Search

Automatic segmentation of 3D objects in computed tomography (CT) is challenging. Current methods, based mainly on artificial intelligence (AI) and end-to-end deep learning (DL) networks, are weak in garnering high-level anatomic information, which leads to compromised efficiency and robustness. This can be overcome by incorporating natural intelligence (NI) into AI methods via computational models of human anatomic knowledge.We formulate a hybrid intelligence (HI) approach that integrates the complementary strengths of NI and AI for organ segmentation in CT images and illustrate performance in the application of radiation therapy (RT) planning via multisite clinical evaluation.The system employs five modules: (i) body region recognition, which automatically trims a given image to a precisely defined target body region; (ii) NI-based automatic anatomy recognition object recognition (AAR-R), which performs object recognition in the trimmed image without DL and outputs a localized fuzzy model for each object; (iii) DL-based recognition (DL-R), which refines the coarse recognition results of AAR-R and outputs a stack of 2D bounding boxes (BBs) for each object; (iv) model morphing (MM), which deforms the AAR-R fuzzy model of each object guided by the BBs output by DL-R; and (v) DL-based delineation (DL-D), which employs the object containment information provided by MM to delineate each object. NI from (ii), AI from (i), (iii), and (v), and their combination from (iv) facilitate the HI system.The HI system was tested on 26 organs in neck and thorax body regions on CT images obtained prospectively from 464 patients in a study involving four RT centers. Data sets from one separate independent institution involving 125 patients were employed in training/model building for each of the two body regions, whereas 104 and 110 data sets from the 4 RT centers were utilized for testing on neck and thorax, respectively. In the testing data sets, 83% of the images had limitations such as streak artifacts, poor contrast, shape distortion, pathology, or implants. The contours output by the HI system were compared to contours drawn in clinical practice at the four RT centers by utilizing an independently established ground-truth set of contours as reference. Three sets of measures were employed: accuracy via Dice coefficient (DC) and Hausdorff boundary distance (HD), subjective clinical acceptability via a blinded reader study, and efficiency by measuring human time saved in contouring by the HI system. Overall, the HI system achieved a mean DC of 0.78 and 0.87 and a mean HD of 2.22 and 4.53 mm for neck and thorax, respectively. It significantly outperformed clinical contouring in accuracy and saved overall 70% of human time over clinical contouring time, whereas acceptability scores varied significantly from site to site for both auto-contours and clinically drawn contours.The HI system is observed to behave like an expert human in robustness in the contouring task but vastly more efficiently. It seems to use NI help where image information alone will not suffice to decide, first for the correct localization of the object and then for the precise delineation of the boundary.

Transmission beams have been proposed for ultra-high dose (or FLASH) proton planning, limiting the organ sparing potentials of proton therapy. By pulling back the ranges of the highest energy proton beams and compensating proton ranges to adapt to the target distally, the exit dose of proton beams can be eliminated to better protect organs at risk while still preserving FLASH dose rate delivery.An inverse planning tool was developed to optimize intensity modulated proton therapy using a single-energy layer for FLASH radiation therapy planning. The range pull-backs were calculated to stop single-energy proton beams at the distal edge of the target. The spot map and weights of each field were optimized to achieve a sufficient dose rate using proton beam Bragg peaks. A C-shape target in phantom, along with 6 consecutive lung cancer patients previously treated using proton stereotactic body radiation therapy were planned using this novel Bragg Peak method and also transmission technique. Dosimetry characteristics and 3-dimensional dose rate were investigated.The minimum monitor units (MU) for transmission and Bragg peak plans were 400 MU/spot and 1200 MU/spot, respectively, corresponding to spot peak dose rates of 670 GyRBE (relative biological effectiveness) per second and 1950 GyRBE per second. Bragg peak plans yield a generally comparable target uniformity while significantly reducing dose spillage volume from the low to medium dose level. For all the 6 lung cases delivery of 34 GyRBE in 1 fraction, assessing Radiation Therapy Oncology Group 0915 constraints, the lung VThis first proof-of-concept study has demonstrated this novel method of combining range pull-back and powerful inverse optimization capable of achieving FLASH dose rate based on currently available machine parameters using a single-energy Bragg peak. Similar target coverage and uniformity can be maintained by Bragg peak FLASH plans while substantially improving the sparing of organs at risk compared with transmission plans.