of molecular information combining spatial proteomics, genomics, immunohistochemistry or metabolomics and the implementation of artificial intelligence and machine learning approaches, represent hugely promising steps forward toward the possibility to uncover intricate relationships and interactions among various molecular components, providing a complete picture of the biological landscape whilst fostering thyroid nodule diagnosis.

A novel Gateaux derivatives with efficient DCNN-Resunet method for segmenting multi-class brain tumor

In hospitals and pathology, observing the features and locations of brain tumors in Magnetic Resonance Images (MRI) is a crucial task for assisting medical professionals in both treatment and diagnosis. The multi-class information about the brain tumor is often obtained from the patient's MRI dataset. However, this information may vary in different shapes and sizes for various brain tumors, making it difficult to detect their locations in the brain. To resolve these issues, a novel customized Deep Convolution Neural Network (DCNN) based Residual-Unet (ResUnet) model with Transfer Learning (TL) is proposed for predicting the locations of the brain tumor in an MRI dataset. The DCNN model has been used to extract the features from input images and select the Region Of Interest (ROI) by using the TL technique for training it faster. Furthermore, the min-max normalizing approach is used to enhance the color intensity value for particular ROI boundary edges in the brain tumor images. Specifically, the boundary edges of the brain tumors have been detected by utilizing Gateaux Derivatives (GD) method to identify the multi-class brain tumors precisely. The proposed scheme has been validated on two datasets namely the brain tumor, and Figshare MRI datasets for detecting multi-class Brain Tumor Segmentation (BTS).The experimental results have been analyzed by evaluation metrics namely, accuracy (99.78, and 99.03), Jaccard Coefficient (93.04, and 94.95), Dice Factor Coefficient (DFC) (92.37, and 91.94), Mean Absolute Error (MAE) (0.0019, and 0.0013), and Mean Squared Error (MSE) (0.0085, and 0.0012) for proper validation. The proposed system outperforms the state-of-the-art segmentation models on the MRI brain tumor dataset.

CNN-based fully automatic wrist cartilage volume quantification in MR images: A comparative analysis between different CNN architectures

PURPOSE

Automatic measurement of wrist cartilage volume in MR images.

METHODS

We assessed the performance of four manually optimized variants of the U-Net architecture, nnU-Net and Mask R-CNN frameworks for the segmentation of wrist cartilage. The results were compared to those from a patch-based convolutional neural network (CNN) we previously designed. The segmentation quality was assessed on the basis of a comparative analysis with manual segmentation. The best networks were compared using a cross-validation approach on a dataset of 33 3D VIBE images of mostly healthy volunteers. Influence of some image parameters on the segmentation reproducibility was assessed.

RESULTS

The U-Net-based networks outperformed the patch-based CNN in terms of segmentation homogeneity and quality, while Mask R-CNN did not show an acceptable performance. The median 3D DSC value computed with the U-Net_AL (0.817) was significantly larger than DSC values computed with the other networks. In addition, the U-Net_AL provided the lowest mean volume error (17%) and the highest Pearson correlation coefficient (0.765) with respect to the ground truth values. Of interest, the reproducibility computed using U-Net_AL was larger than the reproducibility of the manual segmentation. Moreover, the results indicate that the MRI-based wrist cartilage volume is strongly affected by the image resolution.

CONCLUSIONS

U-Net CNN with attention layers provided the best wrist cartilage segmentation performance. In order to be used in clinical conditions, the trained network can be fine-tuned on a dataset representing a group of specific patients. The error of cartilage volume measurement should be assessed independently using a non-MRI method.

