Magnetic Resonance Imaging Tumor Research Articles

A Multi-Center, Multi-Parametric MRI Dataset of Primary and Secondary Brain Tumors

Brain metastases (BMs) and high-grade gliomas (HGGs) are the most common and aggressive types of malignant brain tumors in adults, with often poor prognosis and short survival. As their clinical symptoms and image appearances on conventional magnetic resonance imaging (MRI) can be astonishingly similar, their accurate differentiation based solely on clinical and radiological information can be very challenging, particularly for “cancer of unknown primary”, where no systemic malignancy is known or found. Non-invasive multiparametric MRI and radiomics offer the potential to identify these distinct biological properties, aiding in the characterization and differentiation of HGGs and BMs. However, there is a scarcity of publicly available multi-origin brain tumor imaging data for tumor characterization. In this paper, we introduce a multi-center, multi-origin brain tumor MRI (MOTUM) imaging dataset obtained from 67 patients: 29 with high-grade gliomas, 20 with lung metastases, 10 with breast metastases, 2 with gastric metastasis, 4 with ovarian metastasis, and 2 with melanoma metastasis. This dataset includes anonymized DICOM files alongside processed FLAIR, T1-weighted, contrast-enhanced T1-weighted, T2-weighted sequences images, segmentation masks of two tumor regions, and clinical data. Our data-sharing initiative is to support the benchmarking of automated tumor segmentation, multi-modal machine learning, and disease differentiation of multi-origin brain tumors in a multi-center setting.

MR-CT image fusion method of intracranial tumors based on Res2Net.

Information complementarity can be achieved by fusing MR and CT images, and fusion images have abundant soft tissue and bone information, facilitating accurate auxiliary diagnosis and tumor target delineation. The purpose of this study was to construct high-quality fusion images based on the MR and CT images of intracranial tumors by using the Residual-Residual Network (Res2Net) method. This paper proposes an MR and CT image fusion method based on Res2Net. The method comprises three components: feature extractor, fusion layer, and reconstructor. The feature extractor utilizes the Res2Net framework to extract multiscale features from source images. The fusion layer incorporates a fusion strategy based on spatial mean attention, adaptively adjusting fusion weights for feature maps at each position to preserve fine details from the source images. Finally, fused features are input into the feature reconstructor to reconstruct a fused image. Qualitative results indicate that the proposed fusion method exhibits clear boundary contours and accurate localization of tumor regions. Quantitative results show that the method achieves average gradient, spatial frequency, entropy, and visual information fidelity for fusion metrics of 4.6771, 13.2055, 1.8663, and 0.5176, respectively. Comprehensive experimental results demonstrate that the proposed method preserves more texture details and structural information in fused images than advanced fusion algorithms, reducing spectral artifacts and information loss and performing better in terms of visual quality and objective metrics. The proposed method effectively combines MR and CT image information, allowing the precise localization of tumor region boundaries, assisting clinicians in clinical diagnosis.

AI-assisted Segmentation Tool for Brain Tumor MR Image Analysis.

TumorPrism3D software was developed to segment brain tumors with a straightforward and user-friendly graphical interface applied to two- and three-dimensional brain magnetic resonance (MR) images. The MR images of 185 patients (103 males, 82 females) with glioblastoma multiforme were downloaded from The Cancer Imaging Archive (TCIA) to test the tumor segmentation performance of this software. Regions of interest (ROIs) corresponding to contrast-enhancing lesions, necrotic portions, and non-enhancing T2 high signal intensity components were segmented for each tumor. TumorPrism3D demonstrated high accuracy in segmenting all three tumor components in cases of glioblastoma multiforme. They achieved a better Dice similarity coefficient (DSC) ranging from 0.83 to 0.91 than 3DSlicer with a DSC ranging from 0.80 to 0.84 for the accuracy of segmented tumors. Comparative analysis with the widely used 3DSlicer software revealed TumorPrism3D to be approximately 37.4% faster in the segmentation process from initial contour drawing to final segmentation mask determination. The semi-automated nature of TumorPrism3D facilitates reproducible tumor segmentation at a rapid pace, offering the potential for quantitative analysis of tumor characteristics and artificial intelligence-assisted segmentation in brain MR imaging.

Magnetic resonance imaging-based prognostic model for subsequent distant metastasis in patients with ipsilateral breast tumor recurrence following breast-conserving surgery.

