Differentiation Of Breast Lesions Research Articles

Computer-Aided Classification of Breast Lesions Based on US RF Time Series Using a Novel Machine Learning Approach.

One of the most promising adjuncts for screening breast cancer is ultrasound (US) radio-frequency (RF) time series. It has the superiority of not requiring any supplementary equipment over other methods. This research aimed to propound a machine learning (ML) approach for automatically classifying benign, probably benign, suspicious, and malignant breast lesions based on the features extracted from the accumulated US RF time series. In this article, 220 data of the aforementioned categories, recorded from 118 patients, were analyzed. The dataset, named RFTSBU, was registered by a SuperSonic Imagine Aixplorer medical/research system equipped with a linear transducer. The regions of interest (ROIs) of the B-mode images were manually selected by an expert radiologist before computing the suggested features. Regarding time, frequency, and time-frequency domains, 291 various features were extracted from each ROI. Finally, the features were classified by a pioneering technique named the reference classification method (RCM). Furthermore, the Lee filter was applied to evaluate the effectiveness of reducing speckle noise on the outcomes. The accuracy of two-class, three-class, and four-class classifications were respectively calculated 98.59 ± 0.71%, 98.13 ± 0.69%, and 96.10 ± 0.66% (considering 10 repetitions) while support vector machine (SVM) and K-nearest neighbor (KNN) classifiers with 5-fold cross-validation were utilized. This article represented the proposed approach, named CCRFML, to distinguish between breast lesions based on registered in vivo RF time series employing an ML framework. The proposed method's impressive level of classification accuracy attests to its capability of effectively assisting medical professionals in the noninvasive differentiation of breast lesions.

Shear-Wave Elastography Gradient Analysis of Newly Diagnosed Breast Tumours: A Critical Analysis.

A better understanding of the peritumoral stroma changes due to tumour invasion using non-invasive diagnostic methods may improve the differentiation between benign and malignant breast lesions. This study aimed to assess the correlation between breast lesion differentiation and intra- and peritumoral shear-wave elastography (SWE) gradients. A total of 135 patients with newly diagnosed breast lesions were included. Intratumoral, subsurface, and three consecutive peritumoral SWE value measurements (with three repetitions) were performed. Intratumoral, interface, and peritumoral gradients (Gradient 1 and Gradient 2) were calculated using averaged SWE values. Statistical analysis included descriptive statistics and an ordinary one-way ANOVA to compare overall and individual gradients among Breast Imaging-Reporting and Data System (BI-RADS) 2, 3, and 5 groups. Malignant tumours showed higher average SWE velocity values at the tumour centre (BI-RADS 2/3: 4.1 ± 1.8 m/s vs. BI-RADS 5: 4.9 ± 2.0 m/s, p = 0.04) and the first peritumoral area (BI-RADS 2/3: 3.4 ± 1.8 m/s vs. BI-RADS 5: 4.3 ± 1.8 m/s, p = 0.003). No significant difference was found between intratumoral gradients (0.03 ± 0.32 m/s vs. 0.0 ± 0.28 m/s; p > 0.999) or gradients across the tumour-tissue interface (-0.17 ± 0.18 m/s vs. -0.13 ± 0.35 m/s; p = 0.202). However, the first peritumoral gradient (-0.16 ± 0.24 m/s vs. -0.35 ± 0.31 m/s; p < 0.0001) and the second peritumoral gradient (-0.11 ± 0.18 m/s vs. -0.22 ± 0.28 m/s; p = 0.037) were significantly steeper in malignant tumours. The AUC was best for PTG1 (0.7358) and PTG2 (0.7039). A threshold value for peritumoral SWI PT1 above 3.76 m/s and for PTG1 below -0.238 m/s·mm-1 indicated malignancy in 90.6% of cases. Evaluating the peritumoral SWE gradient may improve the diagnostic pre-test probability, as malignant tumours showed a significantly steeper curve of the elasticity values in the peritumoral stroma compared to the linear regression with a relatively flat curve of benign lesions.

Stability of Radiomic Features against Variations in Lesion Segmentations Computed on Apparent Diffusion Coefficient Maps of Breast Lesions.

