Diagnosis Of Tumors Research Articles

Smell cancer by machine learning-assisted peptide/MXene bioelectronic array

Non-invasive detection of tumors is of utmost importance to save lives. Nonetheless, identifying tumors through gas analysis is a challenging task. In this work, biosensors with remarkable gas-sensing characteristics were developed using a self-assembly method consisting of peptides and MXene. Based on these biosensors, a mimetic biosensor array (MBA) was fabricated and integrated into a real-time testing platform (RTP). In addition, machine learning (ML) algorithms were introduced to improve the RTP's detection and identification capabilities of exhaled gas signals. The synthesized biosensor, with the ability to specifically bind to targeted gas molecules, demonstrated higher performance than the pristine MXene, with a response up to 150% greater. Besides, the MBA successfully detected 15 odor molecules affiliated with five categories of alcohols, ketones, aldehydes, esters, and acids by pattern recognition algorithms. Furthermore, with the ML assistance, the RTP detected the breath odor samples from volunteers of four categories, including healthy populations, patients of lung cancer, upper digestive tract cancer, and lower digestive tract cancer, with accuracies of 100%, 94.1%, 90%, and 95.2%, respectively. In summary, we have developed a cost-effective and precise model for non-invasive tumor diagnosis. Furthermore, this prototype also offers a versatile solution for diagnosing other diseases like nephropathy, diabetes, etc.

Chemiluminescent Afterglow Material for Enhanced Tumor Diagnosis and Photodynamic Therapy

AbstractAfterglow materials offer great advantages for imaging, including ultra‐long luminescent lifetimes for sustained signal after excitation, high signal‐to‐noise ratios due to minimal tissue autofluorescence interference, and the ability to achieve deep tissue penetration with near‐infrared (NIR) afterglow. AIEgens, known for their potent singlet oxygen (¹O₂) generation during photodynamic therapy (PDT), further enhance the approach. Here is the first report on how to integrate AIEgens with chemiluminescent agents for constructing NIR afterglow materials, enabling chemiluminescence resonance energy transfer (CRET)‐mediated activation of AIEgens for targeted PDT. DCL/TBQ nanoparticles (NPs) exemplify this promising theranostic design. These NPs exhibit high selectivity and sensitivity toward ONOO−, a biomarker associated with tumors, with a low limit of detection (46.1 nm). Additionally, DCL/TBQ NPs boast impressive deep tissue penetration (2 cm) and a remarkable 120‐fold improvement in signal‐to‐noise ratio for tumor afterglow imaging. Most importantly, significant tumor growth inhibition capabilities are demonstrated. This approach holds immense potential for the development of next‐generation theranostic agents, enabling simultaneous tumor diagnosis and treatment with improved accuracy and efficacy.

Dual‐Locked Fluorescent Probes Activated by Aminopeptidase N and the Tumor Redox Environment for High‐Precision Imaging of Tumor Boundaries

AbstractClear delineation of tumor margins is essential for accurate resection and decreased recurrence rate in the clinic. Fluorescence imaging is emerging as a promising alternative to traditional visual inspection by surgeons for intraoperative imaging. However, traditional probes lack accuracy in tumor diagnosis, making it difficult to depict tumor boundaries accurately. Herein, we proposed an offensive and defensive integration (ODI) strategy based on the “attack systems (invasive peptidase) and defense systems (reductive microenvironment)” of multi‐dimensional tumor characteristics to design activatable fluorescent probes for imaging tumor boundaries precisely. Screened out from a series of ODI strategy‐based probes, ANQ performed better than traditional probes based on tumor unilateral correlation by distinguishing between tumor cells and normal cells and minimizing false‐positive signals from living metabolic organs. To further improve the signal‐to‐background ratio in vivo, derivatized FANQ, was prepared and successfully applied to distinguish orthotopic hepatocellular carcinoma tissues from adjacent tissues in mice models and clinical samples. This work highlights an innovative strategy to develop activatable probes for rapid diagnosis of tumors and high‐precision imaging of tumor boundaries, providing more efficient tools for future clinical applications in intraoperative assisted resection.

