Search Results (88)

Using neural networks has become the standard technique for medical diagnostics, especially in cancer detection and classification. This work evaluates the performance of Vision Transformer architectures, including Swin Transformer and MaxViT, for several datasets of magnetic resonance imaging (MRI) and computed tomography (CT) scans. We used three training sets of images with brain, lung, and kidney tumors. Each dataset included different classification labels, from brain gliomas and meningiomas to benign and malignant lung conditions and kidney anomalies such as cysts and cancers. This work aims to analyze the behavior of the neural networks in each dataset and the benefits of combining different image modalities and tumor classes. We designed several experiments by fine-tuning the models on combined and individual datasets. The results revealed that the Swin Transformer achieved the highest accuracy, with an average of 99.0% on single datasets and reaching 99.43% on the combined dataset. This research highlights the adaptability of Transformer-based models to various human organs and image modalities. The main contribution lies in evaluating multiple ViT architectures across multi-organ tumor datasets, demonstrating their generalization to multi-organ classification. Integrating these models across diverse datasets could mark a significant advance in precision medicine, paving the way for more efficient healthcare solutions. Full article

(1) Background: There has been an ongoing concern for several decades that radiofrequencies emitted from mobile phones are related to brain cancer risk. We calculated temporal trends in brain cancer incidence rates in adults and children and compared them to mobile phone subscription data over the same time period. (2) Methods: We analyzed the Surveillance, Epidemiology and End Results (SEER 22) cancer database between 2000 and 2021. Age-standardized incidence rates (ASR) per 100,000 people were calculated and the annual percentage change (APC) for malignant and benign brain cancer and vestibular schwannomas (acoustic neuromas of the 8th cranial nerve) was established. The total number of mobile phone subscriptions in the United States was plotted for the period 1985–2024. (3) Results: The APC for adolescents and adults was −0.6 (p = 0.0004) for malignant tumors, −0.06 (p = 0.551) for temporal lobe tumors, and 1.9 (p = 0.00003) for benign tumors. The APC for benign acoustic neuroma was 0.09 (p = 0.8237), suggesting that mobile phone use is unlikely to be associated with this tumor type. There was a 1200-fold increase in the number of cell phone subscriptions during this period. (4) Conclusions: These findings suggest that mobile phone use does not appear to be associated with an increased risk of brain cancer, either malignant or benign. Full article

Background and Clinical Significance: Solitary fibrous tumors (SFTs) arising from the lung parenchyma without any relation to the pleura are rare. Case Presentation: We report a case of highly aggressive intraparenchymal SFT of the lung in a 52-year-old woman with rapid distant metastasis to the brain, lungs, and bones within one year post-operation. Chest computed tomography (CT) showed a 5.5 cm-sized, round, but partially lobulated mass with ambiguous enhancement in the right upper lobe. Positron emission tomography/computed tomography (PET/CT) demonstrated strong homogeneous FDG uptake. Unfortunately, the patient succumbed to the disease within one year of diagnosis. Conclusions: Among intrapulmonary SFT, the cellular variant may appear as a cystic mass due to accompanying hemorrhage, coagulation necrosis, and myxoid degeneration. In the absence of mediastinal metastatic adenopathy, it can be mistaken for a benign cystic mass, making PET/CT findings a crucial tool for suggesting a malignancy. Furthermore, as cellular-type intrapulmonary SFT can exhibit aggressive distant metastasis, understanding the CT and PET/CT findings in this condition is essential for accurate diagnosis and treatment planning. Full article

