Dosimetric Planning Tradeoffs to Reduce Heart Dose Using Machine Learning-Guided Decision Support Software in Patients with Lung Cancer.

PURPOSE: Cardiac toxicity is a well-recognized risk after radiation therapy (RT) in patients with non-small cell lung cancer (NSCLC). However, the extent to which treatment planning optimization can reduce mean heart dose (MHD) without untoward increases in lung dose is unknown. METHODS AND MATERIALS: Retrospective analysis of RT plans from 353 consecutive patients with locally advanced NSCLC treated with intensity modulated RT (IMRT) or 3-dimensional conformal RT. Commercially available machine learning-guided clinical decision support software was used to match RT plans. A leave-one-out predictive model was used to examine lung dosimetric tradeoffs necessary to achieve a MHD reduction. RESULTS: Of all 232 patients, 91 patients (39%) had RT plan matches showing potential MHD reductions of >4 to 8 Gy without violating the upper limit of lung dose constraints (lung volume [V] receiving 20 Gy (V20 Gy) <37%, V5 Gy <70%, and mean lung dose [MLD] <20 Gy). When switching to IMRT, 75 of 103 patients (72.8%) had plan matches demonstrating improved MHD (average 2.0 Gy reduction, P < .0001) without violating lung constraints. Examining specific lung dose tradeoffs, a mean ≥3.7 Gy MHD reduction was achieved with corresponding absolute increases in lung V20 Gy, V5 Gy, and MLD of 3.3%, 5.0%, and 1.0 Gy, respectively. CONCLUSIONS: Nearly 40% of RT plans overall, and 73% when switched to IMRT, were predicted to have reductions in MHD >4 Gy with potentially clinically acceptable tradeoffs in lung dose. These observations demonstrate that decision support software for optimizing heart-lung dosimetric tradeoffs is feasible and may identify patients who might benefit most from more advanced RT technologies.

Artificial intelligence in radiation oncology: A specialty-wide disruptive transformation?

Artificial intelligence (AI) is emerging as a technology with the power to transform established industries, and with applications from automated manufacturing to advertising and facial recognition to fully autonomous transportation. Advances in each of these domains have led some to call AI the "fourth" industrial revolution [1]. In healthcare, AI is emerging as both a productive and disruptive force across many disciplines. This is perhaps most evident in Diagnostic Radiology and Pathology, specialties largely built around the processing and complex interpretation of medical images, where the role of AI is increasingly seen as both a boon and a threat. In Radiation Oncology as well, AI seems poised to reshape the specialty in significant ways, though the impact of AI has been relatively limited at present, and may rightly seem more distant to many, given the predominantly interpersonal and complex interventional nature of the specialty. In this overview, we will explore the current state and anticipated future impact of AI on Radiation Oncology, in detail, focusing on key topics from multiple stakeholder perspectives, as well as the role our specialty may play in helping to shape the future of AI within the larger spectrum of medicine.

Clinical decision support of radiotherapy treatment planning: A data-driven machine learning strategy for patient-specific dosimetric decision making.

BACKGROUND AND PURPOSE: Clinical decision support systems are a growing class of tools with the potential to impact healthcare. This study investigates the construction of a decision support system through which clinicians can efficiently identify which previously approved historical treatment plans are achievable for a new patient to aid in selection of therapy. MATERIAL AND METHODS: Treatment data were collected for early-stage lung and postoperative oropharyngeal cancers treated using photon (lung and head and neck) and proton (head and neck) radiotherapy. Machine-learning classifiers were constructed using patient-specific feature-sets and a library of historical plans. Model accuracy was analyzed using learning curves, and historical treatment plan matching was investigated. RESULTS: Learning curves demonstrate that for these datasets, approximately 45, 60, and 30 patients are needed for a sufficiently accurate classification model for radiotherapy for early-stage lung, postoperative oropharyngeal photon, and postoperative oropharyngeal proton, respectively. The resulting classification model provides a database of previously approved treatment plans that are achievable for a new patient. An exemplary case, highlighting tradeoffs between the heart and chest wall dose while holding target dose constant in two historical plans is provided. CONCLUSIONS: We report on the first artificial-intelligence based clinical decision support system that connects patients to past discrete treatment plans in radiation oncology and demonstrate for the first time how this tool can enable clinicians to use past decisions to help inform current assessments. Clinicians can be informed of dose tradeoffs between critical structures early in the treatment process, enabling more time spent on finding the optimal course of treatment for individual patients.

