Diffusion Tensor Imaging for Characterizing Changes in Triple-Negative Breast Cancer During Neoadjuvant Systemic Therapy.

BACKGROUND: Assessment of treatment response in triple-negative breast cancer (TNBC) may guide individualized care for improved patient outcomes. Diffusion tensor imaging (DTI) measures tissue anisotropy and could be useful for characterizing changes in the tumors and adjacent fibroglandular tissue (FGT) of TNBC patients undergoing neoadjuvant systemic treatment (NAST). PURPOSE: To evaluate the potential of DTI parameters for prediction of treatment response in TNBC patients undergoing NAST. STUDY TYPE: Prospective. POPULATION: Eighty-six women (average age: 51 ± 11 years) with biopsy-proven clinical stage I-III TNBC who underwent NAST followed by definitive surgery. 47% of patients (40/86) had pathologic complete response (pCR). FIELD STRENGTH/SEQUENCE: 3.0 T/reduced field of view single-shot echo-planar DTI sequence. ASSESSMENT: Three MRI scans were acquired longitudinally (pre-treatment, after 2 cycles of NAST, and after 4 cycles of NAST). Eleven histogram features were extracted from DTI parameter maps of tumors, a peritumoral region (PTR), and FGT in the ipsilateral breast. DTI parameters included apparent diffusion coefficients and relative diffusion anisotropies. pCR status was determined at surgery. STATISTICAL TESTS: Longitudinal changes of DTI features were tested for discrimination of pCR using Mann-Whitney U test and area under the receiver operating characteristic curve (AUC). A P value <0.05 was considered statistically significant. RESULTS: 47% of patients (40/86) had pCR. DTI parameters assessed after 2 and 4 cycles of NAST were significantly different between pCR and non-pCR patients when compared between tumors, PTRs, and FGTs. The median surface/average anisotropy of the PTR, measured after 2 and 4 cycles of NAST, increased in pCR patients and decreased in non-pCR patients (AUC: 0.78; 0.027 ± 0.043 vs. -0.017 ± 0.042 mm2 /s). DATA CONCLUSION: Quantitative DTI features from breast tumors and the peritumoral tissue may be useful for predicting the response to NAST in TNBC. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 4.

Predicting pathological complete response to neoadjuvant systemic therapy for triple-negative breast cancers using deep learning on multiparametric MRIs.

We trained and validated a deep learning model that can predict the treatment response to neoadjuvant systemic therapy (NAST) for patients with triple negative breast cancer (TNBC). Dynamic contrast enhanced (DCE) MRI and diffusion-weighted imaging (DWI) of the pre-treatment (baseline) and after four cycles (C4) of doxorubicin/cyclophosphamide treatment were used as inputs to the model for prediction of pathologic complete response (pCR). Based on the standard pCR definition that includes disease status in either breast or axilla, the model achieved areas under the receiver operating characteristic curves (AUCs) of 0.96 ± 0.05, 0.78 ± 0.09, 0.88 ± 0.02, and 0.76 ± 0.03, for the training, validation, testing, and prospective testing groups, respectively. For the pCR status of breast only, the retrained model achieved prediction AUCs of 0.97 ± 0.04, 0.82 ± 0.10, 0.86 ± 0.03, and 0.83 ± 0.02, for the training, validation, testing, and prospective testing groups, respectively. Thus, the developed deep learning model is highly promising for predicting the treatment response to NAST of TNBC.Clinical Relevance- Deep learning based on serial and multiparametric MRIs can potentially distinguish TNBC patients with pCR from non-pCR at the early stage of neoadjuvant systemic therapy, potentially enabling more personalized treatment of TNBC patients.

Longitudinal dynamic contrast-enhanced MRI radiomic models for early prediction of response to neoadjuvant systemic therapy in triple-negative breast cancer.

Early prediction of neoadjuvant systemic therapy (NAST) response for triple-negative breast cancer (TNBC) patients could help oncologists select individualized treatment and avoid toxic effects associated with ineffective therapy in patients unlikely to achieve pathologic complete response (pCR). The objective of this study is to evaluate the performance of radiomic features of the peritumoral and tumoral regions from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) acquired at different time points of NAST for early treatment response prediction in TNBC. This study included 163 Stage I-III patients with TNBC undergoing NAST as part of a prospective clinical trial (NCT02276443). Peritumoral and tumoral regions of interest were segmented on DCE images at baseline (BL) and after two (C2) and four (C4) cycles of NAST. Ten first-order (FO) radiomic features and 300 gray-level-co-occurrence matrix (GLCM) features were calculated. Area under the receiver operating characteristic curve (AUC) and Wilcoxon rank sum test were used to determine the most predictive features. Multivariate logistic regression models were used for performance assessment. Pearson correlation was used to assess intrareader and interreader variability. Seventy-eight patients (48%) had pCR (52 training, 26 testing), and 85 (52%) had non-pCR (57 training, 28 testing). Forty-six radiomic features had AUC at least 0.70, and 13 multivariate models had AUC at least 0.75 for training and testing sets. The Pearson correlation showed significant correlation between readers. In conclusion, Radiomic features from DCE-MRI are useful for differentiating pCR and non-pCR. Similarly, predictive radiomic models based on these features can improve early noninvasive treatment response prediction in TNBC patients undergoing NAST.

