Brain Tumor Imaging Research Articles

Adaptive Detection and Classification of Brain Tumour Images Based on Photoacoustic Imaging

A new imaging technique called photoacoustic imaging (PAI) combines the advantages of ultrasound imaging and optical absorption to provide structural and functional details of tissues. It has broad application prospects in the accurate diagnosis and treatment monitoring of brain tumours. However, the existing photoacoustic image classification algorithms cannot effectively distinguish benign tumours from malignant tumours. To address this problem, the YoLov8-MedSAM model is proposed in this research to provide precise and adaptable brain tumour identification and detection segmentation. Additionally, it employs convolutional neural networks (CNNs) to classify and identify tumours in order to distinguish between benign and malignant variations in PAI. The experimental results show that the method proposed in this study not only effectively detects and segments brain tumours of various shapes and sizes but also increases the accuracy of brain tumour classification to 97.02%. The method provides richer and more valuable diagnostic information to the clinic and effectively optimizes the diagnosis and treatment strategy of brain tumours.

IMG-21. HOW CAN WE BEST UTILISE HISTORICAL IMAGING DATASETS FOR RESEARCH IN PAEDIATRIC NEURO-ONCOLOGY? A REVIEW OF HISTORICAL PRE-OPERATIVE IMAGING PERFORMED FOR 92 PAEDIATRIC BRAIN TUMOUR PATIENTS WITH COMPARISON TO 2021 SIOPE GUIDELINES

Abstract BACKGROUND Utilisation of historical imaging is important for studying long-term outcomes in paediatric brain tumours often pooling data across multiple centres retrospectively over many years. Disparities in MRI sequence parameters, imaging planes, fields of view and resolution limit quantitative radiomic analysis and segmentation algorithms. We review historical imaging datasets, analysing the MRI scans performed assessing suitability for modern research techniques. METHODS Retrospective review of presenting MRI scans was performed in 92 paediatric brain tumour patients between 2006-2020. Whether imaging was performed internally at our paediatric neurosciences centre or externally at their referring hospitals was recorded. Image sequences, planes and slice thickness were compared with 2021 SIOPE guidelines for paediatric brain tumour imaging. T2 signal intensities for tumour, white and grey matter were compared for scans completed in different centres. Statistical testing was performed with T-Test and Paired T-Test. RESULTS 75% of patients had all SIOPE essential sequences and 60.9% were in the recommended planes. Only 1 patient had the desired slice thickness in all sequences recommended for 1.5T scanners. 38.5% had T1 and 27.8% had post-contrast T1 in the ≤1mm slice thickness recommended for 3T scanners. Comparison between 62 internal and 30 external scans revealed statistically significant differences in T2 signal intensities for regions of interest (ROI) within tumour, white and grey matter (p<0.01). Comparison of matched ROI for 12 patients imaged internally and externally demonstrated statistically significant differences in T2 signal intensities (p<0.05). Differences persisted despite normalisation of T2 signal intensity as ratios between tumour and the weighted mean of white and grey matter (p<0.01). CONCLUSIONS This study highlights the challenges of non-standardisation of imaging resolution and acquisition parameters in historical imaging. One approach to utilise these datasets is to use qualitative classifications where human experts label imaging features and encode data for future statistical or machine learning analysis.

Deep Learning Realizes Photoacoustic Imaging Artifact Removal

Photoacoustic imaging integrates the strengths of optics and ultrasound, offering high resolution, depth penetration, and multimodal imaging capabilities. Practical considerations with instrumentation and geometry limit the number of available acoustic sensors and their “view” of the imaging target, which result in image reconstruction artifacts degrading image quality. To address this problem, YOLOv8-Pix2Pix is proposed as a hybrid artifact-removal algorithm, which is advantageous in comprehensively eliminating various types of artifacts and effectively restoring image details compared to existing algorithms. The proposed algorithm demonstrates superior performance in artifact removal and segmentation of photoacoustic images of brain tumors. For the purpose of further expanding its application fields and aligning with actual clinical needs, an experimental system for photoacoustic detection is designed in this paper to be verified. The experimental results show that the processed images are better than the pre-processed images in terms of reconstruction metrics PSNR and SSIM, and also the segmentation performance is significantly improved, which provides an effective solution for the further development of photoacoustic imaging technology.

