Research

12 pages, 2471 KiB

Open AccessArticle

Deep Learning-Driven Estimation of Centiloid Scales from Amyloid PET Images with ¹¹C-PiB and ¹⁸F-Labeled Tracers in Alzheimer’s Disease

by Tensho Yamao, Kenta Miwa, Yuta Kaneko, Noriyuki Takahashi, Noriaki Miyaji, Koki Hasegawa, Kei Wagatsuma, Yuto Kamitaka, Hiroshi Ito and Hiroshi Matsuda

Brain Sci. 2024, 14(4), 406; https://doi.org/10.3390/brainsci14040406 - 21 Apr 2024

Viewed by 266

Abstract

Background: Standard methods for deriving Centiloid scales from amyloid PET images are time-consuming and require considerable expert knowledge. We aimed to develop a deep learning method of automating Centiloid scale calculations from amyloid PET images with ¹¹C-Pittsburgh Compound-B (PiB) tracer and assess [...] Read more.

Background: Standard methods for deriving Centiloid scales from amyloid PET images are time-consuming and require considerable expert knowledge. We aimed to develop a deep learning method of automating Centiloid scale calculations from amyloid PET images with ¹¹C-Pittsburgh Compound-B (PiB) tracer and assess its applicability to ¹⁸F-labeled tracers without retraining. Methods: We trained models on 231 ¹¹C-PiB amyloid PET images using a 50-layer 3D ResNet architecture. The models predicted the Centiloid scale, and accuracy was assessed using mean absolute error (MAE), linear regression analysis, and Bland–Altman plots. Results: The MAEs for Alzheimer’s disease (AD) and young controls (YC) were 8.54 and 2.61, respectively, using ¹¹C-PiB, and 8.66 and 3.56, respectively, using ¹⁸F-NAV4694. The MAEs for AD and YC were higher with ¹⁸F-florbetaben (39.8 and 7.13, respectively) and ¹⁸F-florbetapir (40.5 and 12.4, respectively), and the error rate was moderate for ¹⁸F-flutemetamol (21.3 and 4.03, respectively). Linear regression yielded a slope of 1.00, intercept of 1.26, and R² of 0.956, with a mean bias of −1.31 in the Centiloid scale prediction. Conclusions: We propose a deep learning means of directly predicting the Centiloid scale from amyloid PET images in a native space. Transferring the model trained on ¹¹C-PiB directly to ¹⁸F-NAV4694 without retraining was feasible. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

26 pages, 2275 KiB

Open AccessArticle

Positive Effect of Super-Resolved Structural Magnetic Resonance Imaging for Mild Cognitive Impairment Detection

by Ovidijus Grigas, Robertas Damaševičius and Rytis Maskeliūnas

Brain Sci. 2024, 14(4), 381; https://doi.org/10.3390/brainsci14040381 - 14 Apr 2024

Viewed by 370

Abstract

This paper presents a novel approach to improving the detection of mild cognitive impairment (MCI) through the use of super-resolved structural magnetic resonance imaging (MRI) and optimized deep learning models. The study introduces enhancements to the perceptual quality of super-resolved 2D structural MRI [...] Read more.

This paper presents a novel approach to improving the detection of mild cognitive impairment (MCI) through the use of super-resolved structural magnetic resonance imaging (MRI) and optimized deep learning models. The study introduces enhancements to the perceptual quality of super-resolved 2D structural MRI images using advanced loss functions, modifications to the upscaler part of the generator, and experiments with various discriminators within a generative adversarial training setting. It empirically demonstrates the effectiveness of super-resolution in the MCI detection task, showcasing performance improvements across different state-of-the-art classification models. The paper also addresses the challenge of accurately capturing perceptual image quality, particularly when images contain checkerboard artifacts, and proposes a methodology that incorporates hyperparameter optimization through a Pareto optimal Markov blanket (POMB). This approach systematically explores the hyperparameter space, focusing on reducing overfitting and enhancing model generalizability. The research findings contribute to the field by demonstrating that super-resolution can significantly improve the quality of MRI images for MCI detection, highlighting the importance of choosing an adequate discriminator and the potential of super-resolution as a preprocessing step to boost classification model performance. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

