Download presentation
Presentation is loading. Please wait.
1
An Investigation into the Relationship between Semantic and Content Based Similarity Using LIDC Grace Dasovich Robert Kim Midterm Presentation August 21 2009
2
Outline Related Work Data Modeling Approach and Results –Similarity Measures –Artificial Neural Network –Multivariate Linear Regression Conclusions Future Work
3
Computer-Aided Diagnosis (CADx) based on low-level image features –Armato et al. developed a linear discriminant classifier using features of lung nodules –Need to find the relationship between the image features and radiologists’ ratings Related Work
4
Image features and the semantic ratings –Lung Interpretations Barb et al. developed Evolutionary System for Semantic Exchange of Information in Collaborative Environments (ESSENCE) Raicu et al. used ensemble classifiers and decision trees to predict semantic ratings Samala et al. used several combinations of image features and the radiologists’ ratings to classify nodules Related Work
5
–Similarity Li et al. investigated four different methods to compute similarity measures for lung nodules –Feature-based –Pixel-value-difference –Cross correlation –ANN Related Work
6
Materials LIDC Dataset 149 Unique Nodules –One slice per nodule, largest nodule area 9 Semantic Characteristics –Calcification and Internal Structure had little variation, thus were not used 64 Content Features –Shape, size, intensity, and texture 6 Data
7
Related Work Data Modeling Approach and Results –Similarity Measures –Artificial Neural Network –Multivariate Linear Regression Conclusions Future Work Outline
8
Cosine Similarity Jeffrey Divergence Euclidean Distance Similarity Measures
11
Computed feature distance measures Similarity Measures
12
Outline Related Work Data Modeling Approach and Results –Similarity Measures –Artificial Neural Network –Multivariate Linear Regression Conclusions Future Work
13
Two three-layer ANNs –Input (64 neurons), hidden layer (5 neurons), output (1) –Input (64 neurons), hidden layer (5 neurons), output (7) Input = 64 feature distances Output = Semantic similarity or difference in semantic ratings Hyperbolic tangent function, backpropagation algorithm, 200 iterations Methods
14
ANN with a single output –640 random pairs from all 109 nodules –231 pairs from nodules with malignancy > 3 –496 pairs from nodules with area > 122 mm 2 Methods
15
ANN with seven outputs –640 random pairs from all 109 nodules
16
Leave-one-out method –Cosine similarity or Jeffrey divergence or difference in Semantic ratings used as teaching data –An ANN trained with entire dataset minus one image pair –The pair left out used for testing –Correlation between calculated radiologists’ similarity and ANN output calculated Methods
17
ANN with a single output –640 random pairs from all 109 nodules –231 pairs from nodules with malignancy > 3 –496 pairs from nodules with area > 122 mm 2 ANN with seven outputs –640 random pairs from all 109 nodules Methods
18
ANN using 640 random pairs Results
19
ANN using 231 pairs with malignancy rating > 3 Results
20
ANN using 496 pairs with area > 122 mm 2 Results
21
ANN output vs. target values using Jeffrey divergence for the 640 pairs (r = 0.438) Results
22
ANN using random 640 pairs and the Jeffrey divergence with seven semantic ratings Results
23
Outline Related Work Data Modeling Approach and Results –Similarity Measures –Artificial Neural Network –Multivariate Linear Regression Conclusions Future Work
24
Methods Normalization of Features –Min-Max Technique –Z-Score Technique Pair Selection –Looked for matches between k number of most similar images based on semantic and content 24 Methods
25
Multivariate Regression Analysis –Select features with highest correlation coefficients –Feature distance measures 25 Methods
26
Nodule Analysis –Determine differences between selected and non-selected nodules –Define requirements for our model Methods
27
Results 27 Results
28
d(i, j)d 2 (i, j)exp(d(i, j)) Cosine0.8710.8490.866 Jeffrey0.6470.6330.608
29
Results Correlation CoefficientFeature 0.1175Equivalent Diameter 0.1085Energy (Haralick) 0.0823Gabor Mean 135_05 0.0647Convex Area 0.0467Gabor STD 135_04 0.0322Min Intensity BG 0.0295Markov 4 0.0280Variance (Haralick) 0.0265Gabor STD 45_05 0.0238SD Intensity R 2 = 0.871 29 Results
30
30 Results
31
31 Results
32
32 Results
33
A. Equivalent Diameter, B. Standard Deviation of Intensity, C. Malignancy, D. Subtlety
34
Preliminary Issues The ANN also is not yet sufficient to predict semantic similarity from content –Best correlation 0.438 –Malignancy correlation 0.521 –Jeffrey performed better unlike linear model A semantic gap still exists Conclusions
35
Our linear model applies to a specific type of nodule –Characteristics: High malignancy, high texture, low lobulation, and low spiculation –Features: Larger diameter, greater intensity Linear models are not sufficient for determination of similarities –R 2 of 0.871 with chosen nodules 35 Conclusions
36
Future Work Reduce variability among radiologists –Use only nodules with radiologists’ agreement Find best combination of content features –64 may be too many –Currently only using 2D Future Work
37
Different semantic distance measures –Some ratings are ordinal, Jeffery is for categorical Different methods of machine learning –Incorporate radiologists’ feedback into training –Ensemble of classifiers Future Work
38
Thanks for Listening Any Questions? 38 Thanks for Listening
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.