Evaluation of an artificial intelligent hydrocephalus diagnosis model based on transfer learning

Artificial Intelligence in the Training of Radiology Residents: a Multicenter Randomized Controlled Trial

The aim of the present study was to compare the effectiveness of AI-assisted training and conventional human training in clinical practice. This was a multicenter, randomized, controlled clinical trial conducted in five national-level residency training hospitals. Residents from five hospitals participated, divided into three groups: conventional training (Group A), conventional plus specialty training (Group B), and conventional plus AI-assisted training (Group C). The content of the training was ultrasound diagnosis of thyroid nodules. The training lasted for 18 months, and the three groups of participants were phase-tested every 3 months to compare the effect of the training. The diagnostic accuracy of all three groups gradually increased with increasing training time. Among the three groups, groups B and C had higher accuracy than group A (P < .001), and there was no significant difference between groups B and C (P = .64). Over the training period, diagnostic confidence increased in all groups. Negative activating emotions decreased significantly over time in all groups (95% CI, - 0.81 to - 0.37; P < .001), while positive activating emotions increased significantly (95% CI, 0.18 to 0.53; P < .001). Current research shows that all three approaches are viable for training radiology residents. Furthermore, the AI-assisted approach had no negative emotional impact on the trainees, suggesting that integrating AI into radiology training programs could provide a reliable and effective means of achieving the educational goals of medical education.

The Quantitative Evaluation of Automatic Segmentation in Lumbar Magnetic Resonance Images

OBJECTIVE

This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans.

METHODS

Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net's segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness.

RESULTS

The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements.

CONCLUSION

Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Structural neuroimaging markers of normal pressure hydrocephalus versus Alzheimer's dementia and Parkinson's disease, and hydrocephalus versus atrophy in chronic TBI-a narrative review

Introduction

Normal Pressure Hydrocephalus (NPH) is a prominent type of reversible dementia that may be treated with shunt surgery, and it is crucial to differentiate it from irreversible degeneration caused by its symptomatic mimics like Alzheimer's Dementia (AD) and Parkinson's Disease (PD). Similarly, it is important to distinguish between (normal pressure) hydrocephalus and irreversible atrophy/degeneration which are among the chronic effects of Traumatic Brain Injury (cTBI), as the former may be reversed through shunt placement. The purpose of this review is to elucidate the structural imaging markers which may be foundational to the development of accurate, noninvasive, and accessible solutions to this problem.

Methods

By searching the PubMed database for keywords related to NPH, AD, PD, and cTBI, we reviewed studies that examined the (1) distinct neuroanatomical markers of degeneration in NPH versus AD and PD, and atrophy versus hydrocephalus in cTBI and (2) computational methods for their (semi-) automatic assessment on Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) scans.

Results

Structural markers of NPH and those that can distinguish it from AD have been well studied, but only a few studies have explored its structural distinction between PD. The structural implications of cTBI over time have been studied. But neuroanatomical markers that can predict shunt response in patients with either symptomatic idiopathic NPH or post-traumatic hydrocephalus have not been reliably established. MRI-based markers dominate this field of investigation as compared to CT, which is also reflected in the disproportionate number of MRI-based computational methods for their automatic assessment.

Conclusion

Along with an up-to-date literature review on the structural neurodegeneration due to NPH versus AD/PD, and hydrocephalus versus atrophy in cTBI, this article sheds light on the potential of structural imaging markers as (differential) diagnostic aids for the timely recognition of patients with reversible (normal pressure) hydrocephalus, and opportunities to develop computational tools for their objective assessment.

Automatic MRI volumetry in asymptomatic cases at risk for normal pressure hydrocephalus

