Accurate Pathological Diagnosis Research Articles

Cytological diagnosis of follicular dendritic cell sarcoma with a unique pattern of D2-40 immunoexpression.

Fine needle aspiration procedure is routinely used for cytological diagnosis of nodal or extra nodal lesions. Follicular dendritic cell sarcoma (FDCS) is a rare mesenchymal neoplasm arising from follicular dendritic cells of lymphoid follicles at nodal and extranodal sites. Multimodal therapies have emerged for FDCS, necessitating its accurate pathologic diagnosis with additional ancillary testing for directing clinical management. By immunohistochemical analysis, FDCS is positive for the complement receptors CD21, CD23, and CD35. In addition, D2-40 is reported to be highly sensitive for FDCS with a strong membranous pattern of expression. In this study, we present the cytological diagnosis of a case of FDCS in retroperitoneal lymph nodes with an emphasis on a unique staining pattern of D2-40 which showed a strong nuclear pattern in tumor cells comparable to the membranous pattern of D2-40 on the control tissue and other surgical cases of FDCS in our comparative study.

Lymph node metastasis of intrahepatic cholangiocarcinoma: the present and prospect of detection and dissection.

Intrahepatic cholangiocarcinoma (ICC) ranks as the second most primary liver cancer that often goes unnoticed with a high mortality rate. Hepatectomy is the main treatment for ICC, but only 15% of patients are suitable for surgery. Despite advancements in therapeutic approaches, ICC has an unfavorable prognosis, largely due to lymph node metastasis (LNM) that is closely linked to the elevated recurrence rates. Consequently, the identification of precise and suitable techniques for the detection and staging of LNM assumes paramount importance for ICC therapy. While preoperative imaging plays a crucial role in ICC diagnosis, its efficacy in accurately diagnosing LNM remains unsatisfactory. The inclusion of lymph node dissection as part of the hepatectomy procedures is significant for the accurate pathological diagnosis of LNM, although it continues to be a topic of debate. The concept of sentinel lymph node in ICC has presented a novel and potentially valuable approach for diagnosing LNM. This review aims to explore the current state and prospects of LNM in ICC, offering a promising avenue for enhancing the clinical diagnosis and treatment of ICC to improve patient prognosis.

Subcutaneous panniculitis-like T-cell lymphoma (SPTCL) in a 15-Year-old male presenting with orofacial Swelling

BackgroundSubcutaneous panniculitis-like T-cell lymphoma (SPTCL) is a rare form of non-Hodgkin lymphoma that primarily affects subcutaneous tissues. Its occurrence in the orofacial region is exceptionally uncommon, presenting diagnostic challenges due to symptom overlap with more prevalent orofacial condition.Case presentationThis report details the case of a 15-year-old male who presented with persistent left-sided facial swelling, initially misdiagnosed as facial cellulitis. Diagnostic complexity arose from the similarity of symptoms to common orofacial diseases. Comprehensive diagnostic approaches, including liquid-based thin-layer cytometry, immunohistochemistry, and advanced imaging, were pivotal in identifying SPTCL. The recurrence of symptoms following the cessation of dexamethasone treatment indicated hormone dependency. Surgical intervention and subsequent histopathological analysis confirmed SPTCL, with immunohistochemical profiling playing a critical role in the definitive diagnosis. The patient’s management involved a multidisciplinary approach, leading to a referral to a hematology specialist and subsequent favorable outcomes.ConclusionsThis case underscores the diagnostic challenges of orofacial lymphomas such as SPTCL and highlights the necessity for early, accurate pathological diagnosis. It emphasizes the role of advanced diagnostic techniques and the importance of a comprehensive, multidisciplinary approach in the management of such rare cases. This report contributes to the limited but growing body of literature on SPTCL in the orofacial region, providing insights for clinicians in similar future cases.

The Role of Fine-Needle Aspiration Cytology in the Evaluation of Breast Lumps.

