Diagnosis Of Malignant Tumors Research Articles

Non-primary solid malignancies of breast in needle core biopsy: a clinicopathological analysis of 23 cases

Objective: To investigate the accurate diagnosis and differential diagnosis of non-primary solid malignant tumors in breast needle core biopsy. Methods: Twenty-three cases of breast, axilla or neck lymph nodes pathologically diagnosed as non-primary solid malignant tumors were collected at the First Affiliated Hospital of Nanjing Medical University, Nanjing, China from January 2013 to March 2023. The differential diagnoses and diagnostic features were analyzed, based on combining clinical data, histology, and expression characteristics of biomarkers. Results: All patients were female, with age ranging from 29 to 75 years (average 56 years). The average time from the diagnosis of primary tumor to the current diagnosis was 21 months (0 to 204 months).The primary sites included the ovary (9 cases), the lung (5 cases), the gastrointestinal tract (4 cases), the pancreas, intrahepatic bile duct, thyroid gland, nasal cavity and forearm skin (1 case each). No carcinoma in situ was found in any of the cases. The morphological differences were significant among the tumors, but similar to the primary tumors. The tumors of neuroendocrine and female reproductive tract had great morphological and immunophenotypic overlaps with breast cancer. Metastatic lung cancer cells showed obvious atypia and tumor giant cells. The morphology and immunophenotype of metastatic serous carcinoma of female reproductive system might resemble invasive micropapillary carcinoma of the breast. Metastatic adenocarcinoma of the gastrointestinal tract often had features of mucous secretion. Metastatic neuroendocrine tumors were bland in appearance and morphologically similar to solid papillary carcinoma of breast, but negative for ER. TRPS1 was mostly negative (18/23) and variably positive in ovarian (4/9) and intrahepatic bile duct (1/1) tumors. Conclusions: The diagnosis of breast needle core biopsy specimen should be combined with clinical history, imaging study, and careful examination of histological features, such as presence of in situ component, morphological similarity between the primary and metastatic tumors, and using appropriate markers to differentiate the primary from metastatic tumors.

Detection of tumor marker CA72-4 with an electrochemical immunosensor based on MnO2 nanosheets and HNM-AuPtPd nanocomposites.

To accurately detect tumor marker carbohydrate antigen 72-4 (CA72-4) of serum samples is of great significance for the early diagnosis of malignant tumors. In the present study, MnO2/hollow nanobox metal-organic framework (HNM)-AuPtPd nanocomposites were prepared via multi-step synthesis and superposition method and a series of characterizations were carried out. A highly sensitive immunosensor Ab/MnO2/HNM-AuPtPd/GCE based on the composite nanomaterial was further prepared and used to detect the tumor marker CA72-4. The constructed immunosensor achieved signal amplification by increasing the electrocatalytic activity to H2O2 by means of the synergistic effect of MnO2 ultra-thin nanosheets (MnO2 UNs) and HNM-AuPtPd. At the same time, the electrochemical properties of the immunosensor were analyzed using cyclic voltammetry, electrochemical impedance, amperometry (with the test voltage of -0.4 V), and differential pulse voltammetry. The experimental results showed that the MnO2/HNM-AuPtPd nanocomposites were successfully prepared, and the immunosensor Ab/MnO2/HNM-AuPtPd/GCE demonstrated an excellent electrochemical performance. The electrochemical immunosensor had the highest detection sensitivity under the optimal experimental conditions, such as incubation pH of 7.0, incubation time of 60 min, with the addition of 15 μL of H2O2, and in the concentration range 0.001-500 U/mL. It had a low detection limit of 1.78×10-5 U/mL (S/N = 3). Moreover, the serum sample recovery were in the range from 99.38 to 100.52%. This study provides a new method and experimental basis for the detection of tumor markers in clinical practice.

Dynamics of morbidity and mortality from cancer in Gomel region: statistical analysis and forecast using ARIMA model up to 2030

Objective. To analyze the time series of morbidity and mortality from breast cancer, prostate cancer, colorectal cancer and cervical cancer in Gomel region for the period from 1982 to 2022 using ARIMA method and to make a prediction up to 2030. Materials and methods. We analyzed morbidity and mortality data from these cancers using statistical methods, including ARIMA modeling. Data on age at diagnosis, stage of disease, percentages of cancer detected at different stages, percentages of mortality and its dynamics after diagnosis were used. Results. On the basis of data analysis using ARIMA model, a model for predicting the incidence of cancer in the near future was developed. According to the forecast, it should be expected that there will be an increase in the incidence of breast, prostate, cervical and colorectal cancer until 2030, a decrease in the age of patients at first detection, a change in the pattern of detection at different stages and an increase in the percentage of disease detection in preventive examinations. Mortality from these types of cancer is projected to increase, with some changes in the average age of patientsof death indicators and stage dynamics. Conclusion. Predicting cancer incidence and mortality rates emphasizes the need for increased screening and early diagnosis of malignant neoplasms. This can improve earlier detection of the disease and increase the effectiveness of treatment, reducing overall cancer mortality.

