Medical Imaging Biomarker Discovery and Integration Towards AI-Based Personalized Radiotherapy

Intensity-modulated radiation therapy (IMRT) has been used for high-accurate physical dose distribution sculpture and employed to modulate different dose levels into Gross Tumor Volume (GTV), Clinical Target Volume (CTV) and Planning Target Volume (PTV). GTV, CTV and PTV can be prescribed at different dose levels, however, there is an emphasis that their dose distributions need to be uniform, despite the fact that most types of tumour are heterogeneous. With traditional radiomics and artificial intelligence (AI) techniques, we can identify biological target volume from functional images against conventional GTV derived from anatomical imaging. Functional imaging, such as multi parameter MRI and PET can be used to implement dose painting, which allows us to achieve dose escalation by increasing doses in certain areas that are therapy-resistant in the GTV and reducing doses in less aggressive areas. In this review, we firstly discuss several quantitative functional imaging techniques including PET-CT and multi-parameter MRI. Furthermore, theoretical and experimental comparisons for dose painting by contours (DPBC) and dose painting by numbers (DPBN), along with outcome analysis after dose painting are provided. The state-of-the-art AI-based biomarker diagnosis techniques is reviewed. Finally, we conclude major challenges and future directions in AI-based biomarkers to improve cancer diagnosis and radiotherapy treatment.

A Study of Dose Painting Radiotherapy Guided by Three-Dimensional Arterial Spin labeling Perfusion Magnetic Resonance Imaging for Non-Enhancing Low-Grade Gliomas

Background: The purpose of this study was to investigate the feasibility and dosimetric characteristics of dose painting for non-enhancing low-grade gliomas (NE-LGGs) guided by three-dimensional arterial spin labeling (3D-ASL) perfusion magnetic resonance imaging.Methods: Eighteen patients with NE-LGGs were enrolled. 3D-ASL, T2 fluid attenuated inversion recovery (T2 FLAIR) and contrast-enhanced T1-weight magnetic resonance images were obtained. The gross tumor volume (GTV) was delineated on the T2 FLAIR. The hyper-perfusion region of the GTV (GTV-ASL) was determined by 3D-ASL, and the GTV-SUB was obtained by subtracting the GTV-ASL from the GTV. The planning target volume (PTV), PTV-ASL and PTV-SUB were developed by expanding the external margins of the GTV, GTV-ASL and GTV-SUB, respectively. Three plans were established for each patient: in plan 1, the traditional homogeneous prescription dose to the PTV was 45-60 Gy; in plan 2 and plan 3, the dose to the PTV-ASL increased by 10-20% based on plan 1, without the maximum dose constraint to the PTV-ASL in plan 3. The dosimetric differences among the three plans were compared.Results: Compared with plan 1, the dose to 2% (D2%), 98% (D98%) and 50% (Dmean) of PTV-ASL volumes increased by 14.67%, 16.17% and 14.31% in plan 2 and 19.84%, 15.52% and 14.27% in plan 3, respectively (P < 0.05); the D2% of the PTV, PTV-SUB increased by 11.89% and 8.34% in plan 2, 15.89% and 8.49% in plan 3, respectively (P< 0.05). The PTV coverages were comparable among the three plans (P > 0.05). In Plan 2 and plan 3, the conformity indexs decreased by 18.60% and 12.79%; while the homogeneity indexs increased by 1.43 and 2 times (P<0.05). Compared with plan 1, the D0.1cc of brain stem and Dmax of optic chiasma slightly increased in plan 2 and plan 3, but the absolute doses met the dose constraint. The other organs at risk were similar among the three plans (P > 0.05).Conclusions: The sub-volume with hyper-perfusion for NE-LGG radiotherapy can be segmented based on the perfusion difference guided by 3D-ASL. And the radiation dose to the hyper-perfusion area increased safely by 10-20% through dose painting.

