Assessment of three different software systems in the evaluation of dynamic MRI of the breast

Past, Present, and Future of Machine Learning and Artificial Intelligence for Breast Cancer Screening

Breast cancer screening has evolved substantially over the past few decades because of advancements in new image acquisition systems and novel artificial intelligence (AI) algorithms. This review provides a brief overview of the history, current state, and future of AI in breast cancer screening and diagnosis along with challenges involved in the development of AI systems. Although AI has been developing for interpretation tasks associated with breast cancer screening for decades, its potential to combat the subjective nature and improve the efficiency of human image interpretation is always expanding. The rapid advancement of computational power and deep learning has increased greatly in AI research, with promising performance in detection and classification tasks across imaging modalities. Most AI systems, based on human-engineered or deep learning methods, serve as concurrent or secondary readers, that is, as aids to radiologists for a specific, well-defined task. In the future, AI may be able to perform multiple integrated tasks, making decisions at the level of or surpassing the ability of humans. Artificial intelligence may also serve as a partial primary reader to streamline ancillary tasks, triaging cases or ruling out obvious normal cases. However, before AI is used as an independent, autonomous reader, various challenges need to be addressed, including explainability and interpretability, in addition to repeatability and generalizability, to ensure that AI will provide a significant clinical benefit to breast cancer screening across all populations.

MRI of the Lactating Breast: Computer-Aided Diagnosis False Positive Rates and Background Parenchymal Enhancement Kinetic Features

RATIONALE AND OBJECTIVES

To investigate the application of computer-added diagnosis (CAD) in dynamic contrast-enhanced (DCE) MRI of the healthy lactating breast, focusing on false-positive rates and background parenchymal enhancement (BPE) coloring patterns in comparison with breast cancer features in non-lactating patients.

MATERIALS AND METHODS

The study population was composed of 58 healthy lactating patients and control groups of 113 healthy premenopausal non-lactating patients and 55 premenopausal non-lactating patients with newly-diagnosed breast cancer. Patients were scanned on 1.5-T MRI using conventional DCE protocol. A retrospective analysis of DCE-derived CAD properties was conducted using a commercial software that is regularly utilized in our routine radiological work-up. Qualitative morphological characterization and automatically-obtained quantitative parametric measurements of the BPE-induced CAD coloring were categorized and subgroups' trends and differences between the lactating and cancer cohorts were statistically assessed.

RESULTS

CAD false-positive coloring was found in the majority of lactating cases (87%). Lactation BPE coloring was characteristically non-mass enhancement (NME)-like shaped (87%), bilateral (79%) and symmetric (64%), whereas, unilateral coloring was associated with prior irradiation (p <0.0001). Inter-individual variability in CAD appearance of both scoring-grade and kinetic-curve dominance was found among the lactating cohort. When compared with healthy non-lactating controls, CAD false positive probability was significantly increased [Odds ratio 40.2, p <0001], while in comparison with the breast cancer cohort, CAD features were mostly inconclusive, even though increased size parameters were significantly associated with lactation-BPE (p <0.00001).

CONCLUSION

BPE was identified as a common source for false-positive CAD coloring on breast DCE-MRI among lactating population. Despite several typical characteristics, overlapping features with breast malignancy warrant a careful evaluation and clinical correlation in all cases with suspected lactation induced CAD coloring.

Percentage volume of delayed kinetics in computer-aided diagnosis of MRI of the breast to reduce false-positive results and unnecessary biopsies

AIM

To investigate the best cut-off percentage volume of delayed kinetics using magnetic resonance imaging (MRI) with computer-aided diagnosis (CAD) to reduce unnecessary biopsies in patients with newly diagnosed breast cancer.

MATERIALS AND METHODS

Between January 2017 and December 2018, 94 malignant and 56 benign masses were analysed using MRI CAD. All malignant and benign masses measured <2 cm and were confirmed histopathologically. The optimal cut-off values for washout, plateau, and persistent components were determined using the maximum Youden Index. The positive predictive value (PPV) was analysed using morphological descriptors and combining the percentage volume of delayed kinetics.

RESULTS

The area under the curve (AUC) was highest at ≤73% persistent component (AUC=0.759). In the subgroup analyses of masses <1 cm, the AUC was highest a plateau of >26% (AUC=0.697). When the persistent ≤73% criterion was applied to the lesions of C4a, the positive predictive value (PPV) increased from 61.9% to 72.44% with reduced false-negative cases and when applied to the lesions of C4a and C4b, the PPV increased from 61.9% to 78.1% with slightly increased false-negative cases. For subcentimetre lesions, the PPV increased from 46.77% to 54.72% with the same number of false-negative cases, when a plateau of >26% was applied to C4a, and the PPV increased from 46.77% to 61.36% with five false-negative cases when applied to C4a and C4b.

CONCLUSION

The percentage volume of delayed kinetics has the potential to improve the PPV of breast MRI. When suspicious masses <2 cm do not show ≤73% persistence, follow-up rather than biopsy could be considered; however, to avoid increasing false-negative cases, delayed kinetic information should be used with caution and accurate margin assessment is essential.

Determination of recall rates for assessment in high-risk women undergoing annual surveillance breast MRI

AIM

To review all surveillance breast magnetic resonance imaging (MRI) examinations performed over a 6-year period at an Irish national centre to determine the recall rate, biopsy rate, and cancer-detection rates.

MATERIALS AND METHODS

All breast MRI examinations performed for surveillance purposes in women at high risk of developing breast cancer between January 2009 and December 2014 were reviewed. The Breast Imaging-Reporting and Data System (BI-RADS) score for each MRI examination was determined, the type of additional imaging performed, and the method of biopsy, if performed, was recorded. Histology of the biopsy specimens was reviewed.

RESULTS

Data for 715 women undergoing 1445 surveillance MRI examinations were identified. Of the examinations, 10.9% (157/1445) had MRI BI-RADS scores that required recall for further imaging and 6.3% (91/1445) required a biopsy. Recall rates were 14.2% (86/607) and 8.5% (71/838) in the prevalent and incident rounds, respectively. The overall cancer detection rate was 17 per 1000.

CONCLUSION

The current UK guideline was not achieved and no studies to date have achieved the target of <7%. Aiming for this target could risk lowering the cancer-detection rate. The authors would suggest a target rate of <15% and <10% for the prevalent round and incident rounds, respectively.

Comparing performance of the CADstream and the DynaCAD breast MRI CAD systems : CADstream vs. DynaCAD in breast MRI

Computer-aided diagnosis (CAD) systems are software programs that use algorithms to find patterns associated with breast cancer on breast magnetic resonance imaging (MRI). The most commonly used CAD systems in the USA are CADstream (CS) (Merge Healthcare Inc., Chicago, IL) and DynaCAD for Breast (DC) (Invivo, Gainesville, FL). Our primary objective in this study was to compare the CS and DC breast MRI CAD systems for diagnostic accuracy and postprocessed image quality. Our secondary objective was to compare the evaluation times of radiologists using each system. Three radiologists evaluated 30 biopsy-proven malignant lesions and 29 benign lesions on CS and DC and rated the lesions' malignancy status using the Breast Imaging Reporting and Data System. Image quality was ranked on a 0-5 scale, and mean reading times were also recorded. CS detected 70 % of the malignant and 32 % of the benign lesions while DC detected 81 % of the malignant lesions and 34 % of the benign lesions. Analysis of the area under the receiver operating characteristic curve revealed that the difference in diagnostic performance was not statistically significant. On image quality scores, CS had significantly higher volume rendering (VR) (p < 0.0001) and motion correction (MC) scores (p < 0.0001). There were no statistically significant differences in the remaining image quality scores. Differences in evaluation times between DC and CS were also not statistically significant. We conclude that both CS and DC perform similarly in aiding detection of breast cancer on MRI. MRI CAD selection will likely be based on other factors, such as user interface and image quality preferences, including MC and VR.

Performance of a fully automatic lesion detection system for breast DCE-MRI

PURPOSE

To describe and test a new fully automatic lesion detection system for breast DCE-MRI.

MATERIALS AND METHODS

Studies were collected from two institutions adopting different DCE-MRI sequences, one with and the other one without fat-saturation. The detection pipeline consists of (i) breast segmentation, to identify breast size and location; (ii) registration, to correct for patient movements; (iii) lesion detection, to extract contrast-enhanced regions using a new normalization technique based on the contrast-uptake of mammary vessels; (iv) false positive (FP) reduction, to exclude contrast-enhanced regions other than lesions. Detection rate (number of system-detected malignant and benign lesions over the total number of lesions) and sensitivity (system-detected malignant lesions over the total number of malignant lesions) were assessed. The number of FPs was also assessed.

RESULTS

Forty-eight studies with 12 benign and 53 malignant lesions were evaluated. Median lesion diameter was 6 mm (range, 5-15 mm) for benign and 26 mm (range, 5-75 mm) for malignant lesions. Detection rate was 58/65 (89%; 95% confidence interval [CI] 79%-95%) and sensitivity was 52/53 (98%; 95% CI 90%-99%). Mammary median FPs per breast was 4 (1st-3rd quartiles 3-7.25).

CONCLUSION

The system showed promising results on MR datasets obtained from different scanners producing fat-sat or non-fat-sat images with variable temporal and spatial resolution and could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve lesion detection. Further evaluation is needed before it may be used in clinical practice.

Computer-aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T

Objective

The purpose of the study was to evaluate the accuracy of 3.0-T breast MRI interpretation using manual and fully automated kinetic analyses.

Material and methods

Manual MRI interpretation was done on an Advantage Workstation. Retrospectively, all examinations were processed with a computer-aided detection (CAD) system. CAD data sets were interpreted by two experienced breast radiologists and two residents. For each lesion automated analysis of enhancement kinetics was evaluated at 50% and 100% thresholds. Forty-nine malignant and 22 benign lesions were evaluated.

Results

Using threshold enhancement alone, the sensitivity and specificity of CAD were 97.9% and 86.4%, respectively, for the 50% threshold, and 97.9% and 90%, respectively, for the 100% threshold. Manual interpretation by two breast radiologists showed a sensitivity of 84.6% and a specificity of 68.8%. For the same two radiologists the mean sensitivity and specificity for CAD-based interpretation was 90.4% (not significant) and 81.3% (significant at p < 0.05), respectively. With one-way ANOVA no significant differences were found between the two breast radiologists and the two residents together, or between any two readers separately.

Conclusion

CAD-based analysis improved the specificity compared with manual analysis of enhancement. Automated analysis at 50% and 100% thresholds showed a high sensitivity and specificity for readers with varying levels of experience.