Objective: Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains. Method: We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists. Conclusion: The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists. Significance: This study shows the potential of using semi-supervised GAN-based bladder tissue classification when annotations are limited in multi-domain data. The dataset is available at https://zenodo.org/record/7741476#.ZBQUK7TMJ6k
翻译:目标:在经尿道膀胱肿瘤切除(TURBT)手术过程中,准确的膀胱组织视觉分类对于提高早期癌症诊断和治疗至关重要。在TURBT干预期间,白光成像(WLI)和狭带成像(NBI)技术用于病变检测。每种成像技术提供各种各样的视觉信息,使临床医生能够识别和分类癌性病变。使用两种成像技术的计算机视觉方法可以改进内窥镜诊断。我们解决了当只有一种域中的注释可用,即WLI,并且内窥镜图像对应于未配对数据集时,即不存在完全相等的NBI和WLI领域之间的每个图像的挑战。方法:我们提出了一种基于半监督生成对抗网络(GAN)的方法,由三个主要组件组成:在标记的WLI数据上训练的教师网络;循环一致性GAN进行不成对的图像对图像转换,以及多输入学生网络。为了确保所提供的GAN生成的合成图像的质量,我们在专家的帮助下进行了详细的定量和定性分析。结论:所提出的方法用于组织分类的整体平均分类准确性、精度和召回率分别为0.90、0.88和0.89;而在未标记的领域(NBI)中获得的相同指标为0.92、0.64和0.94。生成图像的质量足以欺骗专家。意义:本研究展示了在多域数据中注释有限时使用半监督GAN基于膀胱组织分类的潜力。数据集可在https://zenodo.org/record/7741476#.ZBQUK7TMJ6k 上找到。