Flexible radioluminescence imaging for FDG-guided surgery.

PURPOSE: Flexible radioluminescence imaging (Flex-RLI) is an optical method for imaging 18F-fluorodeoxyglucose (FDG)-avid tumors. The authors hypothesize that a gadolinium oxysulfide: terbium (GOS:Tb) flexible scintillator, which loosely conforms to the body contour, can enhance tumor signal-to-background ratio (SBR) compared with RLI, which utilizes a flat scintillator. The purpose of this paper is to characterize flex-RLI with respect to alternative modalities including RLI, beta-RLI (RLI with gamma rejection), and Cerenkov luminescence imaging (CLI). METHODS: The photon sensitivity, spatial resolution, and signal linearity of flex-RLI were characterized with in vitro phantoms. In vivo experiments utilizing 13 nude mice inoculated with the head and neck (UMSCC1-Luc) cell line were then conducted in accordance with the institutional Administrative Panel on Laboratory Animal Care. After intravenous injection of 18F-FDG, the tumor SBR values for flex-RLI were compared to those for RLI, beta-RLI, and CLI using the Wilcoxon signed rank test. RESULTS: With respect to photon sensitivity, RLI, beta-RLI, and flex-RLI produced 1216.2, 407.0, and 98.6 times more radiance per second than CLI. Respective full-width half maximum values across a 0.5 mm capillary tube were 6.9, 6.4, 2.2, and 1.5 mm, respectively. Flex-RLI demonstrated a near perfect correlation with 18F activity (r = 0.99). Signal uniformity for flex-RLI improved after more aggressive homogenization of the GOS powder with the silicone elastomer during formulation. In vivo, the SBR value for flex-RLI (median 1.29; interquartile range 1.18-1.36) was statistically greater than that for RLI (1.08; 1.02-1.14; p < 0.01) by 26%. However, there was no statistically significant difference in SBR values between flex-RLI and beta-RLI (p = 0.92). Furthermore, there was no statistically significant difference in SBR values between flex-RLI and CLI (p = 0.11) in a more limited dataset. CONCLUSIONS: Flex-RLI provides high quality images with SBRs comparable to those from CLI and beta-RLI in a single 10 s acquisition.

ß-Radioluminescence Imaging: A Comparative Evaluation with Cerenkov Luminescence Imaging.

UNLABELLED: Cerenkov luminescence imaging (CLI) can provide high-resolution images of (18)F-FDG-avid tumors but requires prolonged acquisition times because of low photon sensitivity. In this study, we proposed a new modality, termed ß-radioluminescence imaging (ß-RLI), which incorporates a scintillator with a γ-rejection strategy for imaging ß particles. We performed a comparative evaluation of ß-RLI with CLI in both in vitro and in vivo systems. METHODS: Using in vitro phantoms, we characterized the photon sensitivity and resolution of CLI and ß-RLI. We also conducted a series of in vivo experiments with xenograft mouse models using both amelanotic (A375, UMSCC1-Luc) and melanotic (B16F10-Luc) cell lines. The B16F10 and UMSCC1 cell lines were transfected with the luciferase gene (Luc). CLI was acquired over 300 s, and ß-RLI was acquired using two 10-s acquisitions. We correlated (18)F -: FDG activities, as assessed by PET, with tumor radiances for both ß-RLI and CLI. We also compared tumor signal-to-background ratios (SBRs) between these modalities for amelanotic and melanotic tumors. RESULTS: For in vitro experiments, the photon sensitivity for ß-RLI was 560-fold greater than that for CLI. However, the spatial resolution for ß-RLI (4.4 mm) was inferior to that of CLI (1.0 mm). For in vivo experiments, correlations between (18)F-FDG activity and tumor radiance were 0.52 (P < 0.01) for ß-RLI, 0.81 (P = 0.01) for amelanotic lesions with CLI, and -0.08 (negative contrast; P = 0.80) for melanotic lesions with CLI. Nine of 13 melanotic lesions had an SBR less than 1 for CLI, despite an SBR greater than 1 among all lesions for ß-RLI. CONCLUSION: ß-RLI can produce functional images of both amelanotic and melanotic tumors in a shorter time frame than CLI. Further engineering developments are needed to realize the full clinical potential of this modality.