Background: Primary cardiac tumors (PCTs) are rare entities, with only a minority being malignant and capable of distant dissemination. Among the rarest and most challenging metastatic events are brain metastases originating from cardiac tumors. Due to the heart’s direct access to systemic circulation, even benign tumors such as atrial myxomas may cause cerebral embolic phenomena. Understanding the distinct biological behavior, diagnostic pathways, therapeutic strategies, and prognostic implications of these cases remains limited by the scarcity of the available literature. Methods: A systematic review was conducted following PRISMA guidelines. PubMed, Scopus, Embase, and other major databases were systematically searched using specific MeSH terms and keywords related to cardiac tumors and brain metastases. After applying strict inclusion and exclusion criteria, nineteen studies were included, comprising sixteen single-patient case reports and three multi-patient series. Extracted data included tumor histology, cardiac and brain imaging findings, neurological presentation, treatment approaches, and patient outcomes. Results: A total of 320 patients were analyzed. Atrial myxomas represented the predominant benign tumors causing embolic cerebral events, while angiosarcomas and other cardiac sarcomas were responsible for true hematogenous brain metastases. Brain involvement was frequently hemorrhagic and manifested with seizures, focal deficits, or signs of intracranial hypertension. Cardiac echocardiography and cardiac magnetic resonance imaging (CMR) were essential for tumor detection, while brain MRI, including SWI and DWI sequences, and CT scanning were critical for cerebral lesion characterization. Treatment strategies varied according to tumor type and included surgery, radiotherapy, and systemic therapies. Malignant cardiac tumors correlated with a poor prognosis, with median survival post-CNS involvement ranging from 12 to 14 months. Conclusions: Brain metastases from PCTs, though rare, represent a distinct and serious clinical phenomenon. Benign tumors like myxomas mainly cause embolic cerebral events, whereas malignant tumors, particularly sarcomas, lead to true metastatic brain lesions. Recognizing this biological distinction is crucial for diagnosis, prognostication, and therapeutic planning. An integrated multidisciplinary approach combining advanced cardiac and neuroimaging techniques is vital for early detection and appropriate management. Despite multimodal treatment, survival remains limited, underscoring the urgent need for novel targeted therapies and improved surveillance strategies. Full article

Background/Objectives: Non-invasive motor mapping with navigated transcranial magnetic stimulation (nTMS) is an established diagnostic tool to identify spatial relationships between functional and tumor areas and to characterize motor excitability. Recently, nTMS has been used to analyze the impact of different brain tumor entities on motor excitability. However, entity-specific excitability patterns are not sufficiently validated yet. Methods: We retrospectively analyzed nTMS motor mapping data of 800 motor-eloquent brain tumor patients in this observational study. The motor excitability profile consisted of four nTMS parameters (resting motor threshold (RMT), cortical motor area, amplitude and latency) measured on both hemispheres. The relationship between motor excitability parameters and tumor entity, glioma subtype and motor status were assessed using multiple regressions analyses. Regression models included patient- and tumor-specific factors. Results: Gliomas had more frequent pathologic RMT ratios (OR 1.76, 95%CI: 1.06–2.89, p = 0.030) compared to benign entities. In the subgroup of gliomas, pathologic RMT ratios were more associated with the isocitrate dehydrogenase (IDH)-wildtype status (OR 0.43, 95%CI: 0.23–0.79, p = 0.006) and less so with higher WHO grades (OR 1.61, 95%CI: 0.96–2.71, p = 0.074). This was true for both IDH-mutant astrocytomas (OR 0.43, 95%CI: 0.20–0.91, p = 0.027) and IDH-mutant oligodendrogliomas (OR 0.43, 95%CI: 0.20–0.93, p = 0.031). Motor area enlargement on the tumor hemisphere was more frequently observed in lower WHO-graded gliomas (OR 0.87, 95%CI: 0.78–0.97, p = 0.019). Interestingly, a larger cortical motor area was additionally found for oligodendrogliomas on the healthy hemisphere (OR 1.18, 95%CI: 1.01–1.39, p = 0.041). Motor deficits were related with higher RMT (OR 1.12, 95%CI: 1.05–1.21, p = 0.001), reduced amplitude (OR 0.78, 95%CI: 0.64–0.96, p = 0.019) and prolonged latency (OR 1.12, 95%CI: 1.02–1.24, p = 0.025) in the tumor hemisphere. Conclusions: Neuroplastic phenomena such as adjustment of the motor excitability level and an enlargement of the nTMS-positive motor area were more frequently observed in benign tumors and in IDH-mutated gliomas. Consequently, patients experienced motor deficits less often, suggesting a differentiated susceptibility to resection-related paresis. Future studies will analyze which stimulation paradigms are most effective in stimulating and optimizing neuroplasticity processes to improve the functional outcomes (and thus the quality of life) for patients. Full article

