MRI Segmentation Research Articles

Artificial Intelligence in Obstetric and Gynecological MR Imaging.

This review explores the significant progress and applications of artificial intelligence (AI) in obstetrics and gynecological MRI, charting its development from foundational algorithmic techniques to deep learning strategies and advanced radiomics. This review features research published over the last few years that has used AI with MRI to identify specific conditions such as uterine leiomyosarcoma, endometrial cancer, cervical cancer, ovarian tumors, and placenta accreta. In addition, it covers studies on the application of AI for segmentation and quality improvement in obstetrics and gynecology MRI. The review also outlines the existing challenges and envisions future directions for AI research in this domain. The growing accessibility of extensive datasets across various institutions and the application of multiparametric MRI are significantly enhancing the accuracy and adaptability of AI. This progress has the potential to enable more accurate and efficient diagnosis, offering opportunities for personalized medicine in the field of obstetrics and gynecology.

LSTM-NAS-Net: Enhanced Brain Tumor Segmentation in MRI and CT Images using LSTM-Autoencoder-based Neural Architecture Search

Brain Tumour (BT) a mass or a lump or a growth which occurs due to abnormal cell division or unusual growth of cells in the brain tissue. Initially, the two major types of BT are Primary BT and Secondary BT, the tumour that originate from brain is known as Primary BT and it may be cancerous or non-cancerous. The tumour the initiates from other part of the body and spreads to the brain is stated as secondary BT. Diagnosing BT generally involves a multiple investigation method, such as MRI, CT, PET, SPECT as well as the neurological examinations and blood investigations, whereas some of the patients may need biopsies to evaluate the tumour size and stage. Here we use MRI and CT images for BT segmentation whereas these modalities play a major role in diagnosing, treating, planning and monitoring the BT patients. Moreover, the multimodal data can provide a quantitative information’s about the tumour size, shape, volume and texture. While segmenting the BT the lack of segmentation methods and the interpretability of the segmented regions are limited. To overcome this, we propose a novel LSTM autoencoder bas NAS method which is used for the extracting the BT features and these features can be fused using Contextual Integration Module (CIM) and segmented using the Segmentation Guided Regulizer (SGR) which helps to overcome the stated issues. Finally, the performance metrices are calculated by comparing with the state-of -the -art methods and our method achieves a best segmenting metrices.

Early prognostication of overall survival for pediatric diffuse midline gliomas using MRI radiomics and machine learning: A two-center study.

Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors that are diagnosed and monitored through MRI. We developed an automatic pipeline to segment subregions of DMG and select radiomic features that predict patient overall survival (OS). We acquired diagnostic and post-radiation therapy (RT) multisequence MRI (T1, T1ce, T2, and T2 FLAIR) and manual segmentations from 2 centers: 53 from 1 center formed the internal cohort and 16 from the other center formed the external cohort. We pretrained a deep learning model on a public adult brain tumor data set (BraTS 2021), and finetuned it to automatically segment tumor core (TC) and whole tumor (WT) volumes. PyRadiomics and sequential feature selection were used for feature extraction and selection based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 12-month survival from diagnosis. One model used only data obtained at diagnosis prior to any therapy (baseline study) and the other used data at both diagnosis and post-RT (post-RT study). Overall survival prediction accuracy was 77% and 81% for the baseline study, and 85% and 78% for the post-RT study, for internal and external cohorts, respectively. Homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio indicate shorter OS. Machine learning analysis of MRI radiomics has potential to accurately and noninvasively predict which pediatric patients with DMG will survive less than 12 months from the time of diagnosis to provide patient stratification and guide therapy.

Brain growth until adolescence after a neonatal focal injury: sex related differences beyond lesion effect.

