Ștefan Paul-Andrei, Coțe Adrian, Csutak Csaba, Lupean Roxana-Adelina, Lebovici Andrei, Mihu Carmen Mihaela, Lenghel Lavinia Manuela, Pușcas Marius Emil, Roman Andrei, Feier Diana
Department of Biomedical Imaging and Image-Guided Therapy, General Hospital of Vienna (AKH), Medical University of Vienna, 1090 Vienna, Austria.
Anatomy and Embryology, Morphological Sciences Department, "Iuliu Haţieganu" University of Medicine and Pharmacy, Victor Babeș Street, Number 8, 400012 Cluj-Napoca, Romania.
Diagnostics (Basel). 2023 Jan 26;13(3):442. doi: 10.3390/diagnostics13030442.
The conventional magnetic resonance imaging (MRI) evaluation and staging of cervical cancer encounters several pitfalls, partially due to subjective evaluations of medical images. Fifty-six patients with histologically proven cervical malignancies (squamous cell carcinomas, = 42; adenocarcinomas, = 14) who underwent pre-treatment MRI examinations were retrospectively included. The lymph node status (non-metastatic lymph nodes, = 39; metastatic lymph nodes, = 17) was assessed using pathological and imaging findings. The texture analysis of primary tumours and lymph nodes was performed on T2-weighted images. Texture parameters with the highest ability to discriminate between the two histological types of primary tumours and metastatic and non-metastatic lymph nodes were selected based on Fisher coefficients (cut-off value > 3). The parameters' discriminative ability was tested using an k nearest neighbour (KNN) classifier, and by comparing their absolute values through an univariate and receiver operating characteristic analysis. Results: The KNN classified metastatic and non-metastatic lymph nodes with 93.75% accuracy. Ten entropy variations were able to identify metastatic lymph nodes (sensitivity: 79.17-88%; specificity: 93.48-97.83%). No parameters exceeded the cut-off value when differentiating between histopathological entities. In conclusion, texture analysis can offer a superior non-invasive characterization of lymph node status, which can improve the staging accuracy of cervical cancers.
宫颈癌的传统磁共振成像（MRI）评估和分期存在一些缺陷，部分原因是医学图像的主观评估。回顾性纳入了56例经组织学证实为宫颈恶性肿瘤（鳞状细胞癌，n = 42；腺癌，n = 14）且接受了治疗前MRI检查的患者。使用病理和影像学检查结果评估淋巴结状态（非转移性淋巴结，n = 39；转移性淋巴结，n = 17）。在T2加权图像上对原发肿瘤和淋巴结进行纹理分析。基于Fisher系数（临界值> 3）选择对两种组织学类型的原发肿瘤以及转移性和非转移性淋巴结具有最高区分能力的纹理参数。使用k最近邻（KNN）分类器测试参数的区分能力，并通过单变量和受试者工作特征分析比较其绝对值。结果：KNN对转移性和非转移性淋巴结的分类准确率为93.75%。十个熵变化能够识别转移性淋巴结（敏感性：79.17 - 88%；特异性：93.48 - 97.83%）。在区分组织病理学实体时，没有参数超过临界值。总之，纹理分析可以提供对淋巴结状态更好的非侵入性特征描述，这可以提高宫颈癌的分期准确性。