Current status and progress of research on the ADP-dependent glucokinase gene.

ADP-dependent glucokinase (ADPGK) produces glucose-6-phosphate with adenosine diphosphate (ADP) as the phosphate group donor, in contrast to ATP-dependent hexokinases (HKs). Originally found in archaea, ADPGK is involved in glycolysis. However, its biological function in most eukaryotic organisms is still unclear, and the molecular mechanism of action requires further investigation. This paper provides a concise overview of ADPGK's origin, biological function and clinical application. It aims to furnish scientific information for the diagnosis and treatment of human metabolic diseases, neurological disorders, and malignant tumours, and to suggest new strategies for the development of targeted drugs.

The role of fine-needle aspiration biopsy in the diagnosis of malignant tumors.

Cytopathology and histopathology play a key role in the process of diagnosing oncological diseases and premalignant conditions. Fine-needle aspiration (FNA) is one of the techniques used for obtaining biopsy of a wide variety of body tissues, causing patients minimal discomfort. Therefore, it is often considered to be the best strategy for investigating and diagnosing some precancerous or potential malignant lesions. Being successful as a means of confirming the clinical suspicion of metastatic recurrence in the cases of an already known cancer, the interest has further focused on the preliminary diagnosis of various types of benign or malignant tumors. In cases of inoperable tumors, this technique is useful for formulating the final diagnosis. FNA biopsy proved its effectiveness as a highly accurate, cost-effective, and safe technique, with potential high diagnostic yield. Immunohistochemistry, used as an additional tool to classical histopathological examination, remains a very practical and reliable technique that promises good results especially in determining the site of origin within metastatic disease.

A rationally designed nuclei-targeting FAPI 04-based molecular probe with enhanced tumor uptake for PET/CT and fluorescence imaging.

Fibroblast activation protein inhibitor (FAPI) -based probes have been widely studied in the diagnosis of various malignant tumors with positron emission tomography/computed tomography (PET/CT). However, current imaging studies of FAPI-based probes face challenges in rapid clearance rate and potential false-negative results. Furthermore, FAPI has been rarely explored in optical imaging. Considering this, further modifications are imperative to improve the properties of FAPI-based probes to address existing limitations and broaden their application scenarios. In this study, we rationally introduced methylene blue (MB) to FAPIs, thereby imparting nuclei-targeting and fluorescence imaging capabilities to the probes. Furthermore, we evaluated the added value of FAPI-based fluorescence imaging to traditional PET/CT, exploring the potential application of FAPI-based probes in intraoperative fluorescence imaging. A new FAPI-based probe, namely NOTA-FAPI-MB, was designed for both PET/CT and fluorescence imaging by conjugation of MB. The targeting efficacy of the probe was evaluated on fibroblast activation protein (FAP)-transfected cell line and human primary cancer-associated fibroblasts (CAFs). Subsequently, PET/CT and fluorescence imaging were conducted on tumor-bearing mice. The tumor detection and boundary delineation were assessed by fluorescence imaging of tissues from hepatocellular carcinoma (HCC) patients. NOTA-FAPI-MB demonstrated exceptional targeting ability towards FAP-transfected cells and CAFs in comparison to NOTA-FAPI. This benefit arises from the cationic methylene blue (MB) affinity for anionic nucleic acids. PET/CT imaging of tumor-bearing mice revealed significantly higher tumor uptake of [18F]F-NOTA-FAPI-MB (standard uptake value of 2.20 ± 0.31) compared to [18F]F-FDG (standard uptake value of 1.66 ± 0.14). In vivo fluorescence imaging indicated prolonged retention at the tumor site, with retention lasting up to 24h. In addition, the fluorescent probes enabled more precise lesion detection and tumor margin delineation than clinically used indocyanine green (ICG), achieving a 100.0% (6/6) tumor-positive rate for NOTA-FAPI-MB while 33.3% (2/6) for ICG. These findings highlighted the potential of NOTA-FAPI-MB in guiding intraoperative surgical procedures. The NOTA-FAPI-MB was successfully synthesized, in which FAPI and MB simultaneously contributed to the targeting effect. Notably, the nuclear delivery mechanism of the probes improved intracellular retention time and targeting efficacy, broadening the imaging time window for fluorescence imaging. In vivo PET/CT demonstrated favorable performance of NOTA-FAPI-MB compared to [18F]F-FDG. This study highlights the significance of fluorescence imaging as an adjunct technique to PET/CT. Furthermore, the encouraging results obtained from the imaging of human HCC tissues hold promise for the potential application of NOTA-FAPI-MB in intraoperative fluorescent surgery guidance within clinical settings.

