An algorithm for automatic analysis of portal images: clinical evaluation for prostate treatments.

The aim of this study is to assess the clinical value of an algorithm for automatic analysis of portal images by measuring the method's performance in a clinical study of treatment of prostate cancer. The algorithm is based on chamfer matching and measures displacements of patients relative to prescribed radiation beam positions. In this paper we propose a method to quantify the mean standard deviation (MSD) of the performance of automatic analysis relative to the MSD of the performance of trained radiographers using the clinical data set only, i.e. without using additional phantoms or simulations. The clinical data set in this study consists of 99 regional AP prostate images of 15 different patients. To assess the performance the automatic analysis in relation to that of the human observers, we studied the results of the unsupervised automatic analysis, as well as the results of a less-trained human observer and a well-trained human observer assisted by the automatic analysis (in this combination, automatic analysis is done first and the result is modified by the well-trained observer if the observer does not agree). First, the intra-observer variations of the well-trained observer are measured by repetitive analysis of a small subset of the clinical data. The distribution of differences in analysis between two arbitrary observers is described by the chi 2 distribution, and is tabulated in literature. We define the agreement histogram of an observer O as an estimator for the chi 2 distribution between O and the well-trained human observer, parameterized by the ratio of the intra-observer variations of O and the well-trained observer.(ABSTRACT TRUNCATED AT 250 WORDS)

Time trend of patient setup deviations during pelvic irradiation using electronic portal imaging.

An electronic portal imaging device (EPID) was used to detect patient setup displacement during the course of a 3-field pelvic irradiation of two groups of patients: 10 rectal and 10 prostate carcinomas. These patients were irradiated with conventional treatment techniques in routine clinical practice. A total of 469 portal images and 60 simulator films were used to determine the values of setup deviations in the X- Y- and Z-directions of a fixed coordinate system, corresponding to the medio-lateral, cranio-caudal and antero-posterior direction, respectively. The absolute displacement averaged over all setups and patients ranged between 0.4 mm and 1.4 mm with a standard deviation (S.D.) of 1.6-3.9 mm. The overall distribution along each direction could be separated into a distribution of random deviations (S.D.s ranging from 1.2 to 2.8 mm) around the mean deviation of each patient and a distribution of the means themselves: the distribution of systematic deviations (S.D.s ranging from 1.0 to 2.6 mm). Significant gradual displacement as a function of time was detected in 5 out of the 20 patients, 2 in the rectum and 3 in the prostate group. This "time trend" was found along each of the 3 directions specified. The magnitude of the time-dependent displacement throughout the course of treatment ranged between 4 and 11 mm. It can be concluded that for treatments requiring a high level of precision, portal images should be made and analyzed during the whole treatment course in order to detect and correct significant time trends.