Diffusion-weighted imaging (DWI) combined with radiomics can aid in the differentiation of breast lesions. Segmentation characteristics, however, might influence radiomic features. To evaluate feature stability, we implemented a standardized pipeline featuring shifts and shape variations of the underlying segmentations. A total of 103 patients were retrospectively included in this IRB-approved study after multiparametric diagnostic breast 3T MRI with a spin-echo diffusion-weighted sequence with echoplanar readout (b-values: 50, 750 and 1500 s/mm2). Lesion segmentations underwent shifts and shape variations, with >100 radiomic features extracted from apparent diffusion coefficient (ADC) maps for each variation. These features were then compared and ranked based on their stability, measured by the Overall Concordance Correlation Coefficient (OCCC) and Dynamic Range (DR). Results showed variation in feature robustness to segmentation changes. The most stable features, excluding shape-related features, were FO (Mean, Median, RootMeanSquared), GLDM (DependenceNonUniformity), GLRLM (RunLengthNonUniformity), and GLSZM (SizeZoneNonUniformity), which all had OCCC and DR > 0.95 for both shifting and resizing the segmentation. Perimeter, MajorAxisLength, MaximumDiameter, PixelSurface, MeshSurface, and MinorAxisLength were the most stable features in the Shape category with OCCC and DR > 0.95 for resizing. Considering the variability in radiomic feature stability against segmentation variations is relevant when interpreting radiomic analysis of breast DWI data.

Integrating intratumoral and peritumoral radiomics with deep transfer learning for DCE-MRI breast lesion differentiation: A multicenter study comparing performance with radiologists

PurposeTo conduct the fusion of radiomics and deep transfer learning features from the intratumoral and peritumoral areas in breast DCE-MRI images to differentiate between benign and malignant breast tumors, and to compare the diagnostic accuracy of this fusion model against the assessments made by experienced radiologists. Materials and MethodsThis multi-center study conducted a retrospective analysis of DCE-MRI images from 330 women diagnosed with breast cancer, with 138 cases categorized as benign and 192 as malignant. The training and internal testing sets comprised 270 patients from center 1, while the external testing cohort consisted of 60 patients from center 2. A fusion feature set consisting of radiomics features and deep transfer learning features was constructed from both intratumoral (ITR) and peritumoral (PTR) areas. The Least absolute shrinkage and selection operator (LASSO) based support vector machine was chosen as the classifier by comparing its performance with five other machine learning models. The diagnostic performance and clinical usefulness of fusion model were verified and assessed through the area under the receiver operating characteristics (ROC) and decision curve analysis. Additionally, the performance of the fusion model was compared with the diagnostic assessments of two experienced radiologists to evaluate its relative accuracy. The study strictly adhered to CLEAR and METRICS guidelines for standardization to ensure rigorous and reproducible methods. ResultsThe findings show that the fusion model, utilizing radiomics and deep transfer learning features from the ITR and PTR, exhibited exceptional performance in classifying breast tumors, achieving AUCs of 0.950 in the internal testing set and 0.921 in the external testing set. This performance significantly surpasses that of models relying on singular regional radiomics or deep transfer learning features alone. Moreover, the fusion model demonstrated superior diagnostic accuracy compared to the evaluations conducted by two experienced radiologists, thereby highlighting its potential to support and enhance clinical decision-making in the differentiation of benign and malignant breast tumors. ConclusionThe fusion model, combining multi-regional radiomics with deep transfer learning features, not only accurately differentiates between benign and malignant breast tumors but also outperforms the diagnostic assessments made by experienced radiologists. This underscores the model’s potential as a valuable tool for improving the accuracy and reliability of breast tumor diagnosis.