Detection and Classification of Brain Tumor in MRI Images using EPCMA+ML-ELM

Substantial clinical statistics along with analytical features can be extracted from brain tumor images. The identified quantitative measures of exact tumor regions aid physicians and radiologists in effective treatment. Magnetic Resonance Imaging (MRI) images of the brain are considered. Handling these images is challenging mainly owing to variance in addition to complexity in detecting tumors. In this paper, images are segmented using Enhanced Possibilistic C-Means Algorithm (EPCMA) and classified using Multi-Layered Extreme Learning Machine (ML-ELM). System performance is observed based on classification accuracy, sensitivity and specificity. Index Terms: Brain Tumor, Possibilistic C-Means Algorithm, Extreme Learning Machine, MRI

GMAlignNet: multi-scale lightweight brain tumor image segmentation with enhanced semantic information consistency

Although the U-shaped architecture, represented by UNet, has become a major network model for brain tumor segmentation, the repeated convolution and sampling operations can easily lead to the loss of crucial information. Additionally, directly fusing features from different levels without distinction can easily result in feature misalignment, affecting segmentation accuracy. On the other hand, traditional convolutional blocks used for feature extraction cannot capture the abundant multi-scale information present in brain tumor images. This paper proposes a multi-scale feature-aligned segmentation model called GMAlignNet that fully utilizes Ghost convolution to solve these problems. Ghost hierarchical decoupled fusion unit and Ghost hierarchical decoupled unit are used instead of standard convolutions in the encoding and decoding paths. This transformation replaces the holistic learning of volume structures by traditional convolutional blocks with multi-level learning on a specific view, facilitating the acquisition of abundant multi-scale contextual information through low-cost operations. Furthermore, a feature alignment unit is proposed that can utilize semantic information flow to guide the recovery of upsampled features. It performs pixel-level semantic information correction on misaligned features due to feature fusion. The proposed method is also employed to optimize three classic networks, namely DMFNet, HDCNet, and 3D UNet, demonstrating its effectiveness in automatic brain tumor segmentation. The proposed network model was applied to the BraTS 2018 dataset, and the results indicate that the proposed GMAlignNet achieved Dice coefficients of 81.65%, 90.07%, and 85.16% for enhancing tumor, whole tumor, and tumor core segmentation, respectively. Moreover, with only 0.29 M parameters and 26.88G FLOPs, it demonstrates better potential in terms of computational efficiency and possesses the advantages of lightweight. Extensive experiments on the BraTS 2018, BraTS 2019, and BraTS 2020 datasets suggest that the proposed model exhibits better potential in handling edge details and contour recognition.

Internet of things and deep learning based digital twins for diagnosis of brain tumor by analyzing MRI images

Although brain tumours are few, they have one of the highest mortality rates among all types of cancer due to their abnormal growth and proliferation. Brain tumours develop due to the accumulation of abnormal tissues in the brain. Various forms of abnormal tissue exist, however, in the majority of cases, they develop in a regular manner and perish without creating any detrimental effects. Digital twins are occasionally known as digital mirrors, digital mapping, and digital replicas. All of these are synonymous terms for the identical entity. It is a technique for transferring digital or physical information from one realm to another. Image processing involves enhancing or eliminating data from a photograph to achieve a certain objective. Convolutional neural networks are a specific type of neural network that take signals from images as input and produce the image itself or a subset of its elements as output. This research presents a technique for identifying brain cancers using digital replicas and advanced machine learning algorithms by analysing MRI images. Images obtained from MRI machines are stored in a centralised cloud using Internet of Things (IoT) digital devices. The input pictures and other health-related data are then retrieved from cloud storage. The Particle Swarm Optimization approach chooses features. Brain tumor images are classified using machine learning techniques such as convolutional neural networks, support vector machines, and extreme learning machines. The CNN algorithm demonstrates greater accuracy when assessing MRI images for the purpose of identifying brain tumours.

Radiosynthesis and Preclinical Evaluation of m-[18F]FET and [18F]FET-OMe as Novel [18F]FET Analogs for Brain Tumor Imaging.

