Breast MRI during lactation: effects on tumor conspicuity using dynamic contrast-enhanced (DCE) in comparison with diffusion tensor imaging (DTI) parametric maps

Abstract Background Breast cancer is the most prevalent cancer among females. Dynamic contrast-enhanced MRI (DCE-MRI) breast is highly sensitive (90%) in the detection of breast cancer. Despite its high sensitivity in detecting breast cancer, its specificity (72%) is moderate. Owing to 3-T breast MRI which has the advantage of a higher signal to noise ratio and shorter scanning time rather than the 1.5-T MRI, the adding of new techniques as diffusion tensor imaging (DTI) to breast MRI became more feasible. Diffusion-weighted imaging (DWI) which tracks the diffusion of the tissue water molecule as well as providing data about the integrity of the cell membrane has been used as a valuable additional tool of DCE-MRI to increase its specificity. Based on DWI, more details about the microstructure could be detected using diffusion tensor imaging. The DTI applies diffusion in many directions so apparent diffusion coefficient (ADC) will vary according to the measured direction raising its sensitivity to microstructure elements and cellular density. This study aimed to investigate the diagnostic accuracy of DTI in the assessment of breast lesions in comparison to DWI. Results By analyzing the data of the 50 cases (31 malignant cases and 19 benign cases), the sensitivity and specificity of DWI in differentiation between benign and malignant lesions were about 90% and 63% respectively with PPV 90% and NPV 62%, while the DTI showed lower sensitivity and specificity about 81% and 51.7%, respectively, with PPV 78.9% and NPV 54.8% (P-value ≤ 0.05). Conclusion While the DWI is still the most established diffusion parameter, DTI may be helpful in the further characterization of tumor microstructure and differentiation between benign and malignant breast lesions.

Download Full-text

Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based Assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images

Diagnostics ◽

10.3390/diagnostics10050330 ◽

2020 ◽

Vol 10 (5) ◽

pp. 330

Author(s):

Mio Adachi ◽

Tomoyuki Fujioka ◽

Mio Mori ◽

Kazunori Kubota ◽

Yuka Kikuchi ◽

...

Keyword(s):

Artificial Intelligence ◽

Magnetic Resonance ◽

Diagnostic Performance ◽

Maximum Intensity Projection ◽

Breast Mri ◽

Magnetic Resonance Images ◽

Maximum Intensity ◽

Validation Data ◽

Dynamic Contrast Enhanced ◽

Contrast Enhanced

We aimed to evaluate an artificial intelligence (AI) system that can detect and diagnose lesions of maximum intensity projection (MIP) in dynamic contrast-enhanced (DCE) breast magnetic resonance imaging (MRI). We retrospectively gathered MIPs of DCE breast MRI for training and validation data from 30 and 7 normal individuals, 49 and 20 benign cases, and 135 and 45 malignant cases, respectively. Breast lesions were indicated with a bounding box and labeled as benign or malignant by a radiologist, while the AI system was trained to detect and calculate possibilities of malignancy using RetinaNet. The AI system was analyzed using test sets of 13 normal, 20 benign, and 52 malignant cases. Four human readers also scored these test data with and without the assistance of the AI system for the possibility of a malignancy in each breast. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were 0.926, 0.828, and 0.925 for the AI system; 0.847, 0.841, and 0.884 for human readers without AI; and 0.889, 0.823, and 0.899 for human readers with AI using a cutoff value of 2%, respectively. The AI system showed better diagnostic performance compared to the human readers (p = 0.002), and because of the increased performance of human readers with the assistance of the AI system, the AUC of human readers was significantly higher with than without the AI system (p = 0.039). Our AI system showed a high performance ability in detecting and diagnosing lesions in MIPs of DCE breast MRI and increased the diagnostic performance of human readers.

Download Full-text