Automatic Detection of Alzheimer's Disease using Deep Learning Models and Neuro-Imaging: Current Trends and Future Perspectives

Deep learning algorithms have a huge influence on tackling research issues in the field of medical image processing. It acts as a vital aid for the radiologists in producing accurate results toward effective disease diagnosis. The objective of this research is to highlight the importance of deep learning models in the detection of Alzheimer's Disease (AD). The main objective of this research is to analyze different deep learning methods used for detecting AD. This study examines 103 research articles published in various research databases. These articles have been selected based on specific criteria to find the most relevant findings in the field of AD detection. The review was carried out based on deep learning techniques such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transfer Learning (TL). To propose accurate methods for the detection, segmentation, and severity grading of AD, the radiological features need to be examined in greater depth. This review attempts to analyze different deep learning methods applied for AD detection using neuroimaging modalities like Positron Emission Tomography (PET), Magnetic Resonance Imaging (MRI), etc. The focus of this review is restricted to deep learning works based on radiological imaging data for AD detection. There are a few works that have utilized other biomarkers to understand the effect of AD. Also, articles published in English were alone considered for analysis. This work concludes by highlighting the key research issues towards effective AD detection. Though several methods have yielded promising results in AD detection, the progression from Mild Cognitive Impairment (MCI) to AD need to be analyzed in greater depth using DL models.

Artificial Intelligence-Assisted Evaluation of the Spatial Relationship between Brain Arteriovenous Malformations and the Corticospinal Tract to Predict Postsurgical Motor Defects

BACKGROUND AND PURPOSE

Preoperative evaluation of brain AVMs is crucial for the selection of surgical candidates. Our goal was to use artificial intelligence to predict postsurgical motor defects in patients with brain AVMs involving motor-related areas.

MATERIALS AND METHODS

Eighty-three patients who underwent microsurgical resection of brain AVMs involving motor-related areas were retrospectively reviewed. Four artificial intelligence-based indicators were calculated with artificial intelligence on TOF-MRA and DTI, including FN5mm/50mm (the proportion of fiber numbers within 5-50mm from the lesion border), FN10mm/50mm (the same but within 10-50mm), FP5mm/50mm (the proportion of fiber voxel points within 5-50mm from the lesion border), and FP10mm/50mm (the same but within 10-50mm). The association between the variables and long-term postsurgical motor defects was analyzed using univariate and multivariate analyses. Least absolute shrinkage and selection operator regression with the Pearson correlation coefficient was used to select the optimal features to develop the machine learning model to predict postsurgical motor defects. The area under the curve was calculated to evaluate the predictive performance.

RESULTS

In patients with and without postsurgical motor defects, the mean FN5mm/50mm, FN10mm/50mm, FP5mm/50mm, and FP10mm/50mm were 0.24 (SD, 0.24) and 0.03 (SD, 0.06), 0.37 (SD, 0.27) and 0.06 (SD, 0.08), 0.06 (SD, 0.10) and 0.01 (SD, 0.02), and 0.10 (SD, 0.12) and 0.02 (SD, 0.05), respectively. Univariate and multivariate logistic analyses identified FN10mm/50mm as an independent risk factor for long-term postsurgical motor defects (P = .002). FN10mm/50mm achieved a mean area under the curve of 0.86 (SD, 0.08). The mean area under the curve of the machine learning model consisting of FN10mm/50mm, diffuseness, and the Spetzler-Martin score was 0.88 (SD, 0.07).

CONCLUSIONS

The artificial intelligence-based indicator, FN10mm/50mm, can reflect the lesion-fiber spatial relationship and act as a dominant predictor for postsurgical motor defects in patients with brain AVMs involving motor-related areas.

Machine Learning-Enabled Determination of Diffuseness of Brain Arteriovenous Malformations from Magnetic Resonance Angiography

