Response to neoadjuvant treatment of invasive ductal breast carcinomas including outcome evaluation: MRI analysis by an automatic CAD system in comparison to visual evaluation

Imaging findings for response evaluation of ductal carcinoma in situ in breast cancer patients treated with neoadjuvant systemic therapy: a systematic review and meta-analysis

OBJECTIVES

In approximately 45% of invasive breast cancer (IBC) patients treated with neoadjuvant systemic therapy (NST), ductal carcinoma in situ (DCIS) is present. Recent studies suggest response of DCIS to NST. The aim of this systematic review and meta-analysis was to summarise and examine the current literature on imaging findings for different imaging modalities evaluating DCIS response to NST. More specifically, imaging findings of DCIS pre- and post-NST, and the effect of different pathological complete response (pCR) definitions, will be evaluated on mammography, breast MRI, and contrast-enhanced mammography (CEM).

METHODS

PubMed and Embase databases were searched for studies investigating NST response of IBC, including information on DCIS. Imaging findings and response evaluation of DCIS were assessed for mammography, breast MRI, and CEM. A meta-analysis was conducted per imaging modality to calculate pooled sensitivity and specificity for detecting residual disease between pCR definition no residual invasive disease (ypT0/is) and no residual invasive or in situ disease (ypT0).

RESULTS

Thirty-one studies were included. Calcifications on mammography are related to DCIS, but can persist despite complete response of DCIS. In 20 breast MRI studies, an average of 57% of residual DCIS showed enhancement. A meta-analysis of 17 breast MRI studies confirmed higher pooled sensitivity (0.86 versus 0.82) and lower pooled specificity (0.61 versus 0.68) for detection of residual disease when DCIS is considered pCR (ypT0/is). Three CEM studies suggest the potential benefit of simultaneous evaluation of calcifications and enhancement.

CONCLUSIONS AND CLINICAL RELEVANCE

Calcifications on mammography can remain despite complete response of DCIS, and residual DCIS does not always show enhancement on breast MRI and CEM. Moreover, pCR definition effects diagnostic performance of breast MRI. Given the lack of evidence on imaging findings of response of the DCIS component to NST, further research is demanded.

KEY POINTS

• Ductal carcinoma in situ has shown to be responsive to neoadjuvant systemic therapy, but imaging studies mainly focus on response of the invasive tumour. • The 31 included studies demonstrate that after neoadjuvant systemic therapy, calcifications on mammography can remain despite complete response of DCIS and residual DCIS does not always show enhancement on MRI and contrast-enhanced mammography. • The definition of pCR has impact on the diagnostic performance of MRI in detecting residual disease, and when DCIS is considered pCR, pooled sensitivity was slightly higher and pooled specificity slightly lower.

Artificial Intelligence and Myocardial Contrast Enhancement Pattern

PURPOSE OF REVIEW

Machine learning (ML) and deep learning (DL) are two important categories of AI algorithms. Nowadays, AI technology has been gradually applied to cardiac magnetic resonance imaging (CMRI), covering the fields of myocardial contrast enhancement (MCE) pattern and automatic ventricular segmentation. This paper mainly discusses the relationship between machine learning and deep learning based on AI and pattern of MCE in CMRI.

RECENT FINDINGS

It found that some histogram and GLCM parameters in ML algorithm had significant statistical differences in diagnosis of cardiomyopathy and differentiation of fibrosis and normal myocardial tissue. In the DL algorithm, there was no significant difference between CNN and observers in measuring myocardial fibrosis. The rapid development of texture parameter analysis methods would promote the medical imaging based on AI into a new era. Histogram and GLCM parameters are the research hotspot of unsupervised learning of MCE images. CNN has a great advantage in automatically identifying and quantifying myocardial fibrosis reflected by LGE images.

