Automatic Lesion Segmentation Research Articles

Automated multiple sclerosis progression rate computation of a patient from 2D FLAIR images with Rayleigh-Weibull-Fuzzy imaging and augmented morphing method

Multiple sclerosis (MS) is a neurological demyelinating disorder affecting brain and spinal cord by attacking the myelin sheaths of nerves. Estimation of the volumetric changes in MS lesions is a challenging and specialized task which is executed and judged by medical experts. The change in the volume of the lesions provides crucial information on MS progression or regression by comparing the magnetic resonance images (MRI) taken in successive scans. However, visual comparison of the images, even with an expert eye, would not always lead to a conclusive decision nor a consensus on progression or regression. Therefore, we present an automated expert system for estimating MS progression rate by automatic lesion segmentation and volume estimation using two-dimensional MRIs, which is also adaptable to various parameters, slice thickness and increment. A clinical dataset is specially formed for this research which contains three sets of 135 MR images of an MS patient generated within approximately 23- and 6-month periods consecutively with identical device parameters. The lesions are segmented by a novel Rayleigh-Weibull-Fuzzy (RWF) imaging method based on the Nakagami distribution and specialized fuzzy 2-means. Subsequently, the segmentation module is trained to fit the ground truths images created by experts to achieve the highest dice score possible for a total number of 56 images containing lesions, which is found as 93.76%. Afterwards, several imaginary image sequences are generated by augmented linear and nonlinear morphing for re-segmentation of imaginary lesions by RWF. Finally, we estimated the volumetric change between the first two MRI sequences to adjust the morphing module and to predict the progression rate of the lesions in time. The framework automatically selected the highest accuracy, which is 99.9% in the training session and estimated the progression rate in the testing phase with 99.69% accuracy, which are not achievable without augmented morphing methodology. For the first time in the literature, an automated framework could estimate the MS progression rate from the raw MR images, which is also the main innovation of this paper and the outputs would be beneficial for the experts working on this field.

Artificial Bee Colony (ABC) optimization Algorithm Based Automatic Segmentation and Detection of Suspicious Lesions in Lung CT Images

Artificial Bee Colony (ABC) optimization Algorithm Based Automatic Segmentation and Detection of Suspicious Lesions in Lung CT Images

Automatic detection and segmentation of lesions in 18F-FDG PET/CT imaging of patients with Hodgkin lymphoma using 3D dense U-Net.

The accuracy of automatic tumor segmentation in PET/computed tomography (PET/CT) images is crucial for the effective treatment and monitoring of Hodgkin lymphoma. This study aims to address the challenges faced by certain segmentation algorithms in accurately differentiating lymphoma from normal organ uptakes due to PET image resolution and tumor heterogeneity. Variants of the encoder-decoder architectures are state-of-the-art models for image segmentation. Among these kinds of architectures, U-Net is one of the most famous and predominant for medical image segmentation. In this study, we propose a fully automatic approach for Hodgkin lymphoma segmentation that combines U-Net and DenseNet architectures to reduce network loss for very small lesions, which is trained using the Tversky loss function. The hypothesis is that the fusion of these two deep learning models can improve the accuracy and robustness of Hodgkin lymphoma segmentation. A dataset with 141 samples was used to train our proposed network. Also, to test and evaluate the proposed network, we allocated two separate datasets of 20 samples. We achieved 0.759 as the mean Dice similarity coefficient with a median value of 0.767, and interquartile range (0.647-0.837). A good agreement was observed between the ground truth of test images against the predicted volume with precision and recall scores of 0.798 and 0.763, respectively. This study demonstrates that the integration of U-Net and DenseNet architectures, along with the Tversky loss function, can significantly enhance the accuracy of Hodgkin lymphoma segmentation in PET/CT images compared to similar studies.