Dual-Locked Fluorescent Probes Activated by Aminopeptidase N and the Tumor Redox Environment for High-Precision Imaging of Tumor Boundaries.

Clear delineation of tumor margins is essential for accurate resection and decreased recurrence rate in the clinic. Fluorescence imaging is emerging as a promising alternative to traditional visual inspection by surgeons for intraoperative imaging. However, traditional probes lack accuracy in tumor diagnosis, making it difficult to depict tumor boundaries accurately. Herein, we proposed an offensive and defensive integration (ODI) strategy based on the "attack systems (invasive peptidase) and defense systems (reductive microenvironment)" of multi-dimensional tumor characteristics to design activatable fluorescent probes for imaging tumor boundaries precisely. Screened out from a series of ODI strategy-based probes, ANQ performed better than traditional probes based on tumor unilateral correlation by distinguishing between tumor cells and normal cells and minimizing false-positive signals from living metabolic organs. To further improve the signal-to-background ratio in vivo, derivatized FANQ, was prepared and successfully applied to distinguish orthotopic hepatocellular carcinoma tissues from adjacent tissues in mice models and clinical samples. This work highlights an innovative strategy to develop activatable probes for rapid diagnosis of tumors and high-precision imaging of tumor boundaries, providing more efficient tools for future clinical applications in intraoperative assisted resection.

SwinVNETR: Swin V-net Transformer with non-local block for volumetric MRI Brain Tumor Segmentation

Brain Tumor Segmentation (BTS) and classification are important and growing research fields. Magnetic resonance imaging (MRI) is commonly used in the diagnosis of brain tumours owing to its low radiation exposure and high image quality. One of the current subjects in the field of medical imaging is how to quickly and precisely segment MRI scans of brain tumours. Unfortunately, most existing brain tumour segmentation algorithms use inadequate 2D picture segmentation methods and fail to capture the spatial correlation between features. In this study, we propose a segmentation model (SwinVNETR) Swin V-NetTRansformer-based architecture with a non-local block. This model was trained using the Brain Tumor Segmentation Challenge BraTS 2021 dataset. The Dice similarity coefficients for the enhanced tumour (ET), whole tumour (WT), and tumour core (TC) are 0.84, 0.91, and 0.87, respectively. By leveraging this methodology, we can segment brain tumours more accurately than ever before. In conclusion, we present the findings of our model through the application of the Grad-CAM methodology, an eXplainable Artificial Intelligence (XAI) technique utilized to elucidate the insights derived from the model, which helped in better understanding; doctors can better diagnose and treat patients with brain tumours.

The Clinical Significance of CRNDE Gene Methylation, Polymorphisms, and CRNDEP Micropeptide Expression in Ovarian Tumors.

CRNDE is an oncogene expressed as a long non-coding RNA. However, our team previously reported that the CRNDE gene also encodes a micropeptide, CRNDEP. The amino acid sequence of CRNDEP has recently been revealed by other researchers, too. This study aimed to investigate genetic alterations within the CRNDEP-coding region of the CRNDE gene, methylation profiling of this gene, and CRNDEP expression analysis. All investigations were performed on clinical material from patients with ovarian tumors of diverse aggressiveness. We found that CRNDEP levels were significantly elevated in highly aggressive tumors compared to benign neoplasms. Consistently, a high level of this micropeptide was a negative, independent, prognostic, and predictive factor in high-grade ovarian cancer (hgOvCa) patients. The cancer-promoting role of CRNDE(P), shown in our recent study, was also supported by genetic and epigenetic results obtained herein, revealing no CRNDEP-disrupting mutations in any clinical sample. Moreover, in borderline ovarian tumors (BOTS), but not in ovarian cancers, the presence of a single nucleotide polymorphism in CRNDE, rs115515594, significantly increased the risk of recurrence. Consistently, in BOTS only, the same genetic variant was highly overrepresented compared to healthy individuals. We also discovered that hypomethylation of CRNDE is associated with increased aggressiveness of ovarian tumors. Accordingly, hypomethylation of this gene's promoter/first exon correlated with hgOvCa resistance to chemotherapy, but only in specimens with accumulation of the TP53 tumor suppressor protein. Taken together, these results contribute to a better understanding of the role of CRNDE(P) in tumorigenesis and potentially may lead to improvements in screening, diagnosis, and treatment of ovarian neoplasms.

