Ghose Soumya, Denham James W, Ebert Martin A, Kennedy Angel, Mitra Jhimli, Dowling Jason A
Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Ave, Cleveland, OH, 44106, USA.
School of Medicine and Public Health, University of Newcastle, Callaghan, NSW, 2308, Australia.
Australas Phys Eng Sci Med. 2016 Dec;39(4):933-941. doi: 10.1007/s13246-016-0496-0. Epub 2016 Nov 14.
Perirectal space segmentation in computed tomography images aids in quantifying radiation dose received by healthy tissues and toxicity during the course of radiation therapy treatment of the prostate. Radiation dose normalised by tissue volume facilitates predicting outcomes or possible harmful side effects of radiation therapy treatment. Manual segmentation of the perirectal space is time consuming and challenging in the presence of inter-patient anatomical variability and may suffer from inter- and intra-observer variabilities. However automatic or semi-automatic segmentation of the perirectal space in CT images is a challenging task due to inter patient anatomical variability, contrast variability and imaging artifacts. In the model presented here, a volume of interest is obtained in a multi-atlas based segmentation approach. Un-supervised learning in the volume of interest with a Gaussian-mixture-modeling based clustering approach is adopted to achieve a soft segmentation of the perirectal space. Probabilities from soft clustering are further refined by rigid registration of the multi-atlas mask in a probabilistic domain. A maximum a posteriori approach is adopted to achieve a binary segmentation from the refined probabilities. A mean volume similarity value of 97% and a mean surface difference of 3.06 ± 0.51 mm is achieved in a leave-one-patient-out validation framework with a subset of a clinical trial dataset. Qualitative results show a good approximation of the perirectal space volume compared to the ground truth.
计算机断层扫描图像中的直肠周间隙分割有助于量化前列腺放射治疗过程中健康组织接受的辐射剂量以及毒性。通过组织体积归一化的辐射剂量有助于预测放射治疗的结果或可能的有害副作用。直肠周间隙的手动分割在存在患者间解剖变异的情况下既耗时又具有挑战性，并且可能存在观察者间和观察者内的变异性。然而，由于患者间解剖变异、对比度变异和成像伪影，CT图像中直肠周间隙的自动或半自动分割是一项具有挑战性的任务。在此提出的模型中，通过基于多图谱的分割方法获得感兴趣体积。采用基于高斯混合模型聚类方法在感兴趣体积中进行无监督学习，以实现直肠周间隙的软分割。通过在概率域中对多图谱掩码进行刚性配准，进一步细化软聚类的概率。采用最大后验方法从细化概率中实现二元分割。在一个包含临床试验数据集子集的留一患者验证框架中，平均体积相似性值达到97%，平均表面差异为3.06±0.51mm。定性结果表明，与真实情况相比，直肠周间隙体积的近似效果良好。