Training Artificial Neural Networks to Detect Multiple Sclerosis Lesions Using Granulometric Data from Preprocessed Magnetic Resonance Images with Morphological Transformations

The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool used for diagnosing MS, understanding the course of the disease, and analyzing the effects of treatments. However, undesirable components may appear during the generation of MRI scans, such as noise or intensity variations. Mathematical morphology (MM) is a powerful image analysis technique that helps to filter the image and extract relevant structures. Granulometry is an image measurement tool for measuring MM that determines the size distribution of objects in an image without explicitly segmenting each object. While several methods have been proposed for the automatic segmentation of MS lesions in MRI scans, in some cases, only simple data preprocessing, such as image resizing to standardize the input dimensions, has been performed before the algorithm training. Therefore, this paper proposes an MRI preprocessing algorithm capable of performing elementary morphological transformations in brain images of MS patients and healthy individuals in order to delete undesirable components and extract the relevant structures such as MS lesions. Also, the algorithm computes the granulometry in MRI scans to describe the size qualities of lesions. Using this algorithm, we trained two artificial neural networks (ANNs) to predict MS diagnoses. By computing the differences in granulometry measurements between an image with MS lesions and a reference image (without lesions), we determined the size characterization of the lesions. Then, the ANNs were evaluated with the validation set, and the performance results (test accuracy = 0.9753; cross-entropy loss = 0.0247) show that the proposed algorithm can support specialists in making decisions to diagnose MS and estimating the disease progress based on granulometry values.

Inteligencia Artificial, Imagen Médica y Medicina de Precisión: Avances y Perspectivas

The role of artificial intelligence (AI) applied to medical imaging in developing and strengthening personalized medicine is described as a continuous process of improvement, a set of opportunities, and a professional challenge of enormous significance. This paper outlines the main processes in which AI is involved regarding imaging, including data preparation, image harmonization, automatic segmentation of organs and lesions, labeling, extraction of radiomic features, and the development of predictive clinical models. It will also address aspects related to the integration of these solutions into clinical practice to enhance accuracy and efficiency in the care process, diagnosis, and treatment, making it more personalized, efficient, and precise. Projects like PRIMAGE and CHAIMELEON highlight the transformative potential of AI and the fundamental role of interdisciplinary collaboration in realizing this potential, based on ongoing multiprofesional collaboration to address the ethical, regulatory, technical, and clinical challenges that accompany these advancements.

Radiomics features for the discrimination of tuberculomas from high grade gliomas and metastasis: a multimodal study.

Tuberculomas are prevalent in developing countries and demonstrate variable signals on MRI resulting in the overlap of the conventional imaging phenotype with other entities including glioma and brain metastasis. An accurate MRI diagnosis is important for the early institution of anti-tubercular therapy, decreased patient morbidity, mortality, and prevents unnecessary neurosurgical excision. This study aims to assess the potential of radiomics features of regular contrast images including T1W, T2W, T2W FLAIR, T1W post contrast images, and ADC maps, to differentiate between tuberculomas, high-grade-gliomas and metastasis, the commonest intra parenchymal mass lesions encountered in the clinical practice. This retrospective study includes 185 subjects. Images were resampled, co-registered, skull-stripped, and zscore-normalized. Automated lesion segmentation was performed followed by radiomics feature extraction, train-test split, and features reduction. All machine learning algorithms that natively support multiclass classification were trained and assessed on features extracted from individual modalities as well as combined modalities. Model explainability of the best performing model was calculated using the summary plot obtained by SHAP values. Extra tree classifier trained on the features from ADC maps was the best classifier for the discrimination of tuberculoma from high-grade-glioma and metastasis with AUC-score of 0.96, accuracy-score of 0.923, Brier-score of 0.23. This study demonstrates that radiomics features are effective in discriminating between tuberculoma, metastasis, and high-grade-glioma with notable accuracy and AUC scores. Features extracted from the ADC maps surfaced as the most robust predictors of the target variable.