O-([18F]Fluoroethyl)-l-tyrosine ([18F]FET) is actively transported into the brain and cancer cells by LAT1 and possibly other amino acid transporters, which enables brain tumor imaging by positron emission tomography (PET). However, tumor delivery of this probe in the presence of competing amino acids may be limited by a relatively low affinity for LAT1. The aim of the present work was to evaluate the meta-substituted [18F]FET analog m-[18F]FET and the methyl ester [18F]FET-OMe, which were designed to improve tumor delivery by altering the physicochemical, pharmacokinetic, and/or transport properties. Both tracers could be prepared with good radiochemical yields of 41-56% within 66-90 min. Preclinical evaluation with [18F]FET as a reference tracer demonstrated reduced in vitro uptake of [18F]FET-OMe by U87 glioblastoma cells and no advantage for in vivo tumor imaging. In contrast, m-[18F]FET showed significantly improved in vitro uptake and accelerated in vivo tumor accumulation in an orthotopic glioblastoma model. As such, our work identifies m-[18F]FET as a promising alternative to [18F]FET for brain tumor imaging that deserves further evaluation with regard to its transport properties and in vivo biodistribution.

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction.

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical-pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0.

Brain tumor segmentation in MRI with multi-modality spatial information enhancement and boundary shape correction

Brain tumor segmentation is currently of a priori guiding significance in medical research and clinical diagnosis. Brain tumor segmentation techniques can accurately partition different tumor areas on multi-modality images captured by magnetic resonance imaging (MRI). Due to the unpredictable pathological process of brain tumor generation and growth, brain tumor images often show irregular shapes and uneven internal gray levels. Existing neural network-based segmentation methods with an encoding/decoding structure can perform image segmentation to some extent. However, they ignore issues such as differences in multi-modality information, loss of spatial information, and under-utilization of boundary information, thereby limiting the further improvement of segmentation accuracy. This paper proposes a multimodal spatial information enhancement and boundary shape correction method consisting of a modality information extraction (MIE) module, a spatial information enhancement (SIE) module, and a boundary shape correction (BSC) module. The above three modules act on the input, backbone, and loss functions of deep convolutional networks (DCNN), respectively, and compose an end-to-end 3D brain tumor segmentation model. The three proposed modules can solve the low utilization rate of effective modality information, the insufficient spatial information acquisition ability, and the improper segmentation of key boundary positions can be solved. The proposed method was validated on BraTS2017, 2018, and 2019 datasets. Comparative experimental results confirmed the effectiveness and superiority of the proposed method over state-of-the-art segmentation methods.

An Optimization Numerical Spiking Neural Membrane System with Adaptive Multi-Mutation Operators for Brain Tumor Segmentation.

Magnetic Resonance Imaging (MRI) is an important diagnostic technique for brain tumors due to its ability to generate images without tissue damage or skull artifacts. Therefore, MRI images are widely used to achieve the segmentation of brain tumors. This paper is the first attempt to discuss the use of optimization spiking neural P systems to improve the threshold segmentation of brain tumor images. To be specific, a threshold segmentation approach based on optimization numerical spiking neural P systems with adaptive multi-mutation operators (ONSNPSamos) is proposed to segment brain tumor images. More specifically, an ONSNPSamo with a multi-mutation strategy is introduced to balance exploration and exploitation abilities. At the same time, an approach combining the ONSNPSamo and connectivity algorithms is proposed to address the brain tumor segmentation problem. Our experimental results from CEC 2017 benchmarks (basic, shifted and rotated, hybrid, and composition function optimization problems) demonstrate that the ONSNPSamo is better than or close to 12 optimization algorithms. Furthermore, case studies from BraTS 2019 show that the approach combining the ONSNPSamo and connectivity algorithms can more effectively segment brain tumor images than most algorithms involved.

