Are cone beam CT image matching skills transferrable from planning CT to planning MRI for MR-only prostate radiotherapy?

Objectives: Treatment verification for MR-only planning has focused on fiducial marker matching, however, these are difficult to identify on MR. An alternative is using the MRI for soft-tissue matching with cone beam computed tomography images (MR-CBCT). However, therapeutic radiographers have limited experience of MRI. This study aimed to assess transferability of therapeutic radiographers CT-CBCT prostate image matching skills to MR-CBCT image matching. Methods: 23 therapeutic radiographers with 3 months–5 years’ experience of online daily CT-CBCT soft-tissue matching prostate cancer patients participated. Each observer completed a baseline assessment of 10 CT-CBCT prostate soft-tissue image matches, followed by 10 MR-CBCT prostate soft-tissue image match assessment. A MRI anatomy training intervention was delivered and the 10 MR-CBCT prostate soft-tissue image match assessment was repeated. Limits of agreement were calculated as the disagreement of the observers with mean of all observers. Results: Limits of agreement at CT-CBCT baseline were 2.8 mm, 2.8 mm, 0.7 mm (vertical, longitudinal, lateral). MR-CBCT matches prior to training were 3.3 mm, 3.1 mm, 0.9 mm, and after training 2.6 mm, 2.4 mm, 1.1 mm (vertical, longitudinal, lateral). Results show similar limits of agreement across the assessments, and variation reduced following the training intervention. Conclusion: This suggests therapeutic radiographers’ prostate CBCT image matching skills are transferrable to a MRI planning scan, since MR-CBCT matching has comparable observer variation to CT-CBCT matching. Advances in knowledge: This is the first publication assessing interobserver MR-CBCT prostate soft tissue matching in an MR-only pathway.

Relative effectiveness of celebrity and product match-up for two high consumer involvement situations

PurposeThe study attempted to gauge the relative effectiveness of celebrity and product image match-up in comparison to non-celebrity attractive endorsers for two distinct high involvement situations. Also, due to the expected demographic diversity among target consumers, the study aimed at assessing the impact of respondent's age and gender on the effectiveness of image match-up.Design/methodology/approachBuilding on the three-order hierarchy model, two experiments were conducted (utilising celebrity and non-celebrity endorsers) for two high involvement hierarchies, i.e. standard learning and dissonance/attribution. Through fictitious print advertisement, the experiments assessed the effectiveness of the match-up in terms of consumer attitudes towards advertisement and brand and intentions to purchase.FindingsThe match-up consistently and significantly outperformed non-celebrity attractive endorser in case of standard learning hierarchy. The same conclusion was not established for dissonance/attribution hierarchy due to the lack of significant results. The findings also suggest that the match-up subdues the impact of consumer's gender and age on consumer attitudes only in case of standard learning hierarchy.Research limitations/implicationsThe study provides interesting theoretical implication by challenging a widely held postulation about the applicability of celebrity and product match-up under high involvement.Practical implicationsThe research provides the practitioners with a better understanding of important issues, mainly, whether to use a celebrity endorser and selecting the right celebrity, especially if high involvement is expected.Originality/valuePrevious research concerning celebrity endorsements has largely considered consumer involvement as unitary, i.e. either high or low. However, the multifaceted aspect of consumer involvement is well established in the field of consumer psychology. The present research, therefore, is a pioneering attempt as it studies the effectiveness of match-up for two distinct high involvement situations. Moreover, unlike the majority of previous studies that have focused on the performance of “celebrity match” versus “celebrity mismatch”, the impact of match-up was studied in comparison to a non-celebrity attractive endorser.

Comparisons of image-matching software when identifying pool frog (Pelophylax lessonae) individuals from a reintroduced population

Photographic identification of individual animals is a non-invasive and cost-effective method that can provide demographic information on wild populations. This study aims to compare two photo-matching algorithms (Wild- ID and I3S-Spot) using a reintroduced population of pool frogs (Pelophylax lessonae) in the UK as a case study. We compared the following parameters 1) sex and age, 2) image quality, 3) image collection size and 4) processing time to evaluate successful image match rates. There were no significant differences in successful match rates found between sex and age groups. Wild-ID was more sensitive to image quality than I3S-Spot. There was a significant negative relationship between image collection size and successful match rates for I3S-Spot, however, no such relationship for Wild-ID. The findings of our study can be used by conservation practitioners to reduce workload and improve accuracy during population monitoring activities.

