AAR-RT - A system for auto-contouring organs at risk on CT images for radiation therapy planning: Principles, design, and large-scale evaluation on head-and-neck and thoracic cancer cases.

Contouring (segmentation) of Organs at Risk (OARs) in medical images is required for accurate radiation therapy (RT) planning. In current clinical practice, OAR contouring is performed with low levels of automation. Although several approaches have been proposed in the literature for improving automation, it is difficult to gain an understanding of how well these methods would perform in a realistic clinical setting. This is chiefly due to three key factors - small number of patient studies used for evaluation, lack of performance evaluation as a function of input image quality, and lack of precise anatomic definitions of OARs. In this paper, extending our previous body-wide Automatic Anatomy Recognition (AAR) framework to RT planning of OARs in the head and neck (H&N) and thoracic body regions, we present a methodology called AAR-RT to overcome some of these hurdles. AAR-RT follows AAR's 3-stage paradigm of model-building, object-recognition, and object-delineation. Model-building: Three key advances were made over AAR. (i) AAR-RT (like AAR) starts off with a computationally precise definition of the two body regions and all of their OARs. Ground truth delineations of OARs are then generated following these definitions strictly. We retrospectively gathered patient data sets and the associated contour data sets that have been created previously in routine clinical RT planning from our Radiation Oncology department and mended the contours to conform to these definitions. We then derived an Object Quality Score (OQS) for each OAR sample and an Image Quality Score (IQS) for each study, both on a 1-to-10 scale, based on quality grades assigned to each OAR sample following 9 key quality criteria. Only studies with high IQS and high OQS for all of their OARs were selected for model building. IQS and OQS were employed for evaluating AAR-RT's performance as a function of image/object quality. (ii) In place of the previous hand-crafted hierarchy for organizing OARs in AAR, we devised a method to find an optimal hierarchy for each body region. Optimality was based on minimizing object recognition error. (iii) In addition to the parent-to-child relationship encoded in the hierarchy in previous AAR, we developed a directed probability graph technique to further improve recognition accuracy by learning and encoding in the model "steady" relationships that may exist among OAR boundaries in the three orthogonal planes. Object-recognition: The two key improvements over the previous approach are (i) use of the optimal hierarchy for actual recognition of OARs in a given image, and (ii) refined recognition by making use of the trained probability graph. Object-delineation: We use a kNN classifier confined to the fuzzy object mask localized by the recognition step and then fit optimally the fuzzy mask to the kNN-derived voxel cluster to bring back shape constraint on the object. We evaluated AAR-RT on 205 thoracic and 298 H&N (total 503) studies, involving both planning and re-planning scans and a total of 21 organs (9 - thorax, 12 - H&N). The studies were gathered from two patient age groups for each gender - 40-59 years and 60-79 years. The number of 3D OAR samples analyzed from the two body regions was 4301. IQS and OQS tended to cluster at the two ends of the score scale. Accordingly, we considered two quality groups for each gender - good and poor. Good quality data sets typically had OQS ≥ 6 and had distortions, artifacts, pathology etc. in not more than 3 slices through the object. The number of model-worthy data sets used for training were 38 for thorax and 36 for H&N, and the remaining 479 studies were used for testing AAR-RT. Accordingly, we created 4 anatomy models, one each for: Thorax male (20 model-worthy data sets), Thorax female (18 model-worthy data sets), H&N male (20 model-worthy data sets), and H&N female (16 model-worthy data sets). On "good" cases, AAR-RT's recognition accuracy was within 2 voxels and delineation boundary distance was within ∼1 voxel. This was similar to the variability observed between two dosimetrists in manually contouring 5-6 OARs in each of 169 studies. On "poor" cases, AAR-RT's errors hovered around 5 voxels for recognition and 2 voxels for boundary distance. The performance was similar on planning and replanning cases, and there was no gender difference in performance. AAR-RT's recognition operation is much more robust than delineation. Understanding object and image quality and how they influence performance is crucial for devising effective object recognition and delineation algorithms. OQS seems to be more important than IQS in determining accuracy. Streak artifacts arising from dental implants and fillings and beam hardening from bone pose the greatest challenge to auto-contouring methods.

Comparison of acute toxicities between contemporary forward-planned 3D conformal radiotherapy and inverse-planned intensity-modulated radiotherapy for whole breast radiation.

The use of inverse-planned intensity-modulated radiation therapy for whole breast radiation treatment has become more prevalent, but this may impose an increased cost on the health system. We hypothesized that when applied with the same treatment planning goals, tangential forward-planned field-in-field 3D conformal radiotherapy and tangential inverse-planned intensity-modulated radiotherapy would be associated with comparable toxicities. Women who underwent tangential whole breast irradiation at our institution from 2011 to 2015 planned using either forward-planned field-in-field 3D conformal radiotherapy or intensity-modulated radiotherapy were retrospectively analyzed. Grade 2+ Radiation dermatitis was the primary endpoint. A total of 201 and 212 women had undergone field-in-field 3D conformal radiotherapy and intensity-modulated radiotherapy, respectively. No differences were observed between the two modalities regarding acute radiation dermatitis, breast pain, or fatigue. In a multivariable logistic regression that incorporated the use of boost, hypofractionation, use of chemotherapy, patient positioning, use of a supraclavicular field, and breast planning target volume, intensity-modulated radiotherapy was not correlated with different rates of Grade 2+ radiation dermatitis. This study supports the routine first-line use of field-in-field 3D conformal radiotherapy for whole breast radiation instead of tangential intensity-modulated radiotherapy from the standpoint of equivalence in acute toxicity. Further investigation is needed to assess whether there are subgroups of women who may still benefit from intensity-modulated radiotherapy.

The allure of multi-line games in modern slot machines.

AIMS: In multi-line slot machines, players can wager on more than one line per spin. We sought to show that players preferred multi-line over single-line games, and that certain game features could cause multi-line game play to feel more rewarding. MEASUREMENT AND PARTICIPANTS: Reward was measured using post-reinforcement pauses (PRPs) following each outcome (the time between outcome delivery and the next spin). Gamblers (n = 102) played 250 spins on a 20-line game and 250 spins on a one-line game (answering questions about game experiences following each session). Playing one-line, a small credit gain (e.g. 2 cents) was a net win. In the 20-line game it was a net loss of 18 credits but was still accompanied by 'winning' sights and sounds. RESULTS: Most players (94%) preferred the 20-line game. PRPs for small credit gains (net losses) in the 20-line game were equivalent, or larger than in the one-line game where such gains were wins. The largest increase in PRP size was between the 0 and 2 credit conditions for both games. Thus 20-line players reacted as though these net losses of 18 credits were rewarding. Players' estimates of the number of true wins were accurate in the one-line game, but they significantly over-estimated the number of true wins in the 20-line game (P < 0.01). Problem gamblers felt more skilful (P < 0.01) and were more absorbed (P < 0.01) by multi-line than single-line game play. CONCLUSIONS: Multi-line games appear to be more appealing to gaming machine ('slots') players than single-line games. These games may be particularly absorbing for those with gambling problems.