Deep Learning for Fully Automatic Tumor Segmentation on Serially Acquired Dynamic Contrast-Enhanced MRI Images of Triple-Negative Breast Cancer.

Accurate tumor segmentation is required for quantitative image analyses, which are increasingly used for evaluation of tumors. We developed a fully automated and high-performance segmentation model of triple-negative breast cancer using a self-configurable deep learning framework and a large set of dynamic contrast-enhanced MRI images acquired serially over the patients' treatment course. Among all models, the top-performing one that was trained with the images across different time points of a treatment course yielded a Dice similarity coefficient of 93% and a sensitivity of 96% on baseline images. The top-performing model also produced accurate tumor size measurements, which is valuable for practical clinical applications.

A Feasibility Study on Deep Learning Reconstruction to Improve Image Quality With PROPELLER Acquisition in the Setting of T2-Weighted Gynecologic Pelvic Magnetic Resonance Imaging.

OBJECTIVES: Evaluate deep learning (DL) to improve the image quality of the PROPELLER (Periodically Rotated Overlapping Parallel Lines with Enhanced Reconstruction technique) for 3 T magnetic resonance imaging of the female pelvis. METHODS: Three radiologists prospectively and independently compared non-DL and DL PROPELLER sequences from 20 patients with a history of gynecologic malignancy. Sequences with different noise reduction factors (DL 25%, DL 50%, and DL 75%) were blindly reviewed and scored based on artifacts, noise, relative sharpness, and overall image quality. The generalized estimating equation method was used to assess the effect of methods on the Likert scales. Quantitatively, the contrast-to-noise ratio and signal-to-noise ratio (SNR) of the iliac muscle were calculated, and pairwise comparisons were performed based on a linear mixed model. P values were adjusted using the Dunnett method. Interobserver agreement was assessed using the κ statistic. P value was considered statistically significant at less than 0.05. RESULTS: Qualitatively, DL 50 and DL 75 were ranked as the best sequences in 86% of cases. Images generated by the DL method were significantly better than non-DL images ( P < 0.0001). Iliacus muscle SNR on DL 50 and DL 75 was significantly better than non-DL images ( P < 0.0001). There was no difference in contrast-to-noise ratio between the DL and non-DL techniques in the iliac muscle. There was a high percent agreement (97.1%) in terms of DL sequences' superior image quality (97.1%) and sharpness (100%) relative to non-DL images. CONCLUSION: The utilization of DL reconstruction improves the image quality of PROPELLER sequences with improved SNR quantitatively.

A Radiomics Model Based on Synthetic MRI Acquisition for Predicting Neoadjuvant Systemic Treatment Response in Triple-Negative Breast Cancer.

Purpose To determine if a radiomics model based on quantitative maps acquired with synthetic MRI (SyMRI) is useful for predicting neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC). Materials and Methods In this prospective study, 181 women diagnosed with stage I-III TNBC were scanned with a SyMRI sequence at baseline and at midtreatment (after four cycles of NAST), producing T1, T2, and proton density (PD) maps. Histopathologic analysis at surgery was used to determine pathologic complete response (pCR) or non-pCR status. From three-dimensional tumor contours drawn on the three maps, 310 histogram and textural features were extracted, resulting in 930 features per scan. Radiomic features were compared between pCR and non-pCR groups by using Wilcoxon rank sum test. To build a multivariable predictive model, logistic regression with elastic net regularization and cross-validation was performed for texture feature selection using 119 participants (median age, 52 years [range, 26-77 years]). An independent testing cohort of 62 participants (median age, 48 years [range, 23-74 years]) was used to evaluate and compare the models by area under the receiver operating characteristic curve (AUC). Results Univariable analysis identified 15 T1, 10 T2, and 12 PD radiomic features at midtreatment that predicted pCR with an AUC greater than 0.70 in both the training and testing cohorts. Multivariable radiomics models of maps acquired at midtreatment demonstrated superior performance over those acquired at baseline, achieving AUCs as high as 0.78 and 0.72 in the training and testing cohorts, respectively. Conclusion SyMRI-based radiomic features acquired at midtreatment are potentially useful for identifying early NAST responders in TNBC. Keywords: MR Imaging, Breast, Outcomes Analysis ClinicalTrials.gov registration no. NCT02276443 Supplemental material is available for this article. © RSNA, 2023 See also the commentary by Houser and Rapelyea in this issue.