Background Breast cancer is the most frequently diagnosed cancer in women worldwide, accounting for more than one in ten new cancer cases each year. It ranks as the second leading cause of cancer-related mortality among women. The majority of patients present with palpable breast lumps. Effective surgical management of breast cancer largely depends on accurate preoperative pathological diagnosis. This study evaluates the diagnostic accuracy and prognostic implications of fine-needle aspiration cytology (FNAC) compared with core needle biopsy (CNB) in breast carcinoma. Objectives The objectives of this study are to assess the sensitivity and specificity of FNACand CNB, to compare the diagnostic accuracy of FNAC and CNB against histopathological findings from gross specimens in the evaluation of breast lumps, and to identify and examine the limitations associated with both FNAC and CNB procedures. Materials and methods This study included female patients presenting with clinically suspicious palpable breast lumps at the General Surgery OPD of Bankura Sammilani Medical College and Hospital, Bankura. All patients underwent FNAC followed by CNB. The cytological and CNB diagnoses were compared with the final pathological diagnosis obtained from excisional biopsy. Results The study included 44 female patients aged 20 to 70 years. The most common age group for breast carcinoma was 50-59 years (36.36%). Malignancy was diagnosed in 75% of cases (33/44), with right breast involvement (65%) being more common than the left. The upper outer quadrant (59%) was the most frequently affected area. Among the 33 confirmed malignant cases, 69.70% had lesions larger than 5 cm. FNAC demonstrated a sensitivity of 93.93%, specificity of 100%, positive predictive value (PPV) of 100%, negative predictive value (NPV) of 84.61%, and diagnostic accuracy of 95.45%. CNB showed a sensitivity of 96.97%, specificity of 100%, PPV of 100%, NPV of 91.67%, and diagnostic accuracy of 97.73%. Both methods correlated significantly with the final histopathology results (p < 0.05). FNAC identified ductal carcinoma in 93.55% of cases, while CNB identified it in 96.77%. Conclusion CNBprovides additional information on receptor status but is more resource-intensive. FNACremains a cost-effective and time-efficient first-line diagnostic tool, especially in resource-constrained settings like rural India. FNAC should be employed for initial diagnosis, with CNB reserved for cases requiring further clarification.

PST-Diff: Achieving High-Consistency Stain Transfer by Diffusion Models With Pathological and Structural Constraints.

Histopathological examinations heavily rely on hematoxylin and eosin (HE) and immunohistochemistry (IHC) staining. IHC staining can offer more accurate diagnostic details but it brings significant financial and time costs. Furthermore, either re-staining HE-stained slides or using adjacent slides for IHC may compromise the accuracy of pathological diagnosis due to information loss. To address these challenges, we develop PST-Diff, a method for generating virtual IHC images from HE images based on diffusion models, which allows pathologists to simultaneously view multiple staining results from the same tissue slide. To maintain the pathological consistency of the stain transfer, we propose the asymmetric attention mechanism (AAM) and latent transfer (LT) module in PST-Diff. Specifically, the AAM can retain more local pathological information of the source domain images, while ensuring the model's flexibility in generating virtual stained images that highly confirm to the target domain. Subsequently, the LT module transfers the implicit representations across different domains, effectively alleviating the bias introduced by direct connection and further enhancing the pathological consistency of PST-Diff. Furthermore, to maintain the structural consistency of the stain transfer, the conditional frequency guidance (CFG) module is proposed to precisely control image generation and preserve structural details according to the frequency recovery process. To conclude, the pathological and structural consistency constraints provide PST-Diff with effectiveness and superior generalization in generating stable and functionally pathological IHC images with the best evaluation score. In general, PST-Diff offers prospective application in clinical virtual staining and pathological image analysis.

Gastric dysplasia arising from a submucosal heterotopic gastric gland.

A submucosal heterotopic gastric gland (SHGG) is characterized by benign ectopic gastric tissue within the submucosa. Neoplasms arising from SHGGs are rare, and their definitive diagnosis via endoscopic biopsy is often challenging. We report the case of a 74-year-old man undergoing screening esophagogastroduodenoscopy, which revealed a subepithelial lesion with a central orifice in the upper body of the stomach. Endoscopic submucosal dissection (ESD) was performed because the endoscopic biopsy revealed a suspected pyloric gland adenoma. Pathological examination of the resected specimen confirmed SHGG with focal dysplasia. The patient recovered uneventfully and remained free of recurrence over a 5-year follow-up period. This case highlights the utility of ESD in both the treatment and accurate pathological diagnosis of neoplasms arising from SHGGs.