Early focal brain injuries lead to long-term disabilities with frequent cognitive impairments, suggesting global dysfunction beyond the lesion. While plasticity of the immature brain promotes better learning, outcome variability across individuals is multifactorial. Males are more vulnerable to early injuries and neurodevelopmental disorders than females, but long-term sex differences in brain growth after an early focal lesion have not been described yet. With this MRI longitudinal morphometry study of brain development after a Neonatal Arterial Ischemic Stroke (NAIS), we searched for differences between males and females in the trajectories of ipsi- and contralesional gray matter growth in childhood and adolescence, while accounting for lesion characteristics. We relied on a longitudinal cohort (AVCnn) of patients with unilateral NAIS who underwent clinical and MRI assessments at ages 7 and 16 were compared to age-matched controls. Non-lesioned volumes of gray matter (hemispheres, lobes, regions, deep structures, cerebellum) were extracted from segmented T1 MRI images at 7 (Patients: 23 M, 16 F; Controls: 17 M, 18 F) and 16 (Patients: 18 M, 11 F; Controls: 16 M, 15 F). These volumes were analyzed using a Linear Mixed Model accounting for age, sex, and lesion characteristics. Whole hemisphere volumes were reduced at both ages in patients compared to controls (gray matter volume: -16% in males, -10% in females). In ipsilesional hemisphere, cortical gray matter and thalamic volume losses (average -13%) mostly depended on lesion severity, suggesting diaschisis, with minimal effect of patient sex. In the contralesional hemisphere however, we consistently found sex differences in gray matter volumes, as only male volumes were smaller than in male controls (average -7.5%), mostly in territories mirroring the contralateral lesion. Females did not significantly deviate from the typical trajectories of female controls. Similar sex differences were found in both cerebellar hemispheres. These results suggest sex-dependent growth trajectories after an early brain lesion with a contralesional growth deficit in males only. The similarity of patterns at ages 7 and 16 suggests that puberty has little effect on these trajectories, and that most of the deviation in males occurs in early childhood, in line with the well-described perinatal vulnerability of the male brain, and with no compensation thereafter.

Multiparametric MRI radiomics for predicting disease-free survival and high-risk histopathological features for tumor recurrence in endometrial cancer.

Current preoperative imaging is insufficient to predict survival and tumor recurrence in endometrial cancer (EC), necessitating invasive procedures for risk stratification. To establish a multiparametric MRI radiomics model for predicting disease-free survival (DFS) and high-risk histopathologic features in EC. This retrospective study included 71 patients with histopathology-proven EC and preoperative MRI over a 10-year period. Clinicopathology data were extracted from health records. Manual MRI segmentation was performed on T2-weighted (T2W), apparent diffusion coefficient (ADC) maps and dynamic contrast-enhanced T1-weighted images (DCE T1WI). Radiomic feature (RF) extraction was performed with PyRadiomics. Associations between RF and histopathologic features were assessed using logistic regression. Associations between DFS and RF or clinicopathologic features were assessed using the Cox proportional hazards model. All RF with univariate analysis p-value < 0.2 were included in elastic net analysis to build radiomic signatures. The 3-year DFS rate was 68% (95% CI = 57%-80%). There were no significant clinicopathologic predictors for DFS, whilst the radiomics signature was a strong predictor of DFS (p<0.001, HR 3.62, 95% CI 1.94, 6.75). From 107 RF extracted, significant predictive elastic net radiomic signatures were established for deep myometrial invasion (p=0.0097, OR 4.81, 95% CI 1.46, 15.79), hysterectomy grade (p=0.002, OR 5.12, 95% CI 1.82, 14.45), hysterectomy histology (p=0.0061, OR 18.25, 95% CI 2.29,145.24) and lymphovascular space invasion (p<0.001, OR 5.45, 95% CI 2.07, 14.36). Multiparametric MRI radiomics has the potential to create a non-invasive a priori approach to predicting DFS and high-risk histopathologic features in EC.