Background/Objectives: Tuberous sclerosis complex (TSC) is a rare, autosomal dominant genetic disorder caused by mutations in the TSC1 and TSC2 genes, which disrupt the regulation of the mammalian target of rapamycin (mTOR) pathway, a critical regulator of cellular growth. The disorder presents as a multisystem condition, with benign tumors (hamartomas) developing in organs such as the brain, skin, heart, kidneys, and lungs, leading to significant clinical variability and impact on quality of life. This review aims to summarize recent advances in the understanding of TSC pathogenesis and clinical variability and evaluate the therapeutic breakthroughs in targeted treatments. Methods: A narrative review was conducted using various available databases. We applied objective evaluation metrics, such as the impact factor of the journals and the citation count, to assess the quality of the studies. Results: Targeted therapies, particularly mTOR inhibitors (mTORis), have shown efficacy in reducing hamartoma size, improving neuropsychiatric symptoms, and enhancing patient outcomes. Despite these advances, variability in disease expression poses challenges in diagnosis and individualized management strategies. Conclusions: Challenges such as early diagnosis, optimizing long-term outcomes, and addressing residual unmet needs remain critical. Future research should prioritize precision medicine approaches and patient-centered care models within centers of expertise to improve treatment efficacy and quality of life for individuals with TSC. Full article

Background/Objective: Alzheimer’s disease is a progressive brain syndrome causing cognitive decline and, ultimately, death. Early diagnosis is essential for timely medical intervention, with MRI medical imaging serving as a primary diagnostic tool. Machine learning (ML) and deep learning (DL) methods are increasingly utilized to analyze these images, but accurately distinguishing between healthy and diseased states remains a challenge. This study aims to address these limitations by developing an integrated approach combining swarm intelligence with ML and DL techniques for Alzheimer’s disease classification. Method: This proposal methodology involves sourcing Alzheimer’s disease-related MRI images and extracting features using convolutional neural networks (CNNs) and the Gray Level Co-occurrence Matrix (GLCM). The Harris Hawks Optimization (HHO) algorithm is applied to select the most significant features. The selected features are used to train a multi-layer perceptron (MLP) neural network and further processed using a long short-term (LSTM) memory network in order to classify tumors as malignant or benign. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset is utilized for assessment. Results: The proposed method achieved a classification accuracy of 97.59%, sensitivity of 97.41%, and precision of 97.25%, outperforming other models, including VGG16, GLCM, and ResNet-50, in diagnosing Alzheimer’s disease. Conclusions: The results demonstrate the efficacy of the proposed approach in enhancing Alzheimer’s disease diagnosis through improved feature extraction and selection techniques. These findings highlight the potential for advanced ML and DL integration to improve diagnostic tools in medical imaging applications. Full article

Brain cancer, with its varied nature, demands early detection for timely treatment. This study aims to refine the diagnosis of brain tumors using convolutional neural network algorithms. Currently, diagnostic accuracy is limited, therefore, our approach uses five different CNN architectures to accurately identify and classify affected brain regions, specifically glioma, meningioma, or pituitary tumors. The AlexNet architecture remarkably achieved training accuracy (99.84%) and validation accuracy (95.19%). By employing GradCAM, heat maps visually clarify the results. This research aims to improve the diagnosis of brain tumors using advanced CNN algorithms. In particular, the success of AlexNet indicates greater diagnostic and treatment potential, promising better outcomes for patients. Full article