The feasibility of a dose painting procedure to treat prostate cancer based on mpMR images and hierarchical clustering

Background We aimed to assess the feasibility of a dose painting (DP) procedure, known as simultaneous integrated boost intensity modulated radiation Therapy (SIB-IMRT), for treating prostate cancer with dominant intraprostatic lesions (DILs) based on multi-parametric magnetic resonance (mpMR) images and hierarchical clustering with a machine learning technique. Methods The mpMR images of 120 patients were used to create hierarchical clustering and draw a dendrogram. Three clusters were selected for performing agglomerative clustering. Then, the DIL acquired from the mpMR images of 20 patients were categorized into three groups to have them treated with a DP procedure being composed of three planning target volumes (PTVs) determined as PTV1, PTV2, and PTV3 in treatment plans. The DP procedure was carried out on the patients wherein a total dose of 80, 85 and 91 Gy were delivered to the PTV1, PTV2, and PTV3, respectively. Dosimetric and radiobiologic parameters [Tumor Control Probability (TCP) and Normal Tissue Complication Probability (NTCP)] of the DP procedure were compared with those of the conventional IMRT and Three-Dimensional Conformal Radiation Therapy (3DCRT) procedures carried out on another group of 20 patients. A post-treatment follow-up was also made four months after the radiotherapy procedures. Results All the dosimetric variables and the NTCPs of the organs at risks (OARs) revealed no significant difference between the DP and IMRT procedures. Regarding the TCP of three investigated PTVs, significant differences were observed between the DP versus IMRT and also DP versus 3DCRT procedures. At post-treatment follow-up, the DIL volumes and apparent diffusion coefficient (ADC) values in the DP group differed significantly (p-value < 0.001) from those of the IMRT. However, the whole prostate ADC and prostate-specific antigen (PSA) indicated no significant difference (p-value > 0.05) between the DP versus IMRT. Conclusions The results of this comprehensive clinical trial illustrated the feasibility of our DP procedure for treating prostate cancer based on mpMR images validated with acquired patients’ dosimetric and radiobiologic assessment and their follow-ups. This study confirms significant potential of the proposed DP procedure as a promising treatment planning to achieve effective dose escalation and treatment for prostate cancer. Trial registration: IRCT20181006041257N1; Iranian Registry of Clinical Trials, Registered: 23 October 2019, https://en.irct.ir/trial/34305.

Prognostic Relevance of 18F-FDG-PET/CT-Guided Target Volume Delineation in Loco-Regionally Advanced Nasopharyngeal Carcinomas: A Comparative Study

IntroductionAn optimal approach to define tumor volume in locoregionally advanced nasopharyngeal carcinoma (NPC) using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) remains unclear. This retrospective study aimed at comparing the outcomes and toxicities of different FDG-PET/CT-guided techniques for primary tumor volume delineation in locoregionally advanced NPC.MethodsFrom August 2015 to February 2018, 292 patients with stage III-IVB NPC received FDG-PET/CT-guided IMRT. Three PET/CT-based techniques were used to determine the gross tumor volume (GTV) as follows: visual criteria (group A; n = 98), a standard uptake value (SUV) threshold of 2.5 (group B; n = 95), and a threshold of 50% maximal intensity (group C, n = 99) combined with a dose-painting technique.ResultsIn groups A, B, and C, the 5-year LRFS rates were 89.4%, 90.0%, and 97.8%, respectively (p = 0.043). The 5-year DMFS rates were 75.1%, 76.0%, and 87.7%, respectively (p = 0.043). The 5-year DFS rates were 70.9%, 70.3%, and 82.2%, respectively (p = 0.048). The 5-year OS rates were 73.5%, 73.9%, and 84.9%, respectively (p = 0.038). Group C showed significantly higher 5-year LRFS, LRRFS, DMFS, DFS, and OS than those in groups A and B (p &lt; 0.05). No statistically significant differences were observed between the three study groups in the cumulative incidences of grade 3-4 acute and late toxicities. Multivariate analyses showed that the PET/CT-guided technique for target volume delineation was an independent prognostic factor for 5-year LRFS, DFS, DMFS, and OS (p = 0.039, p = 0.030, p = 0.035 and p = 0.028, respectively), and was marginally significant in predicting LRRFS (p = 0.080).ConclusionsThe 50% SUVmax threshold regimen for GTV delineation with dose-painting appeared to be superior to the visual criteria or SUV2.5 threshold in locoregionally advanced NPC, and there was no increased toxicity.