Impact of training data composition on the generalizability of convolutional neural network aortic cross-section segmentation in four-dimensional magnetic resonance flow imaging

BackgroundTime-resolved, three-dimensional phase-contrast magnetic resonance imaging (4D flow MRI) plays an important role in assessing cardiovascular diseases. However, the manual or semi-automatic segmentation of aortic vessel boundaries in 4D flow data introduces variability and limits reproducibility of aortic hemodynamics visualization and quantitative flow-related parameter computation. This paper explores the potential of deep learning to improve 4D flow MRI segmentation by developing models for automatic segmentation and analyzes the impact of the training data on the generalization of the model across different sites, scanner vendors, sequences, and pathologies. MethodsThe study population consists of 260 4D flow MRI datasets, including subjects without known aortic pathology, healthy volunteers, and patients with bicuspid aortic valve (BAV) examined at different hospitals. The dataset was split to train segmentation models on subsets with different representations of characteristics such as pathology, gender, age, scanner model, vendor, and field strength. An enhanced 3D U-net convolutional neural network (CNN) architecture with residual units was trained for 2D+t aortic cross-sectional segmentation. The model performance was evaluated using Dice score, Hausdorff distance, and average symmetric surface distance on test data, datasets with characteristics not represented in the training set (model-specific), and an overall evaluation set. Standard diagnostic flow parameters were computed and compared with manual segmentation results using Bland-Altman analysis and interclass correlation. ResultsThe representation of technical factors such as scanner vendor and field strength in the training dataset had the strongest influence on the overall segmentation performance. Age had a greater impact than gender. Models solely trained on BAV patients’ datasets performed well on datasets of healthy subjects but not vice versa. ConclusionThis study highlights the importance of considering a heterogeneous dataset for the training of widely applicable automatic CNN segmentations in 4D flow MRI, with a particular focus on the inclusion of different pathologies and technical aspects of data acquisition.

Toward Accurate Cardiac MRI Segmentation With Variational Autoencoder-Based Unsupervised Domain Adaptation.

Accurate myocardial segmentation is crucial in the diagnosis and treatment of myocardial infarction (MI), especially in Late Gadolinium Enhancement (LGE) cardiac magnetic resonance (CMR) images, where the infarcted myocardium exhibits a greater brightness. However, segmentation annotations for LGE images are usually not available. Although knowledge gained from CMR images of other modalities with ample annotations, such as balanced-Steady State Free Precession (bSSFP), can be transferred to the LGE images, the difference in image distribution between the two modalities (i.e., domain shift) usually results in a significant degradation in model performance. To alleviate this, an end-to-end Variational autoencoder based feature Alignment Module Combining Explicit and Implicit features (VAMCEI) is proposed. We first re-derive the Kullback-Leibler (KL) divergence between the posterior distributions of the two domains as a measure of the global distribution distance. Second, we calculate the prototype contrastive loss between the two domains, bringing closer the prototypes of the same category across domains and pushing away the prototypes of different categories within or across domains. Finally, a domain discriminator is added to the output space, which indirectly aligns the feature distribution and forces the extracted features to be more favorable for segmentation. In addition, by combining CycleGAN and VAMCEI, we propose a more refined multi-stage unsupervised domain adaptation (UDA) framework for myocardial structure segmentation. We conduct extensive experiments on the MSCMRSeg 2019, MyoPS 2020 and MM-WHS 2017 datasets. The experimental results demonstrate that our framework achieves superior performances than state-of-the-art methods.

