Accurate Diagnosis Of Tumors Research Articles

Metabolic Acidity/H2O2 Dual‐Cascade‐Activatable Molecular Imaging Platform toward Metastatic Breast Tumor Malignancy

Fluorescence imaging in the second near‐infrared window (NIR‐II) is crucial for accurate tumor diagnosis, offering superior resolution and penetration capabilities. Current NIR‐II probes are limited by either being "always on" or responding to one stimulus, leading to low signal‐to‐noise ratios and potential false positives. We introduced a dual‐lock‐controlled probe, HN‐PBA, activated by both H2O2 and tumor acidic environment. This dual response ensures bright fluorescence at tumor sites, leading to higher tumor‐to‐normal tissue ratios (T/NT) compared to conventional “always on” probes and probes activated only by H2O2. This strategy allows precise tumor identification and removal of primary and metastatic tumors, achieving superior T/NT ratios (24.3/6.4 for orthotopic and lung metastasis, respectively). Our probe also effectively detected lung metastatic foci as small as ≤ 0.7 mm and showed the capability for accurate lesion localization in clinical breast cancer specimens. This dual‐stimuli‐responsive strategy could aid future diagnostic probe design.

β-galactosidase instructed in situ self-assembly fluorogenic probe for prolonged and accurate imaging of ovarian tumor

Fluorescent probes are essential for optical imaging and have been extensively employed for precise cancer diagnosis studies. β-galactosidase (β-gal) serves as a primary biomarker for ovarian cancer and has been utilized to develop imaging probes for accurate tumor diagnosis. However, traditional small molecular probes have limitations in terms of rapid diffusion and metabolic clearance from the target lesion, resulting in a short imaging window and compromised tumor-to-background ratios (TBR). Herein, we integrated an enzyme-instructed in situ self-assembly strategy to construct Gal-IRFF, a small molecule-based activatable near-infrared (NIR) fluorogenic probe. Upon cleavage by endogenous β-gal overexpressed in ovarian cancer cells, IRFF exhibited enhanced NIR fluorescence signals and self-assembled into nanoparticles through intermolecular interactions of the Phe-Phe (FF) dipeptide moiety, which facilitated probe accumulation and retention within the tumor lesion. Compared with the small molecule probe Gal-IR, our proposed self-assembly probe Gal-IRFF demonstrated a lower limit of detection (LOD) towards β-gal and showed remarkable improvements in distribution and retention time within SKOV3 cells in vitro and tumors in vivo, thereby providing a long-term imaging window for real-time monitoring β-gal levels in ovarian tumors. Therefore, this study highlights the potential of an enzyme-instructed self-assembly fluorogenic probe design approach for achieving precise tumor diagnosis in vivo.

3D DNAzyme Motor Nanodevice With Self-Powered FRET Amplifier and Self-Supplied H2O2 for Enhancing Human Neutrophil Elastase Profiling and Chemodynamic Therapy in Lung Tumor.

The development of theragnostic nanosystems integrating FRET (fluorescence resonance energy transfer) imaging and chemodynamic therapy (CDT) for accurate diagnosis and effective treatment of lung tumors is still a big challenge. Herein, a peptide-assembled 3D DNAzyme motor nanodevice is engineered for a self-powered FRET amplifier profiling human neutrophil elastase (HNE) and self-supplied H2O2 enhancing CDT. The nanodevice is prepared by depositing AuNPs on ZIF-8, in which ZIF-8 co-loaded the lysosomal targeting peptide-modified copper peroxides (PCPs) and hairpins (H1, H2, and H3), AuNPs are co-labeled by DNAzyme-peptide (DP) conjugate and H3. In the tumor micro-environment, HNE driven 3D DNAzyme walker followed by an exponential amplification constructed by a synergistic cross-activation between hybridization chain reaction and DNAzyme, generating a self-powered FRET amplifier. The FRET amplifier specifically measures HNE with a sensitivity of 0.026pM, and successfully images exogenous HNE in living cells and monitors HNE in mouse models. Moreover, the PCPs can target lysosomes, reducing lysosome escape. The self-supplying H2O2 undertaken by PCPs improves the Cu (II)-catalyzed Fenton-like reaction, effectively causing cell apoptosis to inhibit tumor growth. Significantly, the nanodevice successfully screens inhibitors and discriminates the HNE level in normal and lung cancer tissues, suggesting that the nanodevice provides an effective tool for the diagnosis and treatment of lung tumors.

MR Image Fusion-Based Parotid Gland Tumor Detection.