The diffuseness of brain arteriovenous malformations (bAVMs) is a significant factor in surgical outcome evaluation and hemorrhagic risk prediction. However, there are still predicaments in identifying diffuseness, such as the judging variety resulting from different experience and difficulties in quantification. The purpose of this study was to develop a machine learning (ML) model to automatically identify the diffuseness of bAVM niduses using three-dimensional (3D) time-of-flight magnetic resonance angiography (TOF-MRA) images. A total of 635 patients with bAVMs who underwent TOF-MRA imaging were enrolled. Three experienced neuroradiologists delineated the bAVM lesions and identified the diffuseness on TOF-MRA images, which were considered the ground-truth reference. The U-Net-based segmentation model was trained to segment lesion areas. Eight mainstream ML models were trained through the radiomic features of segmented lesions to identify diffuseness, based on which an integrated model was built and yielded the best performance. In the test set, the Dice score, F2 score, precision, and recall for the segmentation model were 0.80 [0.72-0.84], 0.80 [0.71-0.86], 0.84 [0.77-0.93], and 0.82 [0.69-0.89], respectively. For the diffuseness identification model, the ensemble-based model was applied with an area under the Receiver-operating characteristic curves (AUC) of 0.93 (95% CI 0.87-0.99) in the training set. The AUC, accuracy, precision, recall, and F1 score for the diffuseness identification model were 0.95, 0.90, 0.81, 0.84, and 0.83, respectively, in the test set. The ML models showed good performance in automatically detecting bAVM lesions and identifying diffuseness. The method may help to judge the diffuseness of bAVMs objectively, quantificationally, and efficiently.

DeepACSA: Automatic Segmentation of Cross-Sectional Area in Ultrasound Images of Lower Limb Muscles Using Deep Learning

PURPOSE

Muscle anatomical cross-sectional area (ACSA) can be assessed using ultrasound and images are usually evaluated manually. Here, we present DeepACSA, a deep learning approach to automatically segment ACSA in panoramic ultrasound images of the human rectus femoris (RF), vastus lateralis (VL), gastrocnemius medialis (GM) and lateralis (GL) muscles.

METHODS

We trained three muscle-specific convolutional neural networks (CNN) using 1772 ultrasound images from 153 participants (age = 38.2 yr, range = 13-78). Images were acquired in 10% increments from 30% to 70% of femur length for RF and VL and at 30% and 50% of muscle length for GM and GL. During training, CNN performance was evaluated using intersection-over-union scores. We compared the performance of DeepACSA to manual analysis and a semiautomated algorithm using an unseen test set.

RESULTS

Comparing DeepACSA analysis of the RF to manual analysis with erroneous predictions removed (3.3%) resulted in intraclass correlation (ICC) of 0.989 (95% confidence interval = 0.983-0.992), mean difference of 0.20 cm 2 (0.10-0.30), and SEM of 0.33 cm 2 (0.26-0.41). For the VL, ICC was 0.97 (0.96-0.968), mean difference was 0.85 cm 2 (-0.4 to 1.31), and SEM was 0.92 cm 2 (0.73-1.09) after removal of erroneous predictions (7.7%). After removal of erroneous predictions (12.3%), GM/GL muscles demonstrated an ICC of 0.98 (0.96-0.99), a mean difference of 0.43 cm 2 (0.21-0.65), and an SEM of 0.41 cm 2 (0.29-0.51). Analysis duration was 4.0 ± 0.43 s (mean ± SD) for analysis of one image in our test set using DeepACSA.

CONCLUSIONS

DeepACSA provides fast and objective segmentation of lower limb panoramic ultrasound images comparable with manual segmentation. Inaccurate model predictions occurred predominantly on low-quality images, highlighting the importance of high-quality image for accurate prediction.

Improving across-dataset brain tissue segmentation for MRI imaging using transformer

Brain tissue segmentation has demonstrated great utility in quantifying MRI data by serving as a precursor to further post-processing analysis. However, manual segmentation is highly labor-intensive, and automated approaches, including convolutional neural networks (CNNs), have struggled to generalize well due to properties inherent to MRI acquisition, leaving a great need for an effective segmentation tool. This study introduces a novel CNN-Transformer hybrid architecture designed to improve brain tissue segmentation by taking advantage of the increased performance and generality conferred by Transformers for 3D medical image segmentation tasks. We first demonstrate the superior performance of our model on various T1w MRI datasets. Then, we rigorously validate our model's generality applied across four multi-site T1w MRI datasets, covering different vendors, field strengths, scan parameters, and neuropsychiatric conditions. Finally, we highlight the reliability of our model on test-retest scans taken in different time points. In all situations, our model achieved the greatest generality and reliability compared to the benchmarks. As such, our method is inherently robust and can serve as a valuable tool for brain related T1w MRI studies. The code for the TABS network is available at: https://github.com/raovish6/TABS.

