Artificial Intelligence-Guided Prediction of Dental Doses Before Planning of Radiation Therapy for Oropharyngeal Cancer: Technical Development and Initial Feasibility of Implementation.

Purpose: The aim was to develop a novel artificial intelligence (AI)-guided clinical decision support system, to predict radiation doses to subsites of the mandible using diagnostic computed tomography scans acquired before any planning of head and neck radiation therapy (RT). Methods and Materials: A dose classifier was trained using RT plans from 86 patients with oropharyngeal cancer; the test set consisted of an additional 20 plans. The classifier was trained to predict whether mandible subsites would receive a mean dose >50 Gy. The AI predictions were prospectively evaluated and compared with those of a specialist head and neck radiation oncologist for 9 patients. Positive predictive value (PPV), negative predictive value (NPV), Pearson correlation coefficient, and Lin concordance correlation coefficient were calculated to compare the AI predictions to those of the physician. Results: In the test data set, the AI predictions had a PPV of 0.95 and NPV of 0.88. For 9 patients evaluated prospectively, there was a strong correlation between the predictions of the AI algorithm and physician (P = .72, P < .001). Comparing the AI algorithm versus the physician, the PPVs were 0.82 versus 0.25, and the NPVs were 0.94 versus 1.0, respectively. Concordance between physician estimates and final planned doses was 0.62; this was 0.71 between AI-based estimates and final planned doses. Conclusion: AI-guided decision support increased precision and accuracy of pre-RT dental dose estimates.

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.

Spatially-resolved hydraulic conductivity estimation via poroelastic magnetic resonance elastography.

Poroelastic magnetic resonance elastography is an imaging technique that could recover mechanical and hydrodynamical material properties of in vivo tissue. To date, mechanical properties have been estimated while hydrodynamical parameters have been assumed homogeneous with literature-based values. Estimating spatially-varying hydraulic conductivity would likely improve model accuracy and provide new image information related to a tissue's interstitial fluid compartment. A poroelastic model was reformulated to recover hydraulic conductivity with more appropriate fluid-flow boundary conditions. Simulated and physical experiments were conducted to evaluate the accuracy and stability of the inversion algorithm. Simulations were accurate (property errors were < 2%) even in the presence of Gaussian measurement noise up to 3%. The reformulated model significantly decreased variation in the shear modulus estimate (p << 0.001) and eliminated the homogeneity assumption and the need to assign hydraulic conductivity values from literature. Material property contrast was recovered experimentally in three different tofu phantoms and the accuracy was improved through soft-prior regularization. A frequency-dependence in hydraulic conductivity contrast was observed suggesting that fluid-solid interactions may be more prominent at low frequency. In vivo recovery of both structural and hydrodynamical characteristics of tissue could improve detection and diagnosis of neurological disorders such as hydrocephalus and brain tumors.

Silicone breast phantoms for elastographic imaging evaluation.

PURPOSE: Breast cancer is a major public health issue for women, and early detection significantly increases survival rate. Currently, there is increased research interest in elastographic soft-tissue imaging techniques based on the correlation between pathology and mechanical stiffness. Anthropomorphic breast phantoms are critical for ex vivo validation of emerging elastographic technologies. This research develops heterogeneous breast phantoms for use in testing elastographic imaging modalities. METHODS: Mechanical property estimation of eight different elastomers is performed to determine storage moduli (E') and damping ratios (ζ) using a dynamic mechanical analyzer. Dynamic compression testing was carried out isothermally at room temperature over a range of 4-50 Hz. Silicone compositions with physiologically realistic storage modulus were chosen for mimicking skin adipose, cancerous tumors, and pectoral muscles and 13 anthropomorphic breast phantoms were constructed for ex vivo trials of digital image elastotomography (DIET) breast cancer screening system. A simpler fabrication was used to assess the possibility of multiple tumor detection using magnetic resonance elastography (MRE). RESULTS: Silicone materials with ranges of storage moduli (E') from 2 to 570 kPa and damping ratios (ζ) from 0.03 to 0.56 were identified. The resulting phantoms were tested in two different elastographic breast cancer diagnostic modalities. A significant contrast was successfully identified between healthy tissues and cancerous tumors both in MRE and DIET. CONCLUSIONS: The phantoms presented promise aid to researchers in elastographic imaging modalities for breast cancer detection and provide a foundation for silicone based phantom materials for mimicking soft tissues of other human organs.