Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning.

Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

Virtual Bronchoscopy-Guided Treatment Planning to Map and Mitigate Radiation-Induced Airway Injury in Lung SAbR.

PURPOSE: Radiation injury to the bronchial tree is an important yet poorly understood potential side effect in lung stereotactic ablative radiation therapy (SAbR). We investigate the integration of virtual bronchoscopy in radiation therapy planning to quantify dosage to individual airways. We develop a risk model of airway collapse and develop treatment plans that reduce the risk of radiation-induced airway injury. METHODS AND MATERIALS: Pre- and post-SAbR diagnostic-quality computerized tomography (CT) scans were retrospectively collected from 26 lung cancer patients. From each scan, the bronchial tree was segmented using a virtual bronchoscopy system and registered deformably to the planning CT. Univariate and stepwise multivariate Cox regressions were performed, examining factors such as age, comorbidities, smoking pack years, airway diameter, and maximum point dosage (Dmax). Logistic regression was utilized to formulate a risk function of segmental collapse based on Dmax and diameter. The risk function was incorporated into the objective function along with clinical dosage volume constraints for planning target volume (PTV) and organs at risk (OARs). RESULTS: Univariate analysis showed that segmental diameter (P = .014) and Dmax (P = .007) were significantly correlated with airway segment collapse. Multivariate stepwise Cox regression showed that diameter (P = .015), Dmax (P < .0001), and pack/years of smoking (P = .02) were significant independent factors associated with collapse. Risk management-based plans enabled significant dosage reduction to individual airway segments while fulfilling clinical dosimetric objectives. CONCLUSION: To our knowledge, this is the first systematic investigation of functional avoidance in lung SAbR based on mapping and minimizing doses to individual bronchial segments. Our early results show that it is possible to substantially lower airway dosage. Such dosage reduction may potentially reduce the risk of radiation-induced airway injury, while satisfying clinically prescribed dosimetric objectives.

Online dosimetric evaluation of larynx SBRT: A pilot study to assess the necessity of adaptive replanning.

PURPOSE: We have initiated a multi-institutional phase I trial of 5-fraction stereotactic body radiotherapy (SBRT) for Stage III-IVa laryngeal cancer. We conducted this pilot dosimetric study to confirm potential utility of online adaptive replanning to preserve treatment quality. METHODS: We evaluated ten cases: five patients enrolled onto the current trial and five patients enrolled onto a separate phase I SBRT trial for early-stage glottic larynx cancer. Baseline SBRT treatment plans were generated per protocol. Daily cone-beam CT (CBCT) or diagnostic CT images were acquired prior to each treatment fraction. Simulation CT images and target volumes were deformably registered to daily volumetric images, the original SBRT plan was copied to the deformed images and contours, delivered dose distributions were re-calculated on the deformed CT images. All of these were performed on a commercial treatment planning system. In-house software was developed to propagate the delivered dose distribution back to reference CT images using the deformation information exported from the treatment planning system. Dosimetric differences were evaluated via dose-volume histograms. RESULTS: We could evaluate dose within 10 minutes in all cases. Prescribed coverage to gross tumor volume (GTV) and clinical target volume (CTV) was uniformly preserved; however, intended prescription dose coverage of planning treatment volume (PTV) was lost in 53% of daily treatments (mean: 93.9%, range: 83.9-97.9%). Maximum bystander point dose limits to arytenoids, parotids, and spinal cord remained respected in all cases, although variances in carotid artery doses were observed in a minority of cases. CONCLUSIONS: Although GTV and CTV SBRT dose coverage is preserved with in-room three-dimensional image guidance, PTV coverage can vary significantly from intended plans and dose to critical structures may exceed tolerances. Online adaptive treatment re-planning is potentially necessary and clinically applicable to fully preserve treatment quality. Confirmatory trial accrual and analysis remains ongoing.

An accurate algorithm to match imperfectly matched images for lung tumor detection without markers.

In order to locate lung tumors on kV projection images without internal markers, digitally reconstructed radiographs (DRRs) are created and compared with projection images. However, lung tumors always move due to respiration and their locations change on projection images while they are static on DRRs. In addition, global image intensity discrepancies exist between DRRs and projections due to their different image orientations, scattering, and noises. This adversely affects comparison accuracy. A simple but efficient comparison algorithm is reported to match imperfectly matched projection images and DRRs. The kV projection images were matched with different DRRs in two steps. Preprocessing was performed in advance to generate two sets of DRRs. The tumors were removed from the planning 3D CT for a single phase of planning 4D CT images using planning contours of tumors. DRRs of background and DRRs of tumors were generated separately for every projection angle. The first step was to match projection images with DRRs of background signals. This method divided global images into a matrix of small tiles and similarities were evaluated by calculating normalized cross-correlation (NCC) between corresponding tiles on projections and DRRs. The tile configuration (tile locations) was automatically optimized to keep the tumor within a single projection tile that had a bad matching with the corresponding DRR tile. A pixel-based linear transformation was determined by linear interpolations of tile transformation results obtained during tile matching. The background DRRs were transformed to the projection image level and subtracted from it. The resulting subtracted image now contained only the tumor. The second step was to register DRRs of tumors to the subtracted image to locate the tumor. This method was successfully applied to kV fluoro images (about 1000 images) acquired on a Vero (BrainLAB) for dynamic tumor tracking on phantom studies. Radiation opaque markers were implanted and used as ground truth for tumor positions. Although other organs and bony structures introduced strong signals superimposed on tumors at some angles, this method accurately located tumors on every projection over 12 gantry angles. The maximum error was less than 2.2 mm, while the total average error was less than 0.9mm. This algorithm was capable of detecting tumors without markers, despite strong background signals.