Ultrasound Viscosity Imaging in Breast Lesions: A Multicenter Prospective Study

Rationale and ObjectivesTo explore and validate the clinical value of ultrasound (US) viscosity imaging in differentiating breast lesions by combining with BI-RADS, and then comparing the diagnostic performances with BI-RADS alone. Materials and MethodsThis multicenter, prospective study enrolled participants with breast lesions from June 2021 to November 2022. A development cohort (DC) and validation cohort (VC) were established. Using histological results as reference standard, the viscosity related parameter with the highest area under the receiver operating curve (AUC) was selected as the optimal one. Then the original BI-RADS would upgrade or not based on the value of this parameter. Finally, the results were validated in the VC and total cohorts. In the DC, VC and total cohorts, all breast lesions were divided into the large lesion, small lesion and overall groups respectively. ResultsA total of 639 participants (mean age, 46 years ±14) with 639 breast lesions (372 benign and 267 malignant lesions) were finally enrolled in this study including 392 participants in the DC and 247 in the VC. In the DC, the optimal viscosity related parameter in differentiating breast lesions was calculated to be A’-S2-Vmax, with the AUC of 0.88 (95% CI: 0.84, 0.91). Using > 9.97 Pa.s as the cutoff value, the BI-RADS was then modified. The AUC of modified BI-RADS significantly increased from 0.85 (95% CI: 0.81, 0.88) to 0.91 (95% CI: 0.87, 0.93), 0.85 (95% CI: 0.80, 0.89) to 0.90 (95% CI: 0.85, 0.93), and 0.85 (95% CI: 0.82, 0.87) to 0.90 (95% CI: 0.88, 0.92) in the DC, VC and total cohorts respectively (P <.05 for all). ConclusionsThe quantitative viscous parameters evaluated by US viscosity imaging contribute to breast cancer diagnosis when combined with BI-RADS.

Differentiation of invasive ductal and lobular carcinoma of the breast using MRI radiomic features: a pilot study.

Breast cancer (BC) is one of the main causes of cancer-related mortality among women. For clinical management to help patients survive longer and spend less time on treatment, early and precise cancer identification and differentiation of breast lesions are crucial. To investigate the accuracy of radiomic features (RF) extracted from dynamic contrast-enhanced Magnetic Resonance Imaging (DCE MRI) for differentiating invasive ductal carcinoma (IDC) from invasive lobular carcinoma (ILC). This is a retrospective study. The IDC of 30 and ILC of 28 patients from Dukes breast cancer MRI data set of The Cancer Imaging Archive (TCIA), were included. The RF categories such as shape based, Gray level dependence matrix (GLDM), Gray level co-occurrence matrix (GLCM), First order, Gray level run length matrix (GLRLM), Gray level size zone matrix (GLSZM), NGTDM (Neighbouring gray tone difference matrix) were extracted from the DCE-MRI sequence using a 3D slicer. The maximum relevance and minimum redundancy (mRMR) was applied using Google Colab for identifying the top fifteen relevant radiomic features. The Mann-Whitney U test was performed to identify significant RF for differentiating IDC and ILC. Receiver Operating Characteristic (ROC) curve analysis was performed to ascertain the accuracy of RF in distinguishing between IDC and ILC. Ten DCE MRI-based RFs used in our study showed a significant difference (p <0.001) between IDC and ILC. We noticed that DCE RF, such as Gray level run length matrix (GLRLM) gray level variance (sensitivity (SN) 97.21%, specificity (SP) 96.2%, area under curve (AUC) 0.998), Gray level co-occurrence matrix (GLCM) difference average (SN 95.72%, SP 96.34%, AUC 0.983), GLCM interquartile range (SN 95.24%, SP 97.31%, AUC 0.968), had the strongest ability to differentiate IDC and ILC. MRI-based RF derived from DCE sequences can be used in clinical settings to differentiate malignant lesions of the breast, such as IDC and ILC, without requiring intrusive procedures.