Assessment of Response to Neoadjuvant Systemic Treatment in Triple-Negative Breast Cancer Using Functional Tumor Volumes from Longitudinal Dynamic Contrast-Enhanced MRI.

Early assessment of neoadjuvant systemic therapy (NAST) response for triple-negative breast cancer (TNBC) is critical for patient care in order to avoid the unnecessary toxicity of an ineffective treatment. We assessed functional tumor volumes (FTVs) from dynamic contrast-enhanced (DCE) MRI after 2 cycles (C2) and 4 cycles (C4) of NAST as predictors of response in TNBC. A group of 100 patients with stage I-III TNBC who underwent DCE MRI at baseline, C2, and C4 were included in this study. Tumors were segmented on DCE images of 1 min and 2.5 min post-injection. FTVs were measured using the optimized percentage enhancement (PE) and signal enhancement ratio (SER) thresholds. The Mann-Whitney test was used to compare the performance of the FTVs at C2 and C4. Of the 100 patients, 49 (49%) had a pathologic complete response (pCR) and 51 (51%) had a non-pCR. The maximum area under the receiving operating characteristic curve (AUC) for predicting the treatment response was 0.84 (p < 0.001) for FTV at C4 followed by FTV at C2 (AUC = 0.82, p < 0.001). The FTV measured at baseline was not able to discriminate pCR from non-pCR. FTVs measured on DCE MRI at C2, as well as at C4, of NAST can potentially predict pCR and non-pCR in TNBC patients.

Prediction of pathologic complete response to neoadjuvant systemic therapy in triple negative breast cancer using deep learning on multiparametric MRI.

Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer. Neoadjuvant systemic therapy (NAST) followed by surgery are currently standard of care for TNBC with 50-60% of patients achieving pathologic complete response (pCR). We investigated ability of deep learning (DL) on dynamic contrast enhanced (DCE) MRI and diffusion weighted imaging acquired early during NAST to predict TNBC patients' pCR status in the breast. During the development phase using the images of 130 TNBC patients, the DL model achieved areas under the receiver operating characteristic curves (AUCs) of 0.97 ± 0.04 and 0.82 ± 0.10 for the training and the validation, respectively. The model achieved an AUC of 0.86 ± 0.03 when evaluated in the independent testing group of 32 patients. In an additional prospective blinded testing group of 48 patients, the model achieved an AUC of 0.83 ± 0.02. These results demonstrated that DL based on multiparametric MRI can potentially differentiate TNBC patients with pCR or non-pCR in the breast early during NAST.

MRI-Based Digital Models Forecast Patient-Specific Treatment Responses to Neoadjuvant Chemotherapy in Triple-Negative Breast Cancer.

Triple-negative breast cancer (TNBC) is persistently refractory to therapy, and methods to improve targeting and evaluation of responses to therapy in this disease are needed. Here, we integrate quantitative MRI data with biologically based mathematical modeling to accurately predict the response of TNBC to neoadjuvant systemic therapy (NAST) on an individual basis. Specifically, 56 patients with TNBC enrolled in the ARTEMIS trial (NCT02276443) underwent standard-of-care doxorubicin/cyclophosphamide (A/C) and then paclitaxel for NAST, where dynamic contrast-enhanced MRI and diffusion-weighted MRI were acquired before treatment and after two and four cycles of A/C. A biologically based model was established to characterize tumor cell movement, proliferation, and treatment-induced cell death. Two evaluation frameworks were investigated using: (i) images acquired before and after two cycles of A/C for calibration and predicting tumor status after A/C, and (ii) images acquired before, after two cycles, and after four cycles of A/C for calibration and predicting response following NAST. For Framework 1, the concordance correlation coefficients between the predicted and measured patient-specific, post-A/C changes in tumor cellularity and volume were 0.95 and 0.94, respectively. For Framework 2, the biologically based model achieved an area under the receiver operator characteristic curve of 0.89 (sensitivity/specificity = 0.72/0.95) for differentiating pathological complete response (pCR) from non-pCR, which is statistically superior (P &lt; 0.05) to the value of 0.78 (sensitivity/specificity = 0.72/0.79) achieved by tumor volume measured after four cycles of A/C. Overall, this model successfully captured patient-specific, spatiotemporal dynamics of TNBC response to NAST, providing highly accurate predictions of NAST response. SIGNIFICANCE: Integrating MRI data with biologically based mathematical modeling successfully predicts breast cancer response to chemotherapy, suggesting digital twins could facilitate a paradigm shift from simply assessing response to predicting and optimizing therapeutic efficacy.