12 pages, 1502 KiB

Open AccessArticle

Can Brain Volume-Driven Characteristic Features Predict the Response of Alzheimer’s Patients to Repetitive Transcranial Magnetic Stimulation? A Pilot Study

by Chandan Saha, Chase R. Figley, Brian Lithgow, Paul B. Fitzgerald, Lisa Koski, Behzad Mansouri, Neda Anssari, Xikui Wang and Zahra Moussavi

Brain Sci. 2024, 14(3), 226; https://doi.org/10.3390/brainsci14030226 - 28 Feb 2024

Viewed by 790

Abstract

This study is a post-hoc examination of baseline MRI data from a clinical trial investigating the efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for patients with mild–moderate Alzheimer’s disease (AD). Herein, we investigated whether the analysis of baseline MRI data [...] Read more.

This study is a post-hoc examination of baseline MRI data from a clinical trial investigating the efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for patients with mild–moderate Alzheimer’s disease (AD). Herein, we investigated whether the analysis of baseline MRI data could predict the response of patients to rTMS treatment. Whole-brain T1-weighted MRI scans of 75 participants collected at baseline were analyzed. The analyses were run on the gray matter (GM) and white matter (WM) of the left and right dorsolateral prefrontal cortex (DLPFC), as that was the rTMS application site. The primary outcome measure was the Alzheimer’s disease assessment scale—cognitive subscale (ADAS-Cog). The response to treatment was determined based on ADAS-Cog scores and secondary outcome measures. The analysis of covariance showed that responders to active treatment had a significantly lower baseline GM volume in the right DLPFC and a higher GM asymmetry index in the DLPFC region compared to those in non-responders. Logistic regression with a repeated five-fold cross-validated analysis using the MRI-driven features of the initial 75 participants provided a mean accuracy of 0.69 and an area under the receiver operating characteristic curve of 0.74 for separating responders and non-responders. The results suggest that GM volume or asymmetry in the target area of active rTMS treatment (DLPFC region in this study) may be a weak predictor of rTMS treatment efficacy. These results need more data to draw more robust conclusions. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

11 pages, 2691 KiB

Open AccessArticle

The Commonality and Individuality of Human Brains When Performing Tasks

by Jie Huang

Brain Sci. 2024, 14(2), 125; https://doi.org/10.3390/brainsci14020125 - 25 Jan 2024

Viewed by 836

Abstract

It is imperative to study individual brain functioning toward understanding the neural bases responsible for individual behavioral and clinical traits. The complex and dynamic brain activity varies from area to area and from time to time across the entire brain, and BOLD-fMRI measures [...] Read more.

It is imperative to study individual brain functioning toward understanding the neural bases responsible for individual behavioral and clinical traits. The complex and dynamic brain activity varies from area to area and from time to time across the entire brain, and BOLD-fMRI measures this spatiotemporal activity at large-scale systems level. We present a novel method to investigate task-evoked whole brain activity that varies not only from person to person but also from task trial to trial within each task type, offering a means of characterizing the individuality of human brains when performing tasks. For each task trial, the temporal correlation of task-evoked ideal time signal with the time signal of every point in the brain yields a full spatial map that characterizes the whole brain’s functional co-activity (FC) relative to the task-evoked ideal response. For any two task trials, regardless of whether they are the same task or not, the spatial correlation of their corresponding two FC maps over the entire brain quantifies the similarity between these two maps, offering a means of investigating the variation in the whole brain activity trial to trial. The results demonstrated a substantially varied whole brain activity from trial to trial for each task category. The degree of this variation was task type-dependent and varied from subject to subject, showing a remarkable individuality of human brains when performing tasks. It demonstrates the potential of using the presented method to investigate the relationship of the whole brain activity with individual behavioral and clinical traits. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