Interpretation on the update of 2022 WHO classification of neuroendocrine tumors

The 5th edition of the WHO Endocrine and Neuroendocrine Oncology Blue Book, released in 2022, contained some changes in the classification of neuroendocrine tumors. A brief summary of the main changes has been provided in this section. Mainly summarized as changes in naming, differentiation and classification of neuroendocrine tumors, and tumor grading systems related to anatomical locations, morphological characteristics of neuroendocrine tumors in different locations, auxiliary diagnostic and prognostic/therapeutic markers, differential diagnosis and diagnostic difficulties of neuroendocrine tumors.

Flow cytometry in the differential diagnosis of myelodysplastic neoplasm with low blasts and cytopenia of other causes.

Myelodysplastic neoplasms (MDS) are characterized by cytopenia, morphologic dysplasia, and genetic abnormalities. Multiparameter flow cytometry (FCM) is recommended in the diagnostic work-up of suspected MDS, but alone is not sufficient to establish the diagnosis. Our aim was to investigate the diagnostic power of FCM in a heterogeneous population of patients with cytopenia, excluding cases with increased blast count. We analyzed bone marrow samples from 179 patients with cytopenia (58 MDS, 121 non-MDS) using a standardized 8-color FCM method. We evaluated the sensitivity, specificity, and accuracy of several simple diagnostic approaches, including Ogata score, extended Ogata score, the WHO and ELN iMDSFlow recommended "3 aberrations in two cell compartments method," and the combination of the Ogata score and "3 aberrations in two cell compartments method." The patients were followed until the diagnosis was confirmed, with a median follow-up of 2months (range 0.2-27). The combination of Ogata score and "3 aberrations in two cell compartments method" achieved the highest diagnostic accuracy (78%) with sensitivity and specificity 61% and 86%, respectively. When using only the "3 aberrations in two cell compartments method," the accuracy was 77% with a sensitivity of 72% and a specificity of 79%. The most frequently observed etiologies among the false positive cases were substrate deficiencies, inflammation/infection, or toxic effects. MDS can be excluded in all these cases after a thorough clinical evaluation and a relatively short follow-up. FCM remains an important but supplementary part in an integrated diagnostic process of MDS with low blasts. The combination of the Ogata score and the "3 aberrations in two cell compartments method" slightly improves accuracy compared to the detection of "3 aberrations in two cell compartments method" alone.

Artificial intelligence for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region.

Objective. Determination of the optimal machine learning model for the creation of software for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region. Material and Methods. The clinical material was based on 1254 patients who were examined in the centralized laboratory of the Volgograd Consultative and Diagnostic Polyclinic No. 2. Of these, 139 were subsequently operated on at the Volgograd Regional Clinical Oncology Dispensary for pancreatic malignancies. In 65 (46.7 %) cases, distal pancreatic resection was performed, and in 74 (53.3 %) cases, pancreaticoduodenectomy was performed. In 28 (20.1 %) cases, at the time of tumor detection, patients did not have clinical symptoms. Statistical processing of the data was carried out using the Python programming language. Five different classifiers were used for machine learning. Results. In the course of factor analysis, 11 parameters were selected from 62 laboratory blood parameters, the dynamics of changes in which should be specifically assessed at the stages of screening and early diagnosis of pancreatic neoplasms. A comparative assessment of machine learning techniques showed that the best option for creating the appropriate software was Hist Gradient Boosting (diagnostic accuracy 0.909, sensitivity 0.642, specificity 0.965, negative predictability 0.928, positive predictability 0.794, F1 0.828, logistic regression loss function 0.352, area under the ROC curve 0.89). Conclusion. The creation of software based on the selected algorithm will make it possible to clarify the real effectiveness of machine learning on a larger population of patients with pancreatic neoplasms.

