Department of Oncology, University of Turin, Turin, Italy.
Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy.
Phys Med. 2023 Sep;113:102657. doi: 10.1016/j.ejmp.2023.102657. Epub 2023 Aug 9.
Different methods are available to identify haematopoietically active bone marrow (ActBM). However, their use can be challenging for radiotherapy routine treatments, since they require specific equipment and dedicated time. A machine learning (ML) approach, based on radiomic features as inputs to three different classifiers, was applied to computed tomography (CT) images to identify haematopoietically active bone marrow in anal cancer patients.
A total of 40 patients was assigned to the construction set (training set + test set). Fluorine-18-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) images were used to detect the active part of the pelvic bone marrow (ActPBM) and stored as ground-truth for three subregions: iliac, lower pelvis and lumbosacral bone marrow (ActIBM, ActLPBM, ActLSBM). Three parameters were used for the correspondence analyses between FDG-PET and ML classifiers: DICE index, Precision and Recall.
For the 40-patient cohort, median values [min; max] of the Dice index were 0.69 [0.20; 0.84], 0.76 [0.25; 0.89], and 0.36 [0.15; 0.67] for ActIBM, ActLSBM, and ActLPBM, respectively. The Precision/Recall (P/R) ratio median value for the ActLPBM structure was 0.59 [0.20; 1.84] (over segmentation), while for the other two subregions the P/R ratio median has values of 1.249 [0.43; 4.15] for ActIBM and 1.093 [0.24; 1.91] for ActLSBM (under segmentation).
A satisfactory degree of overlap compared to FDG-PET was found for 2 out of the 3 subregions within pelvic bones. Further optimization and generalization of the process is required before clinical implementation.
有多种方法可用于识别造血活跃的骨髓（ActBM）。然而，由于它们需要特定的设备和专用的时间，对于放射治疗常规治疗来说，它们的使用可能具有挑战性。本研究应用机器学习（ML）方法，基于放射组学特征作为三个不同分类器的输入，来识别肛门癌患者的造血活跃骨髓。
总共 40 名患者被分配到构建集（训练集+测试集）中。氟-18-氟代脱氧葡萄糖正电子发射断层扫描（FDG-PET）图像用于检测骨盆骨髓的活跃部分，并作为ground-truth 存储在三个亚区：髂骨、下骨盆和腰骶骨骨髓（ActIBM、ActLPBM、ActLSBM）中。使用 DICE 指数、精确度和召回率三个参数进行 FDG-PET 和 ML 分类器之间的对应分析。
对于 40 名患者队列，DICE 指数的中位数[最小值；最大值]分别为 0.69 [0.20；0.84]、0.76 [0.25；0.89]和 0.36 [0.15；0.67]，用于 ActIBM、ActLSBM 和 ActLPBM。ActLPBM 结构的 Precision/Recall（P/R）比值中位数为 0.59 [0.20；1.84]（过度分割），而对于其他两个亚区，P/R 比值中位数值分别为 0.43；4.15]用于 ActIBM 和 0.24；1.91]用于 ActLSBM（欠分割）。
在骨盆内的 3 个亚区中的 2 个中，与 FDG-PET 相比，发现了较高的重叠程度。在临床实施之前，需要进一步优化和推广该过程。