Graph Neural Network Enhanced Dual-Branch Network for lesion segmentation in ultrasound images

Ultrasound images are widely used in the detection of breast lesions, thyroid nodules, renal tumors and other medical conditions due to their cost-effectiveness and convenience. Automatic segmentation of lesions in ultrasound images is crucial for clinical diagnosis. U-shaped networks with encoder–decoder architectures and skip connections have achieved significant success in medical image segmentation. However, challenges arise in segmentation due to the inherent blurriness of ultrasound image boundaries and the irregular shapes and volumes of lesions. Despite the capability of transformers to capture global information, we posit that graph neural network (GNN) offers a more flexible approach to capturing irregular features. GNN constructs connections for each part, leveraging global information in the process. In this study, we propose GNN-Enhanced Dual-Branch Network (GED-Net), a robust framework for lesion segmentation in ultrasound images. The Network consists of an encoder with two branches: one for extracting local features using convolutional neural network (CNN) and the other for extracting global features using GNN, along with a fusion module and a decoder. We evaluated the model on four publicly available medical ultrasound datasets including BUSI, Dataset B, DDTI and OASBUD, and demonstrated superior performance compared to most classical U-Net networks and state-of-the-art U-shaped networks. The source code is available at https://github.com/Yakiw/GED-Net.

Longitudinal Lesion Expansion in Chronic Traumatic Brain Injury.

Traumatic brain injury (TBI) is a risk factor for neurodegeneration and cognitive decline, yet the underlying pathophysiologic mechanisms are incompletely understood. This gap in knowledge is in part related to the lack of analytic methods to account for cortical lesions in prior neuroimaging studies. The objective of this study was to develop a lesion detection tool and apply it to an investigation of longitudinal changes in brain structure among individuals with chronic TBI. We identified 24 individuals with chronic moderate-to-severe TBI enrolled in the Late Effects of TBI (LETBI) study who had cortical lesions detected by T1-weighted MRI at two time points. Initial MRI scans were performed more than 1-year post-injury and follow-up scans were performed 3.1 (IQR=1.7) years later. We leveraged FreeSurfer parcellations of T1-weighted MRI volumes and a recently developed super-resolution technique, SynthSR, to identify cortical lesions in this longitudinal dataset. Trained raters received the data in a randomized order and manually corrected the automated lesion segmentation, yielding a final lesion mask for each scan at each timepoint. Lesion volume significantly increased between the two time points with a median volume change of 3.2 (IQR=5.9) mL (p<0.001), and the increases significantly exceeded the possible variance in lesion volume changes due to manual tracing errors (p < 0.001). Lesion volume significantly expanded longitudinally in 23 of 24 subjects, with all FDR corrected p-values ≤ 0.02. Inter-scan duration was not associated with the magnitude of lesion growth. We also demonstrated that the semi-automated tool showed a high level of accuracy compared to "ground truth" manual lesion segmentation. Semi-automated lesion segmentation is feasible in TBI studies and creates opportunities to elucidate mechanisms of post-traumatic neurodegeneration.

Automatic prediction of non-iodine-avid status in lung metastases for radioactive I131 treatment in differentiated thyroid cancer patients.

The growing incidence of differentiated thyroid cancer (DTC) have been linked to insulin resistance and metabolic syndrome. The imperative need for developing effective diagnostic imaging tools to predict the non-iodine-avid status of lung metastasis (LMs) in differentiated thyroid cancer (DTC) patients is underscored to prevent unnecessary radioactive iodine treatment (RAI). Primary cohort consisted 1962 pretreated LMs of 496 consecutive DTC patients with pretreated initially diagnosed LMs who underwent chest CT and subsequent post-treatment radioiodine SPECT. After automatic lesion segmentation by SE V-Net, SE Net deep learning was trained to predict non-iodine-avid status of LMs. External validation cohort contained 123 pretreated LMs of 24 consecutive patients from other two hospitals. Stepwise validation was further performed according to the nodule's largest diameter. The SE-Net deep learning network yielded area under the receiver operating characteristic curve (AUC) values of 0.879 (95% confidence interval: 0.852-0.906) and 0.713 (95% confidence interval: 0.613-0.813) for internal and external validation. With the LM diameter decreasing from ≥10mm to ≤4mm, the AUCs remained relatively stable, for smallest nodules (≤4mm), the model yielded an AUC of 0.783. Decision curve analysis showed that most patients benefited using deep learning to decide radioactive I131 treatment. This study presents a noninvasive, less radioactive and fully automatic approach that can facilitate suitable DTC patient selection for RAI therapy of LMs. Further prospective multicenter studies with larger study cohorts and related metabolic factors should address the possibility of comprehensive clinical transformation.