Brain Tumor MRI Segmentation Method Based on Improved Res-UNet

Brain Tumor MRI Segmentation Method Based on Improved Res-UNet

An accurate and efficient multi-task brain tumour detection with segmented MRI images using auto-metric adolescent neural network

An accurate and efficient multi-task brain tumour detection with segmented MRI images using auto-metric adolescent neural network

Quantum‐inspired hybrid algorithm for image classification and segmentation: Q‐Means++ max‐cut method

AbstractFinding brain tumors is a crucial step in medical diagnosis that can have a big impact on how patients turn out. Conventional detection techniques can be laborious and demand a lot of computing power. Brain tumor detection could be made more effective and precise, thanks to the quickly developing field of quantum computing. In this article, we propose a quantum machine learning (QML)‐based method for brain tumor extraction and detection based on quantum computing. To implement our strategy, we use a Hybrid Quantum‐Classical Convolutional Neural Network (HQC‐CNN) that has been trained using a collection of brain MRI images. Additionally, we employ Batchwise Q‐Means++ Clustering for segmenting the images and a Max‐cut approach with Adiabatic Quantum Computation (AQC) to extract the tumor region from the segmented MRI image. Our results highlight the strength of Quanvolutional Layer in Neural Network and reduced time complexity exponentially or quadratically in clustering and max‐cut algorithms respectively and see the potential of quantum computing for improving the accuracy and speed of medical diagnosis and have implications for the future of healthcare technology.

Treatment evaluation by volumetric segmentation in pediatric optic pathway glioma: evaluation of the effect of bevacizumab on intra-tumor components.

Progressive pediatric optic pathway gliomas (OPGs) are treated by diverse systemic antitumor modalities. Refined insights on the course of intra-tumoral components are limited. We performed an exploratory study on the longitudinal volumetric course of different (intra-)tumor components by manual segmentation of MRI at the start and after 3, 6 and 12months of bevacizumab (BVZ) treatment. Thirty-one patients were treated with BVZ (median 12months, range: 2-39months). During treatment the total tumor volume decreased with median 19.9% (range: -62.3 to + 29.7%; n = 30) within the first 3 months, decreased 19.0% (range: -68.8 to + 96.1%; n = 28) between start and 6 months and 27.2% (range: -73.4 to + 36.0%; n = 21) between start and 12months. Intra-tumoral cysts were present in 12 OPGs, all showed a decrease of volume during treatment. The relative contrast enhanced volume of NF1 associated OPG (n = 11) showed an significant reduction compared to OPG with a KIAA1549-BRAF fusion (p < 0.01). Three OPGs progressed during treatment, but were not preceded by an increase of relative contrast enhancement. Treatment with BVZ of progressive pediatric OPGs leads to a decrease of both total tumor volume and cystic volume for the majority of OPGs with emphasis on the first three months. NF1 and KIAA1549-BRAF fusion related OPGs showed a different (early) treatment effect regarding the tumor enhancing component on MRI, which did not correlate with tumor volume changes. Future research is necessary to further evaluate these findings and its relevance to clinical outcome parameters.

A Systematic Review of Brain MRI Segmentation and Uncertainty Modeling Using Evidence Theory with Implementation of Fuzzy Clustering and Fuzzy Inference Systems Methods

A Systematic Review of Brain MRI Segmentation and Uncertainty Modeling Using Evidence Theory with Implementation of Fuzzy Clustering and Fuzzy Inference Systems Methods

MRI segmentation of tooth tissue in age prediction of sub-adults - a new method for combining data from the 1st, 2nd, and 3rd molars.

We aimed to establish a model combining MRI volume measurements from the 1st, 2nd and 3rd molars for age prediction in sub-adults and compare the age prediction performance of different combinations of all three molars, internally in the study cohort. We examined 99 volunteers using a 1.5T MR scanner with a customized high-resolution single T2 sequence. Segmentation was performed using SliceOmatic (Tomovision©). Age prediction was based on the tooth tissue ratio (high signal soft tissue + low signal soft tissue)/total. The model included three correlation parameters to account for statistical dependence between the molars. Age prediction performance of different combinations of teeth for the three molars was assessed using interquartile range (IQR). We included data from the 1st molars from 87 participants (F/M 59/28), 2nd molars from 93 (F/M 60/33) and 3rd molars from 67 (F/M 45/22). The age range was 14-24years with a median age of 18years. The model with the best age prediction performance (smallest IQR) was 46-47-18 (lower right 1st and 2nd and upper right 3rd molar) in males. The estimated correlation between the different molars was 0.620 (46 vs. 47), 0.430 (46 vs. 18), and 0.598 (47 vs. 18). IQR was the smallest in tooth combinations including a 3rd molar. We have established a model for combining tissue volume measurements from the 1st, 2nd and 3rd molars for age prediction in sub-adults. The prediction performance was mostly driven by the 3rd molars. All combinations involving the 3rd molar performed well.

