Вы находитесь на странице: 1из 6

ACKNOWLEDGEMENT

First of all I thank and praise the Almighty, without whom nothing is possible, for the spiritual support, eternal guidance and all blessing bestowed on us. I take immense pleasure to thank our principal Dr. N.K. Varghese, who has helped me in carrying out my seminar and also for giving me an external support. Needless to mention that Ms. Divya R, Head of the Department of Electronics and Communication Engineering, who had been a source of inspiration and for her timely guidance in the seminar. I would also like to thank other staff of Electronics and Communication Engineering Department for all their valuable assistance in my seminar. I wish to express my deep sense of gratitude to my seminar guide, Ms. Geliz George, for his able guidance and useful; suggestions, which helped me in presenting my seminar in time. Finally, yet importantly, I would like to express my sincere and heartfelt thanks to my beloved parents for their blessings, my friends/classmates for their help and wishes for successful presentation of my seminar.

ABSTRACT
Lymph nodes are assessed routinely in clinical practice and their size is followed throughout radiation or chemotherapy to monitor the effectiveness of cancer treatment. This paper presents a robust learning-based method for automatic detection and segmentation of solid lymph nodes from CT data, with the following contributions. First, it presents a learning based approach to solid lymph node detection that relies on Marginal Space Learning to achieve great speedup with virtually no loss in accuracy. Second, it presents a computationally efficient segmentation method for solid lymph nodes. Third, it introduces two new sets of features that are effective for Lymph node detection, one that self-aligns to high gradients and another set obtained from the segmentation result. The method is evaluated for axillary Lymph node detection detection on 131 volumes containing 371 Lymph node , yielding a 83.0% detection rate with 1.0 false positive per volume. It is further evaluated for pelvic and abdominal Lymph node detection on 54 volumes containing 569 Lymph node, yielding a 80.0% detection rate with 3.2 false positives per volume. The running time is 5-20 seconds per volume for axillary areas and 15-40 seconds for pelvic. An added benefit of the method is the capability to detect and segment conglomerated lymph nodes. Lymph node detection, lymph node segmentation and cancer staging.

TABLE OF CONTENTS
I Certificate II Acknowledgement III Abstract

CHAPTER 1 CHAPTER 2 CHAPTER 3

INTRODUCTION THEORETICAL BACKGROUND BLOCK DIAG AND EXPLANATION 3.1 BLOCK DIAGRAM 3.2 EXPLANATION 3.2.1 DETECTING SPIKES 3.2.2 NEUTRAL ACTIVITY DETECTION 3.2.3 NEUROSTIMULATOR 3.3 ANIMAL EXPERIMENT 3.3.1 ANIMAL PREPARATION 3.3.2 RECORDING SITES 3.3.3 MECHANICAL STIMULI 3.3.4 STIMULATING SITES

1 5 9 10 11 11 12 13 14 14 15 15 17

3.4 STATISTICAL ANALYSIS CHAPTER 4 EXPERIMENT RESULTS AND GRAPHS 4.1 EXPERIMENT RESULTS 4.1.1 PAG & SC VERIFICATION 4.1.2 DISTINGUISHING CLUSTERS OF ISIS 4.1.3 REAL TIME RECOGNITION 4.1.4 PERFORMANCE OF APRIS 4.1.5 SIGNIFICANCE OF PRESSURE & PINCH 4.1.6 INHIBITION FOR PINCH FROM SC 4.2 RESUTS AND DISCUSSION 4.2.1 EFFICIENCY VERIFICATION 4.2.2 APRIS INITIATION 4.2.3 APRIS TRIGGERED STIMULATION 4.2.4 TRIGGERING OF PAG & SC STIMULATION CHAPTER 5 MERITS AND APPLICATIONS 5.1 MERITS 5.2 APPLICATIONS

17 18 19 19 19 20 23 25 26 27 27 28 29 31 33 34 35

CHAPTER 6

DRAWBACKS AND FUTURE ENHANCEMENT 6.1 DRAWBACKS 6.2 FUTURE ENHANCEMENT

36 37 38 39 40 41 42 42

CHAPTER 7

CONCLUSION 7.1 CONCLUSION

CHAPTER 8

BIBILOGRAPHY 8.1 PAPER CONTRIBUTION 8.2 WEB SITES AND LINKS

IV APPENDIXES

LIST OF DIAGRAMS
FIG NO. 1. 2. 3. 4. 5. 6. 7. 8. 9. TITLE STRUCTURE OF NEURON BLOCK DIAG OF APRIS LOCATION OF PAG & SC REPRESENTATION OF CLUSTERS RESPONSE IN DORSAL HORN NEURON RECORDIND OF THE RESPONSE S/GS TRIGGERED BY APRIS IN PAG & SC NEURONS RESPONSE TO STIMULI RESPONSES FROM PAG & SC PAGE NO. 7 10 16 20 22 23 24 25 30

Вам также может понравиться