Benign Lipomatous Soft Tissue Tumors in Nigerians: An Analysis of the Clinical and Morphological Features of a Common but Important Entity.

Introduction Benign lipomatous tumors are soft tissue tumors that exhibit a predominant adipocytic phenotype. Lipomas are the archetype and are the most common benign soft tissue tumors in adults but relatively uncommon in children. Their sex incidence is equivocal. They sometimes occur in combination with other mesenchymal elements, giving rise to variants including fibrolipoma, angiolipoma, myolipoma, spindle cell lipoma, chondroid lipoma, osteolipoma, and chondrolipoma. Their clinical significance is mainly due to the cosmetic disfigurement of patients and the differential diagnosis of malignant soft tissue tumors. Occasionally, due to their large size or presence near vital organs, they may cause life-threatening and/or excruciating pressure symptoms. This study was purposed to address the dearth of local studies on the clinical and morphological characteristics of benign lipomatous tumors in Nigerians, to compare these with those of other populations, and to establish baseline data. Materials and methods This was a retrospective study of all benign lipomatous tumors seen in the anatomic pathology and forensic medicine department of Asokoro District Hospital, Abuja, Federal Capital Territory, Nigeria, over an eight-year period. Surgical pathology reports were retrieved for patients' biodata and clinical information. The appropriate slides were retrieved, and reviewed, and new sections were cut where necessary. The tumors were classified according to the 2020 World Health Organization (WHO) guidelines and categorized based on size as small, medium, or giant. The data obtained were analyzed, and the results were presented as tables, bar charts, ratios, and percentages. Results Four hundred and eighteen cases met the inclusion criteria. Of these, 58.4% (244/418), occurred in females, while 41.6% (174/418) occurred in males. The age range was six to 91 years, while the median age was 42 years. The least number of cases, 0.5% (2/418), were seen in patients aged less than 10 years, while the majority, 35.4% (148/418), occurred in the fifth decade, followed by 27.8% (116/418) in the fourth. Size-wise, the majority of tumors, 60% (253/418), were medium, followed by small, 22.8% (95/418). Giant-sized tumors significantly accounted for 16.7% (70/418) of the cases. The diagnostic spectrum comprised conventional lipoma and variants such as fibrolipoma, spindle cell lipoma, pleomorphic lipoma, angiolipoma, chondrolipoma, intramuscular lipoma, and osteolipoma. Lipoma and fibrolipoma dominated with 87.1% (364/418) and 10.0% (42/418), respectively, while the rest accounted for <3%. The majority, 31.8% (133/418), occurred in the back/shoulder region, followed by the lower limb with 18.2% (76/418). Only two cases occurred in the abdominal/pelvic region. More tumors occurred in females in all the regions except the head and neck, which had a male-to-female ratio of 1.5:1. Multiple site tumors were more common in males in a ratio of 2.5:1. Most, 41.1% (39/95), of the small-sized tumors, occurred in the head/neck region, largely involving the face, 48.7% (19/39). Conclusion Our study showed many similarities in the clinical and morphological features of benign lipomatous tumors between Nigerians and other regions of the world. A notable finding, however, was the significantly higher proportion of giant benign lipomatous tumors when compared tostudies from other regions, a finding that warrants further studies.