Brief Review for Multi-Class Brain Tumor Diseases Schemes Using Machine Learning Techniques

Brain tumor diseases have had a considerable impact worldwide, affecting millions of individuals of different age groups, including both children and adults above 20 years old. Due to they are more needed in people’s lives, using the method based classifying brain tumors by machine learning schemes has become necessary. However, healthcare applications face challenges in identifying the most suitable classification-based metric, such as accuracy, due to the utilization of recent datasets. This study paper aims to provide a thorough evaluation of computational intelligence strategies used in tumor diagnosis. Several successful data mining techniques have been implemented, including wavelet analysis and spatial pixel modulation techniques. Furthermore, feature extraction and reduction techniques, such as the Grey Level Co-occurrence Matrix (GLCM), have been used to prepare the features for classification. Magnetic resonance imaging scan (MRI) is frequently utilized for the diagnosis of brain tumor diseases which is highly applied for classification-based machine learning, The review paper was focused on gliomas, meningiomas, and pituitary adenoma diseases. Technically, the usage of kernel principal component KPCA analysis with the proposed adaptive back propagation neural network scheme produced better performance-based classification metrics, (i.e:99.84%) for the accuracy metric. The aforementioned review articles have demonstrated that usage of the machine learning-based health care applications (brain diseases) classification widely assists the patient’s outcome and operations inside the hospitals. In summary, the paper has highlighted the importance of machine learning schemes for brain tumor detection and classification, and it also provided a comprehensive analysis and comparison of the state-of-the-art to show the methods such as ;(feature extraction, feature reduction), pros, cons, and the contributions for each of them. The paper's results are considered an advantageous starting point for future works.

A Surgical Case of Lipomatous Hypertrophy of the Atrial Septum

We present a rare case of lipomatous hypertrophy of the atrial septum (LHAS) characterized by the abnormal accumulation of adipose tissue within the interatrial septum, forming a tumor-like mass. The reported incidence of LHAS is 2.2–8%, with advancements in imaging techniques expanding diagnostic opportunities. A 75-year-old female with a history of meningioma, right breast cancer, cholecystolithiasis, and ovarian cyst; comorbidities, including diabetes, hypertension, and hyperlipidemia; and a body mass index of 33 kg/m2 underwent resection for an enlarging interatrial septal tumor, ultimately leading to the diagnosis of LHAS. Imaging revealed a 36 mm × 28 mm tumor extending from the atrial septum into the right atrium, with a computed tomography value of –76 HU. Histopathologically, the tumor was mainly composed of mature adipocytes along with hypertrophied myocardial fibers and scattered brown adipocytes, confirming the diagnosis of LHAS. Although LHAS is often managed with observation following diagnosis, our report on surgical intervention presents a rare and noteworthy occurrence. This case highlights the importance of recognizing and addressing the rare occurrence of LHAS, which often requires surgical intervention in cases of tumor enlargement. The successful resection and diagnosis of LHAS in this patient underscore the importance of considering this condition in the differential diagnosis of cardiac tumors.

Myelodysplastic/Myeloproliferative Neoplasms with Features Intermediate between Primary Myelofibrosis and Chronic Myelomonocytic Leukemia: Case Series and Review of the Entity

Diagnosis of myeloid neoplasm is currently performed according to the presence of a predetermined set of clinical, morphological, and molecular diagnostic criteria agreed upon by a consensus of experts. Even strictly adhering to these criteria, it is possible to encounter patients who present features that are not easily ascribable to a single disease category. This is the case, e.g., of patients with de novo myeloid neoplasms with features intermediate between primary myelofibrosis (PMF) and chronic myelomonocytic leukemia (CMML). In this study, we retrospectively searched the pathological database of IRCCS Humanitas Research Hospital to identify cases of chronic myeloid neoplasm with monocytosis with a driver mutation of classic myeloproliferative neoplasms (MPN) and showing morphological MPN features. For each case, we assessed all epidemiological, clinical, histopathological, and molecular data. Then, we carried out a literature review, searching for cases with features similar to those of our patients. We retrieved a total of 13 cases presenting such criteria (9 from the literature review and 4 from our institution); in all of them, there was a coexistence of clinical, histopathological, and molecular myelodysplastic and myeloproliferative features. To date, according to current classifications (World Health Organization and International Consensus Classification), given the presence/absence of essential features for PMF or CMML, these patients should be formally diagnosed as myelodysplastic/myeloproliferative neoplasm unclassified/not otherwise specified (U/NOS). This review aims to summarize the features of these difficult cases and discuss their differential diagnosis and their classification according to the novel classifications and the existing literature on overlapping myeloid neoplasms.