Cerenkov luminescence endoscopy: improved molecular sensitivity with ß--emitting radiotracers.

UNLABELLED: Cerenkov luminescence endoscopy (CLE) is an optical technique that captures the Cerenkov photons emitted from highly energetic moving charged particles (ß(+) or ß(-)) and can be used to monitor the distribution of many clinically available radioactive probes. A main limitation of CLE is its limited sensitivity to small concentrations of radiotracer, especially when used with a light guide. We investigated the improvement in the sensitivity of CLE brought about by using a ß(-) radiotracer that improved Cerenkov signal due to both higher ß-particle energy and lower γ noise in the imaging optics because of the lack of positron annihilation. METHODS: The signal-to-noise ratio (SNR) of (90)Y was compared with that of (18)F in both phantoms and small-animal tumor models. Sensitivity and noise characteristics were demonstrated using vials of activity both at the surface and beneath 1 cm of tissue. Rodent U87MG glioma xenograft models were imaged with radiotracers bound to arginine-glycine-aspartate (RGD) peptides to determine the SNR. RESULTS: γ noise from (18)F was demonstrated by both an observed blurring across the field of view and a more pronounced fall-off with distance. A decreased γ background and increased energy of the ß particles resulted in a 207-fold improvement in the sensitivity of (90)Y compared with (18)F in phantoms. (90)Y-bound RGD peptide produced a higher tumor-to-background SNR than (18)F in a mouse model. CONCLUSION: The use of (90)Y for Cerenkov endoscopic imaging enabled superior results compared with an (18)F radiotracer.

Radioluminescence microscopy: measuring the heterogeneous uptake of radiotracers in single living cells.

Radiotracers play an important role in interrogating molecular processes both in vitro and in vivo. However, current methods are limited to measuring average radiotracer uptake in large cell populations and, as a result, lack the ability to quantify cell-to-cell variations. Here we apply a new technique, termed radioluminescence microscopy, to visualize radiotracer uptake in single living cells, in a standard fluorescence microscopy environment. In this technique, live cells are cultured sparsely on a thin scintillator plate and incubated with a radiotracer. Light produced following beta decay is measured using a highly sensitive microscope. Radioluminescence microscopy revealed strong heterogeneity in the uptake of [(18)F]fluoro-deoxyglucose (FDG) in single cells, which was found consistent with fluorescence imaging of a glucose analog. We also verified that dynamic uptake of FDG in single cells followed the standard two-tissue compartmental model. Last, we transfected cells with a fusion PET/fluorescence reporter gene and found that uptake of FHBG (a PET radiotracer for transgene expression) coincided with expression of the fluorescent protein. Together, these results indicate that radioluminescence microscopy can visualize radiotracer uptake with single-cell resolution, which may find a use in the precise characterization of radiotracers.

Intraoperative imaging of tumors using Cerenkov luminescence endoscopy: a feasibility experimental study.

