Machine Learning Based Computer Aided Diagnosis of Breast Cancer Utilizing Anthropometric and Clinical Features

Breast cancer is one of the most prevalent types of cancers in females, which has become rampant all over the world in recent years. The survival rate of breast cancer patients degrades considerably for patients diagnosed at an advanced stage compared to those diagnosed at an early stage. The objective of this study is two folds. The first one is to find the most relevant biomarkers of breast cancer, which can be attained from regular blood analysis and anthropometric measurements. The other one is to improve the performance of current computer-aided diagnosis (CAD) system of early breast cancer detection. This study utilized a recent data set containing nine anthropometric and clinical attributes. In our methodology, first, we performed multicollinearity analysis and ranked the features based on the weighted average score obtained from four filter-based feature evaluation methods such as F-score, information gain, chi-square statistic, and Minimum Redundancy Maximum Relevance. Next, to improve the separability of the target classes, we scaled and weighted the dataset using min-max normalization and similarity-based attribute weighting by the k-means clustering algorithm, respectively. Finally, we trained standard machine learning (ML) models and evaluated the performance metrics by 10-fold cross-validation method. Our support vector machine (SVM) model with radial basis function (RBF) kernel appeared to be the most successful classifier by utilizing six features, namely, Body Mass Index (BMI), Age, Glucose, MCP-1, Resistin, and Insulin. The obtained classification accuracy, sensitivity, and specificity are 93.9% (95% CI: 93.2–94.6%), 95.1% (95% CI: 94.4–95.8%), and 94.0% (95% CI: 93.3–94.7%), respectively; these performance metrics outperformed state-of-the-art methods reported in the literature. The developed model could potentially assist the medical experts for the early diagnosis of breast cancer by employing a set of attributes that can be easily obtained from regular blood analysis and anthropometric measurements.     

High-throughput proteomic analysis of formalin-fixed paraffin-embedded tissue microarrays using MALDI imaging mass spectrometry

A novel method for high-throughput proteomic analysis of formalin-fixed paraffin-embedded (FFPE) tissue microarrays (TMA) is described using on-tissue tryptic digestion followed by MALDI imaging MS. A TMA section containing 112 needle core biopsies from lung-tumor patients was analyzed using MS and the data were correlated to a serial hematoxylin and eosin (H&E)-stained section having various histological regions marked, including cancer, non-cancer, and normal ones. By correlating each mass spectrum to a defined histological region, statistical classification models were generated that can sufficiently distinguish biopsies from adenocarcinoma from squamous cell carcinoma biopsies. These classification models were built using a training set of biopsies in the TMA and were then validated on the remaining biopsies. Peptide markers of interest were identified directly from the TMA section using MALDI MS/MS sequence analysis. The ability to detect and characterize tumor marker proteins for a large cohort of FFPE samples in a high-throughput approach will be of significant benefit not only to investigators studying tumor biology, but also to clinicians for diagnostic and prognostic purposes.     

Discrimination of benign common nevi from malignant melanoma lesions by use of features based on spectral properties of the wavelet transform

OBJECTIVE: To evaluate the possibilities of describing and discriminating common nevi and malignant melanoma tissue with features based on spectral properties of the Daubechies 4 wavelet transform. STUDY DESIGN: Images of common nevi and malignant melanoma were dissected in square elements. The wavelet coefficients were calculated inside the square elements. The diagonal coefficients and related power spectra were used for further analysis. The analysis results served as guide for the selection of features, including standard deviations of wavelet coefficients inside the frequency bands and the energy of the frequency bands. These features describe properties of the frequency bands, representing information on different scales. To test the usefulness of the features for discrimination, a study set of 80 cases was classified by classification and regression trees analysis. The set was divided into a training set and a test set. RESULTS: In the case of benign common nevi, the energies of the lower frequency bands and higher, whereas malignant melanoma tissue shows more variability of the coefficients in higher-frequency bands. The influence on the detail properties of the images was studied by suppression of coefficients with low values, which are concentrated mainly in higher-frequency bands. In the case of benign common nevi the main information is contained in 15% of the coefficients and in the case of malignant melanoma, in 39%. The results of classification show a clear-cut difference between the cases. The classification correctly classified 95.78% of nevi elements and 94.22% of melanoma elements in the training set and 100% of cases of benign nevi and 80% of cases of malignant melanoma in the test set. CONCLUSION: Features based on the wavelet power spectrum contain sufficient information for differentiation between common nevi and malignant melanomas.     

