Breast elastography: diagnostic performance of computer-aided diagnosis software and interobserver agreement.

OBJECTIVE: To determine the best cutoff value for classifying breast masses by ultrasound elastography, using dedicated software for strain elastography, and to determine the level of interobserver agreement. MATERIALS AND METHODS: We enrolled 83 patients with 83 breast masses identified on ultrasound and referred for biopsy. After B-mode ultrasound examination, the lesions were manually segmented by three radiologists with varying degrees of experience in breast imaging, designated reader 1 (R1, with 15 years), reader 2 (R2, with 2 years), and reader 3 (R3, with 8 years). Elastography was performed automatically on the best image with computer-aided diagnosis (CAD) software. Cutoff values of 70%, 75%, 80%, and 90% of hard areas were applied for determining the performance of the CAD software. The best cutoff value for the most experienced radiologists was then compared with the visual assessment. Interobserver agreement for the best cutoff value was determined, as were the interclass correlation coefficient and concordance among the radiologists for the areas segmented. RESULTS: The best cutoff value of the proportion of hard area within a breast mass, for experienced radiologists, was found to be 75%. At a cutoff value of 75%, the interobserver agreement was excellent between R1 and R2, as well as between R1 and R3, and good between R2 and R3. The interclass concordance coefficient among the three radiologists was 0.950. When assessing the segmented areas by size, we found that the level of agreement was higher among the more experienced radiologists. CONCLUSION: The best cutoff value for a quantitative CAD system to classify breast masses was 75%.

Breast elastography: diagnostic performance of computer-aided diagnosis software and interobserver agreement / Elastografia mamária: desempenho diagnóstico de um software de sistema de diagnóstico assistido por computador e concordância interobservador

Abstract Objective: To determine the best cutoff value for classifying breast masses by ultrasound elastography, using dedicated software for strain elastography, and to determine the level of interobserver agreement. Materials and Methods: We enrolled 83 patients with 83 breast masses identified on ultrasound and referred for biopsy. After B-mode ultrasound examination, the lesions were manually segmented by three radiologists with varying degrees of experience in breast imaging, designated reader 1 (R1, with 15 years), reader 2 (R2, with 2 years), and reader 3 (R3, with 8 years). Elastography was performed automatically on the best image with computer-aided diagnosis (CAD) software. Cutoff values of 70%, 75%, 80%, and 90% of hard areas were applied for determining the performance of the CAD software. The best cutoff value for the most experienced radiologists was then compared with the visual assessment. Interobserver agreement for the best cutoff value was determined, as were the interclass correlation coefficient and concordance among the radiologists for the areas segmented. Results: The best cutoff value of the proportion of hard area within a breast mass, for experienced radiologists, was found to be 75%. At a cutoff value of 75%, the interobserver agreement was excellent between R1 and R2, as well as between R1 and R3, and good between R2 and R3. The interclass concordance coefficient among the three radiologists was 0.950. When assessing the segmented areas by size, we found that the level of agreement was higher among the more experienced radiologists. Conclusion: The best cutoff value for a quantitative CAD system to classify breast masses was 75%.

Resumo Objetivo: Determinar o melhor valor de corte para classificar os nódulos mamários pela elastografia por ultrassom, usando um software dedicado para elastografia por deformação, e determinar o nível de concordância interobservadores. Materiais e Métodos: Foram incluídos no estudo 83 pacientes com 83 massas mamárias identificadas no ultrassom e encaminhados para biópsia. Após o exame ultrassonográfico no modo B, as lesões foram manualmente segmentadas por três radiologistas com diferentes graus de experiência em imagem da mama: leitor 1 (R1, com 15 anos de experiência), leitor 2 (R2, com 2 anos de experiência) e leitor 3 (R3, com 8 anos de experiência). A classificação pela elastografia foi realizada automaticamente com base na melhor imagem com o software diagnóstico auxiliado por computador (DAC). Valores de corte de 70%, 75%, 80% e 90% das áreas duras foram aplicados para determinar o desempenho do software DAC. O melhor valor de corte para os radiologistas foi comparado com a avaliação visual. A concordância interobservadores para o melhor valor de corte foi determinada, assim como o coeficiente de correlação interclasses e a concordância entre os radiologistas para as áreas segmentadas. Resultados: O melhor valor de corte da proporção de área dura dentro de um nódulo mamário foi de 75% para os radiologistas mais experientes. Com um valor de corte de 75%, a concordância interobservadores foi excelente entre R1 e R2 e entre R1 e R3, e boa entre R2 e R3. O coeficiente de concordância interclasses entre os três radiologistas foi de 0,950. Ao avaliar as áreas segmentadas por tamanho, constatamos que o nível de concordância foi maior entre os radiologistas mais experientes. Conclusão: O melhor valor de corte para um sistema quantitativo de DAC para classificar as massas mamárias foi de 75%.

Performance of machine learning software to classify breast lesions using BI-RADS radiomic features on ultrasound images.

BACKGROUND: The purpose of this work was to evaluate computable Breast Imaging Reporting and Data System (BI-RADS) radiomic features to classify breast masses on ultrasound B-mode images. METHODS: The database consisted of 206 consecutive lesions (144 benign and 62 malignant) proved by percutaneous biopsy in a prospective study approved by the local ethical committee. A radiologist manually delineated the contour of the lesions on greyscale images. We extracted the main ten radiomic features based on the BI-RADS lexicon and classified the lesions as benign or malignant using a bottom-up approach for five machine learning (ML) methods: multilayer perceptron (MLP), decision tree (DT), linear discriminant analysis (LDA), random forest (RF), and support vector machine (SVM). We performed a 10-fold cross validation for training and testing of all classifiers. Receiver operating characteristic (ROC) analysis was used for providing the area under the curve with 95% confidence intervals (CI). RESULTS: The classifier with the highest AUC at ROC analysis was SVM (AUC = 0.840, 95% CI 0.6667-0.9762), with 71.4% sensitivity (95% CI 0.6479-0.8616) and 76.9% specificity (95% CI 0.6148-0.8228). The best AUC for each method was 0.744 (95% CI 0.677-0.774) for DT, 0.818 (95% CI 0.6667-0.9444) for LDA, 0.811 (95% CI 0.710-0.892) for RF, and 0.806 (95% CI 0.677-0.839) for MLP. Lesion margin and orientation were the optimal features for all the machine learning methods. CONCLUSIONS: ML can aid the distinction between benign and malignant breast lesion on ultrasound images using quantified BI-RADS descriptors. SVM provided the highest ROC-AUC (0.840).

Evaluation of a Computer-Aided Diagnosis System in the Classification of Lesions in Breast Strain Elastography Imaging.

Purpose: Evaluation of the performance of a computer-aided diagnosis (CAD) system based on the quantified color distribution in strain elastography imaging to evaluate the malignancy of breast tumors. Methods: The database consisted of 31 malignant and 52 benign lesions. A radiologist who was blinded to the diagnosis performed the visual analysis of the lesions. After six months with no eye contact on the breast images, the same radiologist and other two radiologists manually drew the contour of the lesions in B-mode ultrasound, which was masked in the elastography image. In order to measure the amount of hard tissue in a lesion, we developed a CAD system able to identify the amount of hard tissue, represented by red color, and quantify its predominance in a lesion, allowing classification as soft, intermediate, or hard. The data obtained with the CAD system were compared with the visual analysis. We calculated the sensitivity, specificity, and area under the curve (AUC) for the classification using the CAD system from the manual delineation of the contour by each radiologist. Results: The performance of the CAD system for the most experienced radiologist achieved sensitivity of 70.97%, specificity of 88.46%, and AUC of 0.853. The system presented better performance compared with his visual diagnosis, whose sensitivity, specificity, and AUC were 61.29%, 88.46%, and 0.829, respectively. The system obtained sensitivity, specificity, and AUC of 67.70%, 84.60%, and 0.783, respectively, for images segmented by Radiologist 2, and 51.60%, 92.30%, and 0.771, respectively, for those segmented by the Resident. The intra-class correlation coefficient was 0.748. The inter-observer agreement of the CAD system with the different contours was good in all comparisons. Conclusions: The proposed CAD system can improve the radiologist performance for classifying breast masses, with excellent inter-observer agreement. It could be a promising tool for clinical use.

The Feasibility of Classifying Breast Masses Using a Computer-Assisted Diagnosis (CAD) System Based on Ultrasound Elastography and BI-RADS Lexicon.

OBJECTIVES: To determine the applicability of a computer-aided diagnostic system strain elastography system for the classification of breast masses diagnosed by ultrasound and scored using the criteria proposed by the breast imaging and reporting data system ultrasound lexicon and to determine the diagnostic accuracy and interobserver variability. METHODS: This prospective study was conducted between March 1, 2016, and May 30, 2016. A total of 83 breast masses subjected to percutaneous biopsy were included. Ultrasound elastography images before biopsy were interpreted by 3 radiologists with and without the aid of computer-aided diagnostic system for strain elastography. The parameters evaluated by each radiologist results were sensitivity, specificity, and diagnostic accuracy, with and without computer-aided diagnostic system for strain elastography. Interobserver variability was assessed using a weighted κ test and an intraclass correlation coefficient. The areas under the receiver operating characteristic curves were also calculated. RESULTS: The areas under the receiver operating characteristic curve were 0.835, 0.801, and 0.765 for readers 1, 2, and 3, respectively, without computer-aided diagnostic system for strain elastography, and 0.900, 0.926, and 0.868, respectively, with computer-aided diagnostic system for strain elastography. The intraclass correlation coefficient between the 3 readers was 0.6713 without computer-aided diagnostic system for strain elastography and 0.811 with computer-aided diagnostic system for strain elastography. CONCLUSION: The proposed computer-aided diagnostic system for strain elastography system has the potential to improve the diagnostic performance of radiologists in breast examination using ultrasound associated with elastography.

Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images.

This research presents a methodology for the automatic detection and characterization of breast sonographic findings. We performed the tests in ultrasound images obtained from breast phantoms made of tissue mimicking material. When the results were considerable, we applied the same techniques to clinical examinations. The process was started employing preprocessing (Wiener filter, equalization, and median filter) to minimize noise. Then, five segmentation techniques were investigated to determine the most concise representation of the lesion contour, enabling us to consider the neural network SOM as the most relevant. After the delimitation of the object, the most expressive features were defined to the morphological description of the finding, generating the input data to the neural Multilayer Perceptron (MLP) classifier. The accuracy achieved during training with simulated images was 94.2%, producing an AUC of 0.92. To evaluating the data generalization, the classification was performed with a group of unknown images to the system, both to simulators and to clinical trials, resulting in an accuracy of 90% and 81%, respectively. The proposed classifier proved to be an important tool for the diagnosis in breast ultrasound.