Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images.

BACKGROUND: The detection of suspicious microcalcifications on mammography represents one of the earliest signs of a malignant breast tumor. Assessing microcalcifications' characteristics based on their appearance on 2D breast imaging modalities is in many cases challenging for radiologists. The aims of this study were to: (a) analyse the association of shape and texture properties of breast microcalcifications (extracted by scanning breast tissue with a high resolution 3D scanner) with malignancy, (b) evaluate microcalcifications' potential to diagnose benign/malignant patients. METHODS: Biopsy samples of 94 female patients with suspicious microcalcifications detected during a mammography, were scanned using a micro-CT scanner at a resolution of 9 µm. Several preprocessing techniques were applied on 3504 extracted microcalcifications. A high amount of radiomic features were extracted in an attempt to capture differences among microcalcifications occurring in benign and malignant lesions. Machine learning algorithms were used to diagnose: (a) individual microcalcifications, (b) samples. For the samples, several methodologies to combine individual microcalcification results into sample results were evaluated. RESULTS: We could classify individual microcalcifications with 77.32% accuracy, 61.15% sensitivity and 89.76% specificity. At the sample level diagnosis, we achieved an accuracy of 84.04%, sensitivity of 86.27% and specificity of 81.39%. CONCLUSIONS: By studying microcalcifications' characteristics at a level of details beyond what is currently possible by using conventional breast imaging modalities, our classification results demonstrated a strong association between breast microcalcifications and malignancies. Microcalcification's texture features extracted in transform domains, have higher discriminating power to classify benign/malignant individual microcalcifications and samples compared to pure shape-features.

The impact of (simulated) resolution on breast cancer diagnosis based on high-resolution 3D micro-CT microcalcification images.

BACKGROUND: Breast microcalcifications (MCs) are considered to be a robust marker of breast cancer. A machine learning model can provide breast cancer diagnosis based on properties of individual MCs - if their characteristics are captured at high resolution and in 3D. PURPOSE: The main purpose of the study was to explore the impact of image resolution (8 µm, 16 µm, 32 µm, 64 µm) when diagnosing breast cancer using radiomics features extracted from individual high resolution 3D micro-CT MC images. METHODS: Breast MCs extracted from 86 female patients were analyzed at four different spatial resolutions: 8 µm (original resolution) and 16 µm, 32 µm, 64 µm (simulated image resolutions). Radiomic features were extracted at each image resolution in an attempt, to find a compact feature signature allowing to distinguish benign and malignant MCs. Machine learning algorithms were used for classifying individual MCs and samples (i.e., patients). For sample diagnosis, a custom-based thresholding approach was used to combine individual MC results into sample results. We conducted classification experiments when using (a) the same MCs visible in 8 µm, 16 µm, 32 µm, and 64 µm resolution; (b) the same MCs visible in 8 µm, 16 µm, and 32 µm resolution; (c) the same MCs visible in 8 µm and 16 µm resolution; (d) all MCs visible in 8 µm, 16 µm, 32 µm, and 64 µm resolution. Accuracy, sensitivity, specificity, AUC, and F1 score were computed for each experiment. RESULTS: The individual MC results yielded an accuracy of 77.27%, AUC of 83.83%, F1 score of 77.25%, sensitivity of 80.86%, and specificity of 72.2% at 8 µm resolution. For the individual MC classifications we report for the F1 scores: a 2.29% drop when using 16 µm instead of 8 µm, a 4.01% drop when using 32 µm instead of 8 µm, a 10.69% drop when using 64 µm instead of 8 µm. The sample results yielded an accuracy and F1 score of 81.4%, sensitivity of 80.43%, and specificity value of 82.5% at 8 µm. For the sample classifications we report for F1 score values: a 6.3% drop when using 16 µm instead of 8 µm, a 4.91% drop when using 32 µm instead of 8 µm, and a 6.3% drop when using 64 µm instead of 8 µm. CONCLUSIONS: The highest classification results are obtained at the highest resolution (8 µm). If breast MCs characteristics could be visualized/captured in 3D at a higher resolution compared to what is used nowadays in digital mammograms (approximately 70 µm), breast cancer diagnosis will be improved.