The differentiation of benign and malignant parotid gland tumors is of major significance as it directly affects the treatment process. In addition, it is also a vital task in terms of early and accurate diagnosis of parotid gland tumors and the determination of treatment planning accordingly. As in other diseases, the differentiation of tumor types involves several challenging, time-consuming, and laborious processes. In the study, Magnetic Resonance (MR) images of 114 patients with parotid gland tumors are used for training and testing purposes by Image Fusion (IF). After the Apparent Diffusion Coefficient (ADC), Contrast-enhanced T1-w (T1C-w), and T2-w sequences are cropped, IF (ADC, T1C-w), IF (ADC, T2-w), IF (T1C-w, T2-w), and IF (ADC, T1C-w, T2-w) datasets are obtained for different combinations of these sequences using a two-dimensional Discrete Wavelet Transform (DWT)-based fusion technique. For each of these four datasets, ResNet18, GoogLeNet, and DenseNet-201 architectures are trained separately, and thus, 12 models are obtained in the study. A Graphical User Interface (GUI) application that contains the most successful of these trained architectures for each data is also designed to support the users. The designed GUI application not only allows the fusing of different sequence images but also predicts whether the label of the fused image is benign or malignant. The results show that the DenseNet-201 models for IF (ADC, T1C-w), IF (ADC, T2-w), and IF (ADC, T1C-w, T2-w) are better than the others, with accuracies of 95.45%, 95.96%, and 92.93%, respectively. It is also noted in the study that the most successful model for IF (T1C-w, T2-w) is ResNet18, and its accuracy is equal to 94.95%.

Morphological features and genetic background in ectomesenchymal chondromyxoid tumor: A systematic review.

Ectomesenchymal chondromyxoid tumor (EMCMT) is a rare neoplasm that mainly affects the tongue and harbors recurrent, although not exclusive, gene fusions. Owing to its rarity, overlapping features with other tumors may lead to challenges in the microscopic diagnosis. We aimed to perform a systematic review focusing on the histomolecular findings of EMCMT of the oral and maxillofacial region and to evaluate the possible association between microscopic features with the genetic background. An electronic search was made on PubMed, Web of Science, Scopus, Ovid, and Embase. Clinicopathological, immunohistochemical, and molecular data were retrieved. Overall, 114 cases from 53 articles on EMCMT were analyzed. Histologically, EMCMT was described as demarcated (84.2%), lobulated (66.7%), reticulated (51.8%), and arranged in sheets, cords, and strands (42.9%), with 73.7% of lesions with spindle-shaped cells. Myxoid stroma (88.6%), chondroid areas (60.5%), chondromyxoid stroma (57.0%), and fibrous septae (42.9%) were also tumor-outlined features. The most expressed markers were vimentin (100.0%), cyclin D1 (100.0%), GFAP (88.5%), NSE (87.5%), S100 (86.5%), CD56 (76.9%), and CD57 (76.5%). The RREB1-MRTFB fusion was detected in 91.0% of the cases investigated and EWSR1 rearrangements in 17.4%. The presence of the fusion RREB1::MRTFB or chromosome alterations in the EWSR1 gene were not highly specific to the morphological features of EMCMT. This study provides a comprehensive summary of the clinicopathological, immunohistochemical, and molecular characteristics of EMCMT, aiding in a more accurate microscopic diagnosis of this rare tumor.

Regulating Aggregation-Induced Emission Luminogen for Multimodal Imaging-Navigated Synergistic Therapy Involving Anti-Angiogenesis.

As a new avenue for cancer research, phototheranostics has shown inexhaustible and vigorous vitality as it permits real-time diagnosis and concurrent in situ therapy upon non-invasive light-initiation. However, construction of an advanced material, allowing prominent phototheranostic outputs and synchronously surmounting the inherent deficiency of phototheranostics, would be an appealing yet significantly challenging task. Herein, an aggregation-induced emission (AIE)-active luminogen (namely DBD-TM) featured by intensive electron donor-acceptor strength and twisted architecture with finely modulated intramolecular motion, is tactfully designed and prepared. DBD-TM simultaneously possessed fluorescence emission in the second near-infrared (NIR-II) region and high-efficiency photothermal conversion. By integrating DBD-TM with anti-angiogenic agent sorafenib, a versatile nanomaterial is smoothly fabricated and utilized for trimodal imaging-navigated synergistic therapy involving photothermal therapy and anti-angiogenesis toward cancer. This advanced approach is capable of affording accurate tumor diagnosis, complete tumor elimination, and largely restrained tumor recurrence, evidently denoting a prominent theranostic formula beyond phototheranostics. This study will offer a blueprint for exploiting a new generation of cancer theranostics.