The pulmonary nodule: from incidental finding to pathological confirmation

As the number of CT examinations of the lungs increases, so does the prevalence of incidentally discovered pulmonary nodules. While most lung nodules are benign, the risk of malignancy significantly rises with the presence of risk factors and specific imaging features. Upon encountering an incidental nodule, efforts should focus on achieving an accurate pathological diagnosis, particularly to ascertain malignancy while minimizing the risks associated with unnecessary diagnostic procedures. A comprehensive understanding of the typical characteristics and behavior of malignant lung nodules, along with a detailed patient history and standardized clinical and imaging risk assessment, is crucial for determining the optimal diagnostic approach. Additionally, the decision regarding histologic confirmation should consider the patient's comorbidities, preferences, and the examiner's expertise. Emerging sampling technologies provide methods for addressing peripheral lung nodules with minimal risk of complications.

Foreign body pulmonary vessel embolism and granulomatosis in intravenous drug abuse: An autopsy study.

The abuse of illicit drugs causes a myriad of systemic complications. Intravenous (IV) injection of such drugs poses various additional threats, primarily due to the use of excipient materials in them. Pulmonary artery embolism with foreign material and granulomatosis may be encountered in the lungs on histopathological examination in such cases. In this study, we aimed to analyze the histopathological findings in lungs in postmortem specimens with suspected IV drug abuse. This was a retrospective study of 5 years in which 15 cases of known or suspected history of drug abuse were assessed. The clinical details were compiled, and the hematoxylin and eosin (H and E)-stained microscopic slides were retrieved from the archives for reviewing the histopathological features in lungs submitted for postmortem analysis. All the cases were male, aged 21 to 36 years (median: 27 years). Gross examination revealed edematous lungs in four cases (26.6%). On microscopic examination of the lungs, all the cases (100%) showed the presence of basophilic irregular structures to rod-like pale crystalline refractile material, which was accompanied by a granulomatous reaction in the lumen of the pulmonary arteries. Four of these cases (26.6%) showed birefringence on polarizing microscopy. The use of illicit drugs is becoming widespread, especially among young individuals. IV drug abuse increases the rate of morbidity and mortality by affecting primarily the pulmonary vasculature, particularly pulmonary arteries. An acquaintance with the various patterns of pulmonary involvement in IV drug abuse is essential to arrive at an accurate pathological diagnosis and provide a possible cause of death in such cases.

Diffusion-weighted Imaging: New Paradigm in Diagnosis of Early Acute Pancreatitis.

Diffusion-weighted imaging (DWI) has come up as a newer diagnostic modality for the diagnosis of early functional changes in various organs including the pancreas. DWI has shown the ability of early and accurate diagnosis of inflammatory pathologies, before the appearance of morphological changes on imaging. The objectives of this study were to study the diagnostic accuracy of DWI in the diagnosis of early acute interstitial pancreatitis. The present retrospective observational study was conducted at the department of radiodiagnosis of a tertiary teaching hospital for 1 year. Fifty patients who underwent magnetic resonance imaging of the pancreas with clinical or laboratory diagnosis of early pancreatitis were included in the study. The diagnostic accuracy of DWI was analyzed on the basis of quantitative (apparent diffusion coefficient [ADC] values) evaluation in the diagnosis of early acute pancreatitis. Threshold values for ADC were derived for differentiation of inflamed versus normal pancreas. Sensitivity, specificity, positive predictive value (PPV), and negative predictive values (NPV) were obtained by drawing the receiver operating characteristic (ROC) curve. The mean ADC values in the patient group (0.882 × 10 -3 mm 2 /s ± 0.102) were significantly lower than the control group (1.178 × 10 -3 mm 2 /s ± 0.232) with P < 0.001. The ROC curve deciphered a cutoff value of 0.937 × 10 -3 mm 2 /s with a sensitivity of 84%, specificity of 86%, PPV of 85.71%, and NPV of 84.31% for diagnosis of acute pancreatitis using quantitative ADC values. DWI can thus be a succinct modality for early diagnosis of pancreatitis with excellent diagnostic accuracy and superlative advantage of lack of contrast and radiation in comparison to computed tomography scan.