Evaluation of molecular subtypes of breast cancer using MRI BI-RADS Lexicon

BackgroundMolecular subtyping of breast cancer is one of the prognostic factors which play a very important role in managing patient’s treatment plan. The MRI BI-RADS Lexicon is initially used to categorize breast lesions but recent attempts were employed to differentiate breast lesions based on their molecular subtypes using this lexicon. The study aimed to evaluate of the role of the MRI BI-RADS Lexicon in classifying different molecular subtypes of breast cancer especially after coupling with Kaiser scoring system.MethodsThis retrospective study was conducted on 147 patients with 170 malignant breast lesions. They underwent Pre-contrast and a Dynamic contrast MRI study. Retrospective interpretation of the morphological and dynamic criteria of the breast lesions based on the MRI BI-RADS criteria was carried out followed by reassessment of the same lesions by Kaiser scoring. Resulting data were correlated with histopathological and immunological characterization.ResultsLuminal subtypes were more frequently encountered as mass lesions, contrary to the Non-Luminal lesions which showed a more frequent non-mass presentation value (P 0.002). The shape, margin, internal enhancement pattern of the mass lesions showed significant variability between different molecular subtypes (P < 0.001, < 0.001, < 0.001) respectively. On Dynamic study, Plateau curve was a more evident pattern with Luminal lesions contrasting with their Non-Luminal counterparts which showed a washout pattern more frequently (P 0.0004). Most of luminal A cancers were presented as mass lesions with rim enhancement and categorized as BIRADS 4 while most of Her2neu positive cancers (including luminal B entity) were presented as non-mass lesions with irregular shape and dark internal septations and categorized as BIRADS 5 with statistically significant values (P < 0.001). Coupling with Kaiser scoring system improved the categorization of non-luminal tumors as BIRADS 5 lesions especially the aggressive TN cancers.ConclusionsMRI-BIRADS lexicon can be of great value in the non-invasive molecular characterization of breast cancer. Kaiser score improved the categorization of TN cancers which were upgraded to BIRADS 5 category.

Differentiation of invasive ductal and lobular carcinoma of the breast using MRI radiomic features: a pilot study

Background Breast cancer (BC) is one of the main causes of cancer-related mortality among women. For clinical management to help patients survive longer and spend less time on treatment, early and precise cancer identification and differentiation of breast lesions are crucial. To investigate the accuracy of radiomic features (RF) extracted from dynamic contrast-enhanced Magnetic Resonance Imaging (DCE MRI) for differentiating invasive ductal carcinoma (IDC) from invasive lobular carcinoma (ILC). Methods This is a retrospective study. The IDC of 30 and ILC of 28 patients from Dukes breast cancer MRI data set of The Cancer Imaging Archive (TCIA), were included. The RF were extracted from the DCE-MRI sequence using a 3D slicer. The relevance of RF for differentiating IDC from ILC was evaluated using the maximum relevance minimum redundancy (mRMR) and Mann-Whitney test. Receiver Operating Characteristic (ROC) curve analysis was performed to ascertain the accuracy of RF in distinguishing between IDC and ILC. Results Ten DCE MRI-based RFs used in our study showed a significant difference (p &lt;0.001) between IDC and ILC. We noticed that DCE RF, such as Gray level run length matrix (GLRLM) gray level variance (sensitivity (SN) 97.21%, specificity (SP) 96.2%, area under curve (AUC) 0.998), Gray level co-occurrence matrix (GLCM) difference average (SN 95.72%, SP 96.34%, AUC 0.983), GLCM interquartile range (SN 95.24%, SP 97.31%, AUC 0.968), had the strongest ability to differentiate IDC and ILC. Conclusions MRI-based RF derived from DCE sequences can be used in clinical settings to differentiate malignant lesions of the breast, such as IDC and ILC, without requiring intrusive procedures.

Classification of benign and malignant solid breast lesions on the ultrasound images based on the textural features: the importance of the perifocal lesion area

The amount of ultrasound (US) breast exams continues to grow because of the wider endorsement of breast cancer screening programs. When a solid lesion is found during the US the primary task is to decide if it requires a biopsy. Therefore, our goal was to develop a noninvasive US grayscale image analysis for benign and malignant solid breast lesion differentiation. We used a dataset consisting of 105 ultrasound images with 50 benign and 55 malignant non-cystic lesions. Features were extracted from the source image, the image of the gradient module after applying the Sobel filter, and the image after the Laplace filter. Subsequently, eight gray-level co-occurrence matrices (GLCM) were constructed for each lesion, and 13 Haralick textural features were calculated for each GLCM. Additionally, we computed the differences in feature values at different spatial shifts and the differences in feature values between the inner and outer areas of the lesion. The LASSO method was employed to determine the most significant features for classification. Finally, the lesion classification was carried out by various methods. The use of LASSO regression for feature selection enabled us to identify the most significant features for classification. Out of the 13 features selected by the LASSO method, four described the perilesional tissue, two represented the inner area of the lesion and five described the image of the gradient module. The final model achieved a sensitivity of 98%, specificity of 96%, and accuracy of 97%. Considering the perilesional area, Haralick feature differences, and the image of the gradient module can provide crucial parameters for accurate classification of US images. Features with a low AUC index (less than 0.6 in our case) can also be important for improving the quality of classification.