The occurrence of significant Alzheimer's disease (AD) pathology was described in approximately 30% of normal pressure hydrocephalus (NPH) cases, leading to the distinction between neurodegenerative and idiopathic forms of this disorder. Whether or not there is a specific MRI signature of NPH remains a matter of debate. The present study focuses on asymptomatic cases at risk for NPH as defined with automatic machine learning tools and combines automatic MRI assessment of cortical and white matter volumetry, risk of AD (AD-RAI), and brain age gap estimation (BrainAge). Our hypothesis was that brain aging and AD process-independent volumetric changes occur in asymptomatic NPH-positive cases. We explored the volumetric changes in normal aging-sensitive (entorhinal cortex and parahippocampal gyrus/PHG) and AD-signature areas (hippocampus), four control cortical areas (frontal, parietal, occipital, and temporal), and cerebral and cerebellar white matter in 30 asymptomatic cases at risk for NPH (NPH probability >30) compared to 30 NPH-negative cases (NPH probability <5) with preserved cognition. In univariate regression models, NPH positivity was associated with decreased volumes in the hippocampus, parahippocampal gyrus (PHG), and entorhinal cortex bilaterally. The strongest negative association was found in the left hippocampus that persisted when adjusting for AD-RAI and Brain Age values. A combined model including the three parameters explained 36.5% of the variance, left hippocampal volumes, and BrainAge values, which remained independent predictors of the NPH status. Bilateral PHG and entorhinal cortex volumes were negatively associated with NPH-positive status in univariate models but this relationship did not persist when adjusting for BrainAge, the latter remaining the only predictor of the NPH status. We also found a negative association between bilateral cerebral and cerebellar white matter volumes and NPH status that persisted after controlling for AD-RAI or Brain Age values, explaining between 50 and 65% of its variance. These observations support the idea that in cases at risk for NPH, as defined by support vector machine assessment of NPH-related MRI markers, brain aging-related and brain aging and AD-independent volumetric changes coexist. The latter concerns volume loss in restricted hippocampal and white matter areas that could be considered as the MRI signature of idiopathic forms of NPH.

The Diagnostic Accuracy of Artificial Intelligence in Radiological Markers of Normal-Pressure Hydrocephalus (NPH) on Non-Contrast CT Scans of the Brain

Diagnosing normal-pressure hydrocephalus (NPH) via non-contrast computed tomography (CT) brain scans is presently a formidable task due to the lack of universally agreed-upon standards for radiographic parameter measurement. A variety of radiological parameters, such as Evans' index, narrow sulci at high parietal convexity, Sylvian fissures' dilation, focally enlarged sulci, and more, are currently measured by radiologists. This study aimed to enhance NPH diagnosis by comparing the accuracy, sensitivity, specificity, and predictive values of radiological parameters, as evaluated by radiologists and AI methods, utilizing cerebrospinal fluid volumetry. Results revealed a sensitivity of 77.14% for radiologists and 99.05% for AI, with specificities of 98.21% and 57.14%, respectively, in diagnosing NPH. Radiologists demonstrated NPV, PPV, and an accuracy of 82.09%, 97.59%, and 88.02%, while AI reported 98.46%, 68.42%, and 77.42%, respectively. ROC curves exhibited an area under the curve of 0.954 for radiologists and 0.784 for AI, signifying the diagnostic index for NPH. In conclusion, although radiologists exhibited superior sensitivity, specificity, and accuracy in diagnosing NPH, AI served as an effective initial screening mechanism for potential NPH cases, potentially easing the radiologists' burden. Given the ongoing AI advancements, it is plausible that AI could eventually match or exceed radiologists' diagnostic prowess in identifying hydrocephalus.

Automatic Ventriculomegaly Detection in Fetal Brain MRI: A Step-by-Step Deep Learning Model for Novel 2D-3D Linear Measurements

In this study, we developed an automated workflow using a deep learning model (DL) to measure the lateral ventricle linearly in fetal brain MRI, which are subsequently classified into normal or ventriculomegaly, defined as a diameter wider than 10 mm at the level of the thalamus and choroid plexus. To accomplish this, we first trained a UNet-based deep learning model to segment the brain of a fetus into seven different tissue categories using a public dataset (FeTA 2022) consisting of fetal T2-weighted images. Then, an automatic workflow was developed to perform lateral ventricle measurement at the level of the thalamus and choroid plexus. The test dataset included 22 cases of normal and abnormal T2-weighted fetal brain MRIs. Measurements performed by our AI model were compared with manual measurements performed by a general radiologist and a neuroradiologist. The AI model correctly classified 95% of fetal brain MRI cases into normal or ventriculomegaly. It could measure the lateral ventricle diameter in 95% of cases with less than a 1.7 mm error. The average difference between measurements was 0.90 mm in AI vs. general radiologists and 0.82 mm in AI vs. neuroradiologists, which are comparable to the difference between the two radiologists, 0.51 mm. In addition, the AI model also enabled the researchers to create 3D-reconstructed images, which better represent real anatomy than 2D images. When a manual measurement is performed, it could also provide both the right and left ventricles in just one cut, instead of two. The measurement difference between the general radiologist and the algorithm (p = 0.9827), and between the neuroradiologist and the algorithm (p = 0.2378), was not statistically significant. In contrast, the difference between general radiologists vs. neuroradiologists was statistically significant (p = 0.0043). To the best of our knowledge, this is the first study that performs 2D linear measurement of ventriculomegaly with a 3D model based on an artificial intelligence approach. The paper presents a step-by-step approach for designing an AI model based on several radiological criteria. Overall, this study showed that AI can automatically calculate the lateral ventricle in fetal brain MRIs and accurately classify them as abnormal or normal.