Feature-based multimodal registration framework for vertebral pose estimation

PurposeThe reliable estimation of the vertebral body posture helps to aid a safe and effective spine surgery. The proposed work aims to present an MR to X-ray image registration to assess the 3D pose of the vertebral body during spine surgery. The 3D assessment of vertebral pose assists in analyzing the position and orientation of the vertebral body to provide information during various clinical diagnosis conditions such as curvature estimation and pedicle screw insertion surgery.MethodsThe proposed feature-based registration framework extracted vertebral end plates to avoid the mismatch between the intensities of MR and X-ray images. Using the projection matrix, the segmented MRI is forward projected and then registered to the X-ray image using binary image matching similarity and the CMA-ES optimizer.ResultsThe proposed method estimated the vertebral pose by registering the simulated X-ray onto pre-operative MRI. To evaluate the efficacy of the proposed approach, a certain number of experiments are carried out on the simulated dataset.ConclusionThe proposed method is a fast and accurate registration method that can provide 3D information about the vertebral body. This 3D information is useful to improve accuracy during various clinical diagnoses.

Pseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition.

Automatic whole brain and lesion segmentation at 7T presents challenges, primarily from bias fields, susceptibility artifacts including distortions, and registration errors. Here, we sought to use deep learning algorithms (D/L) to do both skull stripping and whole brain segmentation on multiple imaging contrasts generated in a single Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) acquisition on participants clinically diagnosed with multiple sclerosis (MS), bypassing registration errors. Brain scans Segmentation from 3T and 7T scanners were analyzed with software packages such as FreeSurfer, Classification using Derivative-based Features (C-DEF), nnU-net, and a novel 3T-to-7T transfer learning method, Pseudo-Label Assisted nnU-Net (PLAn). 3T and 7T MRIs acquired within 9 months from 25 study participants with MS (Cohort 1) were used for training and optimizing. Eight MS patients (Cohort 2) scanned only at 7T, but with expert annotated lesion segmentation, was used to further validate the algorithm on a completely unseen dataset. Segmentation results were rated visually by experts in a blinded fashion and quantitatively using Dice Similarity Coefficient (DSC). Of the methods explored here, nnU-Net and PLAn produced the best tissue segmentation at 7T for all tissue classes. In both quantitative and qualitative analysis, PLAn significantly outperformed nnU-Net (and other methods) in lesion detection in both cohorts. PLAn's lesion DSC improved by 16% compared to nnU-Net. Limited availability of labeled data makes transfer learning an attractive option, and pre-training a nnUNet model using readily obtained 3T pseudo-labels was shown to boost lesion detection capabilities at 7T.

UPL-SFDA: Uncertainty-Aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation.