Multi-scale deep learning ensemble for segmentation of endometriotic lesions

Ultrasound is a readily available, non-invasive and low-cost screening for the identification of endometriosis lesions, but its diagnostic specificity strongly depends on the experience of the operator. For this reason, computer-aided diagnosis tools based on Artificial Intelligence techniques can provide significant help to the clinical staff, both in terms of workload reduction and in increasing the overall accuracy of this type of examination and its outcome. However, although these techniques are spreading rapidly in a variety of domains, their application to endometriosis is still very limited. To fill this gap, we propose and evaluate a novel multi-scale ensemble approach for the automatic segmentation of endometriosis lesions from transvaginal ultrasounds. The peculiarity of the method lies in its high discrimination capability, obtained by combining, in a fusion fashion, multiple Convolutional Neural Networks trained on data at different granularity. The experimental validation carried out shows that: (i) the proposed method allows to significantly improve the performance of the individual neural networks, even in the presence of a limited training set; (ii) with a Dice coefficient of 82%, it represents a valid solution to increase the diagnostic efficacy of the ultrasound examination against such a pathology.

Domain base dynamic convolution and distance map guidance for anterior mediastinal lesion segmentation

The automatic segmentation of anterior mediastinal lesions in the enhanced CT image plays a significant role in clinical diagnosis. Due to the low incidence rate of anterior mediastinal disease, the data for training segmentation network may come from different hospitals, different equipment, and different operators, which leads to lower generalization and robustness of the trained network. This paper proposes an anterior mediastinal lesion segmentation method based on domain-adaptive dynamic convolution and distance map guidance. Considering the diversity of clinical data sources and equipment differences, the domain prior knowledge is added to the global average-pooling layer of the network, and the dynamic convolution forms specific network parameters for specific domains to enhance domain-specific information. Meanwhile, the Singed Distance Map (SDM) head is involved in the network according to the shape, size and position of the anterior mediastinal lesions to constraint the boundary and assist in localization. Ablation experiments demonstrate that the distance map can effectively constrain the segmentation target and reduce false positives. Both qualitative and quantitative experimental results indicate that our method can achieve more accurate anterior mediastinal lesion segmentation with greater generalization ability. Our approach achieves an overall Dice coefficient of 88.33%, which is 2.31% higher than existing state-of-the-art methods, and has achieved good performance in terms of ASSD evaluation for segmentation edges.

Enhancing skin lesion segmentation with a fusion of convolutional neural networks and transformer models

Accurate segmentation is crucial in diagnosing and analyzing skin lesions. However, automatic segmentation of skin lesions is extremely challenging because of their variable sizes, uneven color distributions, irregular shapes, hair occlusions, and blurred boundaries. Owing to the limited range of convolutional networks receptive fields, shallow convolution cannot extract the global features of images and thus has limited segmentation performance. Because medical image datasets are small in scale, the use of excessively deep networks could cause overfitting and increase computational complexity. Although transformer networks can focus on extracting global information, they cannot extract sufficient local information and accurately segment detailed lesion features. In this study, we designed a dual-branch encoder that combines a convolution neural network (CNN) and a transformer. The CNN branch of the encoder comprises four layers, which learn the local features of images through layer-wise downsampling. The transformer branch also comprises four layers, enabling the learning of global image information through attention mechanisms. The feature fusion module in the network integrates local features and global information, emphasizes important channel features through the channel attention mechanism, and filters irrelevant feature expressions. The information exchange between the decoder and encoder is finally achieved through skip connections to supplement the information lost during the sampling process, thereby enhancing segmentation accuracy. The data used in this paper are from four public datasets, including images of melanoma, basal cell tumor, fibroma, and benign nevus. Because of the limited size of the image data, we enhanced them using methods such as random horizontal flipping, random vertical flipping, random brightness enhancement, random contrast enhancement, and rotation. The segmentation accuracy is evaluated through intersection over union and duration, integrity, commitment, and effort indicators, reaching 87.7 % and 93.21 %, 82.05 % and 89.19 %, 86.81 % and 92.72 %, and 92.79 % and 96.21 %, respectively, on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets, respectively (code: https://github.com/hyjane/CCT-Net).