Background/Objectives: Cardiac rhabdomyoma (CR), the most frequently occurring fetal cardiac tumor, is often an early marker of tuberous sclerosis complex (TSC). This study evaluates outcomes of fetuses with prenatally diagnosed cardiac tumors managed at a single tertiary center. Methods: Medical records of fetuses diagnosed with cardiac tumors between 2009 and 2024 were retrospectively reviewed. Results: Sixteen cases were identified, with a median follow-up of 6.7 years. TSC was confirmed in 14 cases (88%). Multiple tumors were observed in 13 cases (81%), while 3 cases (19%) had solitary tumors. Both non-TSC cases involved solitary tumors. Cardiac complications (arrhythmias, conduction disorders, and hemodynamic abnormalities) occurred in 38% of cases prenatally and 69% postnatally, with larger tumor diameters significantly associated with complications (p = 0.02). No fetal hydrops or mortality occurred; however, one child died at age five due to a seizure. Postnatal tumor regression occurred in 56% of cases and complete regression in 38% by a median age of 2.3 years (range: 0.6–4.4). One tumor remained stable. Brain MRI revealed TSC-related changes in all TSC-affected patients except one, who had a developmental brain anomaly. Most TSC patients experienced epilepsy (71%) and developmental delays. Conclusion: While CRs are typically benign and regress spontaneously, their strong association with TSC highlights the importance of early diagnosis and family counseling. TSC-related epilepsy and psychomotor delays significantly impair the quality of life. Early mTOR inhibitor therapy offers promise in mitigating TSC-related complications and improving outcomes. Full article

Introduction: Colloid cysts are rare intracranial tumors that can cause obstructive hydrocephalus, a potentially life-threatening condition. Despite being typically benign, they often present with insidious symptoms, leading to delayed diagnosis and catastrophic outcomes. Case Report: A 29-year-old woman presented with a two-month history of worsening headaches, nausea, and vomiting. Neuroimaging revealed a colloid cyst obstructing the third ventricle, resulting in hydrocephalus. Despite emergency placement of an external ventricular drain, the patient’s neurological condition deteriorated rapidly, culminating in brain death. Conclusions: This case highlights the critical importance of the early diagnosis and aggressive management of colloid cyst-induced hydrocephalus. The rapid progression of symptoms and devastating outcomes underscore the need for increased awareness among healthcare providers. Given the high mortality associated with this condition, further research is warranted to identify predictive factors and develop effective treatment strategies. Full article

Primary intracranial melanoma is a very rare brain tumor, especially when accompanied by benign intramedullary melanocytoma. Distinguishing between a primary central nervous system (CNS) lesion and metastatic melanoma is extremely difficult, especially when the primary cutaneous lesion is not visible. Here we report a 13-year-old girl admitted to the Neurosurgery Department of the Institute of Polish Mother’s Health Centre in Lodz due to upper limb paresis. An intramedullary tumor of the cervical C3–C4 and an accompanying syringomyelic cavity C1–C7 were revealed. The child underwent partial removal of the tumor due to the risk of damage to spinal cord motor centers. The removed part of the tumor was diagnosed as melanocytoma. Eight months later, a neurological examination revealed paresis of the right sixth cranial nerve, accompanied by bilateral optic disc edema. Diagnostic imaging revealed a brain tumor. The girl underwent resection of both detected the tumors and an additional satellite lesion revealed during the surgery. The removed tumors were diagnosed as malignant melanomas in pathomorphological examination. Molecular analysis revealed NRASQ61K mutation in both the intracranial and the intramedullary tumor. It should be noted that in cases where available evidence is inconclusive, an integrative diagnostic process is essential to reach a definitive diagnosis. Full article

Arachnoid granulations (AGs) are generally benign structures within the subarachnoid space that extend into the dural sinuses and calvarial bone. They can present in a variety of sizes but are termed ‘giant’ arachnoid granulations (GAGs) when they are larger than 1 cm in diameter or take up a significant portion of the dural sinus’ lumen. Vermiform giant arachnoid granulations are a specific type of GAG that are known for their worm-like appearance. Specifically, these vermiform GAGs can be challenging to diagnose as they can mimic other pathologies like dural sinus thrombosis, sinus cavernomas, or brain tumors. In this case series, we present two cases of vermiform giant arachnoid granulations, discuss their imaging characteristics and highlight the diagnostic challenges to improve identification and prevent misdiagnoses. Full article