Domain Adaptation (DA) is important for deep learning-based medical image segmentation models to deal with testing images from a new target domain. As the source-domain data are usually unavailable when a trained model is deployed at a new center, Source-Free Domain Adaptation (SFDA) is appealing for data and annotation-efficient adaptation to the target domain. However, existing SFDA methods have a limited performance due to lack of sufficient supervision with source-domain images unavailable and target-domain images unlabeled. We propose a novel Uncertainty-aware Pseudo Label guided (UPL) SFDA method for medical image segmentation. Specifically, we propose Target Domain Growing (TDG) to enhance the diversity of predictions in the target domain by duplicating the pre-trained model's prediction head multiple times with perturbations. The different predictions in these duplicated heads are used to obtain pseudo labels for unlabeled target-domain images and their uncertainty to identify reliable pseudo labels. We also propose a Twice Forward pass Supervision (TFS) strategy that uses reliable pseudo labels obtained in one forward pass to supervise predictions in the next forward pass. The adaptation is further regularized by a mean prediction-based entropy minimization term that encourages confident and consistent results in different prediction heads. UPL-SFDA was validated with a multi-site heart MRI segmentation dataset, a cross-modality fetal brain segmentation dataset, and a 3D fetal tissue segmentation dataset. It improved the average Dice by 5.54, 5.01 and 6.89 percentage points for the three tasks compared with the baseline, respectively, and outperformed several state-of-the-art SFDA methods.

Tau PET accumulation in Brodmann areas 35 and 36 is associated with individual differences in cognition in non‐demented older adults

AbstractBackgroundMounting evidence indicates that tau accumulation in the entorhinal cortex (EC) occurs early in the course of Alzheimer’s disease (AD). Recent advances in automated segmentation methods allow for the investigation of smaller regions of the medial temporal lobes (MTL), including subregions of the EC. This study examined tau deposition in relation to individual differences in cognition among older adults, assessing whether MTL subregions explained a greater proportion of variance in cognition, when compared to standard labeling methods.MethodAnalyses included 91 BIOCARD study participants who were cognitively unimpaired (CU; n = 82) or had mild cognitive impairment (MCI; n = 9). Stepwise linear regressions were used to examine the contributions of regional tau burden to individual differences in the CDR sum of boxes (CDR‐SB), MMSE, and composite scores of global cognition and memory. Other model variables included amyloid burden, APOE4 status, sex, and education. Amyloid burden was assessed by 11C‐PiB and regional tau was assessed by 18F‐MK‐6240 PET. SUVR values representing tau accumulation were extracted using two MRI segmentation methods: (1) the FreeSurfer‐derived EC label, and (2) Automatic Segmentation of Hippocampal Subfields (ASHS)‐derived MTL subregions, including the EC and Brodmann areas 35 and 36 (Br35, Br36) defined in 1mm‐MNI space. Partial volume correction was applied to the motion‐corrected PET data.ResultTau burden in the right Br35, right Br36, and age were significant predictors of CDR‐SB scores, with the greatest proportion of variance explained when all three were included. The FreeSurfer‐labeled EC and other variables did not significantly contribute to the model. Right Br36 and age were significant predictors of MMSE while right Br36 and APOE4 status were significant predictors of the global cognition composite score, and right Br36 was a significant predictor of the memory composite score. Follow‐up analyses showed that addition of the FreeSurfer EC region did not significantly contribute to any of the models.ConclusionQuantifying tau burden in Br35 and Br36 better accounted for individual variability in cognition, when compared to standard EC labeling approaches. This suggests tau burden in these subregions may help identify CU and MCI individuals who are on a trajectory of decline due to AD.

Hybrid UNet transformer architecture for ischemic stoke segmentation with MRI and CT datasets.

A hybrid UNet and Transformer (HUT) network is introduced to combine the merits of the UNet and Transformer architectures, improving brain lesion segmentation from MRI and CT scans. The HUT overcomes the limitations of conventional approaches by utilizing two parallel stages: one based on UNet and the other on Transformers. The Transformer-based stage captures global dependencies and long-range correlations. It uses intermediate feature vectors from the UNet decoder and improves segmentation accuracy by enhancing the attention and relationship modeling between voxel patches derived from the 3D brain volumes. In addition, HUT incorporates self-supervised learning on the transformer network. This allows the transformer network to learn by maintaining consistency between the classification layers of the different resolutions of patches and augmentations. There is an improvement in the rate of convergence of the training and the overall capability of segmentation. Experimental results on benchmark datasets, including ATLAS and ISLES2018, demonstrate HUT's advantage over the state-of-the-art methods. HUT achieves higher Dice scores and reduced Hausdorff Distance scores in single-modality and multi-modality lesion segmentation. HUT outperforms the state-the-art network SPiN in the single-modality MRI segmentation on Anatomical Tracings of lesion After Stroke (ATLAS) dataset by 4.84% of Dice score and a large margin of 40.7% in the Hausdorff Distance score. HUT also performed well on CT perfusion brain scans in the Ischemic Stroke Lesion Segmentation (ISLES2018) dataset and demonstrated an improvement over the recent state-of-the-art network USSLNet by 3.3% in the Dice score and 12.5% in the Hausdorff Distance score. With the analysis of both single and multi-modalities datasets (ATLASR12 and ISLES2018), we show that HUT can perform and generalize well on different datasets. Code is available at: https://github.com/vicsohntu/HUT_CT.