Lesion attention guided neural network for contrast-enhanced mammography-based biomarker status prediction in breast cancer

Background and objectiveAccurate identification of molecular biomarker statuses is crucial in cancer diagnosis, treatment, and prognosis. Studies have demonstrated that medical images could be utilized for non-invasive prediction of biomarker statues. The biomarker status-associated features extracted from medical images are essential in developing medical image-based non-invasive prediction models. Contrast-enhanced mammography (CEM) is a promising imaging technique for breast cancer diagnosis. This study aims to develop a neural network-based method to extract biomarker-related image features from CEM images and evaluate the potential of CEM in non-invasive biomarker status prediction. MethodsAn end-to-end learning convolutional neural network with the whole breast images as inputs was proposed to extract CEM features for biomarker status prediction in breast cancer. The network focused on lesion regions and flexibly extracted image features from lesion and peri‑tumor regions by employing supervised learning with a smooth L1-based consistency constraint. An image-level weakly supervised segmentation network based on Vision Transformer with cross attention to contrast images of breasts with lesions against the contralateral breast images was developed for automatic lesion segmentation. Finally, prediction models were developed following further selection of significant features and the implementation of random forest-based classification. Results were reported using the area under the curve (AUC), accuracy, sensitivity, and specificity. ResultsA dataset from 1203 breast cancer patients was utilized to develop and evaluate the proposed method. Compared to the method without lesion attention and with only lesion regions as inputs, the proposed method performed better at biomarker status prediction. Specifically, it achieved an AUC of 0.71 (95 % confidence interval [CI]: 0.65, 0.77) for Ki-67 and 0.73 (95 % CI: 0.65, 0.80) for human epidermal growth factor receptor 2 (HER2). ConclusionsA lesion attention-guided neural network was proposed in this work to extract CEM image features for biomarker status prediction in breast cancer. The promising results demonstrated the potential of CEM in non-invasively predicting the biomarker statuses in breast cancer.

Automatic Brain Tissue and Lesion Segmentation and Multi-Parametric Mapping of Contrast-Enhancing Gliomas without the Injection of Contrast Agents: A Preliminary Study.

This study aimed to develop a rapid, 1 mm3 isotropic resolution, whole-brain MRI technique for automatic lesion segmentation and multi-parametric mapping without using contrast by continuously applying balanced steady-state free precession with inversion pulses throughout incomplete inversion recovery in a single 6 min scan. Modified k-means clustering was performed for automatic brain tissue and lesion segmentation using distinct signal evolutions that contained mixed T1/T2/magnetization transfer properties. Multi-compartment modeling was used to derive quantitative multi-parametric maps for tissue characterization. Fourteen patients with contrast-enhancing gliomas were scanned with this sequence prior to the injection of a contrast agent, and their segmented lesions were compared to conventionally defined manual segmentations of T2-hyperintense and contrast-enhancing lesions. Simultaneous T1, T2, and macromolecular proton fraction maps were generated and compared to conventional 2D T1 and T2 mapping and myelination water fraction mapping acquired with MAGiC. The lesion volumes defined with the new method were comparable to the manual segmentations (r = 0.70, p < 0.01; t-test p > 0.05). The T1, T2, and macromolecular proton fraction mapping values of the whole brain were comparable to the reference values and could distinguish different brain tissues and lesion types (p < 0.05), including infiltrating tumor regions within the T2-lesion. Highly efficient, whole-brain, multi-contrast imaging facilitated automatic lesion segmentation and quantitative multi-parametric mapping without contrast, highlighting its potential value in the clinic when gadolinium is contraindicated.