Can New Ultrasound Imaging Techniques Improve Breast Lesion Characterization? Prospective Comparison between Ultrasound BI-RADS and Semi-Automatic Software “SmartBreast”, Strain Elastography, and Shear Wave Elastography

Background: Ultrasound plays a crucial role in early diagnosis of breast cancer. The aim of this research is to evaluate the diagnostic performance of BI-RADS classification in comparison with new semi-automatic software Resona R9, Mindray, “SmartBreast” and strain elastography (SE), point shear wave (pSWE), and 2D shear wave (2D SWE) Elastography for breast lesion differentiation. Methods: Ninety-two breast nodules classified according to BI-RADS lexicon by an expert radiologist were evaluated by a second investigator with B-mode ultrasound, color Doppler, “SmartBreast”, and elastography. Histopathology was considered the gold standard. Results: The agreement between software and investigator was excellent in the identification of the posterior features of breast masses (Cohen’s k = 0.94), good for shape and vascular signal (Cohen’s k, respectively, of 0.6 and 0.65), poor for orientation, margins, and echo pattern (Cohen’s k, respectively, of 0.28, 0.33 and 0.48), moderate for dimensions (Lin’s correlation coefficient of 0.90, p = 0.07). SE showed a greater area under curve (AUC) than pSWE and 2D SWE (0.84, 0.64, and 0.61, respectively), with a greater specificity and a comparable sensitivity to pSWE (respectively, of 0.86 and 0.55, 0.81 and 0.84). Conclusions: SE improved the diagnostic performance of BI-RADS classification more than pSWE and 2D SWE; “SmartBreast” showed good agreement only for shape and vascularization but not for the other ultrasound features of breast lesions.

Diffusion tensor magnetic resonance imaging in differentiation of breast lesions

BackgroundDiffusion tensor imaging (DTI) is a novel approach which uses extra gradients to quantify diffusion in several directions (at least six). The purpose of this research was to determine the role of diffusion tensor magnetic resonance imaging in breast lesion differentiation.ResultsApparent diffusion coefficient (ADC) values were significantly lower in malignant than benign lesions, with a cut-off value of 1.21 × 10−3 mm2/s, this gives a sensitivity of 88.46%, specificity 87.50% and accuracy 86.7%. Values of fractional anisotropy (FA) were higher significantly in malignant compared to benign lesions with a 0.15 cut-off value, has a 95.83% sensitivity, 96.15% specificity, and 95.6%, accuracy. Values of RA were significantly higher in malignant (0.180 ± 0.068) compared to benign lesions, with 0.13 cut-off value. Sensitivity, specificity, and accuracy were, respectively, 91.69%, 92.31%, and 90.2%. Values of λ1 were significantly lower in malignant (1.4 ± 0.453 × 10−3 mm2/s) than in benign (2.19 ± 0.659 × 10−3 mm2/s) lesions with a cut-off value of 1.71 × 10−3 mm2/s. Sensitivity and specificity were, respectively, 95.83 and 96.15%. The combined evaluation by (dynamic contrast enhancement) Sensitivity improved to 100% with DCE and DTI readings, while specificity remained at 95.6%.ConclusionsDTI breast imaging is a noninvasive procedure which demonstrated a high potential utility for cancer detection and serving as a standalone technique or in conjunction with DCE-MRI, the discriminating values of FA, λ1 and λ1–λ3 were high. Their measurements were strongly associated with identification breast malignancy and combined evaluation by DTI parameters and DCE-MRI DTI enhanced the sensitivity, lowered the rate of false-negatives, and completely improved the accuracy of breast lesions differential diagnosis.