19 pages, 19765 KiB

Open AccessArticle

The Effects of Distancing Design Collaboration Necessitated by COVID-19 on Brain Synchrony in Teams Compared to Co-Located Design Collaboration: A Preliminary Study

by Yi-Teng Shih, Luqian Wang, Clive H. Y. Wong, Emily L. L. Sin, Matthias Rauterberg, Zhen Yuan and Leanne Chang

Brain Sci. 2024, 14(1), 60; https://doi.org/10.3390/brainsci14010060 - 07 Jan 2024

Viewed by 1338

Abstract

Due to the widespread involvement of distributed collaboration triggered by COVID-19, it has become a new trend that has continued into the post-pandemic era. This study investigated collective performance within two collaborative environments (co-located and distancing settings) by assessing inter-brain synchrony patterns (IBS) [...] Read more.

Due to the widespread involvement of distributed collaboration triggered by COVID-19, it has become a new trend that has continued into the post-pandemic era. This study investigated collective performance within two collaborative environments (co-located and distancing settings) by assessing inter-brain synchrony patterns (IBS) among design collaborators using functional near-infrared spectroscopy. The preliminary study was conducted with three dyads who possessed 2–3 years of professional product design experience. Each dyad completed two designated design tasks in distinct settings. In the distributed condition, participants interacted through video conferencing in which they were allowed to communicate by verbalization and sketching using a shared digital whiteboard. To prevent the influences of different sketching tools on design outputs, we employed digital sketching for both environments. The interactions between collaborators were identified in three behaviors: verbal only, sketch only, and mixed communication (verbal and sketch). The consequences revealed a higher level of IBS when mixed communication took place in distributed conditions than in co-located conditions. Comparably, the occurrence of IBS increased when participants solely utilized sketching as the interaction approach within the co-located setting. A mixed communication method combining verbalization and sketching might lead to more coordinated cognitive processes when in physical isolation. Design collaborators are inclined to adjust their interaction behaviors in order to adapt to different design environments, strengthen the exchange of ideas, and construct design consensus. Overall, the present paper discussed the performance of virtual collaborative design based on a neurocognitive perspective, contributing valuable insights for the future intervention design that promotes effective virtual teamwork. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

18 pages, 3779 KiB

Open AccessArticle

Distinguishing Laparoscopic Surgery Experts from Novices Using EEG Topographic Features

by Takahiro Manabe, F.N.U. Rahul, Yaoyu Fu, Xavier Intes, Steven D. Schwaitzberg, Suvranu De, Lora Cavuoto and Anirban Dutta

Brain Sci. 2023, 13(12), 1706; https://doi.org/10.3390/brainsci13121706 - 11 Dec 2023

Viewed by 1056

Abstract

The study aimed to differentiate experts from novices in laparoscopic surgery tasks using electroencephalogram (EEG) topographic features. A microstate-based common spatial pattern (CSP) analysis with linear discriminant analysis (LDA) was compared to a topography-preserving convolutional neural network (CNN) approach. Expert surgeons (N = [...] Read more.

The study aimed to differentiate experts from novices in laparoscopic surgery tasks using electroencephalogram (EEG) topographic features. A microstate-based common spatial pattern (CSP) analysis with linear discriminant analysis (LDA) was compared to a topography-preserving convolutional neural network (CNN) approach. Expert surgeons (N = 10) and novice medical residents (N = 13) performed laparoscopic suturing tasks, and EEG data from 8 experts and 13 novices were analysed. Microstate-based CSP with LDA revealed distinct spatial patterns in the frontal and parietal cortices for experts, while novices showed frontal cortex involvement. The 3D CNN model (ESNet) demonstrated a superior classification performance (accuracy > 98%, sensitivity 99.30%, specificity 99.70%, F1 score 98.51%, MCC 97.56%) compared to the microstate based CSP analysis with LDA (accuracy ~90%). Combining spatial and temporal information in the 3D CNN model enhanced classifier accuracy and highlighted the importance of the parietal–temporal–occipital association region in differentiating experts and novices. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