An AutomatedDeep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer.

Uptake segmentation and classification on PSMA PET/CT are important for automating whole-body tumor burden determinations. We developed and evaluated an automated deep learning (DL)-based framework that segments and classifies uptake on PSMA PET/CT. We identified 193 [18F] DCFPyL PET/CT scans of patients with biochemically recurrent prostate cancer from two institutions, including 137 [18F] DCFPyL PET/CT scans for training and internally testing, and 56 scans from another institution for external testing. Two radiologists segmented and labelled foci as suspicious or non-suspicious for malignancy. A DL-based segmentation was developed with two independent CNNs. An anatomical prior guidance was applied to make the DL framework focus on PSMA-avid lesions. Segmentation performance was evaluated by Dice, IoU, precision, and recall. Classification model was constructed with multi-modal decision fusion framework evaluated by accuracy, AUC, F1 score, precision, and recall. Automatic segmentation of suspicious lesions was improved under prior guidance, with mean Dice, IoU, precision, and recall of 0.700, 0.566, 0.809, and 0.660 on the internal test set and 0.680, 0.548, 0.749, and 0.740 on the external test set. Our multi-modal decision fusion framework outperformed single-modal and multi-modal CNNs with accuracy, AUC, F1 score, precision, and recall of 0.764, 0.863, 0.844, 0.841, and 0.847 in distinguishing suspicious and non-suspicious foci on the internal test set and 0.796, 0.851, 0.865, 0.814, and 0.923 on the external test set. DL-based lesion segmentation on PSMA PET is facilitated through our anatomical prior guidance strategy. Our classification framework differentiates suspicious foci from those not suspicious for cancer with good accuracy.

Application of artificial intelligence in brain arteriovenous malformations: Angioarchitectures, clinical symptoms and prognosis prediction.

Artificial intelligence (AI) has rapidly advanced in the medical field, leveraging its intelligence and automation for the management of various diseases. Brain arteriovenous malformations (AVM) are particularly noteworthy, experiencing rapid development in recent years and yielding remarkable results. This paper aims to summarize the applications of AI in the management of AVMs management. Literatures published in PubMed during 1999-2022, discussing AI application in AVMs management were reviewed. AI algorithms have been applied in various aspects of AVM management, particularly in machine learning and deep learning models. Automatic lesion segmentation or delineation is a promising application that can be further developed and verified. Prognosis prediction using machine learning algorithms with radiomic-based analysis is another meaningful application. AI has been widely used in AVMs management. This article summarizes the current research progress, limitations and future research directions.

Deep learning-based automated lesion segmentation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach

ObjectivesFocal cortical dysplasia (FCD) represents one of the most common causes of refractory epilepsy in children. Deep learning demonstrates great power in tissue discrimination by analyzing MRI data. A prediction model was built and verified using 3D full-resolution nnU-Net for automatic lesion detection and segmentation of children with FCD II.MethodsHigh-resolution brain MRI structure data from 65 patients, confirmed with FCD II by pathology, were retrospectively studied. Experienced neuroradiologists segmented and labeled the lesions as the ground truth. Also, we used 3D full-resolution nnU-Net to segment lesions automatically, generating detection maps. The algorithm was trained using fivefold cross-validation, with data partitioned into training (N = 200) and testing (N = 15). To evaluate performance, detection maps were compared to expert manual labels. The Dice-Sørensen coefficient (DSC) and sensitivity were used to assess the algorithm performance.ResultsThe 3D nnU-Net showed a good performance for FCD lesion detection at the voxel level, with a sensitivity of 0.73. The best segmentation model achieved a mean DSC score of 0.57 on the testing dataset.ConclusionThis pilot study confirmed that 3D full-resolution nnU-Net can automatically segment FCD lesions with reliable outcomes. This provides a novel approach to FCD lesion detection.Critical relevance statementOur fully automatic models could process the 3D T1-MPRAGE data and segment FCD II lesions with reliable outcomes.Key points• Simplified image processing promotes the DL model implemented in clinical practice.• The histopathological confirmed lesion masks enhance the clinical credibility of the AI model.• The voxel-level evaluation metrics benefit lesion detection and clinical decisions.Graphical