A Systematic Review on the Effectiveness of Machine Learning in the Detection of Atrial Fibrillation.

Recent endeavors have led to the exploration of Machine Learning (ML) to enhance the detection and accurate diagnosis of heart pathologies. This is due to the growing need to improve efficiency in diagnostics and hasten the process of delivering treatment. Several institutions have actively assessed the possibility of creating algorithms for advancing our understanding of atrial fibrillation (AF), a common form of sustained arrhythmia. This means that artificial intelligence is now being used to analyze electrocardiogram (ECG) data. The data is typically extracted from large patient databases and then subsequently used to train and test the algorithm with the help of neural networks. Machine learning has been used to effectively detect atrial fibrillation with more accuracy than clinical experts, and if applied to clinical practice, it will aid in early diagnosis and management of the condition and thus reduce thromboembolic complications of the disease. In this text, a review of the application of machine learning in the analysis and detection of atrial fibrillation, a comparison of the outcomes (sensitivity, specificity, and accuracy), and the framework and methods of the studies conducted have been presented.

3D U-Net Neural Network Architecture-Assisted LDCT to Acquire Vertebral Morphology Parameters: A Vertebral Morphology Comprehensive Analysis in a Chinese Population.

To evaluate the feasibility of acquiring vertebral height from chest low-dose computed tomography (LDCT) images using an artificial intelligence (AI) system based on 3D U-Net vertebral segmentation technology and the correlation and features of vertebral morphology with sex and age of the Chinese population. Patients who underwent chest LDCT between September 2020 and April 2023 were enrolled. The Altman and Pearson's correlation analyses were used to compare the correlation and consistency between the AI software and manual measurement of vertebral height. The anterior height (Ha), middle height (Hm), posterior height (Hp), and vertebral height ratios (VHRs) (Ha/Hp and Hm/Hp) were measured from T1 to L2 using an AI system. The VHR is the ratio of Ha to Hp or the ratio of Hm to Hp of the vertebrae, which can reflect the shape of the anterior wedge and biconcave vertebrae. Changes in these parameters, particularly the VHR, were analysed at different vertebral levels in different age and sex groups. The results of the AI methods were highly consistent and correlated with manual measurements. The Pearson's correlation coefficients were 0.855, 0.919, and 0.846, respectively. The trend of VHRs showed troughs at T7 and T11 and a peak at T9; however, Hm/Hp showed slight fluctuations. Regarding the VHR, significant sex differences were found at L1 and L2 in all age bands. This innovative study focuses on vertebral morphology for opportunistic analysis in the mainland Chinese population and the distribution tendency of vertebral morphology with ageing using a chest LDCT aided by an AI system based on 3D U-Net vertebral segmentation technology. The AI system demonstrates the potential to automatically perform opportunistic vertebral morphology analyses using LDCT scans obtained during lung cancer screening. We advocate the use of age-, sex-, and vertebral level-specific criteria for the morphometric evaluation of vertebral osteoporotic fractures for a more accurate diagnosis of vertebral fractures and spinal pathologies.

Deep learning-based hyperspectral technique identifies metastatic lymph nodes in oral squamous cell carcinoma-A pilot study.

To establish a system based on hyperspectral imaging and deep learning for the detection of cancer cells in metastatic lymph nodes. The continuous sections of metastatic lymph nodes from 45 oral squamous cell carcinoma (OSCC) patients were collected. An improved ResUNet algorithm was established for deep learning to analyze the spectral curve differences between cancer cells and lymphocytes, and that between tumor tissue and normal tissue. It was found that cancer cells, lymphocytes, and erythrocytes in the metastatic lymph nodes could be distinguished basing hyperspectral image, with overall accuracy (OA) as 87.30% and average accuracy (AA) as 85.46%. Cancerous area could be recognized by hyperspectral image and deep learning, and the average intersection over union (IOU) and accuracy were 0.6253 and 0.7692, respectively. This study indicated that deep learning-based hyperspectral techniques can identify tumor tissue in OSCC metastatic lymph nodes, achieving high accuracy of pathological diagnosis, high work efficiency, and reducing work burden. But these are preliminary results limited to a small sample.

Etiopathology, Epidemiology, Diagnosis, and Treatment of Fungal Keratitis.

