Purpose

The purpose of this study is to determine the optimal representative reconstruction and quantitative image feature set for a computer-aided diagnosis (CADx) scheme for dedicated breast computer tomography (bCT).

Method

We used 93 bCT scans that contain 102 breast lesions (62 malignant, 40 benign). Using an iterative image reconstruction (IIR) algorithm, we created 37 reconstructions with different image appearances for each case. In addition, we added a clinical reconstruction for comparison purposes. We used image sharpness, determined by the gradient of gray value in a parenchymal portion of the reconstructed breast, as a surrogate measure of the image qualities/appearances for the 38 reconstructions. After segmentation of the breast lesion, we extracted 23 quantitative image features. Using leave-one-out-cross-validation (LOOCV), we conducted the feature selection, classifier training, and testing. For this study, we used the linear discriminant analysis classifier. Then, we selected the representative reconstruction and feature set for the classifier with the best diagnostic performance among all reconstructions and feature sets. Then, we conducted an observer study with six radiologists using a subset of breast lesions (N = 50). Using 1000 bootstrap samples, we compared the diagnostic performance of the trained classifier to those of the radiologists.

Result

The diagnostic performance of the trained classifier increased as the image sharpness of a given reconstruction increased. Among combinations of reconstructions and quantitative image feature sets, we selected one of the sharp reconstructions and three quantitative image feature sets with the first three highest diagnostic performances under LOOCV as the representative reconstruction and feature set for the classifier. The classifier on the representative reconstruction and feature set achieved better diagnostic performance with an area under the ROC curve (AUC) of 0.94 (95% CI = [0.81, 0.98]) than those of the radiologists, where their maximum AUC was 0.78 (95% CI = [0.63, 0.90]). Moreover, the partial AUC, at 90% sensitivity or higher, of the classifier (pAUC = 0.085 with 95% CI = [0.063, 0.094]) was statistically better (P-value < 0.0001) than those of the radiologists (maximum pAUC = 0.009 with 95% CI = [0.003, 0.024]).

Conclusion

We found that image sharpness measure can be a good candidate to estimate the diagnostic performance of a given CADx algorithm. In addition, we found that there exists a reconstruction (i.e., sharp reconstruction) and a feature set that maximizes the diagnostic performance of a CADx algorithm. On this optimal representative reconstruction and feature set, the CADx algorithm outperformed radiologists.

Many computer aided diagnosis (CADx) tools for breast cancer begin by fully or semiautomatically segmenting a given breast lesion and then classifying the lesion's likelihood of malignancy using quantitative features extracted from the image. It is often assumed that better segmentation will result in better classification. However, this has not been thoroughly evaluated. The purpose of this study is to evaluate the relationship between computer segmentation performance and computer classification performance. We used 85 breast lesions (32 benign, 56 malignant) from breast computed tomography (CT) cases of 82 women. We prepared one smooth and one sharp iterative image reconstructions (IIR) and a clinical reconstruction for each of the 82 breast CT scans. For each reconstruction, we created 15 segmentation outcomes by applying 15 different segmentation algorithms. Specifically, we simulated 15 segmentation algorithms by changing parameters in a single segmentation algorithm. We then created 15 classification outcomes by conducting quantitative image feature analysis on the segmented image results. Using a 10-fold cross-validation, we evaluated the relationship between segmentation and classification performances. We found a low positive correlation between segmentation and classification performances for the smooth IIR (median Pearson's rho = 0.18), while a moderate positive correlation (median Pearson's rho = 0.4-0.43) was found between the two performances for the sharp IIR and clinical reconstruction. However, we found large variations in both segmentation and classification performances for the sharp IIR and clinical reconstruction. There were cases where segmentation algorithms resulted in similar segmentation performances, but the corresponding classification performances were different. These results indicate that an improvement in segmentation performance does not guarantee an improvement in the corresponding classification performance. Computer segmentation is an indirect variable affecting the computer classification. As better segmentation does not guarantee better classification, we should report both segmentation and classification performances when comparing segmentation algorithms.

