Giarnieri Enrico, Carico Elisabetta, Scarpino Stefania, Ricci Alberto, Bruno Pierdonato, Scardapane Simone, Giansanti Daniele
Cytopathology Unit, Department of Clinical and Molecular Medicine, Sant'Andrea University Hospital, Sapienza University of Rome, Via di Grottarossa 1035, 00189 Rome, Italy.
Morphologic and Molecular Pathology Unit, Department of Clinical and Molecular Medicine, Sant' Andrea University Hospital, Sapienza University of Rome, Via di Grottarossa 1035, 00189 Rome, Italy.
Diagnostics (Basel). 2025 May 14;15(10):1240. doi: 10.3390/diagnostics15101240.
Malignant pleural effusions (MPEs) are common in advanced lung cancer patients. Cytological examination of pleural fluid is essential for identifying cell types but presents diagnostic challenges, particularly when reactive mesothelial cells mimic neoplastic cells. AI-powered diagnostic systems have emerged as valuable tools in digital cytopathology. This study explores the applicability of machine-learning (ML) models and highlights the importance of accessible tools for clinicians, enabling them to develop AI solutions and make advanced diagnostic tools available even in resource-limited settings. The focus is on differentiating normal/reactive cells from neoplastic cells in pleural effusions linked to lung adenocarcinoma. A dataset from the Cytopathology Unit at the Sant'Andrea University Hospital comprising 969 raw images, annotated with 3130 single mesothelial cells and 3260 adenocarcinoma cells, was categorized into two classes based on morphological features. Object-detection models were developed using YOLOv8 and the latest YOLOv11 instance segmentation models. The models achieved an Intersection over Union (IoU) score of 0.72, demonstrating robust performance in class prediction for both categories, with YOLOv11 showing performance improvements over YOLOv8 in different metrics. The application of machine learning in cytopathology offers clinicians valuable support in differential diagnosis while also expanding their ability to engage with AI tools and methodologies. The diagnosis of MPEs is marked by substantial morphological and technical variability, underscoring the need for high-quality datasets and advanced deep-learning models. These technologies have the potential to enhance data interpretation and support more effective clinical treatment strategies in the era of precision medicine.
恶性胸腔积液（MPEs）在晚期肺癌患者中很常见。胸腔积液的细胞学检查对于确定细胞类型至关重要，但也带来了诊断挑战，尤其是当反应性间皮细胞模仿肿瘤细胞时。人工智能驱动的诊断系统已成为数字细胞病理学中有价值的工具。本研究探讨了机器学习（ML）模型的适用性，并强调了为临床医生提供易于使用的工具的重要性，使他们能够开发人工智能解决方案，即使在资源有限的环境中也能使用先进的诊断工具。重点是区分与肺腺癌相关的胸腔积液中的正常/反应性细胞和肿瘤细胞。圣安德烈亚大学医院细胞病理学部门的一个数据集包含969张原始图像，标注了3130个单个间皮细胞和3260个腺癌细胞，根据形态特征分为两类。使用YOLOv8和最新的YOLOv11实例分割模型开发了目标检测模型。这些模型的交并比（IoU）得分达到0.72，在两类的类别预测中表现出强大的性能，YOLOv11在不同指标上比YOLOv8表现更好。机器学习在细胞病理学中的应用为临床医生的鉴别诊断提供了有价值的支持，同时也扩展了他们使用人工智能工具和方法的能力。MPEs的诊断存在很大的形态学和技术变异性，这突出了对高质量数据集和先进深度学习模型的需求。在精准医学时代，这些技术有可能加强数据解读并支持更有效的临床治疗策略。
