Department of Biochemistry

Fluorescence in situ hybridization (FISH) is widely regarded as the gold standard for evaluating human epidermal growth factor receptor 2 (HER2) status in breast cancer; however, it poses challenges such as the need for specialized training and issues related to signal degradation from dye quenching. Silver-enhanced in situ hybridization (SISH) serves as an automated alternative, employing permanent staining suitable for bright-field microscopy. Determining HER2 status involves distinguishing between “Amplified” and “Non-Amplified” regions by assessing HER2 and centromere 17 (CEN17) signals in SISH-stained slides. This study is the first to leverage deep learning for classifying Normal, Amplified, and Non-Amplified regions within HER2-SISH whole slide images (WSIs), which are notably more complex to analyze compared to hematoxylin and eosin (H&E)-stained slides. Our proposed approach consists of a two-stage process: first, we evaluate deep-learning models on annotated image regions, and then we apply the most effective model to WSIs for regional identification and localization. Subsequently, pseudo-color maps representing each class are overlaid, and the WSIs are reconstructed with these mapped regions. Using a private dataset of HER2-SISH breast cancer slides digitized at 40× magnification, we achieved a patch-level classification accuracy of 99.9% and a generalization accuracy of 78.8% by applying transfer learning with a Vision Transformer (ViT) model. The robustness of the model was further evaluated through k-fold cross-validation, yielding an average performance accuracy of 98%, with metrics reported alongside 95% confidence intervals to ensure statistical reliability. This method shows significant promise for clinical applications, particularly in assessing HER2 expression status in HER2-SISH histopathology images. It provides an automated solution that can aid pathologists in efficiently identifying HER2-amplified regions, thus enhancing diagnostic outcomes for breast cancer treatment.

Introduction: Cholangiocarcinoma (CCA) is a highly lethal malignancy originating in the bile ducts, often diagnosed late with poor prognosis. Differentiating benign from malignant biliary tumors remains challenging, necessitating advanced diagnostic techniques. Objective: This study aims to enhance the diagnostic accuracy of endoscopic ultrasound (EUS) for distal cholangiocarcinoma (dCCA) using advanced convolutional neural networks (CCNs) for the classification and segmentation of EUS images, specifically targeting dCCAs, the pancreas, and the bile duct. Materials and Methods: In this retrospective study, EUS images from patients diagnosed with dCCA via biopsy and an EUS-identified bile duct tumor were evaluated. A custom CNN was developed for classification, trained on 156 EUS images. To enhance the model’s robustness, image augmentation techniques were applied, generating a total of 1248 images. For tumor and organ segmentation, the DeepLabv3+ network with ResNet50 architecture was utilized, employing Tversky loss to manage unbalanced classes. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and Intersection over Union (IoU). These methods were implemented in collaboration with the ADAPTED Research Group at the Technical University of Cluj-Napoca. Results: The classification model achieved a high accuracy of 97.82%, with precision and specificity both at 100% and sensitivity at 94.44%. The segmentation models for the pancreas and bile duct demonstrated global accuracies of 84% and 90%, respectively, with robust IoU scores indicating good overlap between predicted and actual contours. The application performed better than the UNet model, particularly in generalization and boundary delineation. Conclusions: This study demonstrates the significant potential of AI in EUS imaging for dCCA, presenting a robust tool that enhances diagnostic accuracy and efficiency. The developed MATLAB application serves as a valuable aid for medical professionals, facilitating informed decision-making and improving patient outcomes in the diagnosis of cholangiocarcinoma and related pathologies.

Background: Lung and colon cancers are among the most prevalent and lethal malignancies worldwide, underscoring the urgent need for advanced diagnostic methodologies. This study aims to develop a hybrid deep learning and machine learning framework for the classification of Colon Adenocarcinoma, Colon Benign Tissue, Lung Adenocarcinoma, Lung Benign Tissue, and Lung Squamous Cell Carcinoma from histopathological images. Methods: Current approaches primarily rely on the LC25000 dataset, which, due to image augmentation, lacks the generalizability required for real-time clinical applications. To address this, Contrast Limited Adaptive Histogram Equalization (CLAHE) was applied to enhance image quality, and 1000 new images from the National Cancer Institute GDC Data Portal were introduced into the Colon Adenocarcinoma, Lung Adenocarcinoma, and Lung Squamous Cell Carcinoma classes, replacing augmented images to increase dataset diversity. A hybrid feature extraction model combining MobileNetV2 and EfficientNetB3 was optimized using the Grey Wolf Optimizer (GWO), resulting in the Lung and Colon histopathological classification technique (MEGWO-LCCHC). Cross-validation and hyperparameter tuning with Optuna were performed on various machine learning models, including XGBoost, LightGBM, and CatBoost. Results: The MEGWO-LCCHC technique achieved high classification accuracy, with the lightweight DNN model reaching 94.8%, LightGBM at 93.9%, XGBoost at 93.5%, and CatBoost at 93.3% on the test set. Conclusions: The findings suggest that our approach enhances classification performance and offers improved generalizability for real-world clinical applications. The proposed MEGWO-LCCHC framework shows promise as a robust tool in cancer diagnostics, advancing the application of AI in oncology.

Objective: We aimed to compare the clinical utility and diagnostic accuracy of the ADNEX model, ROMA score, RMI I, and RMI IV, as well as two serum markers (CA125 and HE4) in preoperative discrimination between benign and malignant adnexal masses (AMs). Methods: We conducted a retrospective study extracting all consecutive patients with AMs seen at our Institution between January 2015 and December 2020. Accuracy metrics included sensitivity (SE), specificity (SP), and area under the receiver operating characteristic curve (AUC), and their 95% confidence intervals (CI) were calculated for basic discrimination between AMs. Model performance was evaluated in terms of discrimination ability and clinical utility (net benefit, NB). Results: A total of 581 women were included; 481 (82.8%) had a benign ovarian tumor and 100 (17.2%) had a malignant tumor. The SE and SP of CA125, HE4, ROMA score, RMI I, RMI IV, and ADNEX model were 0.60 (0.54–0.66) and 0.80 (0.76–0.83); 0.39 (0.30–0.49) and 0.96 (0.94–0.98); 0.59 (0.50–0.68) and 0.92 (0.88–0.95); 0.56 (0.46–0.65) and 0.98 (0.96–0.99); 0.54 (0.44–0.63) and 0.96 (0.94–0.98); 0.82 (0.73–0.88) and 0.91 (0.89–0.94), respectively. The overall AUC was 0.76 (0.74–0.79) for CA125, 0.81 (0.78–0.83) for HE4, 0.82 (0.80–0.85) for ROMA, 0.86 (0.84–0.88) for RMI I, 0.83 (0.81–0.86) for RMI IV, and 0.92 (0.90–0.94) for ADNEX. The NB for ADNEX was higher than other biomarkers and models across all decision thresholds between 5% and 50%. Conclusions: The ADNEX model showed a better discrimination ability and clinical utility when differentiating malignant from benign Ams, compared to CA125, HE4, ROMA score, RMI I, and RMI IV.

Protein arginine methyltransferase 5 (PRMT5) is a critical oncogenic factor in various cancers, and its inhibition has shown promise in suppressing tumor growth. However, the role of PRMT5 in squamous cell carcinoma (SCC) remains largely unexplored. In this study, we analyzed SCC patient data from The Cancer Genome Atlas (TCGA) and the Cancer Dependency Map (DepMap) to investigate the relationship between PRMT5 and SCC proliferation. We employed competition-based cell proliferation assays, 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl-2H-tetrazolium bromide (MTT) assays, flow cytometry, and in vivo mouse modeling to examine the regulatory roles of PRMT5 and its binding partner WDR77 (WD repeat domain 77). We identified downstream targets, including the p63 isoform ΔNp63α and the cyclin-dependent kinase inhibitor p21, through single-cell RNA-seq, RT-qPCR, and Western blot analyses. Our findings demonstrate that upregulation of PRMT5 and WDR77 correlates with the poor survival of head and neck squamous cell carcinoma (HNSCC) patients. PRMT5/WDR77 regulates the HNSCC-specific transcriptome and facilitates SCC proliferation by promoting cell cycle progression. The PRMT5 and WDR77 stabilize the ΔNp63α Protein, which in turn, inhibits p21. Moreover, depletion of PRMT5 and WDR77 repress SCC in vivo. This study reveals for the first time that PRMT5 and WDR77 synergize to promote SCC proliferation via the ΔNp63α-p21 axis, highlighting a novel therapeutic target for SCC.