A PiRNA-disease association model incorporating sequence multi-source information with graph convolutional networks

There is growing evidence that PIWI-interacting RNA (piRNA) is widely involved in the proliferation, invasion, and metastasis of malignant tumors, playing an important regulatory role in numerous human physiological and pathological processes. Disease-associated piRNAs are expected to be biomarkers and novel therapeutic targets for early diagnosis and prognosis of malignant tumors. However, most previous computational models did not fully focus on the rich representation ability of multiple sources of information in piRNA sequences, which affected their performance in predicting piRNA-disease associations (PDAs). In this work, we propose a model, iSG-PDA, which combines the multi-source information of piRNA sequences with graph convolutional neural networks to predict potential PDAs. More specifically, we first fuse multi-source information including piRNA sequences and disease semantics to enhance the expressiveness of data, then deeply mine the advanced hidden features of PDA using graph convolutional networks, and finally exploit random forest to accurately determine the associations between piRNAs and diseases. In the golden standard dataset, the proposed model realized a prediction accuracy of 91.96% at the AUC of 0.9184. In ablation experiments and comparisons with other different models, iSG-PDA exhibits strong competitiveness. Moreover, the results of the case study indicate that 17 of the top 20 PDAs in the proposed model predictive score were confirmed. These preliminary results reveal that iSG-PDA is an effective computational method for predicting PDAs and can provide reliable disease candidate piRNAs for biological experiments.

Inoperable Renal Malignant Glomus Tumor, the answers for all the "W's"?

Glomus tumor, arising from glomus bodies (specialized neurovascular structures involved in thermoregulation), commonly occurs in extremities and rarely in viscera. The spectrum of glomus tumors range from benign tumors to tumors with uncertain malignant potential to tumors of the malignant subtype. A vast majority of visceral glomus tumors are benign. Most common visceral tumors arise in the gastrointestinal tract. Glomus tumors of the kidney are a rare entity of which malignant glomus tumors are exceedingly rare. The index patients in the existing case reports were middle-aged males. We report our experience with malignant glomus tumor of the left kidney in a 60-year-old female, with computed tomography (CT) showing involvement of renal vein and inferior vena cava (IVC). Percutaneous biopsy was performed as imaging did not conform to the appearance of a conventional renal tumor and was reported as malignant glomus tumor after immunohistochemistry. After informed decision, the patient and family elected to proceed with surgery. However, intraoperatively, the left renal mass was found to infiltrate the pancreas, duodenum, aorta, and root of the colonic mesentery due to which surgery was aborted. Biopsy obtained intraoperatively again confirmed diagnosis of left renal malignant glomus tumor. She had an uneventful postoperative recovery. Options of treatment were reviewed by a multidisciplinary board. In light of no proven benefit for systemic therapy, she was referred for supportive care. She was under follow-up and she expired after 7 months due to progressive disease. Our literature review focuses on the clinicopathologic features and the current standard of management of malignant renal glomus tumors.

Fine-needle aspiration diagnosis of secondary malignant tumors of the thyroid gland: A single-institution experience of 17 cases.

Fine-needle aspiration (FNA) is the most commonly used preoperative pathological diagnostic tool for thyroid tumors. Secondary malignant tumors of the thyroid gland account for less than 3% of all thyroid malignancies. The aim of this study was to investigate the types and cytopathological features of secondary thyroid tumors, evaluate diagnostic pitfalls in FNA. Cases of secondary thyroid tumors diagnosed in the Department of Pathology of Shaanxi Provincial People's Hospital were collected, and their clinical data, cytologic features, immunohistochemical results, and histopathological diagnoses were summarized. The study included 17 cases (8 males and 9 females) with a mean age of 60.4 ± 9.4 years (range, 45-83 years). Six cases had a known history of primary malignancy prior to FNA aspiration diagnosis. The most common organs of origin were the lungs (5 cases, 3 adenocarcinoma, and 2 small-cell carcinoma) and esophagus (5 cases, 3 squamous-cell carcinoma, 1 adenocarcinoma, and 1 small-cell carcinoma). The next most common was squamous-cell carcinoma of the larynx (3 cases), and gastric tumor (2 cases), including 1 lymphoma and 1 adenocarcinoma. Cell blocks and immunohistochemistry were performed in 12 of these cases. Comparison of the impact of positive history and IHC availability on the accuracy of pathologic diagnosis showed that both were statistically significant. FNA is an effective means of diagnosing secondary malignancies of the thyroid, in which knowledge of the patient's history of malignancy is essential, and the use of cell blocks and immunohistochemistry helps to clarify the pathological diagnosis.