We proposed the neutrosophic approach for segmenting breast lesions in breast computed tomography (bCT) images. The neutrosophic set considers the nature and properties of neutrality (or indeterminacy). We considered the image noise as an indeterminate component while treating the breast lesion and other breast areas as true and false components. We iteratively smoothed and contrast-enhanced the image to reduce the noise level of the true set. We then applied one existing algorithm for bCT images, the RGI segmentation, on the resulting noise-reduced image to segment the breast lesions. We compared the segmentation performance of the proposed method (named as NS-RGI) to that of the regular RGI segmentation. We used 122 breast lesions (44 benign and 78 malignant) of 111 noncontrast enhanced bCT cases. We measured the segmentation performances of the NS-RGI and the RGI using the Dice coefficient. The average Dice values of the NS-RGI and RGI were 0.82 and 0.80, respectively, and their difference was statistically significant ([Formula: see text]). We conducted a subsequent feature analysis on the resulting segmentations. The classifier performance for the NS-RGI ([Formula: see text]) improved over that of the RGI ([Formula: see text], [Formula: see text]).

PURPOSE:The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors. METHODS:A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimal feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit. RESULTS:Among curvature measures, the normalized total curvature (CT) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and CT yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and CT were conducted. The results showed that CT was able to replace the other four image features for the classification task. CONCLUSIONS:The normalized curvature measure contains useful information in classifying breast tumors. Using this, one can reduce the number of features in a classifier, which may result in more robust classifiers for different datasets.

We tested the agreement of radiologists' rankings of different reconstructions of breast computed tomography images based on their diagnostic (classification) performance and on their subjective image quality assessments. We used 102 pathology proven cases (62 malignant, 40 benign), and an iterative image reconstruction (IIR) algorithm to obtain 24 reconstructions per case with different image appearances. Using image feature analysis, we selected 3 IIRs and 1 clinical reconstruction and 50 lesions. The reconstructions produced a range of image quality from smooth/low-noise to sharp/high-noise, which had a range in classifier performance corresponding to AUCs of 0.62 to 0.96. Six experienced Mammography Quality Standards Act (MQSA) radiologists rated the likelihood of malignancy for each lesion. We conducted an additional reader study with the same radiologists and a subset of 30 lesions. Radiologists ranked each reconstruction according to their preference. There was disagreement among the six radiologists on which reconstruction produced images with the highest diagnostic content, but they preferred the midsharp/noise image appearance over the others. However, the reconstruction they preferred most did not match with their performance. Due to these disagreements, it may be difficult to develop a single image-based model observer that is representative of a population of radiologists for this particular imaging task.

Increasing attention is being given to developing quantitative measures of facial expression. This study used quantitative facial expression analysis to examine associations between smiling intensity and psychosocial functioning in patients with head and neck cancer (HNC). Smiling intensity of 95 HNC patients was measured using 48 quantitative measures calculated from facial photographs with and without a smile. We computed a composite smiling intensity score for each patient representing the degree of similarity to healthy controls. A lower composite score indicates that the person is less expressive, on average, than healthy controls. Patients also completed self-report measures assessing domains of body image and quality of life (QOL). Spearman rank correlations were computed to examine relationships between composite scores and psychosocial functioning. Composite scores were significantly correlated with multiple measures of body image and QOL. Specifically, decreased smiling intensity was associated with feelings of dissatisfaction with one's body, perceived negative social impact of body image, increased use of avoidance as a body image-coping strategy, reduced functional well-being, and greater head and neck cancer-specific issues. To the best of our knowledge, this is the first study to demonstrate associations between an objectively quantified facial expression (i.e. smiling) and psychosocial functioning. Most previous studies have measured facial expression qualitatively. These findings indicate that smiling intensity may serve as an important clinical indicator of psychosocial well-being and warrants further clinical investigation.