Virtual CT Myelography: A Patch-Based Machine Learning Model to Improve Intraspinal Soft Tissue Visualization on Unenhanced Dual-Energy Lumbar Spine CT

Background: Distinguishing between the spinal cord and cerebrospinal fluid (CSF) non-invasively on CT is challenging due to their similar mass densities. We hypothesize that patch-based machine learning applied to dual-energy CT can accurately distinguish CSF from neural or other tissues based on the center voxel and neighboring voxels. Methods: 88 regions of interest (ROIs) from 12 patients’ dual-energy (100 and 140 kVp) lumbar spine CT exams were manually labeled by a neuroradiologist as one of 4 major tissue types (water, fat, bone, and nonspecific soft tissue). Four-class classifier convolutional neural networks were trained, validated, and tested on thousands of nonoverlapping patches extracted from 82 ROIs among 11 CT exams, with each patch representing pixel values (at low and high energies) of small, rectangular, 3D CT volumes. Different patch sizes were evaluated, ranging from 3 × 3 × 3 × 2 to 7 × 7 × 7 × 2. A final ensemble model incorporating all patch sizes was tested on patches extracted from six ROIs in a holdout patient. Results: Individual models showed overall test accuracies ranging from 99.8% for 3 × 3 × 3 × 2 patches (N = 19,423) to 98.1% for 7 × 7 × 7 × 2 patches (N = 1298). The final ensemble model showed 99.4% test classification accuracy, with sensitivities and specificities of 90% and 99.6%, respectively, for the water class and 98.6% and 100% for the soft tissue class. Conclusions: Convolutional neural networks utilizing local low-level features on dual-energy spine CT can yield accurate tissue classification and enhance the visualization of intraspinal neural tissue.

SIP-UNet: Sequential Inputs Parallel UNet Architecture for Segmentation of Brain Tissues from Magnetic Resonance Images

Proper analysis of changes in brain structure can lead to a more accurate diagnosis of specific brain disorders. The accuracy of segmentation is crucial for quantifying changes in brain structure. In recent studies, UNet-based architectures have outperformed other deep learning architectures in biomedical image segmentation. However, improving segmentation accuracy is challenging due to the low resolution of medical images and insufficient data. In this study, we present a novel architecture that combines three parallel UNets using a residual network. This architecture improves upon the baseline methods in three ways. First, instead of using a single image as input, we use three consecutive images. This gives our model the freedom to learn from neighboring images as well. Additionally, the images are individually compressed and decompressed using three different UNets, which prevents the model from merging the features of the images. Finally, following the residual network architecture, the outputs of the UNets are combined in such a way that the features of the image corresponding to the output are enhanced by a skip connection. The proposed architecture performed better than using a single conventional UNet and other UNet variants.

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeeze-expand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers' extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation.

A fully automatic deep learning algorithm to segment rectal Cancer on MR images: a multi-center study

The aim of the study is to present and tune a fully automatic deep learning algorithm to segment colorectal cancers (CRC) on MR images, based on a U-Net structure. It is a multicenter study, including 3 different Italian institutions, that used 4 different MRI scanners. Two of them were used for training and tuning the systems, while the other two for the validation. The implemented algorithm consists of a pre-processing step to normalize and to highlight the tumoral area, followed by the CRC segmentation using different U-net structures. Automatic masks were compared with manual segmentations performed by three experienced radiologists, one at each center. The two best performing systems (called mdl2 and mdl3), obtained a median Dice Similarity Coefficient of 0.68(mdl2) - 0.69(mdl3), precision of 0.75(md/2) - 0.71(md/3), and recall of 0.69(mdl2) - 0.73(mdl3) on the validation set. Both systems reached high detection rates, 0.98 and 0.95, respectively, on the validation set. These encouraging results, if confirmed on larger dataset, might improve the management of patients with CRC, since it can be used as a fast and precise tool for further radiomics analyses. Clinical Relevance - To provide a reliable tool able to automatically segment CRC tumors that can be used as first step in future radiomics studies aimed at predicting response to chemotherapy and personalizing treatment.