HE4 as a Biomarker for Diagnosis of Malignant Ovarian Masses in Bangladeshi Population

Ovarian cancer is one of the commonest cancers in gynecology with very high fatality to case ratio. In approximately 70% of all cases of ovarian cancers, the disease is not diagnosed before reaching an advanced stage. Thus early diagnosis of ovarian malignant tumor becomes a key factor in improving the survival rate of patients. This study was aimed to evaluate HE4 (Human Epididymis 4) biomarker for the diagnosis of ovarian malignancy in admitted patients with pelvic mass of ovarian origin scheduled for surgery from Obstetrics and Gynecology department of different medical colleges of Dhaka city and Bangabandhu Sheikh Mujib Medical University (BSMMU). It was a cross-sectional analytical study carried out by non-probability sampling. For this study, 110 admitted patients with ovarian tumor scheduled for surgery were selected.Purpose and procedure of the study was explained in details and informed written consent was taken from all the study subjects before collection of blood sample. Clinical information was taken from the patients’ hospital notes. Before surgery serum HE4 was measured and after surgery, histopathology reports were collected for each patient.Depending on histopathology reports, patients were categorized as benign and malignant. Diagnostic efficacy of HE4 was evaluated with respect to sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and likelihood ratios considering histopathology report as gold standard. To evaluate the performance of HE4 based on optimal cut-off (34.3 pmol/L), we found better sensitivity, NPV and satisfactory likelihood ratios but low specificity and PPV compared to suggested cut-off. The findings of this study shows that HE4 is not a useful biomarker to help in the assessment and management of patients with suspected ovarian cancer.&#x0D; Bangladesh J Med Biochem 2019; 12(1): 11-15

Large-Scale assessment of ChatGPT's performance in benign and malignant bone tumors imaging report diagnosis and its potential for clinical applications

ObjectiveThis study was designed to delve into the complexities involved in diagnosing of benign and malignant bone tumors and to assess the potential of AI technologies like ChatGPT in improving diagnostic accuracy and efficiency. The study also explores the few-shot learning as a method to optimize ChatGPT's performance in specialized medical domains such as benign and malignant bone tumors diagnosis. MethodsA total of 1366 benign and malignant bone tumors-related imaging reports were collected and diagnosed by 25 experienced physicians. The gold standard of diagnosis was established by combining clinical, imaging and pathological principles.These reports were then input into the ChatGPT model which underwent a few-shot learning method to generate diagnostic results. The diagnostic results of the physicians and the AI model were compared to evaluate the performance of ChatGPT. An experiment was conducted to assess the influence of different radiologist's reporting styles on the model's diagnostic performance. Furthermore, in-depth analysis of misdiagnosed cases was carried out, categorizing diagnostic errors and exploring possible causes. ResultsThe diagnostic results generated by ChatGPT showed an accuracy of 0.73, sensitivity of 0.95, and specificity of 0.58. After few-shot learning, ChatGPT demonstrated significant improvement, achieving an accuracy of 0.87, sensitivity of 0.99, and specificity of 0.73, bringing it much closer to the level of physician diagnostics. In an experiment analyzing the influence of the radiologist's reporting style, the model demonstrated higher sensitivity when interpreting reports written by high-level radiologists. In 56 benign cases, ChatGPT misdiagnosed them as malignant. Among these, 35 benign lesions- fibrous dysplasia and osteofibrous dysplasia- were incorrectly identified as metastatic tumors or osteosarcomas; 8 cases of myositis ossificans were wrongly diagnosed as extraosseous osteosarcoma. 7 cases of giant cell tumor of bone at the end of long bone were misdiagnosed as osteosarcoma by intermediate doctors. Chondroblastoma was misdiagnosed as malignant tumor in 6 cases −2 osteosarcoma and 4 chondrosarcoma-In this study, 23 osteosarcoma cases were misdiagnosed by ChatGPT as osteomyelitis; Chondrosarcoma was misdiagnosed as fibrous dysplasia or aneurysmal bone cyst in 8 cases. Four cases of spinal chordoma were misdiagnosed as spinal tuberculosis. ConclusionOur findings highlight the potential of ChatGPT in the diagnosis of benign and malignant bone tumors, offering advantages like enhanced efficiency and a reduction in missed diagnoses. However, the necessity of collaborative interactions between physicians and ChatGPT in practical settings was underscored. With an examination into AI's capacity in benign and malignant bone tumors diagnosis, this study lays the groundwork for future AI advancements in medicine. Additionally, the benefits of few-shot learning in fine-tuning ChatGPT applications in specialized fields were also demonstrated.

Biomarkers of peripheral blood neutrophil extracellular traps in the diagnosis and progression of malignant tumors.