Feature Point Matching Method Based on Consistent Edge Structures for Infrared and Visible Images

Infrared and visible image match is an important research topic in the field of multi-modality image processing. Due to the difference of image contents like pixel intensities and gradients caused by disparate spectrums, it is a great challenge for infrared and visible image match in terms of the detection repeatability and the matching accuracy. To improve the matching performance, a feature detection and description method based on consistent edge structures of images (DDCE) is proposed in this paper. First, consistent edge structures are detected to obtain similar contents of infrared and visible images. Second, common feature points of infrared and visible images are extracted based on the consistent edge structures. Third, feature descriptions are established according to the edge structure attributes including edge length and edge orientation. Lastly, feature correspondences are calculated according to the distance of feature descriptions. Due to the utilization of consistent edge structures of infrared and visible images, the proposed DDCE method can improve the detection repeatability and the matching accuracy. DDCE is evaluated on two public datasets and are compared with several state-of-the-art methods. Experimental results demonstrate that DDCE can achieve superior performance against other methods for infrared and visible image match.

STUDY OF AUTOMATIC IMAGE RECTIFICATION AND REGISTRATION OF SCANNED HISTORICAL AERIAL PHOTOGRAPHS

Historical aerial photographs directly provide good evidences of past times. The Research Center for Humanities and Social Sciences (RCHSS) of Taiwan Academia Sinica has collected and scanned numerous historical maps and aerial images of Taiwan and China. Some maps or images have been geo-referenced manually, but most of historical aerial images have not been registered since there are no GPS or IMU data for orientation assisting in the past. In our research, we developed an automatic process of matching historical aerial images by SIFT (Scale Invariant Feature Transform) for handling the great quantity of images by computer vision. SIFT is one of the most popular method of image feature extracting and matching. This algorithm extracts extreme values in scale space into invariant image features, which are robust to changing in rotation scale, noise, and illumination. We also use RANSAC (Random sample consensus) to remove outliers, and obtain good conjugated points between photographs. Finally, we manually add control points for registration through least square adjustment based on collinear equation. In the future, we can use image feature points of more photographs to build control image database. Every new image will be treated as query image. If feature points of query image match the features in database, it means that the query image probably is overlapped with control images.With the updating of database, more and more query image can be matched and aligned automatically. Other research about multi-time period environmental changes can be investigated with those geo-referenced temporal spatial data.

STUDY OF AUTOMATIC IMAGE RECTIFICATION AND REGISTRATION OF SCANNED HISTORICAL AERIAL PHOTOGRAPHS

Historical aerial photographs directly provide good evidences of past times. The Research Center for Humanities and Social Sciences (RCHSS) of Taiwan Academia Sinica has collected and scanned numerous historical maps and aerial images of Taiwan and China. Some maps or images have been geo-referenced manually, but most of historical aerial images have not been registered since there are no GPS or IMU data for orientation assisting in the past. In our research, we developed an automatic process of matching historical aerial images by SIFT (Scale Invariant Feature Transform) for handling the great quantity of images by computer vision. SIFT is one of the most popular method of image feature extracting and matching. This algorithm extracts extreme values in scale space into invariant image features, which are robust to changing in rotation scale, noise, and illumination. We also use RANSAC (Random sample consensus) to remove outliers, and obtain good conjugated points between photographs. Finally, we manually add control points for registration through least square adjustment based on collinear equation. In the future, we can use image feature points of more photographs to build control image database. Every new image will be treated as query image. If feature points of query image match the features in database, it means that the query image probably is overlapped with control images.With the updating of database, more and more query image can be matched and aligned automatically. Other research about multi-time period environmental changes can be investigated with those geo-referenced temporal spatial data.