Ipsilateral breast tumor recurrence (IBTR) following breast-conserving surgery (BCS) has been considered a risk factor for distant metastasis (DM). Limited data are available regarding the subsequent outcomes after IBTR. Therefore, this study aimed to determine the clinical course after IBTR and develop a magnetic resonance imaging (MRI)-based predictive model for subsequent DM. We retrospectively extracted quantitative features from MRI to construct a radiomics cohort, with all eligible patients undergoing preoperative MRI at time of primary tumor and IBTR between 2010 and 2018. Multivariate Cox analysis was performed to identify factors associated with DM. Three models were constructed using different sets of clinicopathological, qualitative, and quantitative MRI features and compared. Additionally, Kaplan-Meier analysis was performed to assess the prognostic value of the optimal model. Among the 183 patients who experienced IBTR, 47 who underwent MRI for both primary and recurrent tumors were enrolled. Multivariate analysis demonstrated that the independent prognostic factors were human epidermal growth factor receptor 2 (HER2) status [hazard ratio (HR) =5.40] and background parenchymal enhancement (BPE) (HR =7.94) (all P values <0.01). Furthermore, four quantitative MRI features of recurrent tumors were selected through the least absolute shrinkage and selection operator (LASSO) method. The combined model exhibited superior performance [concordance index (C-index) 0.77] compared to the clinicoradiological model (C-index 0.71; P=0.006) and radiomics model (C-index 0.70; and P=0.01). Furthermore, the combined model successfully categorized patients into low- and high-risk subgroups with distinct prognoses (P<0.001). The clinicopathological and MRI features of IBTR were associated with secondary events following surgery. Additionally, the MRI-based combined model exhibited the highest predictive efficacy. These findings could be helpful in risk stratification and tailoring follow-up strategies in patients with IBTR.

DNA-Mediated Magnetic-Dimer Assembly for Fault-Free Ultra-High-Field Magnetic Resonance Imaging of Tumors.

Ultra-high-field (UHF) magnetic resonance imaging (MRI) stands as a pivotal cornerstone in biomedical imaging, yet the challenge of false imaging persists, constraining its full potential. Despite the development of dual-mode contrast agents improving conventional MRI, their effectiveness in UHF remains suboptimal due to the high magnetic moment, resulting in diminished T1 relaxivity and excessively enhanced T2 relaxivity. Herein, we report a DNA-mediated magnetic-dimer assembly (DMA) of iron oxide nanoparticles that harnesses UHF-tailored nanomagnetism for fault-free UHF-MRI. DMA exhibits a dually enhanced longitudinal relaxivity of 4.42 mM-1·s-1 and transverse relaxivity of 26.23 mM-1·s-1 at 9 T, demonstrating a typical T1-T2 dual-mode UHF-MRI contrast agent. Importantly, DMA leverages T1-T2 dual-modality image fusion to achieve artifact-free breast cancer visualization, effectively filtering interference from hundred-micrometer-level false-positive signals with unprecedented precision. The UHF-tailored T1-T2 dual-mode DMA contrast agents hold promise for elevating the accuracy of MR imaging in disease diagnosis.

Retraction Note: A novel feature selection method for brain tumor MR image classification based on the Fisher criterion and parameter-free Bat optimization

Retraction Note: A novel feature selection method for brain tumor MR image classification based on the Fisher criterion and parameter-free Bat optimization

Rutin-coated ultrasmall manganese oxide nanoparticles for targeted magnetic resonance imaging and photothermal therapy of malignant tumors

Manganese oxide nanoparticles (MONs)-based contrast agents have attracted increasing attention for magnetic resonance imaging (MRI), attributed to their good biocompatibility and advantageous paramagnetism. However, conventional MONs have poor imaging performance due to low T1 relaxivity. Additionally, their lack of tumor-targeting theranostics capabilities and complex synthesis pathways have impeded clinical applications. Rutin (Ru) is an ideal tumor-targeted ligand that targets glucose transporters (GLUTs) overexpressed in various malignant tumors, and exhibits photothermal effects upon chelation with metal ions. Herein, a series of Ru-coated MONs (Ru/MnO2) were synthesized using a straightforward, rapid one-step process. Specifically, Ru/MnO2-5, with the smallest crystal size of approximately 4 nm, exhibits the highest T1 relaxivity (33.3 mM-1s−1 at 1.5 T, surpassing prior MONs) along with notable stability, photothermal efficacy, and tumor-targeting ability. Furthermore, Ru/MnO2-5 shows promise in MRI and photothermal therapy of H22 tumors owing to its superior GLUTs-mediated tumor-targeting capability.