Augmented Reality Surgical Navigation System Integrated with Deep Learning

Most current surgical navigation methods rely on optical navigators with images displayed on an external screen. However, minimizing distractions during surgery is critical and the spatial information displayed in this arrangement is non-intuitive. Previous studies have proposed combining optical navigation systems with augmented reality (AR) to provide surgeons with intuitive imaging during surgery, through the use of planar and three-dimensional imagery. However, these studies have mainly focused on visual aids and have paid relatively little attention to real surgical guidance aids. Moreover, the use of augmented reality reduces system stability and accuracy, and optical navigation systems are costly. Therefore, this paper proposed an augmented reality surgical navigation system based on image positioning that achieves the desired system advantages with low cost, high stability, and high accuracy. This system also provides intuitive guidance for the surgical target point, entry point, and trajectory. Once the surgeon uses the navigation stick to indicate the position of the surgical entry point, the connection between the surgical target and the surgical entry point is immediately displayed on the AR device (tablet or HoloLens glasses), and a dynamic auxiliary line is shown to assist with incision angle and depth. Clinical trials were conducted for EVD (extra-ventricular drainage) surgery, and surgeons confirmed the system's overall benefit. A "virtual object automatic scanning" method is proposed to achieve a high accuracy of 1 ± 0.1 mm for the AR-based system. Furthermore, a deep learning-based U-Net segmentation network is incorporated to enable automatic identification of the hydrocephalus location by the system. The system achieves improved recognition accuracy, sensitivity, and specificity of 99.93%, 93.85%, and 95.73%, respectively, representing a significant improvement from previous studies.

Influence of Percutaneous Drainage Surgery and the Interval to Perform Laparoscopic Cholecystectomy on Acute Cholecystitis through Genetic Algorithm-Based Contrast-Enhanced Ultrasound Imaging

To discuss the optimal interval time between genetic algorithm-based ultrasound imaging-guided percutaneous drainage surgery (PTGD) and laparoscopic cholecystectomy (LC), 64 cholecystitis patients were selected as the research objects and evenly divided into experimental group (intelligent algorithm was adopted to recognize patients’ ultrasonic images) and control group (professional doctors carried out diagnosis). 92 acute cholecystitis patients undergoing PTGD were divided into three groups. 30 out of the 92 patients received LC within 2 months and were defined as the early group. 32 were performed with LC within 2 to 4 months and were defined as the metaphase group. 28 underwent LC over 4 months and were defined as the late-stage group. The average operation time, the transition from LC to laparotomy, the average postoperative hospital stay, and the incidence of complications of the three groups were compared. The results revealed that the comparison of the diagnostic accuracy and comprehensive effectiveness between experimental group and control group demonstrated that the differences were statistically significant ( $P<0.05$ ). When the optimal interval of implementing LC after PTGD was realized, the corresponding values of the early group were 88.5 minutes, 16.67%, 8.13 days, and 13.75%. Those of the metaphase group were 49.91 minutes, 3.13%, 4.97 days, and 9.52%. Those of the late stage group were 68.78 minutes, 10.71%, 7.09 days, and 11.96%. To sum up, the diagnostic accuracy and comprehensive effectiveness of intelligent algorithm were higher than those of conventional ultrasound, and the optimal interval time of implementing LC after PTGD was 2 to 4 months.

[Brain MRI-Based Artificial Intelligence Software in Patients with Neurodegenerative Diseases: Current Status]

The incidence of neurodegenerative diseases in the older population has increased in recent years. A considerable number of studies have been performed to characterize these diseases. Imaging analysis is an important biomarker for the diagnosis of neurodegenerative disease. Objective and reliable assessment and precise detection are important for the early diagnosis of neurodegenerative diseases. Artificial intelligence (AI) using brain MRI applied to the study of neurodegenerative diseases could promote early diagnosis and optimal decisions for treatment plans. MRI-based AI software have been developed and studied worldwide. Representatively, there are MRI-based volumetry and segmentation software. In this review, we present the development process of brain volumetry analysis software in neurodegenerative diseases, currently used and developed AI software for neurodegenerative disease in the Republic of Korea, probable uses of AI in the future, and AI software limitations.

Progression in Neuroimaging of Normal Pressure Hydrocephalus

Normal-pressure hydrocephalus is a clinical syndrome that mainly targets the elderly population. It features dementia, impaired walking, and the malfunction of sphincters. The rapid identification and large-scale screening of patients with normal-pressure hydrocephalus (NPH) are of great significance as surgical interventions can greatly improve or even reverse the symptoms. This review aims to summarize the traditional parameters used to diagnose NPH and the emerging progression in neuroimaging of the disease, hoping to provide an up-to-date overall perspective and summarize the possible direction of its future development.

A Novel deep learning approach for the automated diagnosis of normal pressure hydrocephalus

 Normal Pressure Hydrocephalus (NPH), an Atypical Parkinsonian syndrome, is a neurological syndrome that mainly affects elderly people. This syndrome shows the symptoms of Parkinson’s disease (PD), such as walking impairment, dementia, impaired bladder control, and mental impairment. The Magnetic Resonance Imaging (MRI) is the aptest modality for the detection of the abnormal build-up of cerebrospinal fluid in the brain’s cavities or ventricles, which is the major cause of NPH. This work aims to develop an automated biomarker for NPH segmentation and classification (NPH-SC) that efficiently detect hydrocephalus using a deep learning-based approach. Removal of non-cerebral tissues (skull, scalp, and dura) and noise from brain images by skull stripping, unsharp-mask based edge sharpening, segmentation by marker-based watershed algorithm, and labelling are performed to improve the accuracy of the CNN based classification system. The brain ventricles are extracted using the external and internal markers and then fed into the convolutional neural networks (CNN) for classification. This automated NPH-SC model achieved a sensitivity of 96%, a specificity of 100%, and a validation accuracy of 97%. The prediction system, with the help of a CNN classifier, is used for the calculation of test accuracy of the system and obtained promising 98% accuracy.

Multi-Class brain normality and abnormality diagnosis using modified Faster R-CNN

BACKGROUND AND OBJECTIVE

The detection and analysis of brain disorders through medical imaging techniques are extremely important to get treatment on time and sustain a healthy lifestyle. Disorders cause permanent brain damage and alleviate the lifespan. Moreover, the classification of large volumes of medical image data manually by medicine experts is tiring, time-consuming, and prone to errors. This study aims to diagnose brain normality and abnormalities using a novel ResNet50 modified Faster Regions with Convolutional Neural Network(R-CNN) model. The classification task is performed into multiple classes which are hemorrhage, hydrocephalus, and normal. The proposed model both determines the borders of the normal/abnormal parts and classifies them with the highest accuracy.

METHODS

To provide a comprehensive performance analysis in the classification problem, Machine Learning(ML) and Deep Learning(DL) techniques were discussed. Artificial Neural Network(ANN), AdaBoost(AB), Decision Tree(DT), Logistic Regression(LR), Naive Bayes(NB), Random Forest(RF), and Support Vector Machine(SVM) were used as ML models. Besides, various Convolutional Neural Network(CNN) models and proposed ResNet50 modified Faster R-CNN model were used as DL models. Methods were validated using a novel brain dataset that contains both normal and abnormal images.

RESULTS

Based on results, LR obtained the highest result among ML methods and DenseNet201 obtained the highest results among CNN models with the accuracy of 84.80% and 85.68% for the classification task, respectively. Besides, the accuracy obtained by the proposed model is 99.75%.

CONCLUSIONS

Experimental results demonstrate that the proposed model has yielded better performance for detection and classification tasks. This artificial intelligence(AI) framework can be utilized as a computer-aided medical decision support system for medical experts.

SVM-Based Normal Pressure Hydrocephalus Detection

Background and Purpose

As magnetic resonance imaging (MRI) signs of normal pressure hydrocephalus (NPH) may precede clinical symptoms we sought to evaluate an algorithm that automatically detects this pattern.

Methods

A support vector machine (SVM) was trained in 30 NPH patients treated with ventriculoperitoneal shunts and 30 healthy controls. For comparison, four neuroradiologists visually assessed sagittal MPRAGE images and graded them as no NPH pattern, possible NPH pattern, or definite NPH pattern.

Results

Human accuracy to visually detect a NPH was between 0.85 and 0.97. Interobserver agreement was substantial (κ = 0.656). Accuracy of the SVM algorithm was 0.93 and AUROC 0.99. Among 272 prespecified regions, gray matter and CSF volumes of both caudate, the right parietal operculum, the left basal forebrain, and the 4th ventricle showed the highest discriminative power to separate a NPH and a no NPH pattern.

Conclusion

A NPH pattern can be reliably detected using a support vector machine (SVM). Its role in the work-up of asymptomatic patients or neurodegenerative disease has to be evaluated.