Textural characterization of histopathological images for oral sub-mucous fibrosis detection

In the field of quantitative microscopy, textural information plays a significant role very often in tissue characterization and diagnosis, in addition to morphology and intensity. The aim of this work is to improve the classification accuracy based on textural features for the development of a computer assisted screening of oral sub-mucous fibrosis (OSF). In fact, a systematic approach is introduced in order to grade the histopathological tissue sections into normal, OSF without dysplasia and OSF with dysplasia, which would help the oral onco-pathologists to screen the subjects rapidly. In totality, 71 textural features are extracted from epithelial region of the tissue sections using various wavelet families, Gabor-wavelet, local binary pattern, fractal dimension and Brownian motion curve, followed by preprocessing and segmentation. Wavelet families contribute a common set of 9 features, out of which 8 are significant and other 61 out of 62 obtained from the rest of the extractors are also statistically significant (p < 0.05) in discriminating the three stages. Based on mean distance criteria, the best wavelet family (i.e., biorthogonal3.1 (bior3.1)) is selected for classifier design. support vector machine (SVM) is trained by 146 samples based on 69 textural features and its classification accuracy is computed for each of the combinations of wavelet family and rest of the extractors. Finally, it has been investigated that bior3.1 wavelet coefficients leads to higher accuracy (88.38%) in combination with LBP and Gabor wavelet features through three-fold cross validation. Results are shown and discussed in detail. It is shown that combining more than one texture measure instead of using just one might improve the overall accuracy.     

Automatic detection of melanoma progression by histological analysis of secondary sites

We present results from machine classification of melanoma biopsies sectioned and stained with hematoxylin/eosin (H&E) on tissue microarrays (TMA). The four stages of melanoma progression were represented by seven tissue types, including benign nevus, primary tumors with radial and vertical growth patterns (stage I) and four secondary metastatic tumors: subcutaneous (stage II), lymph node (stage III), gastrointestinal and soft tissue (stage IV). Our experiment setup comprised 14,208 image samples based on 164 TMA cores. In our experiments, we constructed an HE color space by digitally deconvolving the RGB images into separate H (hematoxylin) and E (eosin) channels. We also compared three different classifiers: Weighted Neighbor Distance (WND), Radial Basis Functions (RBF), and k-Nearest Neighbors (kNN). We found that the HE color space consistently outperformed other color spaces with all three classifiers, while the different classifiers did not have as large of an effect on accuracy. This showed that a more physiologically relevant representation of color can have a larger effect on correct image interpretation than downstream processing steps. We were able to correctly classify individual fields of view with an average of 96% accuracy when randomly splitting the dataset into training and test fields. We also obtained a classification accuracy of 100% when testing entire cores that were not previously used in training (four random trials with one test core for each of 7 classes, 28 tests total). Because each core corresponded to a different patient, this test more closely mimics a clinically relevant setting where new patients are evaluated based on training with previous cases. The analysis method used in this study contains no parameters or adjustments that are specific to melanoma morphology, suggesting it can be used for analyzing other tissues and phenotypes, as well as potentially different image modalities and contrast techniques.     

Directional features for automatic tumor classification of mammogram images

One way for breast cancer diagnosis is provided by taking radiographic (X-ray) images (termed mammograms) for suspect patients, images further used by physicians to identify potential abnormal areas thorough visual inspection. When digital mammograms are available, computer-aided based diagnostic may help the physician in having a more accurate decision. This implies automatic abnormal areas detection using segmentation, followed by tumor classification. This work aims at describing an approach to deal with the classification of digital mammograms. Patches around tumors are manually extracted to segment the abnormal areas from the remaining of the image, considered as background. The mammogram images are filtered using Gabor wavelets and directional features are extracted at different orientation and frequencies. Principal Component Analysis is employed to reduce the dimension of filtered and unfiltered high-dimensional data. Proximal Support Vector Machines are used to final classify the data. Superior mammogram image classification performance is attained when Gabor features are extracted instead of using original mammogram images. The robustness of Gabor features for digital mammogram images distorted by Poisson noise with different intensity levels is also addressed.     

Automated detection of connective tissue by tissue counter analysis and classification and regression trees.

OBJECTIVE: To evaluate the feasibility of the CART (Classification and Regression Tree) procedure for the recognition of microscopic structures in tissue counter analysis. METHODS: Digital microscopic images of H & E; stained slides of normal human skin and of primary malignant melanoma were overlayed with regularly distributed square measuring masks (elements) and grey value, texture and colour features within each mask were recorded. In the learning set, elements were interactively labeled as representing either connective tissue of the reticular dermis, other tissue components or background. Subsequently, CART models were based on these data sets. RESULTS: Implementation of the CART classification rules into the image analysis program showed that in an independent test set 94.1% of elements classified as connective tissue of the reticular dermis were correctly labeled. Automated measurements of the total amount of tissue and of the amount of connective tissue within a slide showed high reproducibility (r=0.97 and r=0.94, respectively; p<0.001). CONCLUSIONS: CART procedure in tissue counter analysis yields simple and reproducible classification rules for tissue elements.     