THE ROLE OF ARTIFICIAL INTELLIGENCE (AI) ON MRI BRAIN EXAMINATION WITH CLINICAL ISCHEMIC STROKE

Background: Application of Artificial Intelligence (AI) in radiology is named automatic image interpretation of neuroimaging stroke. It takes a short time to minimize the patient's brain damage. Purpose: Determine the role of AI in ischemic brain stroke MRI examination and find out the advantages and disadvantages of applying AI to ischemic brain stroke MRI examination. Review: It was a descriptive and qualitative study with a literature review approach. The selection of articles used the ScienceDirect, Scopus, ProQuest, PubMed, and Publish or Perish databases. The inclusion criteria included full articles, with the topic of AI on ischemic brain stroke MRI examinations published in the 2017 – 2022 range, articles published by English-language international journals with a classification of Q1 – Q3, and having DOI. Seven relevant pieces of article were obtained, then descriptive analysis was carried out by comparing and presenting the articles descriptively in tabular form. Result: The role of AI in MRI brain examination with clinical ischemic stroke, namely its role in automatic lesion segmentation, Time Since Stroke (TSS) classification, and infarct volume prediction. The advantages of AI included short image processing times and accurate results. The disadvantages of AI tended to decrease performance in small lesions, a large number of patients, limited data, and false positive results. The value of the Dice Score Coefficient (DSC) (0.53 – 0.86) was already high even though it had not reached 1 because it depended on the strength of the data used. Conclusion: The role of AI in MRI imaging of ischemic brain stroke helps in the diagnosis and prognosis of ischemic stroke patients. AI in stroke neuroimaging has advantages in time effectiveness and disadvantages in data limitations.

Explainable hybrid vision transformers and convolutional network for multimodal glioma segmentation in brain MRI

Accurate localization of gliomas, the most common malignant primary brain cancer, and its different sub-region from multimodal magnetic resonance imaging (MRI) volumes are highly important for interventional procedures. Recently, deep learning models have been applied widely to assist automatic lesion segmentation tasks for neurosurgical interventions. However, these models are often complex and represented as “black box” models which limit their applicability in clinical practice. This article introduces new hybrid vision Transformers and convolutional neural networks for accurate and robust glioma segmentation in Brain MRI scans. Our proposed method, TransXAI, provides surgeon-understandable heatmaps to make the neural networks transparent. TransXAI employs a post-hoc explanation technique that provides visual interpretation after the brain tumor localization is made without any network architecture modifications or accuracy tradeoffs. Our experimental findings showed that TransXAI achieves competitive performance in extracting both local and global contexts in addition to generating explainable saliency maps to help understand the prediction of the deep network. Further, visualization maps are obtained to realize the flow of information in the internal layers of the encoder-decoder network and understand the contribution of MRI modalities in the final prediction. The explainability process could provide medical professionals with additional information about the tumor segmentation results and therefore aid in understanding how the deep learning model is capable of processing MRI data successfully. Thus, it enables the physicians’ trust in such deep learning systems towards applying them clinically. To facilitate TransXAI model development and results reproducibility, we will share the source code and the pre-trained models after acceptance at https://github.com/razeineldin/TransXAI.

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\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.868 \\mathop {\\pm } 0.056$$\\end{document} 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.