Using patching asymmetric regions to assess ischemic stroke lesion in neuro imaging

Ischemic stroke is a universal ailment that endangers the life of patients and makes them bedridden until death. Over a decade, doctors and radiologists have been dissecting patient status straightforwardly from the printouts of the slice images delivered by different diagnostic imaging modalities. Computed Tomography (CT) is a frequently used imaging strategy for therapeutic analysis and neuroanatomical investigations. The main objective of the paper is to develop a simple technique with less architectural complication and power consumption. The proposed work is to section the ischemic stroke lesion more efficiently from multi-succession CT images using patching the asymmetric region. The Hough transform segment and extracts the features from the asymmetric region of the CT image and finally, the random forest is implemented to classify the unusual tissues from the CT image dependent on their pathological properties. RF classifier has been trained for different parts of the cerebrum for fragmenting the stroke lesion. The acquired outcomes produce better segmentation accuracy when compared with different strategies. The overall efficiency of the proposed method determines the Ischemic stroke with an accuracy of 95% with an RF classifier. Hence this method can be used in the segmentation process of stroke lesions.

A Precise Medical Imaging Approach for Brain MRI Image Classification

Magnetic resonance imaging (MRI) is an accurate and noninvasive method employed for the diagnosis of various kinds of diseases in medical imaging. Most of the existing systems showed significant performances on small MRI datasets, while their performances decrease against large MRI datasets. Hence, the goal was to design an efficient and robust classification system that sustains a high recognition rate against large MRI dataset. Accordingly, in this study, we have proposed the usage of a novel feature extraction technique that has the ability to extract and select the prominent feature from MRI image. The proposed algorithm selects the best features from the MRI images of various diseases. Further, this approach discriminates various classes based on recursive values such as partial Z-value. The proposed approach only extracts a minor feature set through, respectively, forward and backward recursion models. The most interrelated features are nominated in the forward regression model that depends on the values of partial Z-test, while the minimum interrelated features are diminished from the corresponding feature space under the presence of the backward model. In both cases, the values of Z-test are estimated through the defined labels of the diseases. The proposed model is efficiently looking the localized features, which is one of the benefits of this method. After extracting and selecting the best features, the model is trained by utilizing support vector machine (SVM) to provide the predicted labels to the corresponding MRI images. To show the significance of the proposed model, we utilized a publicly available standard dataset such as Harvard Medical School and Open Access Series of Imaging Studies (OASIS), which contains 24 various brain diseases including normal. The proposed approach achieved the best classification accuracy against existing state-of-the-art systems.

BrainSec: Automated Brain Tissue Segmentation Pipeline for Scalable Neuropathological Analysis

As neurodegenerative disease pathological hallmarks have been reported in both grey matter (GM) and white matter (WM) with different density distributions, automating the segmentation process of GM/WM would be extremely advantageous for aiding in neuropathologic deep phenotyping. Standard segmentation methods typically involve manual annotations, where a trained researcher traces the delineation of GM/WM in ultra-high-resolution Whole Slide Images (WSIs). This method can be time-consuming and subjective, preventing a scalable analysis on pathology images. This paper proposes an automated segmentation pipeline (BrainSec) combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues. The final output generates XML annotations that can be visualized via Aperio ImageScope. First, we investigate two baseline models for medical image segmentation: FCN, and U-Net. Then we propose a patch-based approach, BrainSec, to classify the GM/WM/background regions. We demonstrate BrainSec is robust and has reliable performance by testing it on over 180 WSIs that incorporate numerous unique cases as well as distinct neuroanatomic brain regions. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide relevant explanations and insights. In addition, we have integrated BrainSec with an existing Amyloid-β pathology classification model into a unified framework (without incurring significant computation complexity) to identify pathologies, visualize their distributions, and quantify each type of pathologies in segmented GM/WM regions, respectively.