Multiple intraductal papillary neoplasms of bile duct diagnosed based on endoscopic ultrasonography and peroral cholangioscopy findings.

A man in his 30s was referred to our department for evaluation of bile duct stricture and removal of an intrahepatic bile duct stone. Five years before his presentation, he underwent left hepatectomy for a giant hepatic hemangioma. There were no abnormalities in blood biochemical tests. Magnetic resonance cholangiopancreatography showed one 5mm oval defect in region B6 and two 8mm semicircular defects in the hilar bile duct. Endoscopic ultrasound revealed a 3.5mm hypoechoic focal raised lesion in the hilar bile duct. Oral cholangioscopy revealed his two lesions in the hilar bile duct as white papillary elevations with mucus production. The pathological diagnosis of intraductal papillary neoplasm was determined (low-grade dysplasia, type 1, gastric type). After 1 and a half years, no expansion of the bile duct lesion was observed. Initially, it was thought to be a benign stenosis after liver resection, but based on the results of endoscopic ultrasound, we suspected a tumorous lesion, and we were able to make an accurate diagnosis, including histological type, using transoral cholangioscopy.

Combining morphological and functional imaging parameters to diagnose primary bone neoplasms in the skull base, spine and sacrum.

Morphological magnetic resonance (MR) and computed tomography (CT) features are used in combination with histology for diagnosis and treatment selection of primary bone neoplasms. Isolated functional MRI parameters have shown potential in diagnosis. Our goal is to facilitate diagnosis of primary bone neoplasms of the skull base, mobile spine and sacrum, by a comprehensive approach, combining morphological and functional imaging parameters. Pre-treatment MR of 80 patients with histologically proven diagnosis of a primary bone neoplasm of the skull base, mobile spine and sacrum were retrospectively analyzed for morphological and functional MRI parameters. Functional parameters were measured in 4 circular regions of interest per tumor placed on non-adjacent scan slices. Differences in values of functional parameters between different histologies were analyzed with Dunn's test. Chordomas were the predominant histology (60.0%). Most neoplasms (80.0%) originated in the midline and had geographical (78.2%) bone destruction. Amorphous-type calcification (pre-existing bone) was seen only in chordomas. Homogeneous contrast enhancement pattern was seen only in chondrosarcoma and plasmacytoma. Ktrans and Kep were significantly lower in both chordoma, and chondrosarcoma compared to giant cell tumor of the bone (p = 0.006 - 0.011), and plasmacytoma (p = 0.004 - 0.014). Highest diffusion-weighted MRI apparent diffusion coefficient (ADC) values corresponded to chondrosarcoma and were significantly higher to those of chordoma (p = 0.008). We identified the most discriminating morphological parameters and added functional MR parameters based on histopathological features that are useful in making a confident diagnosis of primary bone neoplasms in the skull base, mobile spine and sacrum.

Evaluation of Serum Amino Acid and Carnitine Profile in Dogs with Transmissible Venereal Tumor

The presented study aimed to reveal the changes in serum amino acid and carnitine profiles in dogs with transmissible venereal tumor (TVT). The study material comprised 40 female dogs ranging in age from 3 to 5 years. The dogs were divided into two groups based on genital organ examinations. Group 1 (n=20) consisted of healthy dogs, while Group 2 (n=20) consisted of TVT-positive dogs. The definite diagnosis of transmissible venereal tumor was made based on the detection of intracytoplasmic vacuoles and numerous mitotic figures in the collected vaginal smear samples. Blood samples were taken from dogs in both study groups and serum was obtained. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) was used for the determination of carnitine and amino acid profiles. The obtained data were compared using independent samples t-test. The serum amino acid profiles of Lysine, Aspartic Acid, Tyrosine, Asparagine, Alanine, Arginine, Citrulline, Glutamic Acid, Glycine, Methylglutaryl, Phenylalanine, and Ornithine were found to be lower in the TVT group (P