Estimated Prostate Volume by Semiautomatic Segmentation of MRI Is More Accurately Correlated with Radical Prostatectomy Specimen Weight than the Volume Calculated by Ellipsoid Formula

Introduction: Accurate in vivo prostate volume (PV) estimation is important for obtaining prostate-specific antigen density (PSAD) and further predicting clinically significant prostate cancer (csPCa). We aimed to evaluate the accuracy of multiparametric magnetic resonance imaging (mpMRI)-estimated PV compared to both volume and weight of radical prostatectomy (RP). Methods: We identified 310 PCa patients who underwent RP following combined targeted and systematic biopsy in our institution from September 2019 to February 2021. The MRI PV was determined using a semiautomated segmentation algorithm. RP PV was calculated using the prolate ellipsoid formula (length × width × height × π/6). Formula (prostate weight = [actual weight−3.8 g]/1.05 g/mL) was applied, and the resulting volume was used in further analysis. Results: The median PV from MRI, RP, and RP weight were 39 mL, 38 mL, and 44 mL, respectively. Spearman’s rank correlation coefficients (ρ) were 0.841 (MRI PV vs. RP weight), 0.758 (RP PV vs. RP weight), and 0.707 (MRI PV vs. RP PV) (all p < 0.001). Decreased correlation between the MRI PV and RP PV was observed in the larger (more than 55 mL) prostate. The PSAD derived from MRI PV showed most efficient to detect csPCa in RP specimen (57.9% vs. 57.6% vs. 45.4%). Conclusion: MRI PV is correlated better with RP weight than calculated RP PV, especially in larger prostate. The high csPCa detection rate in final pathology suggested that PSAD derived from MRI PV can be confidently used in clinical practice.

Explainable AI-based Alzheimer's prediction and management using multimodal data.

According to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world's elderly people. Day by day the number of Alzheimer's patients is rising. Considering the increasing rate and the dangers, Alzheimer's disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer's diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data. To solve these issues, this paper proposes a novel explainable Alzheimer's disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, MRI segmentation data, and psychological data. However, currently, there is very little understanding of multimodal five-class classification of Alzheimer's disease. For predicting five class classifications, 9 most popular Machine Learning models are used. These models are Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Adaptive Boosting (AdaB), Support Vector Machine (SVM), and Naive Bayes (NB). Among these models RF has scored the highest value. Besides for explainability, SHapley Additive exPlanation (SHAP) is used in this research work. The performance evaluation demonstrates that the RF classifier has a 10-fold cross-validation accuracy of 98.81% for predicting Alzheimer's disease, cognitively normal, non-Alzheimer's dementia, uncertain dementia, and others. In addition, the study utilized Explainable Artificial Intelligence based on the SHAP model and analyzed the causes of prediction. To the best of our knowledge, we are the first to present this multimodal (Clinical, Psychological, and MRI segmentation data) five-class classification of Alzheimer's disease using Open Access Series of Imaging Studies (OASIS-3) dataset. Besides, a novel Alzheimer's patient management architecture is also proposed in this work.