Diagnostic Pathology最新文献

Background: Accurate assessment of programmed death-ligand 1 (PD-L1) immunohistochemical (IHC) expression is critical for immunotherapy in patients with non-small cell lung cancer (NSCLC). Yet, interpreting its staining is challenging, time-consuming, and causes inter-observer variability, potentially mis-stratifying patients. This necessitates the development of an artificial intelligence (AI) model to effectively quantify PD-L1 expression. Hence, we developed an AI-based deep-learning approach to automatically assess PD-L1 expression in NSCLC using IHC 22C3 assay-stained whole slide images (WSIs).

Methods: A total of 706 patients with NSCLC were included in this study and 1212 WSIs were collected from three distinct study cohorts. We accurately matched the hematoxylin and eosin-stained images of the internal dataset with the IHC WSIs. Foreground regions containing tumor tissue were extracted from WSIs, and a multi-granular multiple-instance learning approach employing instance embeddings with coarse and fine granularities was implemented to extract patch-level morphological features. A multi-grained expression interpreter-based model aggregated these features to stratify PD-L1 expression status.

Results: The model showed strong interpretive ability in all three cohorts and wide applicability to different specimen types. The macro-average area under the receiver operating characteristic curve (AUC) were 0.940/0.915/0.944 for surgical specimens, 0.955/0.844/0.865 for biopsy specimens, and 0.901/0.958/0.883 for metastases.

Conclusion: This study emphasizes the potential benefits of deep learning in automatically, rapidly, and accurately inferring PD-L1 expression from complex IHC images. It also showcases how AI frameworks can improve routine digital pathology workflows in current PD-L1 detection methods.

Medical healthcare has advanced substantially due to advancements in Artificial Intelligence (AI) techniques for early disease detection alongside support for clinical decisions. However, a gap exists in widespread adoption of results of these algorithms by public due to black box nature of models. The undisclosed nature of these systems creates fundamental obstacles within medical sectors that handle crucial cases because medical practitioners needs to understand the reasoning behind the outcome of a particular disease. A hybrid Machine Learning (ML) framework integrating Explainable AI (XAI) strategies that will improve both predictive performance and interpretability is explored in proposed work. The system leverages Decision Trees, Naive Bayes, Random Forests and XGBoost algorithms to predict the medical condition risks of Diabetes, Anaemia, Thalassemia, Heart Disease, Thrombocytopenia within its framework. SHAP (SHapley Additive exPlanations) together with LIME (Local Interpretable Model-agnostic Explanations) adds functionality to the proposed system by displaying important features contributing to each prediction. The framework upholds an accuracy of 99.2% besides the ability to provide understandable explanations for interpretation of model outputs. The performance combined with interpretability from the framework enables clinical practitioners to make decisions through an understanding of AI-generated outputs thereby reducing distrust in AI-driven healthcare.

Background: Gastric cancer is one of the most common cancers worldwide, with its prognosis influenced by factors such as tumor clinical stage, histological type, and the patient's overall health. Recent studies highlight the critical role of lymphatic endothelial cells (LECs) in the tumor microenvironment. Perturbations in LEC function in gastric cancer, marked by aberrant activation or damage, disrupt lymphatic fluid dynamics and impede immune cell infiltration, thereby modulating tumor progression and patient prognosis. Hence, we aimed to construct a prognostically discriminative model group in LECs-related factors.

Methods: Gene expression and clinical data of gastric cancer patients were obtained from The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), and Fudan University Shanghai Cancer Center (FUSCC). Using the Wilcoxon test, we assessed the relationship between LECs, angiogenesis, and the immunological milieu. Differentially expressed and prognostically significant LEC-associated genes were identified through "limma" R package-assisted analysis coupled with univariate Cox analysis. A prognostic model was developed, and LEC-associated gene signatures were refined through least absolute shrinkage and selection operator (LASSO)-Cox regression. Subsequently, the prognostic potential of this model was evaluated using ROC (receiver operating characteristic) curve analysis, Kaplan-Meier survival curve analysis and decision curve analysis (DCA).

Results: LECs exhibited association with angiogenesis, immune cell infiltration, immune escape, and epithelial-mesenchymal transition (EMT). Utilizing an 18-gene signature, gastric cancer patients from TCGA and GEO cohorts were stratified into high- risk and low-risk groups, with the former showing significantly poorer overall survival. Leveraging this gene signature, we designed a LECs-related gastric cancer prognostic model, demonstrating superior performance indicated by the area under the ROC curve (AUC) compared to existing models. Moreover, the nomogram and DCA underscored the clinical utility of our model in predicting the prognosis of GC patients.

Conclusions: Our prognostic signature, based on 18 LECs-related genes, holds promise for refining overall survival prediction in gastric cancer patients, offering a valuable tool for clinical decision-making.

Clinical trial number: Not applicable.

Background: Overexpression of ribosomal proteins has been found in several cancer types and has an important role in cell proliferation and tumorigenesis. Analysis of the expression profiles of cholangiocarcinoma revealed that ribosomal protein L15 (RPL15) was significantly upregulated in cancer tissues compared to surrounding liver and biliary tissues. Thus, we tried to investigate the role of RPL15 in intrahepatic cholangiocarcinoma.

Methods: The expression of RPL15 in intrahepatic cholangiocarcinoma was assessed using immunohistochemistry. The relationships between RPL15 expression levels and clinicopathological parameters were analyzed, along with investigating its prognostic significance in overall survival (OS), disease-specific survival (DSS), local recurrence-free survival (LRFS) and metastasis-free survival (MeFS).

Results: In the cohort comprising 182 patients with intrahepatic cholangiocarcinoma, high expression of RPL15 was significantly associated with advanced tumor (pT) stage (P = 0.005) and high histological grade (P = 0.018). In univariate analyses, overexpression of RPL15 predicted worse DSS (P = 0.0001), LRFS (P < 0.0001) and MeFS (P < 0.0001), but not OS (P = 0.3960). Multivariate analyses revealed that RPL15 overexpression independently predicted worse DSS (P = 0.039), LRFS (P < 0.001) and MeFS (P < 0.001).

Conclusions: Overexpression of RPL15 was identified as an adverse prognostic factor predicting worse outcomes in intrahepatic cholangiocarcinoma. RPL15 could serve as a potential therapeutic target to aid in developing new treatment strategies.

Rationale: SMARCB1 (INI1) deficient sinonasal carcinoma is a subtype of Switch/Sucrose nonfermentable (SWI/SNF) complex deficient sinonasal carcinoma, which is distinct from sinonasal undifferentiated carcinoma (SNUC) in 5th edition of the WHO classification of head and neck tumors. It commonly shows basaloid, eosinophilic, oncocytoid or rhabdoid morphology. However, it can exhibit yolk sac like differentiation in very rare cases, with associated SALL4, GPC-3 and CDX2 and AFP expression, which can lead to the misdiagnosis of primary nasopharyngeal yolk sac tumor (YST).

Patient concerns: A 58-year-old male patient with right nasal cavity mass, he complained for persistent right-sided nasal congestion for 3 months, accompanied by decreased sense of smell and protrusion of the right eyeball.

Diagnosis: Histology showed tumor cells with glandular, large cystic, and microcystic architectural arrangement. Immunohistochemically, the tumor cells expressed SALL-4 and GPC-3. The findings supported obvious yolk sac tumor like features. However, the absence of INI-1 expression confirmed the diagnosis of INI-1 deficient sinonasal carcinoma.

Interventions: The patient underwent 4 rounds of clinical tumor volume (CTV) radiotherapy.

Outcomes: The patient was followed up for 22 months with interval nasopharyngeal MRI and lung CT scan, with no sign of tumor recurrence or metastasis.

Lessons: Our case suggests that INI1-deficient sinonasal carcinoma with yolk sac differentiation is an important differential diagnosis of primary nasopharyngeal yolk sac tumor, which may have favorable disease-free survival with adjuvant radiotherapy alone.

Solitary fibrous tumor (SFT) is a fibroblastic tumor characterized by a prominent staghorn vasculature and collagen deposition. However, little is known about SFTs with alveolar structures. Herein, we present a case of an alveolar pattern SFT in a 55-year-old woman. The tumor was present in the lumbosacral spinal canal and showed an alveolar architecture composed of ovoid to spindle-shaped cells. Immunohistochemical examination showed that the tumor cells were positive for STAT6 (nuclear expression), CD34, CD99, and Bcl-2, but negative for cytokeratins (CK-pan and AE1/AE3), EMA, GFAP, CD31, progesterone receptor, S-100 protein, and smooth muscle actin. Furthermore, NAB2::STAT6 fusion was detected using DNA-based next-generation sequencing, which established the diagnosis of SFT at a molecular level. The present case expands the morphological categories of SFT.

Background: Hereditary leiomyomatosis and renal cell carcinoma syndrome (HLRCC) is an autosomal dominant tumor predisposition syndrome with germline fumarate hydratase (FH) pathogenic variants. We describe the unusual clinical presentation, morphologic, and immunohistochemical features of bilateral renal cell carcinoma (RCC) occurring in polycystic kidneys in a 15-year-old male with HLRCC.

Case presentation: The patient was diagnosed with bilateral polycystic kidneys at 1-year old. At 8-years old he was diagnosed with cutaneous leiomyomas, prompting germline testing which revealed heterozygous variant (c.1301G > A) in the FH gene. Serial imaging identified interval enlargement of several bilateral renal lesions with solid components. Biopsy of a right solid lesion revealed an oncocytic neoplasm. He underwent left total nephrectomy and right partial nephrectomy, revealing numerous bilateral solid and cystic lesions, some with papillary excrescences. Histologic evaluation revealed large cells with eosinophilic to clear cytoplasm and large nuclei with occasional nuclear pseudoinclusions arranged in variable architectural patterns including papillary, tubular, tubulocystic, microcystic and solid. Large cysts were lined by varying thickness of neoplastic cells. By immunohistochemistry, lesional cells were positive for 2-succinocysteine (2SC), TFE3, PAX8 and AMACR, showed retained SDHB, variable FH, and were negative for Cathepsin K, CK20, and CK7. An RNA fusion panel (including TFE3) was negative. Multiple microscopic renal leiomyomas were also present.

Conclusions: Multicystic kidney disease has been previously reported in HLRCC but is not currently included in the WHO classification. Bilateral involvement may mimic polycystic kidney disease and cysts may represent precursor lesions. TFE3-positivity raises the possibility of translocation RCC and is a diagnostic pitfall.

Background: Dysgerminoma, a uncommon malignant neoplasm originating from primitive ovarian germ cells, is exceptionally rare during pregnancy. While several studies have documented dysgerminoma diagnosis via peritoneal effusion cytology, no cases identified during pregnancy have been reported to date. This study presents the first reported case of dysgerminoma diagnosed through peritoneal effusion cytology in a pregnant patient.

Case presentation: A 27-year-old pregnant woman presented to our hospital with an early intrauterine pregnancy and a right adnexal mass detected on B-ultrasound at a local hospital. Cytological evaluation of the peritoneal effusion revealed a polymorphic cell population dominated by discrete large tumor cells mixed with reactive lymphocytes and histiocytes. These tumor cells exhibited moderate to abundant eosinophilic or vacuolated cytoplasm with well-defined borders. Most had round or oval nuclei with high nuclear-to-cytoplasmic (N/C) ratios, granular chromatin with uneven distribution, and distinct nucleoli visible in some cells. While a subset of large cells showed irregular nuclear contours and angular appearances. Immunocytochemistry (ICC) results of cell block (CB) showed positive staining for SALL4, CD117, OCT3/4, PLAP, and D2-40, but negative staining for LCA, CD30, EMA, CK-P, CR, and SF-1. The final diagnosis of dysgerminoma was made by integrating peritoneal effusion cytology, cell block analysis, and ICC results. The patient underwent right adnexectomy and subsequently delivered a healthy female infant at 36 + 4 weeks of gestation. Four-year postoperative follow-up showed no evidence of disease recurrence.

Conclusion: This report describes the cytopathological features of dysgerminoma in peritoneal effusion, specifically the presence of discrete large tumor cells with hyperchromatic nuclei and prominent nucleoli. Cytopathologists should maintain a high index of suspicion for this entity, particularly in young patients, and adopt a comprehensive diagnostic approach including cytomorphological assessment, CB examination, and immunocytochemical analysis to make an accurate diagnosis.