RESUMEN
INTRODUCTION: Histological grading of cutaneous squamous cell carcinoma (cSCC) is crucial for prognosis and treatment decisions, but manual grading is subjective and time-consuming. AIM: This study aimed to develop and validate a deep learning (DL)-based model for automated cSCC grading, potentially improving diagnostic accuracy (ACC) and efficiency. MATERIALS AND METHODS: Three deep neural networks (DNNs) with different architectures (AlexNet, GoogLeNet, ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The models were evaluated on their ACC, sensitivity (SN), specificity (SP), and area under the curve (AUC). Clinical validation was performed on 60 images, comparing the DNNs' predictions with those of a panel of pathologists. RESULTS: The models achieved high performance metrics (ACC>85%, SN>85%, SP>92%, AUC>97%) demonstrating their potential for objective and efficient cSCC grading. The high agreement between the DNNs and pathologists, as well as among different network architectures, further supports the reliability and ACC of the DL models. The top-performing models are publicly available, facilitating further research and potential clinical implementation. CONCLUSIONS: This study highlights the promising role of DL in enhancing cSCC diagnosis, ultimately improving patient care.
Asunto(s)
Carcinoma de Células Escamosas , Aprendizaje Profundo , Neoplasias Cutáneas , Humanos , Carcinoma de Células Escamosas/patología , Carcinoma de Células Escamosas/diagnóstico , Neoplasias Cutáneas/patología , Neoplasias Cutáneas/diagnóstico , Clasificación del Tumor/métodosRESUMEN
The tumor microenvironment (TME), a complex assembly of cellular and extracellular matrix (ECM) components, plays a crucial role in driving tumor progression, shaping treatment responses, and influencing metastasis. This narrative review focuses on the cutaneous squamous cell carcinoma (cSCC) tumor stroma, highlighting its key constituents and their dynamic contributions. We examine how significant changes within the cSCC ECM-specifically, alterations in fibronectin, hyaluronic acid, laminins, proteoglycans, and collagens-promote cancer progression, metastasis, and drug resistance. The cellular composition of the cSCC TME is also explored, detailing the intricate interplay of cancer-associated fibroblasts (CAFs), mesenchymal stem cells (MSCs), endothelial cells, pericytes, adipocytes, and various immune cell populations. These diverse players modulate tumor development, angiogenesis, and immune responses. Finally, we emphasize the TME's potential as a therapeutic target. Emerging strategies discussed in this review include harnessing the immune system (adoptive cell transfer, checkpoint blockade), hindering tumor angiogenesis, disrupting CAF activity, and manipulating ECM components. These approaches underscore the vital role that deciphering TME interactions plays in advancing cSCC therapy. Further research illuminating these complex relationships will uncover new avenues for developing more effective treatments for cSCC.