Computerized microscopic analysis of prostatic fine needle aspirates. Comparison with breast aspirates

Computerized image analysis was employed to analyze fine needle aspiration smears of the prostate and breast using both high-resolution images of individual cells and medium-resolution images of scenes and clusters (contextual analysis). A linear discriminant analysis was used to demonstrate the computer's ability to discriminate between benign and malignant categories for both types of tissue. Correct classification as benign or malignant using contextual analysis was achieved in 22 of 26 prostatic aspirates and in 15 of 18 breast aspirates, as determined by comparison with histology. The addition of high-resolution single-cell analysis resulted in correct classification of 24 of 26 prostatic aspirates and all breast aspirates. For virtually all features, the distinction between benign and malignant was more subtle for prostatic than for breast tissue. The data indicate that contextual analysis may be less effective as an adjunct to high-resolution single-cell microscopy of prostatic specimens than it is for breast specimens.     

Tissue counter analysis of histologic sections of melanoma: influence of mask size and shape, feature selection, statistical methods and tissue preparation.

BACKGROUND: Tissue counter analysis is an image analysis tool designed for the detection of structures in complex images at the macroscopic or microscopic scale. As a basic principle, small square or circular measuring masks are randomly placed across the image and image analysis parameters are obtained for each mask. Based on learning sets, statistical classification procedures are generated which facilitate an automated classification of new data sets. OBJECTIVE: To evaluate the influence of the size and shape of the measuring masks as well as the importance of feature selection, statistical procedures and technical preparation of slides on the performance of tissue counter analysis in microscopic images. As main quality measure of the final classification procedure, the percentage of elements that were correctly classified was used. STUDY DESIGN: HE-stained slides of 25 primary cutaneous melanomas were evaluated by tissue counter analysis for the recognition of melanoma elements (section area occupied by tumour cells) in contrast to other tissue elements and background elements. Circular and square measuring masks, various subsets of image analysis features and classification and regression trees compared with linear discriminant analysis as statistical alternatives were used. The percentage of elements that were correctly classified by the various classification procedures was assessed. In order to evaluate the applicability to slides obtained from different laboratories, the best procedure was automatically applied in a test set of another 50 cases of primary melanoma derived from the same laboratory as the learning set and two test sets of 20 cases each derived from two different laboratories, and the measurements of melanoma area in these cases were compared with conventional assessment of vertical tumour thickness. RESULTS: Square measuring masks were slightly superior to circular masks, and larger masks (64 or 128 pixels in diameter) were superior to smaller masks (8 to 32 pixels in diameter). As far as the subsets of image analysis features were concerned, colour features were superior to densitometric and Haralick texture features. Statistical moments of the grey level distribution were of least significance. CART (classification and regression tree) analysis turned out to be superior to linear discriminant analysis. In the best setting, 95% of melanoma tissue elements were correctly recognized. Automated measurement of melanoma area in the independent test sets yielded a correlation of r=0.846 with vertical tumour thickness (p<0.001), similar to the relationship reported for manual measurements. The test sets obtained from different laboratories yielded comparable results. CONCLUSIONS: Large, square measuring masks, colour features and CART analysis provide a useful setting for the automated measurement of melanoma tissue in tissue counter analysis, which can also be used for slides derived from different laboratories.     

Diagnosis of Breast Masses from Dynamic Contrast-Enhanced and Diffusion-Weighted MR: A Machine Learning Approach

Purpose

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported.

Materials and Methods

The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination.

Results

Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively.

Conclusion

Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.     

Image analysis of hyperchromatic crowded cell groups in SurePath cervical cytology

Objective: The discrimination of hyperchromatic crowded cell groups (HCCGs) in cervical cytology is a difficult and error‐prone interpretive task. While the classic features of dyskaryosis are of undoubted value, the contribution of size, shape and colour intensity of HCCGs is less certain. This study employed morphometric analysis to determine whether HCCG area, shape and colour intensity are useful in categorising them. Methods: Seventy‐five digital images from each of six categories of HCCG were subjected to image analysis. Ten variables relating to HCCG size, shape and colour intensity were assessed by discriminant function analysis. A further 28 cases were employed as a test set to determine the classification accuracy of the discriminant model. All samples were SurePath liquid‐based cytology preparations. Results: Nine of the 10 variables contributed significantly to the model (P < 0.001) but no single variable had sufficient discriminative ability. Classification accuracy was highest for abnormal endocervical HCCGs and lowest for squamous metaplastic cells (64.0 vs. 17.3% correct classification rate). The accuracy of the model for distinguishing normal and abnormal HCCGs was 70.0%, which was significantly higher than chance (P < 0.0001), but this reduced to 64.3% for the test cases, which was no better than chance (P > 0.05). Conclusions: The area, shape and colour intensity of HCCGs, either alone or in combination, have little discriminative value. Practitioners and trainers should focus on the well‐established features of dyskaryosis, such as chromatin pattern, nuclear membrane irregularities and group architecture. In terms of morphometric analysis, DNA ploidy and chromatin texture analysis may be more fruitful avenues of investigation.