Cascade Residual Multiscale Convolution and Mamba-Structured UNet for Advanced Brain Tumor Image Segmentation

In brain imaging segmentation, precise tumor delineation is crucial for diagnosis and treatment planning. Traditional approaches include convolutional neural networks (CNNs), which struggle with processing sequential data, and transformer models that face limitations in maintaining computational efficiency with large-scale data. This study introduces MambaBTS: a model that synergizes the strengths of CNNs and transformers, is inspired by the Mamba architecture, and integrates cascade residual multi-scale convolutional kernels. The model employs a mixed loss function that blends dice loss with cross-entropy to refine segmentation accuracy effectively. This novel approach reduces computational complexity, enhances the receptive field, and demonstrates superior performance for accurately segmenting brain tumors in MRI images. Experiments on the MICCAI BraTS 2019 dataset show that MambaBTS achieves dice coefficients of 0.8450 for the whole tumor (WT), 0.8606 for the tumor core (TC), and 0.7796 for the enhancing tumor (ET) and outperforms existing models in terms of accuracy, computational efficiency, and parameter efficiency. These results underscore the model’s potential to offer a balanced, efficient, and effective segmentation method, overcoming the constraints of existing models and promising significant improvements in clinical diagnostics and planning.

Semantic segmentation of brain tumor images using attention-based residual light u-net model

Semantic segmentation of brain tumor images using attention-based residual light u-net model

A framework for identification of brain tumors from MR images using progressive segmentation

PurposeThis study addresses the critical health issue of brain tumors, focusing on enhancing the accuracy of tumor segmentation from Magnetic Resonance Imaging (MRI) images. The primary research question investigates the effectiveness of a novel Hybrid Watershed–Clustering framework and its underlying Progressive Segmentation of the MR Images using the Radius and Intensity Measure (PS-RIM) algorithm. The aim is to improve the detection and segmentation of brain tumors within MR images, surpassing the efficacy of current methodologies.MethodsThe methodology involves a three-stage process. In the preprocessing stage, noise reduction and intensity normalization techniques are applied to clarify the images. The next stage is region-based segmentation, which includes morphological processing, edge detection, and thresholding to delineate tumor areas accurately. The final post-processing stage enhances segmentation accuracy and reduces false positives by integrating clustering machine learning techniques, specifically the K-Means cluster algorithm, to refine tumor identification.ResultsThe framework's comprehensive evaluation across various MR images shows a significant improvement in accuracy over existing segmentation methods. The PS-RIM algorithm within the framework effectively captures the diverse presentations of tumor appearances in MR images. The research recorded an impressive accuracy rate of 98.11% in tumor detection, demonstrating enhanced identification and segmentation quality.ConclusionsThe study concludes that the proposed Hybrid Watershed–Clustering framework, powered by the PS-RIM algorithm, markedly improves the detection and differentiation of brain tumors in MR images. It exhibits exceptional accuracy, resilience, and computational efficiency. These findings hold substantial potential for advancing computer vision and image analysis in medical diagnostics, which could improve patient outcomes in managing brain tumors.Graphical abstract

DOTATATE PET/MR Imaging Differentiates Secondary-Progressive from de Novo World Health Organization Grade 3 Meningiomas.

WHO grade 3 meningiomas are rare and poorly understood and have a higher propensity for recurrence, metastasis, and worsened clinical outcomes compared with lower-grade meningiomas. The purpose of our study was to prospectively evaluate the molecular profile, PET characteristics, and outcomes of patients with World Health Organization grade 3 meningiomas who were imaged with gallium 68 (68Ga) DOTATATE PET/MR imaging. Patients with World Health Organization grade 3 meningiomas enrolled in our prospective observational cohort evaluating the utility of (68Ga) DOTATATE PET/MR imaging in somatostatin receptor positive brain tumors were included. We stratified patients by de novo-versus-secondary-progressive status and evaluated the differences in the PET standard uptake value, molecular profiles, and clinical outcomes. Patients met the inclusion criteria (secondary-progressive: 7/14; de novo: 7/14). The secondary-progressive cohort had a significantly higher per-patient number of surgeries (4.1 versus 1.6; P = .011) and trended toward a higher number of radiation therapy courses (2.4 versus 1.6; P = .23) and cumulative radiation therapy doses (106Gy versus 68.3Gy; P = .31). The secondary-progressive cohort had a significantly lower progression-free survival compared with the de novo cohort (4.8 versus 37.7 months; P = .004). Secondary-progressive tumors had distinct molecular pathology profiles with higher numbers of mutations (3.5 versus 1.2; P = .024). Secondary-progressive tumors demonstrated higher PET standard uptake values (17.1 versus 12.4; P = .0021). Our study confirms prior work illustrating distinct clinical outcomes in secondary-progressive and de novo World Health Organization grade 3 meningiomas. Furthermore, our findings support (68Ga) DOTATATE PET/MR imaging as a useful management strategy in World Health Organization grade 3 meningiomas and provide insight into meningioma biology, as well as clinical management implications.