Background: Angiocentric glioma (AG) is a rare, benign, and slow-growing tumor. First described in 2005, it is now gaining attention with respect to the possibility of being diagnosed. Even with no statistical differences between sex, it has been reported both in children and the elderly. A total of 120 cases have been described in the literature. The aim of this study is to provide new data for a new statistical assessment of the prevalence and incidence of AG in populations. Case report: An 8-year-old male patient with no history of epilepsy and no need for antiepileptic therapy underwent surgery for a left-parietal brain lesion, revealed through MRI. Imaging was acquired after his first absence episode. The lesion was completely resected. Histological findings indicated angiocentric glioma. No signs of recurrency after two years of follow-up. Conclusion: AG is usually an epilepsy-related low-grade glioma. Few cases exhibit disease progression and exitus. Surgical management should aim for a gross total resection to avoid recurrence and persisting epilepsy. Surgery represents the gold standard in diagnosis and treatment and must be performed as soon as possible in consideration of its healing properties and its useful diagnosis. Full article

Neurofibromatosis type 1 (NF1) is a neurocutaneous disorder. Plexiform neurofibromas (PNFs) are benign tumors commonly formed in patients with NF1. PNFs have a high incidence of developing into malignant peripheral nerve sheath tumors (MPNSTs) with a 5-year survival rate of only 30%. Therefore, the accurate diagnosis and differentiation of MPNSTs from benign PNFs are critical to patient management. We studied a fluorine-18 labeled tryptophan positron emission tomography (PET) radiotracer, 1-(2-[¹⁸F]fluoroethyl)-L-tryptophan (L-[¹⁸F]FETrp), to detect NF1-associated tumors in an animal model. An ex vivo biodistribution study of L-[¹⁸F]FETrp showed a similar tracer distribution and kinetics between the wild-type and triple mutant mice with the highest uptake in the pancreas. Bone uptake was stable. Brain uptake was low during the 90-min uptake period. Static PET imaging at 60 min post-injection showed L-[¹⁸F]FETrp had a comparable tumor uptake with [¹⁸F]fluorodeoxyglucose (FDG). However, L-[¹⁸F]FETrp showed a significantly higher tumor-to-brain ratio than FDG (n = 4, p < 0.05). Sixty-minute-long dynamic PET scans using the two radiotracers showed similar kidney, liver, and lung kinetics. A dysregulated tryptophan metabolism in NF1 mice was further confirmed using immunohistostaining. L-[¹⁸F]FETrp is warranted to further investigate differentiating malignant NF1 tumors from benign PNFs. The study may reveal the tryptophan–kynurenine pathway as a therapeutic target for treating NF1. Full article

Background: Pituitary adenomas are benign brain tumors that impose a heavy burden on patients worldwide. The local burden of disease is yet to be established due to scarcity of data. In line with this, this study aims to present the challenges and gaps in the treatment of pituitary adenomas in the Philippines. Methods: A scoping review of available relevant literature on epidemiology, clinical experience with treatment, health financing, and healthcare delivery system based on the Preferred Reporting Items for Systematic reviews and Meta-analysis guidelines extension for Scoping Reviews was conducted. Results: The scarcity of updated local clinical data, inequity of distribution of resources, inadequate government support, and lack of affordable diagnostic testing, medications, and neurosurgical procedures are the factors that hinder provision of adequate care of pituitary adenomas in the Philippines. Conclusion: There are notable treatment gaps in the management of pituitary adenomas in the Philippines, which may be addressed by strengthening universal healthcare. Strategies to address these gaps were proposed, including improving public-private insurance coverage, increasing manpower, enhancing accessibility to resources, and spreading more awareness. Full article