The mortality rate associated with malignant tumors remains high and there is a lack of effective diagnostic and tumor progression markers. Neutrophil extracellular traps (NETs) can promote tumor-associated thrombosis, invasive metastasis, and inflammatory responses, but there is a lack of research on the value of measuring NETs in the peripheral blood of patients with malignancies. We included 263 patients with malignancies (55 gliomas, 101 ovarian, 64 colorectal, and 43 lung cancers) and 75 healthy controls in this study. We compared the levels of citrullinated histone H3 (citH3), cell-free DNA (cfDNA), and systemic inflammation-related parameters, including neutrophils, lymphocytes, monocytes, platelets, neutrophil-to-lymphocyte ratio, monocyte-to-lymphocyte ratio, platelet-to-lymphocyte ratio, systemic immune inflammation index, and systemic inflammation response index. We assessed the value of changes in NETs in peripheral blood to determine the diagnosis, venous thromboembolism, clinical staging, and systemic inflammatory response in patients with malignancy. The levels of citH3 and cfDNA in peripheral blood can distinguish between healthy controls and tumor patients. The levels of citH3 and cfDNA before clinical intervention did not predict the risk of combined venous thromboembolism in oncology patients in the short-term after clinical intervention. The levels of citH3, cfDNA, and systemic inflammation-related parameters in the peripheral blood of tumor patients increased with the clinical stage. There was a correlation between cfDNA levels in peripheral blood and systemic inflammation-related parameters in tumor patients, and this correlation was more significant in patients with advanced tumors. Changes in NETs in the peripheral blood differ between healthy controls and patients with malignant tumors. NETs may be involved in tumor-induced systemic inflammatory responses through interaction with circulating inflammatory cells, thus promoting tumor progression. NETs may be used as markers to assist in the diagnosis and progression of tumor malignancy.

A retrospective analysis of 350 cases of parotid gland tumors and the value of ultrasound in the diagnosis of benign and malignant parotid gland tumors

AbstractObjectiveTo retrospective analysis of the epidemiological and clinical characteristics of parotid gland tumors, and to explore the value of ultrasound in the differentiation of benign and malignant parotid gland tumors.MethodsThe clinical data of 350 patients with parotid gland tumors in our hospital from 2002 to 2022 were retrospectively analyzed. These patients were examined by ultrasound. The postoperative pathological test results were used as the “gold standard” to verify and analyze the value of color Doppler ultrasound in the differential diagnosis of benign and malignant parotid tumors (PT).ResultsThe male‐to‐female ratio of 350 patients with parotid gland tumors was 1.16:1. The age of patients ranged from 12 to 87 years old. Patients aged 40–65 years accounted for 54.6%, which was the most common age of parotid gland tumors. Among 350 cases, 259 were benign and 91 were malignant. The top three benign PTs were pleomorphic adenoma, Warthin tumor, and basal cell adenoma. The top three malignant tumors were mucoepidermoid carcinoma, acinar cell carcinoma, and adenoid cystic carcinoma. The specificity, sensitivity, accuracy, positive predictive value, and negative predictive value of ultrasonography in the diagnosis of benign and malignant parotid masses were 96.53%, 69.23%, 89.43%, 87.50%, and 87.72%, respectively.ConclusionThe pathological types of parotid gland tumors are complex and diverse. Ultrasonography has high accuracy in the diagnosis of PT, which can provide important evidence for the differentiation of benign and malignant PT, and then assist in the clinical selection of individualized surgical programs.

Effective Combination of 3D-DenseNet's Artificial Intelligence Technology and Gallbladder Cancer Diagnosis Model

Gallbladder cancer is the most common malignant tumor in the biliary system. It has the characteristics of low early diagnosis rate, strong invasiveness and high lymphatic metastasis rate. In recent years, with the rapid development of artificial intelligence technology, relevant technologies based on machine learning and deep learning algorithms have been applied to the diagnosis and treatment of malignant tumors, prognosis assessment and medical image processing, bringing revolutionary changes to the diagnosis and treatment mode of malignant tumors. At present, artificial intelligence technology has been preliminarily studied in the early screening and diagnosis of gallbladder cancer, preoperative lymph node status assessment, intraoperative lymph node dissection, surgical treatment and prognosis assessment, showing certain clinical value. In this paper, in order to assist clinical diagnosis of gallbladder cancer, an improved 3D-DenseNet was used to establish an assisted diagnosis model of gallbladder cancer based on enhanced CT images of patients. Firstly, multiple arterial CT images of patients were converted into 3D images, and the regions of interest were cut out using the gallbladder area marked by doctors. Then, the traditional Dense Net network is optimized, the Dropout mechanism and Soft max loss function are improved, and the cross-entropy function is replaced by Focal loss in the output part for imbalance correction, so as to establish the auxiliary diagnosis model of gallbladder cancer.