Fungal keratitis (FK) is a severe ocular condition resulting from corneal infection that is prevalent in tropical countries, particularly in developing regions of Asia and Africa. Factors like corneal lens misuse, inappropriate steroid use, and diagnostic challenges have provoked the epidemic. FK causes significant vision impairment, scarring, and ocular deformities. Accurate pathological diagnosis is crucial for effective therapeutic intervention. Topical antifungal therapy with surface healing medications proves effective in preventing fungal-borne ulcers. Managing FK requires a comprehensive understanding of fungal pathogenesis, guiding formulation strategies and preventive measures to curb global ocular blindness. This review provides in-depth insights into FK, covering etiology, epidemiology, pathogenesis, therapeutic interventions, antifungal resistance, limitations, prevention, and future perspectives on ocular surface disease management.

Deep Learning Models for Accurate Diagnosis and Detection of Bone Pathologies: A Comprehensive Analysis and Research Challenges

The presence of bone disease has been observed to have a substantial influence on an individual's overall health. There are conventional techniques to detect as well as diagnose them but they often suffer limitations in the form of misdiagnosis because of manual error as well as maximum time consumption. Therefore, it is of utmost importance to accurately and proficiently identify it by integrating conventional methods with advanced artificial intelligence techniques. The objective of this study is to conduct a comprehensive analysis of the present state of research concerning the identification and diagnosis of bone disease using machine learning and deep learning. A review is conducted in accordance with the PRISMA guidelines which focus on the examination of scholarly articles published within the timeframe of 2019 to 2024. This review analyzes peer-reviewed literature and research findings to show how machine and deep learning can improve bone disease diagnosis accuracy. It has been found that in the case of osteoporosis, the highest recall, precision, and F1 score is computed by random forest with 93%, 94%, and 93%, respectively while as advanced CNN technique computed 98% accuracy for osteoporosis and 98.4% accuracy, 95% sensitivity as well as 97% specificity for osteonecrosis. Likewise, for bone tumor and osteoarthritis, AlexNet achieved 98% and 98.90% accuracy, respectively. The study introduces a novel approach to the diagnosis of bone diseases by emphasizing the usage of advanced learning techniques over conventional methods. Additionally, the paper highlights the significance of analyzing the clinical or imaging data and extracting features to improve image quality and provide a pathway toward more accurate and efficient diagnosis of bone diseases. By delving into these techniques, the paper offers valuable insights into enhancing diagnostic capabilities for bone diseases, which ultimately leads to improved patient care and treatment outcomes.

Unveiling Spatial Immune Cell Profile in Kidney Allograft Rejections Using 36-plex Immunofluorescence Imaging.

Kidney allograft rejections are orchestrated by a variety of immune cells. Because of the complex histopathologic features, accurate pathological diagnosis poses challenges even for expert pathologists. The objective of this study was to unveil novel spatial indices associated with transplant rejection by using a spatial bioinformatic approach using 36-plex immunofluorescence image data. The image obtained from 11 T cell-mediated rejection (TCMR) and 12 antibody-mediated rejection (AMR) samples were segmented into 753 737 single cells using DeepCell's Mesmer algorithm. These cells were categorized into 13 distinct cell types through unsupervised clustering based on their biomarker expression profiles. Cell neighborhood analysis allowed us to stratify kidney tissue into 8 distinct neighborhood components consisting of unique cell type enrichment profiles. In contrast to TCMR samples, AMR samples exhibited a higher frequency of neighborhood components that were characterized by an enrichment of CD31+ endothelial cells. Although the overall frequency of CD68+ macrophages in AMR samples was not significantly high, CD68+ macrophages within endothelial cell-rich lesions exhibited a significantly higher frequency in AMR samples than TCMR samples. Furthermore, the frequency of interactions between CD31+ cells and CD68+ cells was significantly increased in AMR samples, implying the pivotal role of macrophages in AMR pathogenesis. Importantly, patients demonstrating a high frequency of CD31:CD68 interactions experienced significantly poorer outcomes in terms of chronic AMR progression. Collectively, these data indicate the potential of spatial bioinformatic as a valuable tool for aiding in pathological diagnosis and for uncovering new insights into the mechanisms underlying transplant rejection.

Clinicopathological significance and prognostic analysis of p21 and EGFR in colorectal cancer: a retrospective analysis on 12 319 cases in China

AimsColorectal cancer (CRC) is the third most common malignancy worldwide. Accurate pathological diagnosis and predictive abilities for treatment response and prognosis are crucial for patients with CRC. This study aims...

Association of the SHOX2 and RASSF1A methylation levels with the pathological evolution of early-stage lung adenocarcinoma

Background The methylation of SHOX2 and RASSF1A shows promise as a potential biomarker for the early screening of lung cancer, offering a solution to remedy the limitations of morphological diagnosis. The aim of this study is to diagnose lung adenocarcinoma by measuring the methylation levels of SHOX2 and RASSF1A, and provide an accurate pathological diagnosis to predict the invasiveness of lung cancer prior to surgery.Material and methods The methylation levels of SHOX2 and RASSF1A were quantified using a LungMe® test kit through methylation-specific PCR (MS-PCR). The diagnostic efficacy of SHOX2 and RASSF1A and the cutoff values were validated using ROC curve analysis. The hazardous factors influencing the invasiveness of lung adenocarcinoma were calculated using multiple regression.Results: The cutoff values of SHOX2 and RASSF1A were 8.3 and 12.0, respectively. The sensitivities of LungMe® in IA, MIA and AIS patients were 71.3% (122/171), 41.7% (15/36), and 16.1% (5/31) under the specificity of 94.1% (32/34) for benign lesions. Additionally, the methylation level of SHOX2, RASSF1A and LungMe® correlated with the high invasiveness of clinicopathological features, such as age, gender, tumor size, TNM stage, pathological type, pleural invasion and STAS. The tumor size, age, CTR values and LungMe® methylation levels were identified as independent hazardous factors influencing the invasiveness of lung adenocarcinoma.Conclusion: SHOX2 and RASSF1A combined methylation can be used as an early detection indicator of lung adenocarcinoma. SHOX2 and RASSF1A combined (LungMe®) methylation is significantly correlated to age, gender, tumor size, TNM stage, pathological type, pleural invasion and STAS. The SHOX2 and RASSF1A methylation levels, tumor size and CTR values could predict the invasiveness of the tumor prior to surgery, thereby providing guidance for the surgical procedure.

Establishment of real-time viral pathogen detection method-surface-enhanced Raman scattering system for porcine circovirus type II

The transition towards large-scale intensive pig farming methods has resulted in an increase in cases of complex, mixed infections, and secondary infections. Porcine circovirus (PCV), the causative agent of PCV disease (PCVD), is a small nonenveloped DNA virus containing a single-stranded circular genome. Previously, PCV was even considered nonpathogenic to pigs. However, a novel strain of PCV, designated PCV-2, has been associated with various disease syndromes in pigs over the last 5 years. PCV-2 primarily induces post-weaning multisystemic wasting syndrome, characterized by clinical signs such as debility, dyspnea, palpable lymphadenopathy, diarrhea, and pallor or icterus. PCV-2 is now recognized as an important emerging pathogen. Early diagnosis and disease prevention have become crucial for effective pig farm management. However, clinical diagnosis may be complicated by antibiotic treatment and atypical disease symptoms. To ensure accurate pathology diagnosis, it is essential to integrate robust laboratory diagnostics with traditional methods. Surface-enhanced Raman Scattering (SERS) spectroscopy has emerged as a potentially powerful technique for whole-organism fingerprinting, enabling rapid identification of bacteria. Biosensors utilizing SERS offer promising capabilities for sensitive and quick detection of bacterial pathogens, thereby reducing diagnosis time. In this study, our aim was to characterize and evaluate a SERS-based diagnostic system for detecting and identifying PCV-2 present in pooled swine sera and feces. We compared the spectra of PCV-2 recovered from the specimens to those of pure PCV-2 to determine the PCV-2 molecular fingerprint. Our results demonstrated successful detection, identification, and classification of PCV-2 in swine sera and feces using SERS. SERS provided reproducible molecular spectroscopic signatures suitable for analytical applications. This approach presents a new and potent tool for real-time surveillance of animal viral pathogens in clinical settings.