BI-RADS categories and breast lesions classification of mammographic images using artificial intelligence diagnostic model

According to BI-RADS criteria, radiologists evaluate mammography images, and breast lesions are classified as malignant or benign. In this retrospective study, an evaluation was made on 264 mammogram images of 139 patients. First, data augmentation was applied, and then the total number of images was increased to 565. Two computer-aided models were then designed to classify breast lesions and BI-RADS categories. The first of these models is the support vector machine (SVM) based model, and the second is the convolutional neural network (CNN) based model. The SVM-based model could classify BI-RADS categories and malignant-benign discrimination with an accuracy rate of 86.42% and 92.59%, respectively. On the other hand, the CNN-based model showed 79.01% and 83.95% accuracy for BI-RADS categories and malignant benign discrimination, respectively. These results showed that a well-designed machine learning-based classification model can give better results than a deep learning model. Additionally, it can be used as a secondary system for radiologists to differentiate breast lesions and BI-RADS lesion categories.

Differentiation of breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using deep transfer learning based on DenseNet201.

In order to achieve better performance, artificial intelligence is used in breast cancer diagnosis. In this study, we evaluated the efficacy of different fine-tuning strategies of deep transfer learning (DTL) based on the DenseNet201 model to differentiate malignant from benign lesions on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). We collected 4260 images of benign lesions and 4140 images of malignant lesions of the breast pertaining to pathologically confirmed cases. The benign and malignant groups was randomly divided into a training set and a testing set at a ratio of 9:1. A DTL model based on the DenseNet201 model was established, and the effectiveness of 4 fine-tuning strategies (S0: strategy 0, S1: strategy; S2: strategy; and S3: strategy) was compared. Additionally, DCE-MRI images of 48 breast lesions were selected to verify the robustness of the model. Ten images were obtained for each lesion. The classification was considered correct if more than 5 images were correctly classified. The metrics for model performance evaluation included accuracy (Ac) in the training and testing sets, precision (Pr), recall rate (Rc), f1 score (f1), and area under the receiver operating characteristic curve (AUROC) in the validation set. The Ac of the 4 fine-tuning strategies reached 100.00% in the training set. The S2 strategy exhibited good convergence in the testing set. The Ac of S2 was 98.01% in the testing set, which was higher than those of S0 (93.10%), S1 (90.45%), and S3 (93.90%). The average classification Pr, Rc, f1, and AUROC of S2 in the validation set were (89.00%, 80.00%, 0.81, and 0.79, respectively) higher than those of S0 (76.00%, 67.00%, 0.69, and 0.65, respectively), S1 (60.00%, 60.00%, 0.60, 0.66, and respectively), and S3 (77.00%, 73.00%, 0.74, 0.72, respectively). The degree of coincidence between S2 and the histopathological method for differentiating between benign and malignant breast lesions was high (κ = 0.749). The S2 strategy can improve the robustness of the DenseNet201 model in relatively small breast DCE-MRI datasets, and this is a reliable method to increase the Ac of discriminating benign from malignant breast lesions on DCE-MRI.

Ultrasound strain elastography-based characterization of in vivo breast lesions using deep learning

Ultrasound strain elastography showed great promise for breast lesion characterization. With the readily available computational power in the clinical workflow, machine learning-based is gaining acceptance in cancer imaging applications. In this study, we combine the latest developments in motion tracking that enables us to obtain high-quality axial strain and full shear strain images to test the deep-learning-based prediction of breast lesion malignancy. To our knowledge, total shear strain images have not been widely used for breast lesion differentiation. More specifically, a PDE-based regularization method [Guo et al., Ultrasonic Imaging (2015)] developed by our group has been improved to get high-quality two-dimensional displacement data. From those high-quality displacement data, total shear strain images can be constructed. We adopted three variants of convolution neural network (CNN) models with attention modules to predict breast lesion malignancy by combining B-mode, axial strain, and total shear strain images and their radiomic features. From our internal database, 150 cases of pathologically-confirmed breast ultrasound data [Hall et al., UMB (2003)] with data augmentation are used to evaluate our machine learning models. Our initial testing results are encouraging with the accuracy and area under the curve being around 0.75.

Application of Artificial Intelligence Computer-Assisted Diagnosis Originally Developed for Thyroid Nodules to Breast Lesions on Ultrasound.

