Association between Artificial Intelligence-Derived Tumor Volume and Oncologic Outcomes for Localized Prostate Cancer Treated with Radiation Therapy

PURPOSE/OBJECTIVE(S)

Although clinical features of multi-parametric magnetic resonance imaging (mpMRI) have been associated with biochemical recurrence in localized prostate cancer, such features are subject to inter-observer variability. We evaluated whether the volume of the dominant intraprostatic lesion (DIL), as provided by a deep learning segmentation algorithm, could provide prognostic information for patients treated with definitive radiation therapy (RT).

MATERIALS/METHODS

We conducted a retrospective study of 438 patients with localized prostate cancer who underwent an endorectal coil, high B-value, 3-Tesla mpMRI and were treated with definitive RT at our institution between 2010 and 2017. We utilized the publicly available nnUNet to train a segmentation model which was used to identify the DIL. We examined the association between the artificial intelligence (AI)-generated DIL volume and oncologic outcomes, including biochemical recurrence and metastasis risk, using cause-specific Cox regression and time-dependent receiver operating characteristic analysis.

RESULTS

The AI model identified DILs with an area under the receiver operating characteristic (AUROC) of 0.827 at the patient level. For the 233 patients with available PI-RADS scores, with a median follow-up of 5.6 years, there were 28 biochemical failures. AI-defined DIL volume was significantly associated with biochemical failure (adjusted hazard ratio 1.60, 95% confidence interval 1.14-2.24, p = 0.007) after adjustment for PI-RADS score. Among all 438 patients with a median follow-up of 6.9 years, there were 49 biochemical failures and 22 metastases. The AUROC for predicting 7-year biochemical failure for AI volume (0.790) was similar to that for National Comprehensive Cancer Network (NCCN) category (p = 0.17). The AUROC for predicting 7-year metastasis for AI volume trended towards being higher compared to NCCN category (0.854 vs 0.769, p = 0.06).

CONCLUSION

An AI algorithm using deep learning could identify the DIL with good performance. AI-defined DIL volume may be able to provide prognostic information independent of the NCCN risk group or other radiologic factors for patients with localized prostate cancer treated with RT.

Theranostic Nanoparticle Uptake in Patient Brain Tumors as Quantified by MP2RAGE T1 Mapping

PURPOSE/OBJECTIVE(S)

Modern radiation therapy techniques provide effective treatments for solid tumors, but there remain challenges with delivering high doses to elusive tumors without causing toxicity to surrounding normal tissue. Pre-clinical trials have demonstrated the theranostic properties of a recently developed gadolinium-based nanoparticle (Gd-NP). The first in-human clinical trial was conducted to assess the safety and dose tolerance of intravenous Gd-NPs in combination with whole brain radiotherapy and showed favorable results, including a significant correlation between tumor uptake and therapeutic response. The second, double-blinded, in-human clinical trial is underway in the US and aims to evaluate if brain-directed stereotactic radiation in conjunction with NPs will improve local tumor control compared to radiation alone. The current work investigates uptake patterns in brain tumors of 23 patients as quantified by magnetization prepared 2 rapid gradient echo (MP2RAGE) T1 mapping.

MATERIALS/METHODS

A phantom containing eight vials of NP-saline solutions at varying concentrations was created to examine the relationship between NP concentration and longitudinal relaxation (T1, in seconds). This relationship is known as relaxivity and is dependent on the contrast agent, field strength and T1 mapping sequence. A 3T MAGNETOM Vida scanner and MP2RAGE sequence were used to image the phantom and MP2RAGE T1 maps were calculated using Bloch equations (QMRLab software). Relaxivity was determined and applied to 23 patient T1 maps (pre- and post- Gd-NP administration) to calculate uptake on an individual tumor basis. Theranostic NP uptake was calculated for every voxel in each of 129 brain metastases and examined for patterns in quantity and distribution.

RESULTS

Average individual tumor uptake ranged from 0.02-0.12 mg/ml, where average overall uptake was equal to 0.05 mg/ml. A relationship between tumor diameter and mean NP concentration was observed and best represented by a power-based curve (R2 = 0.92). In contrast, patients with suspected placebo administration appeared to have no uptake and therefore no relationship with tumor diameter. The distribution of NP concentration within the tumor was also examined; on average, linear uptake profiles through tumor centroids (ant-post, left-right) demonstrated roughly gaussian patterns of uptake with lower concentrations at the tumor edges and higher concentrations at the tumor center. This pattern indicates robust tumor penetration and may have implications for amplifying radiation dose to hypoxic tumors.