Effect of Different Nursing Interventions on Discharged Patients with Cardiac Valve Replacement Evaluated by Deep Learning Algorithm-Based MRI Information

This study was aimed to explore the application of cardiac magnetic resonance imaging (MRI) image segmentation model based on U-Net in the diagnosis of a valvular heart disease. The effect of continuous nursing on the survival of discharged patients with cardiac valve replacement was analyzed in this study. In this study, the filling completion operation, cross entropy loss function, and guidance unit were introduced and optimized based on the U-Net network. The heart MRI image segmentation model ML-Net was established. We compared the Dice, Hausdorff distance (HD), and percentage of area difference (PAD) values between ML-Net and other algorithms. The MRI image features of 82 patients with valvular heart disease who underwent cardiac valve replacement were analyzed. According to different nursing methods, they were randomly divided into the control group (routine nursing) and the intervention group (continuous nursing), with 41 cases in each group. The Glasgow Outcome Scale (GOS) score and the Self-rating Anxiety Scale (SAS) were compared between the two groups to assess the degree of anxiety of patients and the survival status at 6 months, 1 year, 2 years, and 3 years after discharge. The results showed that the Dice coefficient, HD, and PAD of the ML-Net algorithm were (0.896 ± 0.071), (5.66 ± 0.45) mm, and (15.34 ± 1.22) %, respectively. The Dice, HD, and PAD values of the ML-Net algorithm were all statistically different from those of the convolutional neural networks (CNN), fully convolutional networks (FCN), SegNet, and U-Net algorithms (P < 0.05). Atrial, ventricular, and aortic abnormalities can be seen in MRI images of patients with valvular heart disease. The cardiac blood flow signal will also be abnormal. The GOS score of the intervention group was significantly higher than that of the control group (P < 0.01). The SAS score was lower than that of the control group (P < 0.05). The survival rates of patients with valvular heart disease at 6 months, 1 year, 2 years, and 3 years after discharge were significantly higher than those in the control group (P < 0.05). The abovementioned results showed that an effective segmentation model for cardiac MRI images was established in this study. Continuous nursing played an important role in the postoperative recovery of discharged patients after cardiac valve replacement. This study provided a reference value for the diagnosis and prognosis of valvular heart disease.

Artificial Intelligence Algorithm-Based Lumbar and Spinal MRI for Evaluation of Efficacy of Chinkuei Shin Chewan Decoction on Lumbar Spinal Stenosis

The study aimed to explore the application value of lumbar Magnetic Resonance Imaging (MRI) images processed by artificial intelligence algorithms in evaluating the efficacy of chinkuei shin chewan decoction (a traditional Chinese medicine to nourish the kidney) in the treatment of lumbar spinal stenosis (LSS). Specifically, 110 LSS patients admitted to the hospital were selected as the research subjects. They were randomly divided into the control group (n = 55) and experimental group (n = 55) according to different treatment methods. The control group was treated with traditional medicine, and the experimental group additionally took chinkuei shin chewan decoction on its basis. Based on the traditional U-net algorithm, a U-net registration algorithm based on artificial intelligence was designed by introducing the information entropy theory, and the algorithm was applied to the lumbar MRI image evaluation of LSS patients. Compared with the traditional U-net algorithm, the artificial intelligence-based U-net registration algorithm had a decreased noise level (P < 0.05), the Jaccard (J) value (0.84) and the Dice value (0.93) increased significantly versus the traditional algorithm (J = 0.63, Dice = 0.81), and the characteristics of the image were more accurate. Before treatment, the Oswestry Disability Index (ODI) scores of the experimental group and the control group were 44.32 ± 6.45 and 43.32 ± 5.45, respectively. After treatment, the ODI scores of the two groups were 10.21 ± 5.05 and 17.09 ± 5.23, respectively. Both showed significant improvement, while the improvement of the experimental group was more obvious than that of the control group (P < 0.05). The overall effective rates of the two groups of patients were 96.44% and 82.47%, respectively, and the experimental group was significantly higher than the control group (P < 0.05). Under the U-net registration algorithm based on artificial intelligence, the diagnostic accuracy of lumbar MRI in the experimental group was 94.45%, significantly higher than 67.5% before the introduction of the algorithm (P < 0.05). In conclusion, chinkuei shin chewan decoction are effective for the treatment of LSS, and lumbar MRI based on the artificial intelligence U-net registration algorithm can evaluate the efficacy of LSS well and is worthy of promotion.