The Diagnostic Performance of DCE-MRI in Evaluating the Pathological Response to Neoadjuvant Chemotherapy in Breast Cancer: A Meta-Analysis

Background: Neoadjuvant chemotherapy (NAC) is commonly utilized in preoperative treatment for local breast cancer, and it gives high clinical response rates and can result in pathologic complete response (pCR) in 6–25% of patients. In recent years, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has been increasingly used to assess the pathological response of breast cancer to NAC. In present analysis, we assess the diagnostic performance of DCE-MRI in evaluating the pathological response of breast cancer to NAC.

Materials and Methods: A systematic search in PubMed, the Cochrane Library, and Web of Science for original studies was performed. The Quality Assessment of Diagnostic Accuracy Studies-2 tool was used to assess the methodological quality of the included studies. Patient, study, and imaging characteristics were extracted, and sufficient data to reconstruct 2 × 2 tables were obtained. Data pooling, heterogeneity testing, forest plot construction, meta-regression analysis and sensitivity analysis were performed using Stata version 12.0 (StataCorp LP, College Station, TX).

Results: Eighteen studies (969 patients with breast cancer) were included in the present meta-analysis. The pooled sensitivity and specificity of DCE-MRI were 0.80 (95% confidence interval [CI]: 0.70, 0.88) and 0.84 (95% [CI]: 0.79, 0.88), respectively. Meta-regression analysis found no significant factors affecting heterogeneity. Sensitivity analysis showed that studies that set pathological complete response (pCR) (n = 14) as a responder showed a tendency for higher sensitivity compared with those that set pCR and near pCR together (n = 5) as a responder (0.83 vs. 0.72), and studies (n = 14) that used DCE-MRI to early predict the pathological response of breast cancer had a higher sensitivity (0.83 vs. 0.71) and equivalent specificity (0.80 vs. 0.86) compared to studies (n = 5) that assessed the response after NAC completion.

Conclusion: Our results indicated that DCE-MRI could be considered an important auxiliary method for evaluating the pathological response of breast cancer to NAC and used as an effective method for dynamically monitoring the efficacy during NAC. DCE-MRI also performed well in predicting the pCR of breast cancer to NAC. However, due to the heterogeneity of the included studies, caution should be exercised in applying our results.

A Universal Intensity Standardization Method Based on a Many-to-One Weak-Paired Cycle Generative Adversarial Network for Magnetic Resonance Images

In magnetic resonance imaging (MRI), different imaging settings lead to various intensity distributions for a specific imaging object, which brings huge diversity to data-driven medical applications. To standardize the intensity distribution of magnetic resonance (MR) images from multiple centers and multiple machines using one model, a cycle generative adversarial network (CycleGAN)-based framework is proposed. It utilizes a unified forward generative adversarial network (GAN) path and multiple independent backward GAN paths to transform images in different groups into a single reference one. To preserve image details and prevent resolution loss, two jump connections are applied in the CycleGAN generators. A weak-pair strategy is designed to fully utilize the prior knowledge of the organ structure and promote the performance of the GANs. The experiments were conducted on a T2-FLAIR image database with 8192 slices from 489 patients. The database was obtained from four hospitals and five MRI scanners and was divided into nine groups with different imaging parameters. Compared with the representative algorithms, the peak signal-to-noise ratio, the histogram correlation, and the structural similarity were increased by 3.7%, 5.1%, and 0.1% on average, respectively; the gradient magnitude similarity deviation, the mean square error, and the average disparity were reduced by 19.0%, 15.7%, and 9.9% on average, respectively. Experiments also showed the robustness of the proposed model with a different training set configuration and effectiveness of the proposed framework over the original CycleGAN. Therefore, the MR images with different imaging settings could be efficiently standardized by the proposed method, which would benefit various data-driven applications.

Meta-Analysis of Quantitative Dynamic Contrast-Enhanced MRI for the Assessment of Neoadjuvant Chemotherapy in Breast Cancer

The purpose of this meta-analysis was to determine the value of quantitative dynamic contrast-enhanced (DCE) MRI (DCE-MRI) in evaluating the response of breast cancer to neoadjuvant chemotherapy (NAC). PubMed, Embase, and Cochrane Library databases (from building to July 31, 2018) were searched to collect articles about the therapeutic evaluation of NAC using the quantitative DCE-MRI in patients with breast cancer. The sensitivities and specificities of quantitative DCE-MRI in the evaluation of NAC for breast cancer were extracted from the articles. Meta-DiSc1.4 was applied to evaluate the efficacy of the sensitivity and specificity; forest figure and summary receiver operating characteristics (SROC) were created. A total of 356 articles were enrolled in this study, including 739 cases in total, in which 218 cases were effective and the other 521 cases were ineffective to NAC, considering the pathological results as the gold standard. The sensitivity and specificity in the included 14 articles of quantitative DCE-MRI ( Ktrans, kep, and ve) in comprehensively evaluating NAC for breast cancer were 84 per cent (95% confidence interval (CI): 78–88%) and 83 per cent (95% CI: 79–86%), respectively. The area under SROC was 0.899 (95% CI: 0.867–0.943). The sensitivity and specificity in the three articles of Ktrans evaluating NAC for breast cancer were 84.1 per cent (95% CI: 71.0–92.1%) and 81.3 per cent (95% CI: 70.5%-88.5%), respectively. The area under SROC was 0.899 (95% CI: 0.834–0.962). Our study confirmed that the quantitative DCE-MRI is able to monitor NAC treatment for breast cancer because of its high sensitivity and specificity. However, there is a high degree of heterogeneity in published studies, highlighting the lack of standardization in the field.

Modified Quality Threshold Clustering for Temporal Analysis and Classification of Lung Lesions

Lung cancer is the type of cancer that most often kills after the initial diagnosis. To aid the specialist in its diagnosis, temporal evaluation is a potential tool for analyzing indeterminate lesions, which may be benign or malignant, during treatment. With this goal in mind, a methodology is herein proposed for the analysis, quantification, and visualization of changes in lung lesions. This methodology uses a modified version of the quality threshold clustering algorithm to associate each voxel of the lesion to a cluster, and changes in the lesion over time are defined in terms of voxel moves to another cluster. In addition, statistical features are extracted for classification of the lesion as benign or malignant. To develop the proposed methodology, two databases of pulmonary lesions were used, one for malignant lesions in treatment (public) and the other for indeterminate cases (private). We determined that the density change percentage varied from 6.22% to 36.93% of lesion volume in the public database of malignant lesions under treatment and from 19.98% to 38.81% in the private database of lung nodules. Additionally, other inter-cluster density change measures were obtained. These measures indicate the degree of change in the clusters and how each of them is abundant in relation to volume. From the statistical analysis of regions in which the density changes occurred, we were able to discriminate lung lesions with an accuracy of 98.41%, demonstrating that these changes can indicate the true nature of the lesion. In addition to visualizing the density changes occurring in lesions over time, we quantified these changes and analyzed the entire set through volumetry, which is the technique most commonly used to analyze changes in pulmonary lesions.

Classification of breast mass lesions on dynamic contrast-enhanced magnetic resonance imaging by a computer-assisted diagnosis system based on quantitative analysis

The aim of the current study was to develop a semi-automatic and quantitative method for the analysis of a time-intensity curve (TIC) from breast dynamic contrast-enhanced magnetic resonance imaging. The performance of the proposed method, based on the level set segmentation algorithm, was evaluated by comparison with the traditional method. In the traditional method, the lesion area is delineated manually and the corresponding mean TIC is classified subjectively as one of three washout patterns. In addition, only one quantitative parameter, the maximum slope of increase (MSI), is calculated. In the proposed method, the lesion region was determined semi-automatically and the corresponding mean TIC was categorized quantitatively. In addition to MSI, a number of quantitative parameters were derived from the mean TIC and lesion area, including signal intensity slope (SI_slope), initial percentage of enhancement (E_initial), percentage of peak enhancement (E_peak), early signal enhancement ratio (ESER) and second enhancement percentage (SEP). Wilcoxon signed-rank test and receiver operating characteristic analyses were performed for statistical analysis. For TIC categorization the accuracy was 61.54% for the traditional method and 82.05% for the proposed method. Using the proposed method, mean curve accuracies were 84.0% for SI_slope, 66.7% for MSI, 66.0% for E_initial, 66.0% for E_peak, 68.0% for ESER and 44.9% for SEP. In the lesion region, the accuracies for the aforementioned parameters were 80.8, 65.4, 66.7, 62.2, 69.2 and 57.1%, respectively. Accuracy of the MSI value derived from the traditional method was 63.4%. Compared with the traditional method, the proposed semi-automatic method in the current study may provide results with a higher accuracy to differentiate benign and malignant lesions. Therefore, the proposed method should be considered as a supplementary tool for the diagnosis of breast lesions.

Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves

Purpose: To investigate the performance of a new semi-automatic method for analyzing the signal time-intensity curve (TIC) obtained by breast dynamic contrast enhancement (DCE)-MRI.

Methods: In the conventional method, a circular region of interest was drawn manually onto the map reflecting the maximum slope of increase (MSI) to delineate the suspicious lesions. The mean TIC was determined subjectively as one of three different wash-out patterns. In the new method, the lesion area was identified semi-automatically. The mean TIC was categorized quantitatively. In addition to the MSI, other quantitative parameters were calculated, including the signal intensity slope (SI_slope), initial percentage of enhancement (E_initial), percentage of peak enhancement (E_peak), early signal enhancement ratio (ESER), and second enhancement percentage (SEP). The performances were compared with receiver operating characteristic (ROC) analysis and Wilcoxon's test.

Results: For TIC categorization results, the diagnostic accuracy rates were 61.54% with the traditional manual method and 76.92% with the new method. For the mean MSI values from the manual method, the accuracy was 63.41%. For the mean TIC derived using the semi-automatic method, the diagnostic accuracy were 82.05% for SI_slope, 67.31% for MSI, 61.53% for E_initial, 64.75% for E_peak, 64.74% for ESER, and 52.56% for SEP, respectively. For the lesion regions identified by the semi-automatic method, the diagnostic accuracy for above mentioned parameters were 80.13%, 69.87%, 61.54%, 63.47%, 64.74% and 55.13%, respectively.

Conclusion: With respect to the analysis of TIC from breast DCE-MRI, the results demonstrated that the new method increased the diagnostic accuracy, and should be considered as a supplementary tool for distinguishing benign and malignant lesions.

Statistical tools for the temporal analysis and classification of lung lesions

BACKGROUND AND OBJECTIVE

Lung cancer remains one of the most common cancers globally. Temporal evaluation is an important tool for analyzing the malignant behavior of lesions during treatment, or of indeterminate lesions that may be benign. This work proposes a methodology for the analysis, quantification, and visualization of small (local) and large (global) changes in lung lesions. In addition, we extract textural features for the classification of lesions as benign or malignant.

METHODS

We employ the statistical concept of uncertainty to associate each voxel of a lesion to a probability that changes occur in the lesion over time. We employ the Jensen divergence and hypothesis test locally to verify voxel-to-voxel changes, and globally to capture changes in lesion volumes.

RESULTS

For the local hypothesis test, we determine that the change in density varies by between 3.84 and 40.01% of the lesion volume in a public database of malignant lesions under treatment, and by between 5.76 and 35.43% in a private database of benign lung nodules. From the texture analysis of regions in which the density changes occur, we are able to discriminate lung lesions with an accuracy of 98.41%, which shows that these changes can indicate the true nature of the lesion.

CONCLUSION

In addition to the visual aspects of the density changes occurring in the lesions over time, we quantify these changes and analyze the entire set using volumetry. In the case of malignant lesions, large b-divergence values are associated with major changes in lesion volume. In addition, this occurs when the change in volume is small but is associated with significant changes in density, as indicated by the histogram divergence. For benign lesions, the methodology shows that even in cases where the change in volume is small, a change of density occurs. This proves that even in lesions that appear stable, a change in density occurs.

Relating Doses of Contrast Agent Administered to TIC and Semi-Quantitative Parameters on DCE-MRI: Based on a Murine Breast Tumor Model

Objective

To explore the changes in the time-signal intensity curve(TIC) type and semi-quantitative parameters of dynamic contrast-enhanced(DCE)imaging in relation to variations in the contrast agent(CA) dosage in the Walker 256 murine breast tumor model, and to determine the appropriate parameters for the evaluation ofneoadjuvantchemotherapy(NAC)response.

Materials and Methods

Walker 256 breast tumor models were established in 21 rats, which were randomly divided into three groups of7rats each. Routine scanning and DCE-magnetic resonance imaging (MRI) of the rats were performed using a 7T MR scanner. The three groups of rats were administered different dosages of the CA0.2mmol/kg, 0.3mmol/kg, and 0.5mmol/kg, respectively; and the corresponding TICs the semi-quantitative parameters were calculated and compared among the three groups.

Results

The TICs were not influenced by the CA dosage and presented a washout pattern in all of the tumors evaluated and weren’t influenced by the CA dose. The values of the initial enhancement percentage(E_first), initial enhancement velocity(V_first), maximum signal(S_max), maximum enhancement percentage(E_max), washout percentage(E_wash), and signal enhancement ratio(SER) showed statistically significant differences among the three groups (F = 16.952, p = 0.001; F = 69.483, p<0.001; F = 54.838, p<0.001; F = 12.510, p = 0.003; F = 5.248, p = 0.031; F = 9.733, p = 0.006, respectively). However, the values of the time to peak(T_peak), maximum enhancement velocity(V_max), and washout velocity(V_wash)did not differ significantly among the three dosage groups (F = 0.065, p = 0.937; F = 1.505, p = 0.273; χ2 = 1.423, p = 0.319, respectively); the washout slope(Slope_wash), too, was uninfluenced by the dosage(F = 1.654, p = 0.244).

Conclusion

The CA dosage didn’t affect the TIC type, T_peak, V_max, V_wash or Slope_wash. These dose-independent parameters as well as the TIC type might be more useful for monitoring the NAC response because they allow the comparisons of the DCE data obtained using different CA dosages.

Quantitative discrimination between invasive ductal carcinomas and benign lesions based on semi-automatic analysis of time intensity curves from breast dynamic contrast enhanced MRI

Background

Traditional subjective method for the analysis of time-intensity curves (TICs) from breast dynamic contrast enhanced MRI (DCE-MRI) presented a low specificity. Hence, a semi-automatic quantitative method was proposed and evaluated for distinguishing invasive ductal carcinomas from benign lesions.

Materials and methods

In the traditional method, the lesion was extracted by placing a region of interest (ROI) manually. The mean curve of the TICs from the ROI was subjectively classified as one of three patterns. Only one quantitative parameter, the mean value of maximum slope of increase (MSI), was provided. In the new method, the lesion was identified semi-automatically, and the mean curve was classified quantitatively. Some additional parameters, the signal intensity slope (SI_slope), initial percentage of enhancement (E_initial), percentage of peak enhancement (E_peak), early signal enhancement ratio (ESER), and second enhancement percentage (SEP) were derived from the mean curves as well as the lesion areas. Wilcoxon’s test and receiver operating characteristic (ROC) analyses were performed, and P < 0.05 was considered significant.

Results

According to the TIC classification results, the accuracies were 59.16% for the traditional manual method and 76.05% for the new method (P < 0.05). For the mean MSI values from the manual method, the accuracy was 63.35%. For the mean TICs derived from the semi-automatic method, the accuracies were 77.47% for SI_slope, 65.24% for MSI, 58.45% for E_initial, 66.20% for E_peak, 71.83% for ESER, and 54.93% for SEP, respectively. For the lesion regions identified by the semi-automatic method, the accuracies were 73.24%, 72.54%, 58.45%, 62.68%, 64.09%, and 55.64%, respectively.

Conclusion

Compared with traditional subjective method, the semi-automatic quantitative method proposed in this study showed a higher performance, and should be used as a supplementary tool to aid radiologist's subjective interpretation.