12 pages, 1488 KiB

Open AccessArticle

Automatic Diagnosis of Major Depressive Disorder Using a High- and Low-Frequency Feature Fusion Framework

by Junyu Wang, Tongtong Li, Qi Sun, Yuhui Guo, Jiandong Yu, Zhijun Yao, Ning Hou and Bin Hu

Brain Sci. 2023, 13(11), 1590; https://doi.org/10.3390/brainsci13111590 - 15 Nov 2023

Cited by 1 | Viewed by 1077

Abstract

Major Depressive Disorder (MDD) is a common mental illness resulting in immune disorders and even thoughts of suicidal behavior. Neuroimaging techniques serve as a quantitative tool for the assessment of MDD diagnosis. In the domain of computer-aided magnetic resonance imaging diagnosis, current research [...] Read more.

Major Depressive Disorder (MDD) is a common mental illness resulting in immune disorders and even thoughts of suicidal behavior. Neuroimaging techniques serve as a quantitative tool for the assessment of MDD diagnosis. In the domain of computer-aided magnetic resonance imaging diagnosis, current research predominantly focuses on isolated local or global information, often neglecting the synergistic integration of multiple data sources, thus potentially overlooking valuable details. To address this issue, we proposed a diagnostic model for MDD that integrates high-frequency and low-frequency information using data from diffusion tensor imaging (DTI), structural magnetic resonance imaging (sMRI), and functional magnetic resonance imaging (fMRI). First, we designed a meta-low-frequency encoder (MLFE) and a meta-high-frequency encoder (MHFE) to extract the low-frequency and high-frequency feature information from DTI and sMRI, respectively. Then, we utilized a multilayer perceptron (MLP) to extract features from fMRI data. Following the feature cross-fusion, we designed the ensemble learning threshold voting method to determine the ultimate diagnosis for MDD. The model achieved accuracy, precision, specificity, F1-score, MCC, and AUC values of 0.724, 0.750, 0.882, 0.600, 0.421, and 0.667, respectively. This approach provides new research ideas for the diagnosis of MDD. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

11 pages, 1555 KiB

Open AccessArticle

Auto-Classification of Parkinson’s Disease with Different Motor Subtypes Using Arterial Spin Labelling MRI Based on Machine Learning

by Jinhua Xiong, Haiyan Zhu, Xuhang Li, Shangci Hao, Yueyi Zhang, Zijian Wang and Qian Xi

Brain Sci. 2023, 13(11), 1524; https://doi.org/10.3390/brainsci13111524 - 29 Oct 2023

Cited by 1 | Viewed by 1075

Abstract

The purpose of this study was to automatically classify different motor subtypes of Parkinson’s disease (PD) on arterial spin labelling magnetic resonance imaging (ASL-MRI) data using support vector machine (SVM). This study included 38 subjects: 21 PD patients and 17 normal controls (NCs). [...] Read more.

The purpose of this study was to automatically classify different motor subtypes of Parkinson’s disease (PD) on arterial spin labelling magnetic resonance imaging (ASL-MRI) data using support vector machine (SVM). This study included 38 subjects: 21 PD patients and 17 normal controls (NCs). Based on the Unified Parkinson’s Disease Rating Scale (UPDRS) subscores, patients were divided into the tremor-dominant (TD) subtype and the postural instability gait difficulty (PIGD) subtype. The subjects were in a resting state during the acquisition of ASL-MRI data. The automated anatomical atlas 3 (AAL3) template was registered to obtain an ASL image of the same size and shape. We obtained the voxel values of 170 brain regions by considering the location coordinates of these regions and then normalized the data. The length of the feature vector depended on the number of voxel values in each brain region. Three binary classification models were utilized for classifying subjects’ data, and we applied SVM to classify voxels in the brain regions. The left subgenual anterior cingulate cortex (ACC_sub_L) was clearly distinguished in both NCs and PD patients using SVM, and we obtained satisfactory diagnostic rates (accuracy = 92.31%, specificity = 96.97%, sensitivity = 84.21%, and AUCmax = 0.9585). For the right supramarginal gyrus (SupraMarginal_R), SVM distinguished the TD group from the other groups with satisfactory diagnostic rates (accuracy = 84.21%, sensitivity = 63.64%, specificity = 92.59%, and AUCmax = 0.9192). For the right intralaminar of thalamus (Thal_IL_R), SVM distinguished the PIGD group from the other groups with satisfactory diagnostic rates (accuracy = 89.47%, sensitivity = 70.00%, specificity = 6.43%, and AUCmax = 0.9464). These results are consistent with the changes in blood perfusion related to PD subtypes. In addition, the sensitive brain regions of the TD group and PIGD group involve the brain regions where the cerebellothalamocortical (CTC) and the striatal thalamocortical (STC) loops are located. Therefore, it is suggested that the blood perfusion patterns of the two loops may be different. These characteristic brain regions could become potential imaging markers of cerebral blood flow to distinguish TD from PIGD. Meanwhile, our findings provide an imaging basis for personalised treatment, thereby optimising clinical diagnostic and treatment approaches. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

22 pages, 3602 KiB

Open AccessArticle

Brain Tumor Classification from MRI Using Image Enhancement and Convolutional Neural Network Techniques

by Zahid Rasheed, Yong-Kui Ma, Inam Ullah, Yazeed Yasin Ghadi, Muhammad Zubair Khan, Muhammad Abbas Khan, Akmalbek Abdusalomov, Fayez Alqahtani and Ahmed M. Shehata

Brain Sci. 2023, 13(9), 1320; https://doi.org/10.3390/brainsci13091320 - 14 Sep 2023

Cited by 4 | Viewed by 2001

Abstract

The independent detection and classification of brain malignancies using magnetic resonance imaging (MRI) can present challenges and the potential for error due to the intricate nature and time-consuming process involved. The complexity of the brain tumor identification process primarily stems from the need [...] Read more.

The independent detection and classification of brain malignancies using magnetic resonance imaging (MRI) can present challenges and the potential for error due to the intricate nature and time-consuming process involved. The complexity of the brain tumor identification process primarily stems from the need for a comprehensive evaluation spanning multiple modules. The advancement of deep learning (DL) has facilitated the emergence of automated medical image processing and diagnostics solutions, thereby offering a potential resolution to this issue. Convolutional neural networks (CNNs) represent a prominent methodology in visual learning and image categorization. The present study introduces a novel methodology integrating image enhancement techniques, specifically, Gaussian-blur-based sharpening and Adaptive Histogram Equalization using CLAHE, with the proposed model. This approach aims to effectively classify different categories of brain tumors, including glioma, meningioma, and pituitary tumor, as well as cases without tumors. The algorithm underwent comprehensive testing using benchmarked data from the published literature, and the results were compared with pre-trained models, including VGG16, ResNet50, VGG19, InceptionV3, and MobileNetV2. The experimental findings of the proposed method demonstrated a noteworthy classification accuracy of 97.84%, a precision success rate of 97.85%, a recall rate of 97.85%, and an F1-score of 97.90%. The results presented in this study showcase the exceptional accuracy of the proposed methodology in accurately classifying the most commonly occurring brain tumor types. The technique exhibited commendable generalization properties, rendering it a valuable asset in medicine for aiding physicians in making precise and proficient brain diagnoses. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

Review

Jump to: Research, Other

11 pages, 393 KiB

Open AccessReview

Artificial Intelligence as A Complementary Tool for Clincal Decision-Making in Stroke and Epilepsy

by Smit P. Shah and John D. Heiss

Brain Sci. 2024, 14(3), 228; https://doi.org/10.3390/brainsci14030228 - 28 Feb 2024

Viewed by 838

Abstract

Neurology is a quickly evolving specialty that requires clinicians to make precise and prompt diagnoses and clinical decisions based on the latest evidence-based medicine practices. In all Neurology subspecialties—Stroke and Epilepsy in particular—clinical decisions affecting patient outcomes depend on neurologists accurately assessing patient [...] Read more.

Neurology is a quickly evolving specialty that requires clinicians to make precise and prompt diagnoses and clinical decisions based on the latest evidence-based medicine practices. In all Neurology subspecialties—Stroke and Epilepsy in particular—clinical decisions affecting patient outcomes depend on neurologists accurately assessing patient disability. Artificial intelligence [AI] can predict the expected neurological impairment from an AIS [Acute Ischemic Stroke], the possibility of ICH [IntraCranial Hemorrhage] expansion, and the clinical outcomes of comatose patients. This review article informs readers of artificial intelligence principles and methods. The article introduces the basic terminology of artificial intelligence before reviewing current and developing AI applications in neurology practice. AI holds promise as a tool to ease a neurologist’s daily workflow and supply unique diagnostic insights by analyzing data simultaneously from several sources, including neurological history and examination, blood and CSF laboratory testing, CNS electrophysiologic evaluations, and CNS imaging studies. AI-based methods are poised to complement the other tools neurologists use to make prompt and precise decisions that lead to favorable patient outcomes. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

Other

Jump to: Research, Review

12 pages, 573 KiB

Open AccessPerspective

Artificial Intelligence’s Transformative Role in Illuminating Brain Function in Long COVID Patients Using PET/FDG

by Thorsten Rudroff

Brain Sci. 2024, 14(1), 73; https://doi.org/10.3390/brainsci14010073 - 10 Jan 2024

Viewed by 1044

Abstract

Cutting-edge brain imaging techniques, particularly positron emission tomography with Fluorodeoxyglucose (PET/FDG), are being used in conjunction with Artificial Intelligence (AI) to shed light on the neurological symptoms associated with Long COVID. AI, particularly deep learning algorithms such as convolutional neural networks (CNN) and [...] Read more.

Cutting-edge brain imaging techniques, particularly positron emission tomography with Fluorodeoxyglucose (PET/FDG), are being used in conjunction with Artificial Intelligence (AI) to shed light on the neurological symptoms associated with Long COVID. AI, particularly deep learning algorithms such as convolutional neural networks (CNN) and generative adversarial networks (GAN), plays a transformative role in analyzing PET scans, identifying subtle metabolic changes, and offering a more comprehensive understanding of Long COVID’s impact on the brain. It aids in early detection of abnormal brain metabolism patterns, enabling personalized treatment plans. Moreover, AI assists in predicting the progression of neurological symptoms, refining patient care, and accelerating Long COVID research. It can uncover new insights, identify biomarkers, and streamline drug discovery. Additionally, the application of AI extends to non-invasive brain stimulation techniques, such as transcranial direct current stimulation (tDCS), which have shown promise in alleviating Long COVID symptoms. AI can optimize treatment protocols by analyzing neuroimaging data, predicting individual responses, and automating adjustments in real time. While the potential benefits are vast, ethical considerations and data privacy must be rigorously addressed. The synergy of AI and PET scans in Long COVID research offers hope in understanding and mitigating the complexities of this condition. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

26 pages, 1285 KiB

Open AccessSystematic Review

Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review

by Marc Ghanem, Abdul Karim Ghaith, Victor Gabriel El-Hajj, Archis Bhandarkar, Andrea de Giorgio, Adrian Elmi-Terander and Mohamad Bydon

Brain Sci. 2023, 13(12), 1723; https://doi.org/10.3390/brainsci13121723 - 16 Dec 2023

Viewed by 1265

Abstract

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models’ effectiveness in clinical practice it is crucial to [...] Read more.

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models’ effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model’s area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings. Full article

(This article belongs to the Special Issue Advances of AI in Neuroimaging)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances of AI in Neuroimaging

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI