Breast Cancer Detection in a Screening Population: Comparison of Digital Mammography, Computer-Aided Detection Applied to Digital Mammography and Breast Ultrasound

Improving mammography interpretation for both novice and experienced readers: a comparative study of two commercial artificial intelligence software

OBJECTIVES

To evaluate the improvement of mammography interpretation for novice and experienced radiologists assisted by two commercial AI software.

METHODS

We compared the performance of two AI software (AI-1 and AI-2) in two experienced and two novice readers for 200 mammographic examinations (80 cancer cases). Two reading sessions were conducted within 4 weeks. The readers rated the likelihood of malignancy (range, 1-7) and the percentage probability of malignancy (range, 0-100%), with and without AI assistance. Differences in AUROC, sensitivity, and specificity were analyzed.

RESULTS

Mean AUROC increased in both novice (0.86 to 0.90 with AI-1 [p = 0.005]; 0.91 with AI-2 [p < 0.001]) and experienced readers (0.87 to 0.92 with AI-1 [p < 0.001]; 0.90 with AI-2 [p = 0.004]). Sensitivities increased from 81.3 to 88.8% with AI-1 (p = 0.027) and to 91.3% with AI-2 (p = 0.005) in novice readers, and from 81.9 to 90.6% with AI-1 (p = 0.001) and to 87.5% with AI-2 (p = 0.016) in experienced readers. Specificity did not decrease significantly in both novice (p > 0.999, both) and experienced readers (p > 0.999 with AI-1 and 0.282 with AI-2). There was no significant difference in the performance change depending on the type of AI software (p > 0.999).

CONCLUSION

Commercial AI software improved the diagnostic performance of both novice and experienced readers. The type of AI software used did not significantly impact performance changes. Further validation with a larger number of cases and readers is needed.

CLINICAL RELEVANCE STATEMENT

Commercial AI software effectively aided mammography interpretation irrespective of the experience level of human readers.

KEY POINTS

• Mammography interpretation remains challenging and is subject to a wide range of interobserver variability. • In this multi-reader study, two commercial AI software improved the sensitivity of mammography interpretation by both novice and experienced readers. The type of AI software used did not significantly impact performance changes. • Commercial AI software may effectively support mammography interpretation irrespective of the experience level of human readers.

Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images

This study aimed to evaluate the performance of traditional-deep learning combination model based on Doppler ultrasound for diagnosing malignant complex cystic and solid breast nodules. A conventional statistical prediction model based on the ultrasound features and basic clinical information was established. A deep learning prediction model was used to train the training group images and derive the deep learning prediction model. The two models were validated, and their accuracy rates were compared using the data and images of the test group, respectively. A logistic regression method was used to combine the two models to derive a combination diagnostic model and validate it in the test group. The diagnostic performance of each model was represented by the receiver operating characteristic curve and the area under the curve. In the test cohort, the diagnostic efficacy of the deep learning model was better than traditional statistical model, and the combined diagnostic model was better and outperformed the other two models (combination model vs traditional statistical model: AUC: 0.95 > 0.70, P = 0.001; combination model vs deep learning model: AUC: 0.95 > 0.87, P = 0.04). A combination model based on deep learning and ultrasound features has good diagnostic value.

Ultrasonic Features and Molecular Subtype Predict Somatic Mutations in TP53 and PIK3CA Genes in Breast Cancer

RATIONALE AND OBJECTIVES

To predict mutations in TP53 and PIK3CA genes in breast cancer using ultrasound (US) signatures and clinicopathology.

MATERIALS AND METHODS

In this study, we developed and trained a model in 386 breast cancer patients to predict TP53 and PIK3CA mutations. The clinicopathological and US characteristics (including two-dimensional and color Doppler US) were investigated. Statistically significant variables were used to build predictive models, then a combined model was developed using the multivariate logistic regression analysis.

RESULTS

Univariate and multivariate analyses revealed that calcifications on US was an independent predictor of TP53 mutation (p < 0.05), whereas diameter on US and US type were independent predictors of PIK3CA mutation in breast cancer (all p < 0.05). Meanwhile, Luminal B/Human epidermal growth factor receptor two-positive (HER2+), HER2+/estrogen receptor-negative (ER-), and triple-negative breast cancer (TNBC) subtypes were strong predictors of TP53 mutation (odds ratio [OR] = 3.13, 3.18, 3.44, respectively, all p < 0.05). HER2+/ER- and TNBC subtypes were negative predictors of PIK3CA mutation (OR = 0.223, 0.241, respectively, all p < 0.05). The areas under curves (AUCs) for PIK3CA mutation in the training set increased from 0.553-0.610 to 0.741 in the multivariate model that combined US features and molecular subtype, with a sensitivity and specificity of 80.6% and 58.7%, respectively. The application of the multivariate model in the validation set achieved acceptable discrimination (AUC = 0.715). For TP53 mutation, the AUC was 0.653.

CONCLUSION

US is a non-invasive modality to recognize the presence of TP53 and PIK3CA mutation. The models combined with US features and molecular subtype have implications for the practical application of predicting gene mutation for individual decision-making regarding treatment planning.

An AI model of sonographer’s evaluation+ S-Detect + elastography + clinical information improves the preoperative identification of benign and malignant breast masses

Purpose

The purpose of the study was to build an AI model with selected preoperative clinical features to further improve the accuracy of the assessment of benign and malignant breast nodules.

Methods

Patients who underwent ultrasound, strain elastography, and S-Detect before ultrasound-guided biopsy or surgical excision were enrolled. The diagnosis model was built using a logistic regression model. The diagnostic performances of different models were evaluated and compared.

Results

A total of 179 lesions (101 benign and 78 malignant) were included. The whole dataset consisted of a training set (145 patients) and an independent test set (34 patients). The AI models constructed based on clinical features, ultrasound features, and strain elastography to predict and classify benign and malignant breast nodules had ROC AUCs of 0.87, 0.81, and 0.79 in the test set. The AUCs of the sonographer and S-Detect were 0.75 and 0.82, respectively, in the test set. The AUC of the combined AI model with the best performance was 0.89 in the test set. The combined AI model showed a better specificity of 0.92 than the other models. The sonographer’s assessment showed better sensitivity (0.97 in the test set).

Conclusion

The combined AI model could improve the preoperative identification of benign and malignant breast masses and may reduce unnecessary breast biopsies.

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images—437 benign, 210, malignant, and 133 normal—were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1–84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.

Development and Validation of a Simple-to-Use Nomogram for Predicting the Upgrade of Atypical Ductal Hyperplasia on Core Needle Biopsy in Ultrasound-Detected Breast Lesions

Background

The rate of carcinoma upgrade for atypical ductal hyperplasia (ADH) diagnosed on core needle biopsy (CNB) is variable on open excision. The purpose of the present study was to develop and validate a simple-to-use nomogram for predicting the upgrade of ADH diagnosed with ultrasound (US)-guided core needle biopsy in patients with US-detected breast lesions.

Methods

Two retrospective sets, the training set (n = 401) and the validation set (n = 186), from Fudan University Shanghai Cancer Center between January 2014 and December 2019 were retrospectively analyzed. Clinicopathological and US features were selected using univariate and multivariable logistic regression, and the significant features were incorporated to build a nomogram model. Model discrimination and calibration were assessed in the training set and validation set.

Results

Of the 587 ADH biopsies, 67.7% (training set: 267/401, 66.6%; validation set: 128/186, 68.8%) were upgraded to cancers. In the multivariable analysis, the risk factors were age [odds ratio (OR) 2.739, 95% confidence interval (CI): 1.525–5.672], mass palpation (OR 3.008, 95% CI: 1.624–5.672), calcifications on US (OR 4.752, 95% CI: 2.569–9.276), ADH extent (OR 3.150, 95% CI: 1.951–5.155), and suspected malignancy (OR 4.162, CI: 2.289–7.980). The model showed good discrimination, with an area under curve (AUC) of 0.783 (95% CI: 0.736–0.831), and good calibration (p = 0.543). The application of the nomogram in the validation set still had good discrimination (AUC = 0.753, 95% CI: 0.666–0.841) and calibration (p = 0.565). Instead of surgical excision of all ADHs, if those categorized with the model to be at low risk for upgrade were surveillanced and the remainder were excised, then 63.7% (37/58) of surgeries of benign lesions could have been avoided and 78.1% (100/128) malignant lesions could be treated in time.

Conclusions

This study developed a simple-to-use nomogram by incorporating clinicopathological and US features with the overarching goal of predicting the probability of upgrade in women with ADH. The nomogram could be expected to decrease unnecessary surgery by nearly two-third and to identify most of the malignant lesions, helping guide clinical decision making with regard to surveillance versus surgical excision of ADH lesions.

Diagnostic Value of Contrast-Enhanced Ultrasonography With SonoVue in the Differentiation of Benign and Malignant Breast Lesions: A Meta-Analysis

PURPOSE

A meta-analysis was conducted to evaluate the diagnostic performance of contrast-enhanced ultrasonography using the contrast agent SonoVue to differentiate benign from malignant breast lesions.

METHOD

A comprehensive search of the literature was performed using the Embase, PubMed, and Web of Science databases to retrieve studies published before February 2020. Data were extracted, and pooled sensitivity, specificity, and diagnostic odds ratios were calculated with meta-analysis software. Heterogeneity was evaluated via the Q test and I² statistic. Meta-regression and subgroup analyses were applied to evaluate potential sources of heterogeneity. Publication bias was assessed using the Deeks' funnel plot asymmetry test. A summary receiver operating characteristic curve (SROC) was constructed.

RESULTS

A total of 27 studies including 5378 breast lesions subjected to CEUS examination with SonoVue were included in the meta-analysis. The pooled sensitivity and specificity values were 0.90 (95% confidence interval [CI], 0.88-0.91; inconsistency index [I²] = 75.7%) and 0.83 (95% CI, 0.82-0.85; I² = 91.0%), respectively. The pooled diagnostic odds ratio was 48.35% (95% CI, 31.22-74.89; I² = 77.6%). The area under the summary receiver operating characteristic curve (AUC) was 0.9354. Meta-regression analysis revealed the region of patient residence and dose of contrast agent as potential sources of heterogeneity (P < .01). Subgroup analysis showed a higher area under the summary receiver operating characteristic curve for European and higher contrast agent dose subgroups (P < .05).

CONCLUSION

Contrast-enhanced ultrasonography with SonoVue displays high sensitivity, specificity, and accuracy when differentiating benign from malignant breast lesions. Despite its current limitations, this technique presents a promising tool for diagnosing breast lesions in clinical practice.

Computer-aided diagnosis system of thyroid nodules ultrasonography: Diagnostic performance difference between computer-aided diagnosis and 111 radiologists

To evaluate the diagnostic efficiency of computer-aided diagnosis (CAD) system and 111 radiologists with different experience in identifying benign and malignant thyroid nodules, and to summarize the ultrasound features that may affect the diagnostic of CAD and radiologists.Fifty thyroid nodules and 111 radiologists were enrolled in this study. All the 50 nodules were diagnosed by the 111 radiologists and the CAD system simultaneously. The diagnostic performance of the CAD system, senior and junior radiologists with the maximum accuracy were calculated and compared. Interobserver agreement for different ultrasound characteristics between the CAD and senior radiologist were analyzed.CAD system showed a higher specificity than junior radiologist (87.5% vs 70.4%, P = .03), and a lower sensitivity than the senior radiologist and junior radiologist but the statistics were not significant (76.9% vs 86.9%, P > .5; 76.9% vs 82.6%, P > .5). The CAD system and senior radiologist got larger AUC than junior radiologist but the differences were not statistically significant (0.82 vs 0.76, respectively; P = .5). The interobserver agreement for the US characteristics between the CAD system and senior radiologist were: substantial agreement for hypoechoic and taller than wide (kappa value = 0.66, 0.78), and moderate agreement for irregular margin and micro-calcifications (kappa value = 0.52, 0.42).The CAD system achieved equal diagnostic accuracy to the senior radiologists and higher accuracy than the junior radiologists. The interobserver agreements in the US features between the CAD system and senior radiologist were substantial agreement for hypoechoic and taller than wide; moderate agreement for irregular margin and micro-calcifications. The location of a thyroid nodule and the feature of macrocalcification with wide acoustic shadow may influence the analysis of the CAD system.

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%.

Screening Breast Ultrasound Using Handheld or Automated Technique in Women with Dense Breasts

In women with dense breasts (heterogeneously or extremely dense), adding screening ultrasound to mammography increases detection of node-negative invasive breast cancer. Similar incremental cancer detection rates averaging 2.1-2.7 per 1000 have been observed for physician- and technologist-performed handheld ultrasound (HHUS) and automated ultrasound (AUS). Adding screening ultrasound (US) for women with dense breasts significantly reduces interval cancer rates. Training is critical before interpreting examinations for both modalities, and a learning curve to achieve optimal performance has been observed. On average, about 3% of women will be recommended for biopsy on the prevalence round because of screening US, with a wide range of 2%-30% malignancy rates for suspicious findings seen only on US. Breast Imaging Reporting and Data System 3 lesions identified only on screening HHUS can be safely followed at 1 year rather than 6 months. Computer-aided detection and diagnosis software can augment performance of AUS and HHUS; ongoing research on machine learning and deep learning algorithms will likely improve outcomes and workflow with screening US.

A review of computer aided detection in mammography

Breast screening with mammography is widely recognized as the most effective method of detecting early breast cancer and has consistently demonstrated a 20-40% decrease in mortality among screened women. Despite this, the sensitivity of mammography ranges between 70 and 90%. Computer aided detection (CAD) is an artificial intelligence (AI) technique that utilizes pattern recognition to highlight suspicious features on imaging and marks them for the radiologist to review and interpret. It aims to decrease oversights made by interpreting radiologists. Here we review the efficacy of CAD and potential future directions.

False Positive Reduction by an Annular Model as a Set of Few Features for Microcalcification Detection to Assist Early Diagnosis of Breast Cancer

Early automatic breast cancer detection from mammograms is based on the extraction of lesions, known as microcalcifications (MCs). This paper proposes a new and simple system for microcalcification detection to assist in early breast cancer detection. This work uses the two most recognized public mammogram databases, MIAS and DDSM. We are introducing a MC detection method based on (1) Beucher gradient for detection of regions of interest (ROIs), (2) an annulus model for extraction of few and effective features from candidates to MCs, and (3) one classification stage with two different classifiers, k Nearest Neighbor (KNN) and Support Vector Machine (SVM). For dense mammograms in the MIAS database, the performance metrics achieved are sensitivity of 0.9835, false alarm rate of 0.0083, accuracy of 0.9835, and area under the ROC curve of 0.9980 with a KNN classifier. The proposed MC detection method, based on a KNN classifier, achieves, a sensitivity, false positive rate, accuracy and area under the ROC curve of 0.9813, 0.0224, 0.9795 and 0.9974 for the MIAS database; and 0.9035, 0.0439, 0.9298 and 0.9759 for the DDSM database. By slightly reducing the true positive rate the method achieves three instances with false positive rate of 0: 2 on fatty mammograms with KNN and SVM, and one on dense with SVM. The proposed method gives better results than those from state of the art literature, when the mammograms are classified in fatty, fatty-glandular, and dense.

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.