CONCLUSION

Gd-NP uptake in brain metastases can be quantified using MP2RAGE T1 mapping. Uptake was determined for each voxel in each tumor volume, where a gaussian pattern of spatial concentrations was observed. This analysis procedure will be applied to the full data set, when available, to evaluate the impact of NP uptake (in conjunction with radiation therapy) within individual patients and individual tumors.

Technical Note: Preferred dosimeter size and associated correction factors in commissioning high dose per pulse, flattening filter free x-ray beams

PURPOSE

High dose rate flattening filter free (FFF) beams pose new challenges and considerations for accurate reference and relative dosimetry. The authors report errors associated with commonly used ion chambers and introduce simple methods to mitigate them.

METHODS

Dosimetric errors due to (1) ion recombination effects of high dose per pulse (DPP) FFF beams and (2) volume-averaging effects of the radial profile were examined on a TrueBeam STx. Four commonly used cylindrical ion chambers spanning a range of lengths (0.29-2.3 cm) and volumes (0.016-0.6 cm(3)) were used to determine the magnitude of these effects for 6 and 10 MV unflattened x-ray beams (6XFFF and 10XFFF, respectively). Two methods were used to determine the magnitude of ion collection efficiency: (1) direct measurement of the percent depth dose (PDD) for the clinical, high DPP beam in comparison to that obtained after reducing the DPP and (2) measurement of Pion as a function of depth. Two methods were used to quantify the magnitude of volume-averaging: (1) direct measurement of volume-averaging via cross-calibration and (2) calculation of volume-averaging from radial profiles of the beam. Finally, a simple analytical expression for the radial profile volume-averaging correction factor, Prp = [OAR(0.29L)](-1), or the inverse of the off-axis ratio of dose at 0.29L, where L is the length of the chamber's sensitive volume, is introduced to mitigate the volume-averaging effect in Farmer-type chambers.

RESULTS

Errors in measured PDD for the clinical beams were 1.3% ± 0.07% and 1.6% ± 0.07% at 35 cm depth for the 6XFFF and 10XFFF beam, respectively, using an IBA CC13 ion chamber, due to charge recombination with a high DPP. Volume-averaging effects were 0.4% and 0.7% for the 6XFFF and 10XFFF beam, respectively, when measured with a Farmer-type chamber. For the application of TG-51, these errors combine when using a CC13 to measure the PDD and a Farmer for absolute output dosimetry for a total error of up to 2% at dmax for the 10XFFF beam.

CONCLUSIONS

Relative and absolute dosimetry in high DPP, unflattened x-ray beams of 10 MV or higher requires corrections for charge recombination and/or volume-averaging when dosimeters with certain geometries are used. Chambers used for PDD measurement are available that do not require a correction for charge recombination. A simple analytical expression of the correction factor Prp was introduced in this work to account for volume-averaging effects in Farmer chambers. Choice of an appropriate dosimeter coupled with application of the established correction factors Pion and Prp reduces the uncertainty in the PDD measurement and the reference dose measurement.

Turning off artistic ability: the influence of left DBS in art production

BACKGROUND

The influence of Parkinson's disease (PD) as well as deep brain stimulation (DBS) on visual-artistic production of people who have been artists is unclear. We systematically assessed the artistic-creative productions of a patient with PD who was referred to us for management of a left subthalamic region (STN) DBS. The patient was an artist before her disease started, permitting us to analyze changes in her artistic-creative production over the course of the illness and during her treatment with DBS.

METHODS

We collected her paintings from four time periods: Time 1 (Early Pre-Presymptomatic), Time 2 (Later Presymptomatic), Time 3 (Symptomatic), and Time 4 (DBS Symptomatic). A total of 59 paintings were submitted to a panel of judges, who rated the paintings on 6 different artistic qualities including: aesthetics, closure, evocative impact, novelty, representation, technique.

RESULTS

Aesthetics and evocative impact significantly declined from Time 2 to Time 4. Representation and technique indicated a curvilinear relationship, with initial improvement from Time 1 to Time 2 followed by a decline from Time 2 to Time 4.

CONCLUSIONS

These results suggest that left STN/SNR-DBS impacted artistic performances in our patient. The reason for these alterations is not known, but it might be that alterations of left hemisphere functions induce a hemispheric bias reducing the influence the right hemisphere which is important for artistic creativity. The left hemisphere itself plays a critical role in artistic creativity and DBS might have altered left hemisphere functions or altered the mesolimbic system which might have also influenced creativity. Future studies will be required to learn how PD and DBS influence creativity.