Colorectal adenocarcinoma with enteroblastic differentiation: a clinicopathological analysis of eight cases

Objective: To investigate the clinicopathological features of colorectal adenocarcinoma with enteroblastic differentiation (CAED). Methods: Eight cases of CAED diagnosed at the Department of Pathology, Fudan University Shanghai Cancer Center, Shanghai, China from January 2017 to August 2023 were collected. The histopathological, immunohistochemical, molecular and prognostic features of 8 CAED cases were analyzed. The relevant studies were also reviewed. Results: Among the eight patients, there were six males and two females, with an average age of 58 years (range: 29-77 years, median age: 61.5 years). Preoperative serum alpha-fetoprotein levels were elevated in five patients (14.0-286.6 μg/L). Four tumors were located in the colon, and four tumors in the rectum. Two patients were clinically staged as advanced stage (stage Ⅳ), and distant metastasis occurred at the initial diagnosis (one case had liver metastasis, and the other had lung, bone and multiple lymph nodes metastases). Six patients were clinically staged as locally-advanced stage (Stage Ⅱ-Ⅲ). Three of them developed distant metastases after surgery (one case had liver metastasis, one case had lung metastasis, and one case had peritoneal metastasis). Additionally, two patients died at 9 months and 24 months after surgery, respectively. The tumors were composed of various proportions of adenocarcinoma components with enteroblastic differentiation (30%-100%) and classical tubular adenocarcinoma components. The component with enteroblastic differentiation exhibited morphology similar to embryonic intestinal epithelium: cuboidal or columnar tumor cells arranged in tubular, papillary, cribriform, or solid nest patterns, with clear cytoplasm. Immunohistochemical studies showed that tumor cells expressed at least one oncofetal protein (SALL4, Glypican-3, and AFP). In addition, focal squamous differentiation was observed in 3 cases (3/8). Compared to the primary tumor, both CAED and squamous differentiation components were increased in the metastatic tumors. Based on the sequencing results of KRAS, NRAS and BRAF of the primary and/or metastatic tumors, 5 cases were wild-type, while KRAS exon 2 (G13D) mutations were identified in 2 cases. Conclusions: CAED is a rare colorectal malignancy with a dismal prognosis. Accurate pathological diagnosis is prognostically valuable. The histological features of enteroblastic differentiation, elevated serum AFP levels, and the expression of oncofetal proteins play an important role in the tumor diagnosis.

WET-UNet: Wavelet integrated efficient transformer networks for nasopharyngeal carcinoma tumor segmentation.

Nasopharyngeal carcinoma is a malignant tumor that occurs in the epithelium and mucosal glands of the nasopharynx, and its pathological type is mostly poorly differentiated squamous cell carcinoma. Since the nasopharynx is located deep in the head and neck, early diagnosis and timely treatment are critical to patient survival. However, nasopharyngeal carcinoma tumors are small in size and vary widely in shape, and it is also a challenge for experienced doctors to delineate tumor contours. In addition, due to the special location of nasopharyngeal carcinoma, complex treatments such as radiotherapy or surgical resection are often required, so accurate pathological diagnosis is also very important for the selection of treatment options. However, the current deep learning segmentation model faces the problems of inaccurate segmentation and unstable segmentation process, which are mainly limited by the accuracy of data sets, fuzzy boundaries, and complex lines. In order to solve these two challenges, this article proposes a hybrid model WET-UNet based on the UNet network as a powerful alternative for nasopharyngeal cancer image segmentation. On the one hand, wavelet transform is integrated into UNet to enhance the lesion boundary information by using low-frequency components to adjust the encoder at low frequencies and optimize the subsequent computational process of the Transformer to improve the accuracy and robustness of image segmentation. On the other hand, the attention mechanism retains the most valuable pixels in the image for us, captures the remote dependencies, and enables the network to learn more representative features to improve the recognition ability of the model. Comparative experiments show that our network structure outperforms other models for nasopharyngeal cancer image segmentation, and we demonstrate the effectiveness of adding two modules to help tumor segmentation. The total data set of this article is 5000, and the ratio of training and verification is 8:2. In the experiment, accuracy = 85.2% and precision = 84.9% can show that our proposed model has good performance in nasopharyngeal cancer image segmentation.