A novel M-SegNet with global attention CNN architecture for automatic segmentation of brain MRI

In this paper, we propose a novel M-SegNet architecture with global attention for the segmentation of brain magnetic resonance imaging (MRI). The proposed architecture consists of a multiscale deep network at the encoder side, deep supervision at the decoder side, a global attention mechanism, different sizes of convolutional kernels, and combined-connections with skip connections and pooling indices. The multiscale side input layers were used to support deep layers for extracting the discriminative information and the upsampling layer at the decoder side provided deep supervision, which reduced the gradient problem. The global attention mechanism is utilized to capture rich contextual information in the decoder stage by integrating local features with their respective global dependencies. In addition, multiscale convolutional kernels of different sizes were used to extract abundant semantic features from brain MRI scans in the encoder and decoder modules. Moreover, combined-connections were used to pass features from the encoder to the decoder path to recover the spatial information lost during downsampling and makes the model converge faster. Furthermore, we adopted uniform non-overlapping input patches to focus on fine details for the segmentation of brain MRI. We verified the proposed architecture on publicly accessible datasets for the task of segmentation of brain MRI. The experimental results show that the proposed model outperforms conventional methods by achieving an average Dice similarity coefficient score of 0.96.

Brain Image Segmentation in Recent Years: A Narrative Review

Brain image segmentation is one of the most time-consuming and challenging procedures in a clinical environment. Recently, a drastic increase in the number of brain disorders has been noted. This has indirectly led to an increased demand for automated brain segmentation solutions to assist medical experts in early diagnosis and treatment interventions. This paper aims to present a critical review of the recent trend in segmentation and classification methods for brain magnetic resonance images. Various segmentation methods ranging from simple intensity-based to high-level segmentation approaches such as machine learning, metaheuristic, deep learning, and hybridization are included in the present review. Common issues, advantages, and disadvantages of brain image segmentation methods are also discussed to provide a better understanding of the strengths and limitations of existing methods. From this review, it is found that deep learning-based and hybrid-based metaheuristic approaches are more efficient for the reliable segmentation of brain tumors. However, these methods fall behind in terms of computation and memory complexity.

Convolutional Neural Networks and Geometric Moments to Identify the Bilateral Symmetric Midplane in Facial Skeletons from CT Scans

Simple Summary

The bilateral symmetry midplane of the facial skeleton plays a critical role in reconstructive craniofacial surgery. By accurately locating the midplane, surgeons can use the undeformed side of the face as a template for the malformed side. However, the location of the midline is still a subjective procedure, despite its importance. This study aimed to present a 3D technique for automatically calculating the craniofacial symmetry midline of the facial skeleton from CT scans using deep learning techniques. A total of 195 skull images were evaluated and were found to be reliable and provided good accuracy in symmetric images.

Abstract

In reconstructive craniofacial surgery, the bilateral symmetry of the midplane of the facial skeleton plays an important role in surgical planning. Surgeons can take advantage of the intact side of the face as a template for the malformed side by accurately locating the midplane to assist in the preparation of the surgical procedure. However, despite its importance, the location of the midline is still a subjective procedure. The aim of this study was to present a 3D technique using a convolutional neural network and geometric moments to automatically calculate the craniofacial midline symmetry of the facial skeleton from CT scans. To perform this task, a total of 195 skull images were assessed to validate the proposed technique. In the symmetry planes, the technique was found to be reliable and provided good accuracy. However, further investigations to improve the results of asymmetric images may be carried out.