An Effective analysis of brain tumor detection using deep learning

INTRODUCTION: Cancer remains a significant health concern, with early detection crucial for effective treatment. Brain tumors, in particular, require prompt diagnosis to improve patient outcomes. Computational models, specifically deep learning (DL), have emerged as powerful tools in medical image analysis, including the detection and classification of brain tumors. DL leverages multiple processing layers to represent data, enabling enhanced performance in various healthcare applications.&#x0D; OBJECTIVES: This paper aims to discuss key topics in DL relevant to the analysis of brain tumors, including segmentation, prediction, classification, and assessment. The primary objective is to employ magnetic resonance imaging (MRI) pictures for the identification and categorization of brain malignancies. By reviewing prior research and findings comprehensively, this study provides valuable insights for academics and professionals in deep learning seeking to contribute to brain tumor identification and classification.&#x0D; METHODS: The methodology involves a systematic review of existing literature on DL applications in brain tumor analysis, focusing on MRI imaging. Various DL techniques, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models, are explored for their efficacy in tasks such as tumor segmentation, prediction of tumor characteristics, classification of tumor types, and assessment of treatment response.&#x0D; RESULTS: The review reveals significant advancements in DL-based approaches for brain tumor analysis, with promising results in segmentation accuracy, tumor subtype classification, and prediction of patient outcomes. Researchers have developed sophisticated DL architectures tailored to address the complexities of brain tumor imaging data, leading to improved diagnostic capabilities and treatment planning.&#x0D; CONCLUSION: Deep learning holds immense potential for revolutionizing the diagnosis and management of brain tumors through MRI-based analysis. This study underscores the importance of leveraging DL techniques for accurate and efficient brain tumor identification and classification. By synthesizing prior research and highlighting key findings, this paper provides valuable guidance for researchers and practitioners aiming to contribute to the field of medical image analysis and improve outcomes for patients with brain malignancies.

425 Getting Everyone Up to Speed: A Single Institution Pilot of a Neurosurgery Sub-internship Bootcamp

INTRODUCTION: At many institutions, first and second year medical students gain exposure to neurosurgery primarily through shadowing and research projects. Opportunities to acquire clinical experience and technical skills before a neurosurgery sub-internship are often limited. Consequently, students starting sub-internships have wide variability of clinical knowledge and experience. METHODS: We implemented a one-day boot camp at our university. The morning session followed a didactic format covering 14 topics. The afternoon session utilized hands-on stations: navigation-based EVD simulation, burr hole drilling, pinning, spine laminectomy/instrumentation, and OR orientation. Participants completed a pre-test and post-test survey using a 9-point Likert scale (Strongly Disagree [1] to Strongly Agree [9]). RESULTS: Ten medical students participated in the pilot. All participants rated the boot camp positively (Average score of 9.9 ± 0.2 out of 10). Students identified key areas they felt least comfortable with via the pre-test: functional neurosurgery (2.6 ± 1.4), management of neurosurgical floor patients (3.0 ± 1.6), and examination of comatose patients (4.1 ± 2.3). At the end of the event, students expressed statistically significant increased comfort across 16 of the 17 metrics; maximal improvement was noted in brain tumor imaging interpretation (5.9 ± 1.1 vs. 2.9 ± 1.9, p &lt; .001) and knowing what is expected of a sub-intern (7.0 ± 1.1 vs. 4.0 ± 1.6, p &lt; .001). CONCLUSIONS: We successfully implemented a one-day boot camp for medical students about to start their sub-internships. Moving forward, we plan to expand the hands-on learning to other medical students in the region and provide the didactic sessions virtually to allow participation on a national scale. In doing so, we hope to increase sub-internship readiness and reduce barriers for all students interested in neurosurgery.

Brain Tumor Detection and Classification Via Kernel Support Vector Machine Using MRI Images

Abstract: The MR images of the brain requires automatic and accurate classification for medical analysis and interpretation nowadays. Numerous methods have been declared already in the previous years. In this paper we have presented a method which classifies the brain image of MRI into normal and abnormal brain tumor images. This method uses wavelet transform that extract features from images. The next step involves principle component analysis (PCA) that reduces the feature dimensions. These reduced features are then employed to a kernel support vector machine (KSVM). 180 images of the brain were collected from the diseased which contained 130 abnormal brain and 50 normal brain images. Four kernels of different types were performed.

An efficient brain tumor segmentation model based on group normalization and 3D U‐Net

AbstractAccurate segmentation of brain tumors has a vital impact on clinical diagnosis and treatment, and good segmentation results are helpful for the treatment of this disease, which is a serious threat to human health. High‐precision segmentation of brain tumors remains a challenging task due to their diverse shapes, sizes, locations, and complex boundaries. Considering the special structure of medical brain tumor images, many researchers have proposed a brain tumor segmentation (BraTS) network based on 3D U‐Net. However, there are also problems such as insufficient receptive fields and excessive computing costs. In this paper, we propose an efficient BraTS model based on group normalization (GN) and 3D U‐Net (3D‐EffUNet). First, according to the characteristics of brain tumor images, the medical image of the whole case is input into the model, and 3D convolution layers are used to extract features and filter irrelevant information. Then, using 3D U‐Net as the main framework, an efficient convolutional module is designed for more precise processing of brain tumor features. Moreover, an efficient convolution module based on GN and an attention mechanism is introduced to reduce the complexity of the network without affecting the segmentation performance and to increase the awareness of voxels between adjacent dimensions and the local space. Finally, the decoder was used to reconstruct high‐precision BraTS information. The model is trained and tested on the BraTS2021 dataset, and the experimental results show that it can maintain good segmentation performance and greatly reduce the calculation cost.

Brain tumor MRI identification and classification using DWT, PCA and kernel support vector machine

Classification, segmentation, and the identification of the infection region in MRI images of brain tumors are labor-intensive and iterative processes. Numerous anatomical structures of the human body may be envisioned using an image processing theory. With basic imaging methods, it is challenging to see the aberrant human brain's structure. The neurological structure of the human brain may be distinguished and made clearer using the magnetic resonance imaging technique. The MRI approach uses a number of imaging techniques to evaluate and record the human brain’s interior features. In this study, we focused on strategies for noise removal, gray-level co-occurrence matrix (GLCM) extraction of features, and segmentation of brain tumor regions based on Discrete Wavelet Transform (DWT) to minimize complexity and enhance performance. In turn, this reduces any noise that could have been left over after segmentation due to morphological filtering. Brain MRI scans were utilized to test the accuracy of the classification and the location of the tumor using probabilistic neural network classifiers. The classifier's accuracy and position detection were tested using MRI brain imaging. The efficiency of the suggested approach is demonstrated by experimental findings, which showed that normal and diseased tissues could be distinguished from one another from brain MRI scans with about 100% accuracy.

A Bayesian convolutional neural network-based generalized linear model.

Convolutional neural networks (CNNs) provide flexible function approximations for a wide variety of applications when the input variables are in the form of images or spatial data. Although CNNs often outperform traditional statistical models in prediction accuracy, statistical inference, such as estimating the effects of covariates and quantifying the prediction uncertainty, is not trivial due to the highly complicated model structure and overparameterization. To address this challenge, we propose a new Bayesian approach by embedding CNNs within the generalized linear models (GLMs) framework. We use extracted nodes from the last hidden layer of CNN with Monte Carlo (MC) dropout as informative covariates in GLM. This improves accuracy in prediction and regression coefficient inference, allowing for the interpretation of coefficients and uncertainty quantification. By fitting ensemble GLMs across multiple realizations from MC dropout, we can account for uncertainties in extracting the features. We apply our methods to biological and epidemiological problems, which have both high-dimensional correlated inputs and vector covariates. Specifically, we consider malaria incidence data, brain tumor image data, and fMRI data. By extracting information from correlated inputs, the proposed method can provide an interpretable Bayesian analysis. The algorithm can be broadly applicable to image regressions or correlated data analysis by enabling accurate Bayesian inference quickly.