Accurate MRI-Based Brain Tumor Diagnosis: Integrating Segmentation and Deep Learning Approaches

Magnetic Resonance Imaging (MRI) is vital in diagnosing brain tumours, offering crucial insights into tumour morphology and precise localisation. Despite its pivotal role, accurately classifying brain tumours from MRI scans is inherently complex due to their heterogeneous characteristics. This study presents a novel integration of advanced segmentation methods with deep learning ensemble algorithms to enhance the classification accuracy of MRI-based brain tumour diagnosis. We conduct a thorough review of both traditional segmentation approaches and contemporary advancements in region-based and machine learning-driven segmentation techniques. This paper explores the utility of deep learning ensemble algorithms, capitalising on the diversity of model architectures to augment tumour classification accuracy and robustness. Through the synergistic amalgamation of sophisticated segmentation techniques and ensemble learning strategies, this research addresses the shortcomings of traditional methodologies, thereby facilitating more precise and efficient brain tumour classification.

Diagnosis and Classification of Brain Tumors from MRI Images Using the SVM Algorithm

Background: A brain tumor is one of the most common and fatal neurological diseases that may require surgery. The correct diagnosis of the location and size of the tumor can be a diagnostic aid program for medical robots during surgery, and it also helps doctors formulate a suitable treatment plan for the patient. Objectives: To develop an algorithm based on support vector machine (SVM) for the detection and classification of tumors into benign and malignant types on MRI images. Methods: In this retrospective study, 160 MRI images were obtained from the KAGGLE website. The studied subjects included two groups: Benign tumors and malignant tumors. At first, preprocessing and noise removal were done by comparing four filters: Butterworth, wavelet, ideal, and median. Finally, the SVM algorithm was used to classify brain tumors into benign and malignant. Results: The performance evaluation of the filters showed that the median and wavelet filters had the best performance in removing noise from MRI images. Then, the discrete wavelet transform (DWT) extracted the required features from MRI images and was used as the input of the SVM algorithm. The accuracy, precision and specificity of the proposed algorithm in diagnosing benign and malignant brain tumors were 95%, 88% and 91%. Conclusions: The findings of recent studies show that this algorithm can be used to improve the accurate diagnosis of brain tumors and their types. Combining morphological features can also be a diagnostic tool to increase accuracy in robotic surgeries.

Optimized Two-Photon Imaging by Stimuli-Responsive Peptide Self-Assembly Facilitates Self-Assisted Counteraction of Cisplatin-Resistance in Cancer Cells.

Accurate diagnosis and effective treatment of tumors remain significant clinical challenges. While fluorescence imaging is essential for tumor detection, it has limitations in terms of specificity, penetration depth, and emission wavelength. Here, we report a novel glutathione (GSH)-responsive peptide self-assembly excimer probe (pSE) that optimizes two-photon tumor imaging and self-assisted counteraction of the cisplatin resistance in cancer cells. The GSH-responsive self-assembly of pSE induces a monomer-excimer transition of coumarin, promoting a near-infrared redshift of fluorescence emission under two-photon excitation. This process enhances penetration depth and minimizes interference from biological autofluorescence. Moreover, the intracellular self-assembly of pSE impacts GSH homeostasis, modulates relevant signaling pathways, and significantly reduces GSTP1 expression, resulting in decreased cisplatin efflux in cisplatin-resistant cancer cells. The proposed self-assembled excimer probe not only distinguishes cancer cells from normal cells but also enhances the efficacy of cisplatin chemotherapy, offering significant potential in tumor diagnosis and overcoming cisplatin-resistant tumors.

Key updates and interpretation of the ninth version of AJCC staging system for neuroendocrine tumors of the stomach

The cancer staging system of the American Joint Committee on Cancer (AJCC) is the most widely used clinical basis for tumor staging. In October 2023, AJCC released the staging system (ninth version) for the neuroendocrine tumors of stomach (NET), which has been implemented in January 2024. The ninth version of NET staging system mainly updated the histopathologic classification, diagnosis and staging methods, clinical and pathological staging, prognosis grade, tumor and non-tumor prognostic features. The update and implementation of the staging system provide a more detailed reference for the accurate diagnosis, staging and precise treatment of gastric neuroendocrine tumors. Moreover, it is convenient for clinicians to carry out clinical practice. The purpose of our article is to provide a high-level overview of the major changes in AJCC staging system (version 9) for gastric NET based on the latest evidence-based medical research.