As thyroid and breast cancer have several US findings in common, we applied an artificial intelligence computer-assisted diagnosis (AI-CAD) software originally developed for thyroid nodules to breast lesions on ultrasound (US) and evaluated its diagnostic performance. From January 2017 to December 2017, 1042 breast lesions (mean size 20.2 ± 11.8mm) of 1001 patients (mean age 45.9 ± 12.9years) who underwent US-guided core-needle biopsy were included. An AI-CAD software that was previously trained and validated with thyroid nodules using the convolutional neural network was applied to breast nodules. There were 665 benign breast lesions (63.0%) and 391 breast cancers (37.0%). The area under the receiver operating characteristic curve (AUROC) of AI-CAD to differentiate breast lesions was 0.678 (95% confidence interval: 0.649, 0.707). After fine-tuning AI-CAD with 1084 separate breast lesions, the diagnostic performance of AI-CAD markedly improved (AUC 0.841). This was significantly higher than that of radiologists when the cutoff category was BI-RADS 4a (AUC 0.621, P < 0.001), but lower when the cutoff category was BI-RADS 4b (AUC 0.908, P < 0.001). When applied to breast lesions, the diagnostic performance of an AI-CAD software that had been developed for differentiating malignant and benign thyroid nodules was not bad. However, an organ-specific approach guarantees better diagnostic performance despite the similar US features of thyroid and breast malignancies.

Recent topics of the clinical utility of PET/MRI in oncology and neuroscience.

Since the inline positron emission tomography (PET)/magnetic resonance imaging (MRI) system appeared in clinical, more than a decade has passed. In this article, we have reviewed recently-published articles about PET/MRI. There have been articles about staging in rectal and breast cancers by PET/MRI using fluorodeoxyglucose (FDG) with higher diagnostic performance in oncology. Assessing possible metastatic bone lesions is considered a proper target by FDG PET/MRI. Other than FDG, PET/MRI with prostate specific membrane antigen (PSMA)-targeted tracers or fibroblast activation protein inhibitor have been reported. Especially, PSMA PET/MRI has been reported to be a promising tool for determining appropriate sites in biopsy. Independent of tracers, the clinical application of artificial intelligence (AI) for images obtained by PET/MRI is one of the current topics in this field, suggesting clinical usefulness for differentiating breast lesions or grading prostate cancer. In addition, AI has been reported to be helpful for noise reduction for reconstructing images, which would be promising for reducing radiation exposure. Furthermore, PET/MRI has a clinical role in neuroscience, including localization of the epileptogenic zone. PET/MRI with new PET tracers could be useful for differentiation among neurological disorders. Clinical applications of integrated PET/MRI in various fields are expected to be reported in the future.

Compression optical coherence elastography versus strain ultrasound elastography for breast cancer detection and differentiation: pilot study

The aims of this study are (i) to compare ultrasound strain elastography (US-SE) and compression optical coherence elastography (C-OCE) in characterization of elastically linear phantoms, (ii) to evaluate factors that can cause discrepancy between the results of the two elastographic techniques in application to real tissues, and (iii) to compare the results of US-SE and C-OCE in the differentiation of benign and malignant breast lesions. On 22 patients, we first used standard US-SE for in vivo assessment of breast cancer before and then after the lesion excision C-OCE was applied for intraoperative visualization of margins of the tumors and assessment of their type/grade using fresh lumpectomy specimens. For verification, the tumor grades and subtypes were determined histologically. We show that in comparison to US-SE, quantitative C-OCE has novel capabilities due to its ability to locally control stress applied to the tissue and obtain local stress-strain curves. For US-SE, we demonstrate examples of malignant tumors that were erroneously classified as benign and vice versa. For C-OCE, all lesions are correctly classified in agreement with the histology. The revealed discrepancies between the strain ratio given by US-SE and ratio of tangent Young's moduli obtained for the same samples by C-OCE are explained. Overall, C-OCE enables significantly improved specificity in breast lesion differentiation and ability to precisely visualize margins of malignant tumors compared. Such results confirm high potential of C-OCE as a high-speed and accurate method for intraoperative assessment of breast tumors and detection of their margins.

Evaluation of Monoexponential, Stretched-Exponential and Intravoxel Incoherent Motion MRI Diffusion Models in Early Response Monitoring to Neoadjuvant Chemotherapy in Patients With Breast Cancer-A Preliminary Study.

BackgroundThere has been a growing interest in exploring the applications of stretched‐exponential (SEM) and intravoxel incoherent motion (IVIM) models of diffusion‐weighted imaging (DWI) in breast imaging, with the focus on differentiation of breast lesions. However, the use of SEM and IVIM models to predict early response to neoadjuvant chemotherapy (NACT) has received less attention.PurposeTo investigate the value of monoexponential, SEM, and IVIM models to predict early response to NACT in patients with primary breast cancer.Study TypeProspective.PopulationThirty‐seven patients with primary breast cancer (aged 46 ± 11 years) due to undergo NACT.Field Strength/SequencesA 1.5‐T MR scanner, T1 ‐weighted three‐dimensional spoiled gradient‐echo, two‐dimensional single‐shot spin‐echo echo‐planar imaging sequence (DWI) at six b‐values (0–800 s mm−2).AssessmentTumor volume, apparent diffusion coefficient, tissue diffusion (D t ), pseudo‐diffusion coefficient (D p ), perfusion fraction (f), distributed diffusion coefficient, and alpha (α) were extracted, following volumetric sampling of the tumors, at three time‐points: pretreatment, post one and three cycles of NACT.Statistical TestsMann–Whitney test, receiver operating characteristic (ROC) curve. Statistical significance level was P < 0.05.ResultsFollowing NACT, 17 patients were determined to be pathological responders and 20 nonresponders. Tumor volume was significantly larger in nonresponders at each MRI time‐point and demonstrated reasonable performance in predicting response (area under the ROC curve [AUC] = 0.83–0.87). No significant differences between groups were found in the diffusion coefficients at each time‐point (P = 0.09–1). The parameters α (SEM), f, and f × D p (IVIM) were able to differentiate between response groups after one cycle of NACT (AUC = 0.73, 0.72, and 0.74, respectively).ConclusionDiffusion coefficients derived from the monoexponential, SEM, and IVIM models did not predict pathological response. However, the IVIM‐derived parameters f and f × D p and the SEM‐derived parameter α were able to predict response to NACT in breast cancer patients following one cycle of NACT.Level of Evidence2Technical Efficacy Stage2

Qualitative and quantitative strain and shear wave elastography paradigm in differentiation of breast lesions

BackgroundBreast cancer is the most common life-threatening cancer in women worldwide. A high number of women are going through biopsy procedures for characterization of breast masses every day and yet 75% of the pathological results prove these masses to be benign. Ultrasound (US) elastography is a non-invasive technique that measures tissue stiffness. It is convenient for differentiating benign from malignant breast tumors. Our study aims to evaluate the role of qualitative ultrasound elastography scoring (ES), quantitative mass strain ratio (SR), and shear wave elasticity ratio (SWER) in differentiation between benign and malignant breast lesions.ResultsAmong 51 female patients with 77 histopathologically proved breast lesions, 57 breast masses were malignant and 20 were benign. All patients were examined by B-mode ultrasound then strain and shear wave elastographic examinations using ultrasound machine (Logiq E9, GE Medical Systems) with 8.5–12 MHz high-frequency probes. Our study showed that ES best cut-off point > 3 with sensitivity, specificity, PPV, NPP, accuracy was 94.7%, 85%, 94.7%, 85%, 90.9%, respectively, and AUC = 0.926 at P < 0.001, mass SR the best cut-off point > 4.6 with sensitivity, specificity, PPV, NPP, accuracy was 96.5%, 80%, 93.2%, 88.9%, 92.2%, respectively, and AUC = 0.860 at P < 0.001, SWER the best cut-off value > 4.9 with sensitivity, specificity, PPV, NPP and accuracy was 91.2%, 80%, 92.9%, 76.2%, 93.5%, respectively, and AUC = 0.890 at P < 0.001. The mean mass strain ratio for malignant lesions is 10.1 ± 3.7 SD and for solid benign lesions 4.7 ± 4.3 SD (p value 0.001). The mean shear wave elasticity ratio for malignant lesions is 10.6 ± 5.4 SD and for benign (solid and cystic) lesions 3.6 ± 4.2 SD. Using ROC curve and Youden index, the difference in diagnostic performance between ES, SR and SWER was not significant in differentiation between benign and malignant breast lesions and also was non-significant difference when comparing them with conventional US alone.ConclusionES, SR, and SWER have a high diagnostic performance in differentiating malignant from benign breast lesions with no statistically significant difference between them.

Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods

Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions.