Tumor segmentation is a crucial but difficult task in treatment planning and follow-up of cancerous patients. The challenge of automating the tumor segmentation has recently received a lot of attention, but the potential of utilizing hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI), a novel and promising imaging modality in oncology, is still under-explored. Recent approaches have either relied on manual user input and/or performed the segmentation patient-by-patient, whereas a fully unsupervised segmentation framework that exploits the available information from all patients is still lacking.

We present an unsupervised across-patients supervoxel-based clustering framework for lung tumor segmentation in hybrid PET/MRI. The method consists of two steps: First, each patient is represented by a set of PET/MRI supervoxel-features. Then the data points from all patients are transformed and clustered on a population level into tumor and non-tumor supervoxels. The proposed framework is tested on the scans of 18 non-small cell lung cancer patients with a total of 19 tumors and evaluated with respect to manual delineations provided by clinicians. Experiments study the performance of several commonly used clustering algorithms within the framework and provide analysis of i) the effect of tumor size, ii) the segmentation errors, iii) the benefit of across-patient clustering, and iv) the noise robustness.

The proposed framework detected 15 out of 19 tumors in an unsupervised manner. Moreover, performance increased considerably by segmenting across patients, with the mean dice score increasing from $\mathbf{0}.\mathbf{169}\pm \mathbf{0}.\mathbf{295}$ (patient-by-patient) to $\mathbf{0}.\mathbf{470}\pm \mathbf{0}.\mathbf{308}$ (across-patients). Results demonstrate that both spectral clustering and Manhattan hierarchical clustering have the potential to segment tumors in PET/MRI with a low number of missed tumors and a low number of false-positives, but that spectral clustering seems to be more robust to noise.

在癌症患者的治疗计划和随访中，肿瘤分割是至关重要但困难的任务。自动进行肿瘤分割的挑战近来受到了很多关注，但是利用混合正电子发射断层扫描（PET）/磁共振成像（MRI）这种在肿瘤学中新颖而有前途的成像方式的潜力仍未得到开发。最近的方法要么依赖于手动用户输入和/或逐个病人进行分割，但是仍然缺乏一种完全无监督的分割框架，该框架利用了来自所有患者的可用信息。

我们提出了混合PET / MRI中无监督的跨患者基于超素的聚类框架。该方法包括两个步骤：首先，每个患者由一组PET / MRI超体素特征代表。然后，将所有患者的数据点转换并按人群水平聚类为肿瘤和非肿瘤超体素。在对18例总共有19个肿瘤的非小细胞肺癌患者的扫描中测试了所提出的框架，并就临床医生提供的手动描述进行了评估。实验研究了框架内几种常用聚类算法的性能，并提供了以下方面的分析：i）肿瘤大小的影响，ii）分割错误，iii）跨患者聚类的好处，以及iv）噪声鲁棒性。

拟议的框架以无监督方式检测出19个肿瘤中的15个。此外，通过按患者细分，性能显着提高，平均骰子得分从$\mathbf{0}。\mathbf{169}\pm \mathbf{0}。\mathbf{295}$ （逐个病人） $\mathbf{0}。\mathbf{470}\pm \mathbf{0}。\mathbf{308}$（跨患者）。结果表明，光谱聚类和曼哈顿分层聚类均具有在PET / MRI中分割肿瘤的潜力，其中遗漏的肿瘤数量少，假阳性数少，但是光谱聚类似乎对噪声更鲁棒。