A "Dual-Key-and-Lock" MRI Contrast Agent with T1-T2 Switchable Function for Accurate Diagnosis of Tumors.

Extremely small iron oxide nanoparticle (ESIONP)-based stimuli-responsive switchable MRI contrast agents (CAs) show great promise for accurate detection of tumors due to their outstanding advantages of high specificity and low background signal. However, currently developed ESIONP-based switchable CAs often suffer single-biomarker-induced responses, which lack absolute specificity to pathological tissues, potentially diminishing diagnostic accuracy. In this study, weak acidity and hypoxia, two of the most remarkable characteristics of tumors, are introduced as dual biomarker stimuli to construct an ESIONP-based switchable MRI CA (DKL-CA), with its signal switch controlled by a "dual-key-and-lock" strategy. Only when DKL-CA is exposed to a coexisting weakly acidic and hypoxic environment can monodispersed ESIONPs form nanoclusters, thereby realizing a switch from the T1 to T2 contrast. Moreover, DKL-CA exhibits favorable biosafety and the capacity for precise tumor diagnosis in tumor-bearing mice. Overall, DKL-CA paves the way for designing highly accurate ESIONP-based MRI CAs for tumor diagnosis.

Not every knee tumour is a ganglion - retrospective analysis of benign and malign tumour entities around the knee.

Due to a lack of routine, there is often uncertainty regarding diagnostics of tumours around the knee joint. This study aimed to provide knowledge about the frequency, distribution and diagnostic algorithm of different bone and soft tissue tumour entities of the knee at a large referral university hospital in Germany. Retrospective, longitudinal, single-centre study that reviewed adult patients from 2010 until 2020 with a suspected tumours diagnosis around the knee at a university cancer centre. Inclusion criteria were adults with true bone or soft-tissue tumours in the knee joint and in its adjacent compartments. Suspected diagnosis, histological tumour entity, localization and its surgical treatment by biopsy, resection, osteosynthesis or tumour endoprosthesis were investigated. A total number of 310 adult patients were included with a mean age of 54.2 ± 18.8 years. In total 160 (51.6%) soft-tissue tumours (69/43.1% benign; 74/46.2% malignant; 17/10.6% intermediate), 92 (29.6%) primary bone tumours (46/50% benign; 39/42.3% malignant; 7/7.6% intermediate), 36 (11.6%) metastases and 22 (7.1%) lymphomas were detected. 171 (55.1%) tumours were classified as malignant. Suspected diagnosis was matched with histology in 74.5% (231/310) of all cases. In 6 cases a primarily suspected benign diagnosis turned out to be malignant. The majority of primary bone tumours was cartilage derived (63.1%;58/92) and located in the distal 2/3 of the femur, whereas intracapsular tumours of the knee joint were rare (13.0%). Soft-tissue tumours were located primarily in the middle third of the thigh (36.8%). The MRI was the diagnostic tool of choice in 98.1% of soft tissue tumours and 82.6% bone tumours. Awareness is crucial for detecting rare and malignant tumours around the knee, with adipocytic tumours being the most common soft tissue tumour and chondrogenic tumours as the most prevalent malignant bone tumour. Accurate diagnosis of bone tumours necessitates radiographs and frequently an additional MRI scan, while soft tissue tumours require mandatory MRI scans. Incorrectly diagnosing a tumour can have severe consequences, emphasizing the need for histological confirmation in all cases. Additionally, malignant tumours within joint capsules in adults are infrequent.

IMG-18. DIFFERENTIAL DIAGNOSIS OF POSTERIOR FOSSA TUMORS USING RADIOMICS; A FIRST-LINE DIAGNOSTIC STEP REQUIRED FOR DOWNSTREAM ANALYSES