UNLABELLED: Cerenkov luminescence imaging (CLI) is an emerging new molecular imaging modality that is relatively inexpensive, easy to use, and has high throughput. CLI can image clinically available PET and SPECT probes using optical instrumentation. Cerenkov luminescence endoscopy (CLE) is one of the most intriguing applications that promise potential clinical translation. We developed a prototype customized fiberscopic Cerenkov imaging system to investigate the potential in guiding minimally invasive surgical resection. METHODS: All experiments were performed in a dark chamber. Cerenkov luminescence from (18)F-FDG samples containing decaying radioactivity was transmitted through an optical fiber bundle and imaged by an intensified charge-coupled device camera. Phantoms filled with (18)F-FDG were used to assess the imaging spatial resolution. Finally, mice bearing subcutaneous C6 glioma cells were injected intravenously with (18)F-FDG to determine the feasibility of in vivo imaging. The tumor tissues were exposed, and CLI was performed on the mouse before and after surgical removal of the tumor using the fiber-based imaging system and compared with a commercial optical imaging system. RESULTS: The sensitivity of this particular setup was approximately 45 kBq (1.21 µCi)/300 µL. The 3 smallest sets of cylindric holes in a commercial SPECT phantom were identifiable via this system, demonstrating that the system has a resolution better than 1.2 mm. Finally, the in vivo tumor imaging study demonstrated the feasibility of using CLI to guide the resection of tumor tissues. CONCLUSION: This proof-of-concept study explored the feasibility of using fiber-based CLE for the detection of tumor tissue in vivo for guided surgery. With further improvements of the imaging sensitivity and spatial resolution of the current system, CLE may have a significant application in the clinical setting in the near future.

Radioluminescent nanophosphors enable multiplexed small-animal imaging.

We demonstrate the ability to image multiple nanoparticle-based contrast agents simultaneously using a nanophosphor platform excited by either radiopharmaceutical or X-ray irradiation. These radioluminescent nanoparticles emit optical light at unique wavelengths depending on their lanthanide dopant, enabling multiplexed imaging. This study demonstrates the separation of two distinct nanophosphor contrast agents in gelatin phantoms with a recovered phosphor separation correlation of -0.98. The ability to distinguish the two nanophosphors and a Cerenkov component is then demonstrated in a small animal phantom. Combined with the high-resolution potential of low-scattering X-ray excitation, this imaging technique may be a promising method to probe molecular processes in living organisms.

MR water quantitative priors improves the accuracy of optical breast imaging.

Magnetic resonance (MR) guided optical breast imaging is a promising modality to improve the specificity of breast imaging, because it provides high-resolution quantitative maps of total hemoglobin, oxygen saturation, water content, and optical scattering. These properties have been shown to distinguish malignant from benign lesions. However, the optical detection hardware required for deep tissue imaging has poor spectral sensitivity which limits accurate water quantification; this reduces the accuracy of hemoglobin quantification. We present a methodology to improve optical quantification by utilizing the ability of Dixon MR imaging to quantitatively estimate water and fat; this technique effectively reduces optical crosstalk between water and oxyhemoglobin. The techniques described in this paper reduce hemoglobin quantification error by as much as 38%, as shown in a numerical phantom, and an experimental phantom. Error is reduced by as much 20% when imperfect MR water quantification is given. These techniques may also increase contrast between diseased and normal tissue, as shown in breast tissue in vivo. It is also shown that using these techniques may permit fewer wavelengths to be used with similar quantitative accuracy, enabling higher temporal resolution. In addition, it is shown that these techniques can improve the ability of MRI to quantify water in the presence of bias in the Dixon water/fat separation.

Tomographic molecular imaging of x-ray-excitable nanoparticles.

X-ray luminescence computed tomography (XLCT) is proposed as a new dual molecular/anatomical imaging modality. XLCT is based on the selective excitation and optical detection of x-ray-excitable nanoparticles. As a proof of concept, we built a prototype XLCT system and imaged near-IR-emitting Gd(2)O(2)S:Eu phosphors in various phantoms. Imaging in an optically diffusive medium shows that imaging performance is not affected by optical scatter; furthermore, the linear response of the reconstructed images suggests that XLCT is capable of quantitative imaging.

