| 3. |
- Luk, Chiu-Hung, et al.
(författare)
-
Vision-based hazard detection
- 2006
-
Ingår i: Intelligent Engineering Systems Through Artificial Neural Networks - Volume 16. - New York : ASME Press (American Society of Mechanical Engineers). ; , s. 6-
-
Konferensbidrag (refereegranskat)abstract
- Advances in sensor and GPS technologies make possible better guidance tools for vehicle/aerial navigation. In the work reported here we look at the detection of hazards, such as aircraft or other objects, on or near the target runway. Our system consists of two modules: 1) regions of interest (ROI) detection, and 2) hazard recognition. One of the harder problems in object recognition is to segment the target object from a cluttered background. In this system we use a “poor man’s” segmentation, by taking advantage of the fact that we have an approximate reference that we can differentiate from. The regions of interest are defined as significant differences between the input image and the reference image. Since this differencing can be complex due to the fact that the images may not be precisely registered, we employed a novel histogram method which is reasonably invariant to spatial transformations for ROI detection.
|
|
| 4. |
- Roer, O, et al.
(författare)
-
Quality assessment of autografting by probability evaluation: model estimation by clinical end-points in newly diagnosed multiple myeloma patients
- 2006
-
Ingår i: Cytotherapy. - : Elsevier BV. - 1477-2566 .- 1465-3249. ; 8:1, s. 79-88
-
Tidskriftsartikel (refereegranskat)abstract
- Background Pre-transplant clinical evaluation of autografting is an important step in predicting post-transplant support, complications and safety. Today, unfavorable outcomes such as early death or graft failure are rare, making them unsuitable for quality assessment of supportive autografting. However, end-points constructed from frequently occurring clinical events may estimate clinically relevant prognostic models. Methods The present retrospective analysis was based on two consecutive clinical trials in the Nordic area, including up to 640 newly diagnosed multiple myeloma patients. Results In the model, the efficacy (time on antibiotics and use of transfusions) was influenced by pre-transplant variables, including sex, nationality, serum creatinine, hemoglobin, disease stage at diagnosis, response following induction therapy, length of priming and average graft CD34(+) cell number per day of harvest. The toxicity end-point (time to blood cell recovery) was influenced by nationality, marrow plasma cell percentage, serum creatinine, M-component isotype, response to induction therapy, length of priming and graft CD34(+) cell number. The safety (early disease recurrence or death) was influenced by serum creatinine, hemoglobin, treatment response and CD34(+) cell number. Discussion In conclusion, the model illustrates that intervention strategies in quality assessment of autografting may benefit from probability estimates of graded clinical end-points.
|
|