Diagnosis of pediatric central nervous system tumors using methylation profiling of cfDNA from cerebrospinal fluid

Pediatric central nervous system tumors remain challenging to diagnose. Imaging approaches do not provide sufficient detail to discriminate between different tumor types, while the histopathological examination of tumor tissue shows high inter-observer variability. Recent studies have demonstrated the accurate classification of central nervous system tumors based on the DNA methylation profile of a tumor biopsy. However, a brain biopsy holds significant risk of bleeding and damaging the surrounding tissues. Liquid biopsy approaches analyzing circulating tumor DNA show high potential as an alternative and less invasive tool to study the DNA methylation pattern of tumors. Here, we explore the potential of classifying pediatric brain tumors based on methylation profiling of the circulating cell-free DNA (cfDNA) in cerebrospinal fluid (CSF). For this proof-of-concept study, we collected cerebrospinal fluid samples from 19 pediatric brain cancer patients via a ventricular drain placed for reasons of increased intracranial pressure. Analyses on the cfDNA showed high variability of cfDNA quantities across patients ranging from levels below the limit of quantification to 40 ng cfDNA per milliliter of CSF. Classification based on methylation profiling of cfDNA from CSF was correct for 7 out of 20 samples in our cohort. Accurate results were mostly observed in samples of high quality, more specifically those with limited high molecular weight DNA contamination. Interestingly, we show that centrifugation of the CSF prior to processing increases the fraction of fragmented cfDNA to high molecular weight DNA. In addition, classification was mostly correct for samples with high tumoral cfDNA fraction as estimated by computational deconvolution (> 40%). In summary, analysis of cfDNA in the CSF shows potential as a tool for diagnosing pediatric nervous system tumors especially in patients with high levels of tumoral cfDNA in the CSF. Further optimization of the collection procedure, experimental workflow and bioinformatic approach is required to also allow classification for patients with low tumoral fractions in the CSF.

Tumor-Derived Extracellular Vesicles as Liquid Biopsy for Diagnosis and Prognosis of Solid Tumors: Their Clinical Utility and Reliability as Tumor Biomarkers.

Early cancer detection and accurate monitoring are crucial to ensure increased patient survival. Recent research has focused on developing non-invasive biomarkers to diagnose cancer early and monitor disease progression at low cost and risk. Extracellular vesicles (EVs), nanosized particles secreted into extracellular spaces by most cell types, are gaining immense popularity as novel biomarker candidates for liquid cancer biopsy, as they can transport bioactive cargo to distant sites and facilitate intercellular communications. A literature search was conducted to discuss the current approaches for EV isolation and the advances in using EV-associated proteins, miRNA, mRNA, DNA, and lipids as liquid biopsies. We discussed the advantages and challenges of using these vesicles in clinical applications. Moreover, recent advancements in machine learning as a novel tool for tumor marker discovery are also highlighted.

NQO1 and viscosity tandemly responsive NIR fluorescent probe for tumor imaging and monitoring tumor apoptosis

As a common process of programmed cell death, apoptosis plays crucial roles in the occurrence and therapy of tumor. Identifying tumor cells and monitoring tumor cells apoptosis is of great significance in tumor diagnosis and therapy. Herein, a NAD(P)H: quinine oxidoreductase (NQO1) and viscosity tandemly responsive near-infrared fluorescent probe HCy-Q is designed. Firstly, HCy-Q is specifically activated by over-expressed NQO1 to identify NQO1-positive tumor cells. Secondly, the product of HCy-Q hydrolyzed by NQO1 is sensitive to viscosity and capable of detecting mitochondrial viscosity changes. During the doxorubicin-induced apoptosis process of A549 cells, a significant increase in mitochondrial viscosity is observed by using HCy-Q. The novel detection model of NQO1 and viscosity tandemly response makes HCy-Q with great potential for tumor imaging and monitoring tumor apoptosis in vitro and vivo.