Abstract BACKGROUND Accurate radiographic diagnosis of pediatric brain tumors (PBTs) that originate in the brainstem and posterior fossa, including medulloblastoma (MB), pilocytic astrocytoma (PA), ependymoma (EPN), atypical teratoid/rhabdoid tumor (ATRT), and diffuse intrinsic pontine glioma (DIPG), is crucial for optimizing surgical approaches and enhancing neoadjuvant therapies. Existing research on the radiographic differential diagnosis of posterior fossa tumors has limitations, including small sample sizes, lack of inclusion of certain histologies especially rarer tumors such as ATRTs, and incomplete analysis of the whole tumor, including peritumoral edema. In this study, we aimed to perform a comprehensive analysis using radiomics and machine learning to differentiate among the common posterior fossa and brainstem tumors. METHODS We employed 927 radiomic features extracted from whole tumor regions within treatment-naïve, standard multiparametric MRI sequences (pre-/post-contrast T1-weighted, T2-weighted, FLAIR) of 264 patients (106 MBs, 78 PAs, 28 EPNs, 27 ATRTs, and 25 DIPGs), collected from the Children’s Brain Tumor Network (CBTN). We adopted a one-versus-rest classification strategy, employing Support Vector Machines combined with the Least Absolute Shrinkage and Selection Operator (LASSO) for feature selection, and implementing nested cross-validation for robustness. RESULTS The performances of the classifiers were evaluated using the Area Under the Receiver Operating Characteristic Curve, yielding values of 0.84 for MBs, 0.84 for PAs, 0.70 for EPNs, 0.75 for ATRTs, and 0.71 for DIPGs. CONCLUSIONS Our method effectively differentiates between various tumor types in the posterior fossa and brainstem, paving the path towards the development of comprehensive diagnostic and prognostic AI tools for pre-treatment histological diagnosis of these tumors. These AI tools can lead to more tailored, risk-adjusted treatments for PBTs, reducing morbidities and improving patient outcomes. Based on our promising initial results, we will expand our dataset to include more samples and incorporate rarer tumor types, as well as piloting in different molecular subclassifications.

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.

A Review of Artificial Intelligence in Tumor Pathology Image Analysis

Accurate diagnosis of tumors is crucial to the treatment and prognosis of patients. Pathological diagnosis is regarded as the "gold standard" of tumor diagnosis, which helps to detect the disease at an early stage and formulate precise treatment plans for patients. However, traditional pathology diagnosis relies heavily on the expertise and diagnostic experience of physicians, making the quality and accuracy of pathology diagnosis largely dependent on their individual capabilities. With the popularization of Whole Slide Image (WSI) technology, the application of AI in pathology has gained significant momentum. With its powerful analyzing ability, AI has been widely used in computational pathology, especially in pathology-assisted diagnosis, showing great potential. This paper first explores two core tasks of AI in the field of pathology image analysis - image segmentation and image classification. Finally, it looks at the challenges and opportunities facing the field.

Enhancing brain tumor classification in MRI scans with a multi-layer customized convolutional neural network approach.

The necessity of prompt and accurate brain tumor diagnosis is unquestionable for optimizing treatment strategies and patient prognoses. Traditional reliance on Magnetic Resonance Imaging (MRI) analysis, contingent upon expert interpretation, grapples with challenges such as time-intensive processes and susceptibility to human error. This research presents a novel Convolutional Neural Network (CNN) architecture designed to enhance the accuracy and efficiency of brain tumor detection in MRI scans. The dataset used in the study comprises 7,023 brain MRI images from figshare, SARTAJ, and Br35H, categorized into glioma, meningioma, no tumor, and pituitary classes, with a CNN-based multi-task classification model employed for tumor detection, classification, and location identification. Our methodology focused on multi-task classification using a single CNN model for various brain MRI classification tasks, including tumor detection, classification based on grade and type, and tumor location identification. The proposed CNN model incorporates advanced feature extraction capabilities and deep learning optimization techniques, culminating in a groundbreaking paradigm shift in automated brain MRI analysis. With an exceptional tumor classification accuracy of 99%, our method surpasses current methodologies, demonstrating the remarkable potential of deep learning in medical applications. This study represents a significant advancement in the early detection and treatment planning of brain tumors, offering a more efficient and accurate alternative to traditional MRI analysis methods.

Effect of combination of genomic variation–based machine learning and clinical pathology on accurate diagnosis of tumors: Lung adenocarcinoma and lung squamous cell carcinoma.

11174 Background: Non-small cell lung cancer (NSCLC) is the most prevalent form of lung cancer, with lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) being the predominant subtypes. Given the significant differences in treatment approaches and clinical outcomes between LUAD and LUSC, accurate identification of these pathological subtypes prior to treatment initiation is crucial. Methods: This study aimed to enhance the diagnostic accuracy for LUAD and LUSC by integrating a machine learning artificial intelligence (AI) model with the expertise of pathologists. The AI model was trained and validated on a cohort of 10,693 and 5,571 cases from the OrigiMed database, each confirmed by at least three pathologists. Targeted sequencing of 450 cancer-related genes was performed. Results: Analysis of the validation set demonstrated an overall accuracy of 89.2% across 28 tumor types, with individual accuracies ranging from 22.2% to 100%. For the top one prediction, the AI model achieved an accuracy of 82.7% for LUAD and 67.9% for LUSC. However, when considering the top three predictions, the accuracy significantly increased to 92.1% for LUAD and 93.0% for LUSC. To further validate the diagnostic capability of the AI model, a large sample of 4,531 LUAD cases and 207 LUSC cases from 4,502 patients was collected for comparative analysis with pathologists' diagnoses. The results indicated that 87.9% of LUAD cases and 83.6% of LUSC cases were consistent with the AI model's diagnosis, while 4.9% of LUAD and 9.7% of LUSC cases showed discrepancies. To investigate these inconsistencies, a subset of 30 LUAD cases and 16 LUSC cases was selected for re-evaluation by independent pathologists. Four poorly differentiated cases from the discrepancy group were ultimately diagnosed as 2 LUADs and 2 LUSCs, supporting the initial AI diagnosis. For instance, Patient 40 was initially diagnosed with LUSC; however, the AI system identified the pathology as LUAD, which may be attributed to the detection of the KIF5B-RET fusion. This diagnosis was subsequently corroborated by an additional pathologist who observed gland-like structures and ambiguous solid mass formations within the tumor tissue, consistent with LUAD histopathology. Conclusions: In summary, we have presented a machine learning AI model that leverages next-generation sequencing (NGS) technology for the auxiliary diagnosis of cancer. By applying this AI model to diagnose LUAD and LUSC and comparing it with the diagnoses made by human pathologists, we have demonstrated that the integration of pathological diagnosis and AI machine learning can significantly enhance and even surpass the diagnostic capabilities of human physicians. This advancement holds great potential in improving the accuracy of tumor diagnosis and the precision of treatment.

A deep learning-based system for accurate diagnosis of pelvic bone tumors

Bone image analysis and categorizing bone cancers have both seen advancements thanks to deep learning (DL), more notably convolution neural networks (CNN). This study suggests a brand-new CNN-based methodology for categorizing pelvic bone tumors specifically. This work aims to create a pelvic bone computed tomography (CT) image categorization system based on deep learning. The proposed technique uses a convolutional neural network (CNN) architecture to automatically extract information from the CT images and classify them into distinct categories of tumors. A total of 178 3D CT pictures was discovered and added retroactively. DenseNet created the image-based model with Adam optimizer and cross entropy loss. The suggested system's accuracy is assessed using a variety of performance indicators, including sensitivity, specificity, and F1-score. As demonstrated by the experiment findings, the suggested deep learning based classification system has a high degree of accuracy (94%), making it useful for the diagnosis and treatment of pelvic bone tumors. Our promising results might hasten the use of DL-assisted CT diagnosis for pelvic bone tumors in the future.

An Image-Guided Percutaneous Core Needle Biopsy for Accurate Assessment of Musculoskeletal Tumors: A Targeted Diagnosis.

Background Accurate diagnosis of musculoskeletal tumors is essential for guiding appropriate treatment strategies. Percutaneous core needle biopsy (PCNB) is increasingly recognized as a valuable method for obtaining tissue samples for histopathological examination. This study aims to evaluate the diagnostic accuracy and clinical utility of PCNB in diagnosing musculoskeletal tumors. Methodology A total of 152 cases suspected of musculoskeletal tumors underwent PCNB at our tertiary care center between 2020 and 2023. Pre-biopsy evaluation included comprehensive clinical assessment and imaging studies. Core biopsies were performed under image guidance, with specimens sent for histopathological examination and culture sensitivity analysis. Diagnostic yield, accuracy, and performance metrics of PCNB were assessed. Results PCNB demonstrated a diagnostic yield of 93.4%. However, in cases where initial biopsies were inconclusive, repeat core biopsy or open biopsy provided the necessary diagnostic clarity. PCNB demonstrated a remarkable diagnostic accuracy of 97.9%, with a specificity and positive predictive value of 100%. There were no post-biopsy complications and no instances of local recurrence from the biopsy tract. Conclusions PCNB can be a reliable method for diagnosing musculoskeletal tumors, offering high diagnostic accuracy and minimal complications. The utilization of image guidance enhances precision and reduces the risk of complications. PCNB proves effective in diagnosing both primary tumors and bone infections, facilitating timely and appropriate treatment strategies in orthopedic oncology.

Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model’s ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model’s decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.