Comparison of the value of the GI-RADS and ADNEX models in the diagnosis of adnexal tumors by junior physicians.

To compare the diagnostic effectiveness of the Gynecologic Imaging Reporting and Data System (GI-RADS) and Neoplasias in the Adnexa (ADNEX) model for the diagnosis of benign and malignant ovarian tumors by junior physicians. The sonographic data of 634 patients with ovarian tumors confirmed by pathology in our hospital over 4 years were analyzed retrospectively by junior doctors. The diagnostic efficacy of the GI-RADS and ADNEX models was compared based on pathology. (1) Regarding the diagnostic efficacy of the GI-RADS and ADNEX models, the sensitivity was 90.15% and 84.85%, the specificity was 87.65% and 85.86%, the accuracy rates were 88.17% and 85.65%, and the Youden Indices were 0.778 and 0.707, respectively. The areas under the receiver operating characteristic (ROC) curves were 0.924 (95% CI: 0.900-0.943) and 0.933 (95% CI: 0.911-0.951), respectively. The GI-RADS classification was equivalent to that of the ADNEX model in the diagnosis of adnexal tumors (P>0.05). These findings were highly consistent with the pathological results (Kappa values were 0.684 and 0.691, respectively). (2) When differentiating between different pathological types of adnexal tumors, the ADNEX model had the best diagnostic value for distinguishing between benign tumors and stage II-IV ovarian cancer (AUC=0.990, 95% CI: 0.978-0.997). (1) The diagnostic efficacy of the GI-RADS and ADNEX models in the diagnosis of benign and malignant ovarian tumors by junior physicians is excellent and comparable. (2) The ADNEX model shows good value for differentiating ovarian tumors of different pathological types by junior physicians.

Results of invasive diagnosis of primary malignant bone tumors of the pelvis

Results of invasive diagnosis of primary malignant bone tumors of the pelvis

Deep learning-assisted diagnosis of benign and malignant parotid gland tumors based on automatic segmentation of ultrasound images: a multicenter retrospective study.

To construct deep learning-assisted diagnosis models based on automatic segmentation of ultrasound images to facilitate radiologists in differentiating benign and malignant parotid tumors. A total of 582 patients histopathologically diagnosed with PGTs were retrospectively recruited from 4 centers, and their data were collected for analysis. The radiomics features of six deep learning models (ResNet18, Inception_v3 etc) were analyzed based on the ultrasound images that were obtained under the best automatic segmentation model (Deeplabv3, UNet++, and UNet). The performance of three physicians was compared when the optimal model was used and not. The Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI) were utilized to evaluate the clinical benefit of the optimal model. The Deeplabv3 model performed optimally in terms of automatic segmentation. The ResNet18 deep learning model had the best prediction performance, with an area under the receiver-operating characteristic curve of 0.808 (0.694-0.923), 0.809 (0.712-0.906), and 0.812 (0.680-0.944) in the internal test set and external test sets 1 and 2, respectively. Meanwhile, the optimal model-assisted clinical and overall benefits were markedly enhanced for two out of three radiologists (in internal validation set, NRI: 0.259 and 0.213 [p = 0.002 and 0.017], IDI: 0.284 and 0.201 [p = 0.005 and 0.043], respectively; in external test set 1, NRI: 0.183 and 0.161 [p = 0.019 and 0.008], IDI: 0.205 and 0.184 [p = 0.031 and 0.045], respectively; in external test set 2, NRI: 0.297 and 0.297 [p = 0.038 and 0.047], IDI: 0.332 and 0.294 [p = 0.031 and 0.041], respectively). The deep learning model constructed for automatic segmentation of ultrasound images can improve the diagnostic performance of radiologists for PGTs.

Clinicopathological Features of Primary Renal Mesenchymal Neoplasms in Adults: A Cross-sectional Study