Dendrimer/metal-phenolic nanocomplexes encapsulating CuO2 for targeted magnetic resonance imaging and enhanced ferroptosis/cuproptosis/chemodynamic therapy by regulating the tumor microenvironment

The combination of ferroptosis, cuproptosis, and chemodynamic therapy (CDT) would be a potential strategy for tumor diagnosis and enhanced treatment. However, the therapeutic effect was severely limited by the lack of specific delivery of catalytic ions and the low Fenton reaction efficiency in tumor microenvironment (TME) with excess glutathione, limited acidity and insufficient endogenous hydrogen peroxide. In this work, p-carboxybenzenesulfonamide (BS), a carbonic anhydrase IX (CA IX) inhibitor, was modified on the surface of generation-5 poly(amidoamine) dendrimer to load copper peroxide nanoparticles, which were complexed with iron (Fe)-tannic acid (TF) networks for targeted magnetic resonance (MR) imaging and enhanced ferroptosis/cuproptosis/CDT by regulating TME. The formed CuO2@G5-BS/TF nanocomplexes with an average size of 39.4 nm could be specifically accumulated at tumor site and effectively internalized by metastatic 4T1 cells via the specific interaction between BS and CA IX over-expressed on tumor cells. Meanwhile, the inhibition of CA IX activity could not only decrease the intracellular pH to accelerate Fe3+/Cu2+ release, H2O2 self-supply and Fenton reaction, but also suppress tumor metastasis by alleviating the extracellular acidity in TME. Moreover, the reduction of Fe3+/Cu2+ by intracellular glutathione (GSH) could further amplify ROS generation and enhance CDT efficacy, and the GSH depletion could in turn inhibit GPX-4 mediated antioxidant reaction to induce ferroptosis, resulting in effective therapeutic efficacy. In vivo experimental results demonstrated that CuO2@G5-BS/TF could provide better tumor MR imaging, effectively inhibit the growth and metastasis of 4T1 breast tumors, and be metabolized without significant systemic toxicity. Thus, CuO2@G5-BS/TF nanocomplexes provided a new approach for targeted MR imaging and enhanced ferroptosis/cuproptosis/CDT of triple-negative breast cancer. Statement of significanceTaking the advantage of dendrimer and metal-phenolic system, stable CuO2@G5-BS/TF nanocomplexes with an average size of 39.4 nm were synthesized to efficiently load Fe3+ and CuO2 nanoparticles for TNBC treatment and MR imaging. CuO2@G5-BS/TF nanocomplexes could target tumor cells overexpressing CAIX via the specific binding with BS, and the inhibition of CAIX activity could not only decrease the intracellular pH to accelerate Fe3+/Cu2+ release, H2O2 self-supply and Fenton reaction, but also suppress tumor metastasis by alleviating the extracellular acidity. The reduction of Fe3+/Cu2+ by intracellular GSH could further amplify ·OH generation, and the GSH depletion could in turn inhibit GPX-4 mediated antioxidant reaction to induce ferroptosis, resulting in effective therapeutic efficacy by enhanced ferroptosis/cuproptosis/CDT via tumor microenvironment regulation.

Magnetic resonance imaging-based prediction models for differentiating intraspinal schwannomas from meningiomas: classification and regression tree and random forest analysis.

Due to the variations in surgical approaches and prognosis between intraspinal schwannomas and meningiomas, it is crucial to accurately differentiate between the two prior to surgery. Currently, there is limited research exploring the implementation of machine learning (ML) methods for distinguishing between these two types of tumors. This study aimed to establish a classification and regression tree (CART) model and a random forest (RF) model for distinguishing schwannomas from meningiomas. We retrospectively collected 88 schwannomas (52 males and 36 females) and 51 meningiomas (10 males and 41 females) who underwent magnetic resonance imaging (MRI) examinations prior to the surgery. Simple clinical data and MRI imaging features, including age, sex, tumor location and size, T1-weighted images (T1WI) and T2-weighted images (T2WI) signal characteristics, degree and pattern of enhancement, dural tail sign, ginkgo leaf sign, and intervertebral foramen widening (IFW), were reviewed. Finally, a CART model and RF model were established based on the aforementioned features to evaluate their effectiveness in differentiating between the two types of tumors. Meanwhile, we also compared the performance of the ML models to the radiologists. The receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the models and clinicians' discrimination performance. Our investigation reveals significant variations in ten out of 11 variables in the training group and five out of 11 variables in the test group when comparing schwannomas and meningiomas (P<0.05). Ultimately, the CART model incorporated five variables: enhancement pattern, the presence of IFW, tumor location, maximum diameter, and T2WI signal intensity (SI). The RF model combined all 11 variables. The CART model, RF model, radiologist 1, and radiologist 2 achieved an area under the curve (AUC) of 0.890, 0.956, 0.681, and 0.723 in the training group, and 0.838, 0.922, 0.580, and 0.659 in the test group, respectively. The RF prediction model exhibits more exceptional performance than an experienced radiologist in discriminating intraspinal schwannomas from meningiomas. The RF model seems to be better in discriminating the two tumors than the CART model.

Application of Epithelial Growth Factor Receptor-Targeted Magnetic Resonance Imaging and Near-Infrared II Dual-Modal Probe in Lung Cancer Diagnosis and Surgical Resection.

There has been an increase in the use of molecular probe diagnostic techniques for lung cancer, and magnetic resonance imaging (MRI) offers specific advantages for diagnosing pulmonary carcinoma. Furthermore, advancements in near-infrared II (NIR-II) fluorescence have provided a new method for precise intraoperative tumor resection. However, few probes combine preoperative diagnosis with intraoperative imaging. This study aims to fill this research void by employing a dual-modal probe that targets the epidermal growth factor receptor for MR and NIR-II imaging, enabling the preoperative diagnosis of lung cancer using MRI and precise intraoperative tumor localization using NIR-II with a single probe. The imaging effects and targeting ability of the probe were confirmed in cell lines, mouse models, and clinical samples. The MR signal decreased within 24 h in the patient-derived xenograft mouse model. The average signal-to-background ratio of NIR-II reached 3.98 ± 0.27. The clinical sample also showed a decrease in the T2 signal using MRI, and the NIR-II optical signal-to-background ratio was 3.29. It is expected that this probe can improve the diagnostic rate of lung cancer using MRI and enable precise intraoperative tumor resection using NIR-II.

MRI Tumor Segmentation and Tumor Classification using Deep Learning

Abstract: A non-invasive imaging method that creates three-dimensional, finely detailed anatomical pictures is called magnetic resonance imaging (MRI). It is frequently employed in the diagnosis, monitoring, and detection of diseases. A magnetic field and computer-generated radio waves are used in magnetic resonance imaging (MRI), a medical imaging technology that produces detailed pictures of your body's organs and tissues. Manual reading of these image and classification is a tedious task and requires dedicated professionals. The proposed work intends to ease this task using deep learning techniques for MRI tumor segmentation and classification. It uses VGG and CNN architecture for this purpose. This paper demonstrates the use of deep learning in MRI classification

Role of magnetic resonance imaging in the prediction of histological grade in soft tissue sarcomas.

Soft tissue sarcomas are rare malignant tumors with significant heterogeneity. The importance of classifying histological grades is fundamental to defining the treatment approach. To evaluate magnetic resonance imaging (MRI) in predicting the histological grade of soft tissue sarcomas. A retrospective observational study included patients over 18 years undergoing MRI and primary tumor surgery at AC Camargo Cancer Center from January 2015 to June 2022. Two radiologists evaluated MRI criteria (size, margin definition, heterogeneity of the T2 signal, high-intensity peritumoral signal on T2, and postperitumoral contrast), and a grading prediction score was calculated. χ2 and logistic regression analyses were conducted. Sixty-eight patients were included (38 men; median: 48 years). Moreover, 52 high-grade and 16 low-grade tumors were observed. The MRI criteria associated with histological grade were peritumoral high-intensity T2-weighted signals (p < 0.001) and peritumoral postcontrast enhancement (p = 0.006). Logistic regression confirmed their significance (odds ratio [OR]: 11.8 and 8.8, respectively). Each score point increment doubled the chance of high-grade tumors (OR: 2.0; p = 0.014). MRI effectively predicts histological grades of soft tissue sarcomas. Peritumoral high-intensity T2-weighted signals and peritumoral postcontrast enhancement are valuable indicators of high-grade tumors. This highlights MRI's importance in treatment decision-making for sarcoma patients.

Abstract 299: FAP/αSMA association with tumor visibility and progression in prostate cancer

Abstract Introduction Prostate cancer (PCa) ranks as the second most frequently diagnosed cancer in the male population worldwide. The challenge in effectively managing PCa is the absence of well-established biological markers, which often leads to both over and under treatment. To address this issue, a deeper understanding of the molecular alterations within PCa is essential for more accurate patient stratification. In this research, we embark on a comprehensive examination of how the presence of fibroblast activation protein (FAP) and alpha smooth muscle actin (αSMA) in PCa tissue associates with the visibility of the disease in Magnetic Resonance Imaging (MRI) and their impact on cancer progression. The objective of this study is to analyze cell compartmental expression of FAP and aSMA using an AI based image analysis method. We also study the role of FAP and αSMA expression in predicting disease progression and mortality. Materials and Methods We applied FAP (ab207178, Abcam)/αSMA (M0851, DAKO) double chromogen immunohistochemical (IHC) staining to three independent cohorts of formalin-fixed paraffin-embedded (FFPE) prostate cancer tissue microarrays. All together, we analyzed 835 patients’ samples. First cohort consists of 387 patients with preoperative multiparametric MRI and robot-assisted laparoscopic prostatectomy (RALP) as primary treatment. Second cohort was case vs control cohort of Grade group 2-4 localized PCa at radical prostatectomy (RP) with 168 patients. Third cohort consists PCa patents from continuous, population-based collection of radical prostatectomies of 319 patients. Image analysis was performed with Aiforia Create, which is cloud-based deep-learning artificial intelligence software that provides platform for training and validating automated image analysis pipelines using convolutional neural networks. Analysis algorithm in this project was based on semantic, pixel-level area segmentation. Results FAP expression was higher and αSMA lower in MRI-visible tumors compared with MRI-invisible tumors. Stromal and epithelial FAP expression associate with tumor progression. We could also see statistically significant differences in FAP positivity between clinically significant (GS ≥7) and insignificant (GS ≤6) tumors. Hazard ratios imply that FAP and αSMA have significant impact on risk of biochemical recurrence in patients with MRI-visible tumors. Conclusions FAP is closely linked to tumor MRI visibility, cancer progression, and Gleason scores, marking it as a valuable biomarker in PCa assessment. High stromal αSMA is primarily associated with MRI visibility. Our automated AI-based image analysis method has demonstrated reliability, aligning with our previous findings. This advances the potential for more accurate and efficient prostate cancer diagnosis and prognosis, offering a potential benefit to future patient care. Citation Format: Jenni Säilä, Timo-Pekka Lehto, Annabrita Schoonenberg, Katja Välimäki, Andrew Erickson, Antti Rannikko, Olli Kallioniemi, Tuomas Mirtti, Teijo Pellinen. FAP/αSMA association with tumor visibility and progression in prostate cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 299.

Platinum Nanoparticles-Enhanced Ferritin-Mn2+ Interaction for Magnetic Resonance Contrast Enhancement and Efficient Tumor Photothermal Therapy.

Nanoplatforms with high Mn2+ coordination can display efficient T1 magnetic resonance imaging (MRI) contrast enhancement. Herein, an earth gravity-like method for enhanced interaction between Ferritin (Fn) and Mn2+ by the growth of platinum nanoparticles (PNs) in Fn's cage structure via a biomineralization method is first proposed. Fn has good biocompatibility and can provide a suitable growth site for PNs. PNs with negative charge have certain attraction to Mn2+ with positive charge, improving Fn's loading capacity of Mn2+ by attraction force; and thus, achieving efficient MRI contrast enhancement. In addition, PNs can be applied for efficient photothermal therapy (PTT) under near infrared ray (NIR) irradiation. Systemic delivery of this nanoplatform shows obvious MRI contrast enhancement and tumor progression inhibition after NIR irradiation, as well as no obvious side effects. Therefore, this nanoplatform has the potential to contribute to nanotheranostic for clinical transformation.

Comparative Study of Postmortem MRI and Pathological Findings in Malignant Brain Tumors.

This study compared magnetic resonance imaging (MRI) findings of postmortem brain specimens with neuropathological findings to evaluate the value of postmortem MRI. Postmortem MRI was performed on five formalin-fixed whole brains with malignant tumors. Postmortem T2-weighted images detected all neuropathological abnormalities as high-signal regions but also showed histological tumor invasion in areas without edema. Tumor lesions with high necrosis and edema showed high signal intensity on T2-weighted images; in three cases, lesion enlargement was detected on the final prenatal imaging and postmortem MRI. Disease progression immediately before death may have contributed to this difference. In conclusion, the correlation between MRI and neuropathological findings facilitates understanding of the mechanisms responsible for MRI abnormalities. Increased free water due to edema, necrosis, and brain tissue injury can explain the increased signal intensity observed on T2-weighted images. Postmortem MRI may contribute to effective pathology by identifying subtle abnormalities prior to brain dissection.

Performance of MRI for Detection of ≥pT1b Disease in Local Staging of Endometrial Cancer.

Magnetic resonance imaging (MRI) can be used for the preoperative local staging of endometrial cancer (EC). The presence of ≥pT1b disease (i.e., tumor invasion in ≥50% of the myometrium, into the cervical stroma or spread outside the uterus) has important prognostic value and implications for the decision to perform lymphadenectomy. The purpose of this study was to assess the performance of MRI for the detection of ≥pT1b disease and to evaluate whether tumor size measured via MRI was predictive for ≥pT1b disease, independent of imaging signs of deep invasion. MRI T-staging and tumor diameter and volume were correlated with histopathology of the hysterectomy specimen in 126 patients. MRI had a sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 70.0%, 83.3%, 79.2%, 75.3% and 77.0%, respectively, for the detection of ≥pT1b disease. A tumor diameter of ≥40 mm and volume of ≥20 mL measured via MRI were predictive for ≥pT1b disease at rates of 78.3% and 87.1%, respectively. An EC size of at least 5 mm upon MRI was predictive for ≥pT1b disease in more than 50% of cases. Our results support the use of MRI in the preoperative staging of EC and suggest including size criteria in EC staging guidelines.

Detection of Brain Tumour in MRI Images using Deep Belief Network (DBN)

One of the world's deadliest illnesses is brain cancer. It is a cancer that often affects adults as much as children. It is the least likely species to survive, and its diversity is determined by its location, sweetness and structure. The negative effects will stem from the incorrect classification of the tumour brain. Therefore, determining the specific type and rank of the tumour in its early stages is required to select a specific treatment plan. A major concern is the elimination, segmentation and detection of tumour areas infected by magnetic resonance imaging (MRI). Despite the fact that it is a laborious and tedious task done by clinical experts or radiologists whose precision depends entirely on their experience. Computer-aided technology is becoming more and more important for circumventing these limitations. This study investigates a multi-layer Deep Belief Network (DBN) technique for MRI tumour detection. The proposed model is named as Brain Tumour Deep Belief Network (BT-DBN). The BT-DBN was tested with two datasets. The results demonstrate the importance of accuracy parameters relative to the most recent approaches. The results exhibit that the BT-DBN was effective in identifying different types of tumour tissue in MR images of the brain. The precision is 99.51%, the specificity is 94.28%, and the sensitivity is 98.72%.

Brain tumor image segmentation algorithm based on multimodal feature fusion of Bayesian weight distribution

AbstractThis study proposes an improved U‐Net model to address the issues of large semantic differences in skip connections and insufficient utilization of cross‐channel information in magnetic resonance imaging (MRI) images leading to inaccurate segmentation of brain tumor regions in the field of brain tumor segmentation. Firstly, by adding a deep residual module to alter the receptive field, the network's ability to learn tumor information is enhanced. Secondly, a dual attention mechanism was established using Bayesian weighting technology, achieving multi‐channel and multi‐scale feature fusion, and improving the model's learning and extraction of brain tumor boundary information. Finally, the tumor features extracted from different patterns are concatenated through skip connections, effectively integrating feature information from different levels and scales, and reducing semantic differences. We evaluated the performance of the proposed model on the BraTS2018 and BraTS2019 brain tumor image segmentation datasets. The experimental results showed that for the BraTS2018 dataset, the model improved the average dice score by 12.8%, the average sensitivity by 10.4%, and the average Hausdorff Distance by 5.75 compared to traditional U‐Net. On the BraTS2019 dataset, three indicators improved by 12.6%, 11.2%, and 7.46, respectively. The experimental results show that the proposed improved U‐Net model can improve the segmentation performance of brain tumor MRI images without increasing computational time.

Detection of normal and abnormal brain tumor MRI images using machine learning approaches

&lt;p&gt;Without image processing, the modern technological world we live in today would be completely different. Different applications can be found in many different areas, including as medicine, remote sensing, computer vision, and more. Brain tumours occur because of the abnormal growth of brain tissue. Therefore, it is crucial to surgically remove the tumor’s component that has spread throughout the brain. The creation of images of the human body’s internal organs and structures depends on numerous factors, one of which is the use of Magnetic Resonance Imaging (MRI), one of the many medical imaging techniques. Segmenting images is a challenging task in the modern medical field. The tumor’s location and sizes can be detected with more accuracy with the help of a segmentation performed on MRI slices. In this paper, we propose the Adaptive Convex Region Contour (ACRC) algorithm, a novel method for achieving such requirements. Here, we use the Support Vector Machine, often known as SVM, to identify slices and determine whether they are normal or abnormal. Once the SVM results are in, the off-kilter slices will be included into the analysis. Since the human body already has a complex anatomy in 3D. It’s disappointing because MRI slices can only provide images in a plain, 2D plane. Because of its 3D structure, the tumor’s actual shape cannot be detected from a surface image. This means that the transformation from 2D to 3D is important, as it provides necessary data to the surgeons doing the operation. The Rapid Mode Image Matching (RMIM) algorithm should be used when constructing a 3D reconstruction model. Immediately after the 3D model is completed being created, a rough estimate of the tumor’s original volume is generated. The methodological consideration was conducted in the simulated MATLAB software. It was determined from the data that the proposed method is better to the current establishment methodologies in terms of accuracy. &lt;strong&gt;Objective:&lt;/strong&gt; This paper aims to address the need for accurate segmentation of brain tumors in Magnetic Resonance Imaging (MRI) slices. The primary research question revolves around developing a novel segmentation method, the Adaptive Convex Region Contour (ACRC) algorithm, to improve the precision of tumor detection by incorporating a Support Vector Machine (SVM) for identifying abnormal slices.&lt;strong&gt; &lt;/strong&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The proposed approach involves utilizing the SVM to classify MRI slices as either normal or abnormal. The abnormal slices, detected by SVM, are subjected to further analysis. To overcome the limitation of MRI producing 2D images for the inherently 3D human anatomy, a transformation from 2D to 3D is crucial. The Rapid Mode Image Matching (RMIM) algorithm is adopted to construct a 3D reconstruction model of the brain and its tumor. This model allows surgeons to obtain a more accurate understanding of the tumor’s actual 3D shape. &lt;strong&gt;Results: &lt;/strong&gt;The methodology was implemented and evaluated using simulated MATLAB software. The results demonstrate that the proposed ACRC algorithm, combined with SVM-based abnormal slice identification and subsequent 3D reconstruction using RMIM, outperforms existing methodologies in terms of accuracy. The 3D reconstruction provides valuable insights into the tumor’s shape, aiding surgical planning. &lt;strong&gt;Conclusions: &lt;/strong&gt;In conclusion, the research contributes to the field of medical image processing by presenting a comprehensive approach for brain tumor segmentation and 3D reconstruction. The ACRC algorithm, in conjunction with SVM and RMIM, enhances the accuracy of tumor detection and provides critical 3D information for surgical procedures. This advancement holds the potential to improve the efficacy of brain tumor surgeries, underscoring the significance of innovative image processing techniques in modern medical applications.&lt;/p&gt;

Study and Performance Evaluation of Brain MRI Images Using Aartificial Intelligence

The limits and potential of medical imaging are expanded by artificial intelligence. Therefore, in an effort to improve the performance and accuracy of diagnosing brain abnormalities, researchers are constantly working to create an effective and automated diagnosis method. Tumour identification and diagnosis have been achieved by the use of magnetic resonance imaging (MRI). Medical professionals can identify and categorise tumours as normal or abnormal with the aid of digital image processing. This research focuses on various neural networks for brain MRI tumour and non-tumour image categorization and confusion matrix performance evaluation. Otsu's thresholding approach is used for segmentation out of all the segmentation techniques. For feature extraction, a grey level co-occurrence matrix (GLCM) is employed. The classification techniques utilized in this study produce the necessary results in terms of confusion matrix parameters, which may be used to assess the classifier's performance in terms of F1 score, accuracy, sensitivity, and precision.