Inspired gas-induced vascular change in tumors with magnetic-resonance-guided near-infrared imaging: human breast pilot study.

This study investigates differences in the response of breast tumor tissue versus healthy fibroglandular tissue to inspired gases. Cycles of carbogen and oxygen gas are administered while measuring the changes with magnetic-resonance-guided near-infrared imaging in a pilot study of breast cancers. For two patients, analyses are performed with cross-correlation techniques, which measure the strength of hemodynamic modulation. The results show that the overall vasoresponse, indicated by total hemoglobin, of healthy tissue has approximately a 72% and 41% greater correlation to the gas stimulus than the tumor region, in two patients respectively, when background physiological changes are controlled. These data support the hypothesis that tumor vasculature has a poorly functioning vasodilatory mechanism, most likely caused by dysfunctional smooth muscle cells lining the vasculature. This study presents a methodology to quantitatively analyze inspired gas changes in human breast tumors, and demonstrates this technique in a pilot patient population.

X-ray luminescence computed tomography via selective excitation: a feasibility study.

X-ray luminescence computed tomography (XLCT) is proposed as a new molecular imaging modality based on the selective excitation and optical detection of X-ray-excitable phosphor nanoparticles. These nano-sized particles can be fabricated to emit near-infrared (NIR) light when excited with X-rays, and, because because both X-rays and NIR photons propagate long distances in tissue, they are particularly well suited for in vivo biomedical imaging. In XLCT, tomographic images are generated by irradiating the subject using a sequence of programmed X-ray beams, while sensitive photo-detectors measure the light diffusing out of the subject. By restricting the X-ray excitation to a single, narrow beam of radiation, the origin of the optical photons can be inferred regardless of where these photons were detected, and how many times they scattered in tissue. This study presents computer simulations exploring the feasibility of imaging small objects with XLCT, such as research animals. The accumulation of 50 nm phosphor nanoparticles in a 2-mm-diameter target can be detected and quantified with subpicomolar sensitivity using less than 1 cGy of radiation dose. Provided sufficient signal-to-noise ratio, the spatial resolution of the system can be made as high as needed by narrowing the beam aperture. In particular, 1 mm spatial resolution was achieved for a 1-mm-wide X-ray beam. By including an X-ray detector in the system, anatomical imaging is performed simultaneously with molecular imaging via standard X-ray computed tomography (CT). The molecular and anatomical images are spatially and temporally co-registered, and, if a single-pixel X-ray detector is used, they have matching spatial resolution.

Image guided near-infrared spectroscopy of breast tissue in vivo using boundary element method.

We demonstrate quantitative functional imaging using image-guided near-infrared spectroscopy (IG-NIRS) implemented with the boundary element method (BEM) for reconstructing 3-D optical property estimates in breast tissue in vivo. A multimodality MRI-NIR system was used to collect measurements of light reflectance from breast tissue. The BEM was used to model light propagation in 3-D based only on surface discretization in order to reconstruct quantitative values of total hemoglobin (HbT), oxygen saturation, water, and scatter. The technique was validated in experimental measurements from heterogeneous breast-shaped phantoms with known values and applied to a total of seven subjects comprising six healthy individuals and one participant with cancer imaged at two time points during neoadjuvant chemotherapy. Using experimental measurements from a heterogeneous breast phantom, BEM for IG-NIRS produced accurate values for HbT in the inclusion with a <3% error. Healthy breast tissues showed higher HbT and water in fibroglandular tissue than in adipose tissue. In a subject with cancer, the tumor showed higher HbT compared to the background. HbT in the tumor was reduced by 9 µM during treatment. We conclude that 3-D MRI-NIRS with BEM provides quantitative and functional characterization of breast tissue in vivo through measurement of hemoglobin content. The method provides potentially complementary information to DCE-MRI for tumor characterization.

Evaluation of breast tumor response to neoadjuvant chemotherapy with tomographic diffuse optical spectroscopy: case studies of tumor region-of-interest changes.

PURPOSE: To evaluate two methods of summarizing tomographic diffuse optical spectroscopic (DOS) data through region-of-interest (ROI) analysis to differentiate complete from incomplete responses in patients with locally advanced breast cancer undergoing neoadjuvant treatment and to estimate the standard deviations of these methods for power analysis of larger study designs in the future. MATERIALS AND METHODS: Subjects participating in the HIPAA-compliant imaging study, approved by the institutional review board, provided written informed consent and were compensated for their examination participation. Seven of 16 cases in women with complete study data were analyzed by using both fixed- and variable-size (full-width-at-half-maximum) ROI measures of the DOS total hemoglobin concentration (Hb(T)), blood oxygen saturation, water fraction, optical scattering amplitude, and scattering power in the ipsilateral and contralateral breasts. Postsurgical histopathologic analysis was used to categorize patients as having a complete or incomplete treatment response. RESULTS: Average normalized change in Hb(T) was the only DOS parameter to show significant differences (P < or = .05) in the pathologic complete response (pCR) and pathologic incomplete response (pIR) outcomes in seven patients. Mean values of the changes for fixed-size ROIs were -64.2% +/- 50.8 (standard deviation) and 16.9% +/- 38.2 for the pCR and pIR groups, respectively, and those for variable-size ROIs were -96.7% +/- 91.8, and 14.1% +/- 26.7 for the pCR and pIR groups, respectively. CONCLUSION: Tomographic DOS may provide findings predictive of therapeutic response, which could lead to superior individualized patient treatment. SUPPLEMENTAL MATERIAL: http://radiology.rsnajnls.org/cgi/content/full/2522081202/DC1.

Methodology development for three-dimensional MR-guided near infrared spectroscopy of breast tumors.

Combined Magnetic Resonance (MR) and Near Infrared Spectroscopy (NIRS) has been proposed as a unique method to quantify hemodynamics, water content, and cellular size and packing density of breast tumors, as these tissue constituents can be quantified with increased resolution and overlaid on the structural features identified by the MR. However, the choices in how to reconstruct and visualize this information can have a dramatic impact on the feasibility of implementing this modality in the clinic. This is especially true in 3 dimensions, as there is often limited optical sampling of the breast tissue, and methods need to accurately reflect the tissue composition. In this paper, the implementation and display of fully 3D MR image-guided NIRS is outlined and demonstrated using in vivo data from three healthy women and a volunteer undergoing neoadjuvant chemotherapy. Additionally, a display feature presented here scales the transparency of the optical images to the sensitivity of the measurements, providing a logical way to incorporate partial volume sets of optical images onto the MR volume. These concepts are demonstrated with 3D data sets using Volview software online.

Near infrared optical tomography using NIRFAST: Algorithm for numerical model and image reconstruction.

Diffuse optical tomography, also known as near infrared tomography, has been under investigation, for non-invasive functional imaging of tissue, specifically for the detection and characterization of breast cancer or other soft tissue lesions. Much work has been carried out for accurate modeling and image reconstruction from clinical data. NIRFAST, a modeling and image reconstruction package has been developed, which is capable of single wavelength and multi-wavelength optical or functional imaging from measured data. The theory behind the modeling techniques as well as the image reconstruction algorithms is presented here, and 2D and 3D examples are presented to demonstrate its capabilities. The results show that 3D modeling can be combined with measured data from multiple wavelengths to reconstruct chromophore concentrations within the tissue. Additionally it is possible to recover scattering spectra, resulting from the dominant Mie-type scatter present in tissue. Overall, this paper gives a comprehensive over view of the modeling techniques used in diffuse optical tomographic imaging, in the context of NIRFAST software package.