Introduction: Renal mesenchymal tumours are a subset of primary renal tumours arising from the mesenchymal tissue in the kidney. They are a heterogeneous group of mostly benign tumours that exhibit varied behaviours and molecular characteristics. Aim: To analyse the wide spectrum of histological subtypes, their unique clinical presentation, and pathological features of primary renal mesenchymal neoplasms. Materials and Methods: This was a retrospective crosssectional observational clinicopathological study conducted in Department of General Pathology, Christian Medical College, tertiary care hospital, Vellore, Tamil Nadu, India, looking at data of adult Primary Renal Mesenchymal Tumours (PRMT) for a 15- year period between January 2006 and March 2021. Clinical details such as age, presenting symptoms, and tumour size were obtained from the hospital information system. Histopathology and immunohistochemical slides were reviewed for all the cases. Additional Immunohistochemistry (IHC) and molecular studies were performed for the undifferentiated sarcomas. The tumours were categorised into three groups as recommended by the World Health Organisation (WHO) 2020 classification of soft-tissue tumours based on biological behaviour: benign, intermediate, and malignant. Continuous variables are expressed as mean and Standard Deviation (SD). Comparison of categorical variables between groups was performed using the Chi-squared test. Continuous variables between groups were compared using the Student’s t-test for significance. A p-value of less than 0.05 was considered statistically significant. Results: Of the 2164 nephrectomies performed for neoplastic conditions, 97 (4.5%) were diagnosed as renal mesenchymal tumours. There were 59 (60.8%) benign, 10 (10.3%) with intermediate biologic behaviour and 28 (28.9%) malignant tumours. The mean ages at presentation were 40.5 years for benign, 43.4 years for intermediate, and 41 years for malignant tumours, respectively. Haematuria was seen in 11 of 38 (29%) intermediate grade and malignant tumours and in only 6 of 59 (10%) benign tumours, a difference that was statistically significant (p-value=0.017). Malignant tumours 24 of 28 (86%) were more likely to be larger (&gt;7 cm) when compared to benign tumours 28 of 59 (47%) at the time of presentation (p-value=0.027). Classical angiomyolipomas constituted 53/59 (90%) of the benign tumours. Of the 10 intermediate grade tumours, epithelioid angiomyolipomas and solitary fibrous tumours were the most common, accounting for 50% and 30% of the intermediate group, respectively. Undifferentiated small round cell sarcoma was the most common malignant neoplasm, making up 12/28 (43%) of the malignant tumours. Conclusion: The present study found that renal mesenchymal tumours constitute a small but unique group of renal tumours. They are predominantly benign, but up to a quarter are malignant. Malignant tumours tend to be larger and more often present with haematuria. The present study highlights the importance of IHC in the diagnosis of intermediate and malignant mesenchymal tumours and the requirement of exhaustive molecular studies individually tailored to the immuno-profile of malignant tumours.

Разработка нового нанобиотехнологического метода и его применение для дифференциальной диагностики опухолей придаточного аппарата глаза

Aim: to develop a new nanobiotechnology method for the differential diagnosis of ocular adnexal tumors. Patients and Methods: 192 eyelid or conjunctival tumor samples from 192 patients were examined. Controls were healthy tissue samples from the same eye. To register and obtain significant differences in the generation of biogenic silver nanoparticles in situ, the key parameters of the reaction of the reduction of silver cations were selected and optimized. To generate de novo biogenic silver nanoparticles, tissue samples were placed in a sterile solution of a cation source in aseptic conditions. Nanoparticles were generated in situ using a sterile solution of Tollens' reagent (Ag(HN3)2NO3). Results: the optimal parameters of a new nanobiotechnology method were established to conduct the reduction reaction to generate biogenic silver nanoparticles. The required concentration of Tollens' reagent (source of cations) was 63 μg/ml. The wavelength used to observe the de novo generation of biogenic silver nanoparticles (λ) was 410 nm. Obtaining the most significant changes in the optical density of the reaction mixture with biogenic nanoparticles required 10 to 20 min, although the first changes were documented starting from the 5th minute of the reduction reaction. Benign and malignant tumors are characterized by different metabolic activities, i.e., benign eyelid and conjunctival tumors reduce cations more slowly than malignant tumors. The parameters of reducibility of benign ocular adnexal tumors did not significantly differ depending on tumor location and type. Among the malignant conjunctival tumors, melanoma is characterized by the highest reducibility p&lt;0.05). Among the malignant eyelid tumors, no significant differences were found for different tumor types. Conclusions: this novel nanobiotechnology method provides a differential diagnosis of benign and malignant ocular adnexal tumors. The practical relevance of this method lies in differentiating benign and malignant tumors to schedule management strategies and surgical interventions. KEYWORDS: tumor, eyelids, conjunctiva, silver nanoparticles, biogenic synthesis, express diagnostics, ocular oncology. FOR CITATION: Saakyan S.V., Skladnev D.A., Alekseeva A.P., Beznos O.V., Sorokin V.V. Development of a new nanobiotechnology method for the differential diagnosis of ocular adnexal tumors. Russian Journal of Clinical Ophthalmology. 2024;24(1):25–29 (in Russ.). DOI: 10.32364/2311-7729-2024-24-1-5.