O-026 Development of deep learning-based model for differential diagnosis of ovarian neoplasm using pelvic ultrasonography

Abstract Study question Can the deep learning-based diagnostic algorithms of pelvic ultrasonography be a useful clinical tool for evaluating the malignancy risk of ovarian neoplasms? Summary answer AI-based deep learning diagnostic algorithm for pelvic ultrasonography is a potential clinical aid, as it exhibits excellent performance in the differential diagnosis of ovarian neoplasm. What is known already Transvaginal ultrasonography serves as a primary diagnostic tool for adnexal neoplasms due to its widespread availability and user-friendly nature within gynecologic clinics. There have been attempts to employ artificial intelligence algorithms for identifying ovarian malignancy through sonographic evaluations, yet the existing literature is limited, and the optimal processing method for constructing ultrasound-based AI images is not known. This study aims to address this gap by constructing a comprehensive AI-based model and comparing the various input methods for the development of the ultrasound-based diagnostic model. Study design, size, duration A retrospective cohort study was conducted on the clinical records of 1,171 patients diagnosed with ovarian neoplasms through pelvic ultrasonography from May 2002 to August 2021 at our institution. Inclusion criteria mandated that patients undergo pelvic ultrasonographic examination in our department, followed by surgical excision, with a requisite availability of pathologic diagnosis for the identified ovarian neoplasm. Participants/materials, setting, methods The dataset was divided into training, validation, and testing subsets with a distribution ratio of 8:1:1 (2373, 297, 298 images). Pre-processing of ultrasound input was done after removing text annotations and unnecessary non-image data. Deep learning methods with different architectures were utilized, including Swin Transformer, ConvNeXt, MobileNet, ResNet18, EfficientNet V2, and VGG16. Main results and the role of chance This performance analysis encompasses a comparison of various deep learning architectures applied to classification tasks within ultrasound imaging data. The metrics evaluated include Sensitivity, Specificity, Positive Predictive Value (PPV, also known as Precision), Negative Predictive Value (NPV), F1 Score, Accuracy, and the Area Under the Receiver Operating Characteristic curve (AUROC). For Sensitivity, the sequence MobileNet, ResNet-18, EfficientNet-V2, VGG-16, Swin Transformer, and ConvNext is 0.830, 0.851, 0.879, 0.835, 0.883, 0.877; Specificity values follow as 0.848, 0.840, 0.877, 0.866, 0.893, 0.906; PPV (Precision) is reported as 0.848, 0.840, 0.877, 0.866, 0.893, 0.906; NPV metrics are 0.830, 0.851, 0.877, 0.835, 0.879, 0.883; F1 Score progression is 0.838, 0.845, 0.878, 0.848, 0.888, 0.890; Accuracy rates are 0.865, 0.865, 0.895, 0.875, 0.906, 0.909; and finally, AUROC scores span 0.920, 0.920, 0.930, 0.920, 0.930, 0.960. These metrics collectively highlight the nuanced efficacy of each model in ultrasound image classification, with ConvNext demonstrating exceptional performance across the board. Limitations, reasons for caution An external validation of our model using datasets outside our institution has not been carried out yet. Also, the clinical validity of our model in real-life practice has not been investigated. These issues will be addressed subsequently through our continued investigation. Wider implications of the findings A deep-learning model utilizing ConvNeXt yielded excellent diagnostic performance in the differential diagnosis of ovarian neoplasms. The integration of AI-based deep learning models in clinical settings has the potential to significantly enhance the diagnostic accuracy of ultrasonography for ovarian neoplasms. Trial registration number not applicable

Radiomics in the differential diagnosis of gastrointestinal stromal tumors and leiomyomas. A literature review

Radiomics in the differential diagnosis of gastrointestinal stromal tumors and leiomyomas. A literature review