Quantitative Apparent Diffusion Coefficients From Peritumoral Regions as Early Predictors of Response to Neoadjuvant Systemic Therapy in Triple-Negative Breast Cancer.

BACKGROUND: Pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in triple-negative breast cancer (TNBC) is a strong predictor of patient survival. Edema in the peritumoral region (PTR) has been reported to be a negative prognostic factor in TNBC. PURPOSE: To determine whether quantitative apparent diffusion coefficient (ADC) features from PTRs on reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) predict the response to NAST in TNBC. STUDY TYPE: Prospective. POPULATION/SUBJECTS: A total of 108 patients with biopsy-proven TNBC who underwent NAST and definitive surgery during 2015-2020. FIELD STRENGTH/SEQUENCE: A 3.0 T/rFOV single-shot diffusion-weighted echo-planar imaging sequence (DWI). ASSESSMENT: Three scans were acquired longitudinally (pretreatment, after two cycles of NAST, and after four cycles of NAST). For each scan, 11 ADC histogram features (minimum, maximum, mean, median, standard deviation, kurtosis, skewness and 10th, 25th, 75th, and 90th percentiles) were extracted from tumors and from PTRs of 5 mm, 10 mm, 15 mm, and 20 mm in thickness with inclusion and exclusion of fat-dominant pixels. STATISTICAL TESTS: ADC features were tested for prediction of pCR, both individually using Mann-Whitney U test and area under the receiver operating characteristic curve (AUC), and in combination in multivariable models with k-fold cross-validation. A P value < 0.05 was considered statistically significant. RESULTS: Fifty-one patients (47%) had pCR. Maximum ADC from PTR, measured after two and four cycles of NAST, was significantly higher in pCR patients (2.8 ± 0.69 vs 3.5 ± 0.94 mm2 /sec). The top-performing feature for prediction of pCR was the maximum ADC from the 5-mm fat-inclusive PTR after cycle 4 of NAST (AUC: 0.74; 95% confidence interval: 0.64, 0.84). Multivariable models of ADC features performed similarly for fat-inclusive and fat-exclusive PTRs, with AUCs ranging from 0.68 to 0.72 for the cycle 2 and cycle 4 scans. DATA CONCLUSION: Quantitative ADC features from PTRs may serve as early predictors of the response to NAST in TNBC. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 4.

Computer-aided detection of mantle cell lymphoma on 18F-FDG PET/CT using a deep learning convolutional neural network.

18F-FDG PET/CT can provide quantitative characterization with prognostic value for mantle cell lymphoma (MCL). However, detection of MCL is performed manually, which is labor intensive and not a part of the routine clinical practice. This study investigates a deep learning convolutional neural network (DLCNN) for computer-aided detection of MCL on 18F-FDG PET/CT. We retrospectively analyzed 142 baseline 18F-FDG PET/CT scans of biopsy-confirmed MCL acquired between May 2007 and October 2018. Of the 142 scans, 110 were from our institution and 32 were from outside institutions. An Xception-based U-Net was constructed to classify each pixel of the PET/CT images as MCL or not. The network was first trained and tested on the within-institution scans by applying five-fold cross-validation. Sensitivity and false positives (FPs) per patient were calculated for network evaluation. The network was then tested on the outside-institution scans, which were excluded from network training. For the 110 within-institution patients (85 male; median age, 58 [range: 39-84] years), the network achieved an overall median sensitivity of 88% (interquartile range [IQR]: 25%) with 15 (IQR: 12) FPs/patient. Sensitivity was dependent on lesion size and SUVmax but not on lesion location. For the 32 outside-institution patients (24 male; median age, 59 [range: 40-67] years), the network achieved a median sensitivity of 84% (IQR: 24%) with 14 (IQR: 10) FPs/patient. No significant performance difference was found between the within and outside institution scans. Therefore, DLCNN can potentially help with MCL detection on 18F-FDG PET/CT with high sensitivity and limited FPs.

Assessment of Early Response to Neoadjuvant Systemic Therapy in Triple-Negative Breast Cancer Using Amide Proton Transfer-weighted Chemical Exchange Saturation Transfer MRI: A Pilot Study.

Purpose To determine if amide proton transfer-weighted chemical exchange saturation transfer (APTW CEST) MRI is useful in the early assessment of treatment response in persons with triple-negative breast cancer (TNBC). Materials and Methods In this prospective study, a total of 51 participants (mean age, 51 years [range, 26-79 years]) with TNBC were included who underwent APTW CEST MRI with 0.9- and 2.0-µT saturation power performed at baseline, after two cycles (C2), and after four cycles (C4) of neoadjuvant systemic therapy (NAST). Imaging was performed between January 31, 2019, and November 11, 2019, and was a part of a clinical trial (registry number NCT02744053). CEST MR images were analyzed using two methods-magnetic transfer ratio asymmetry (MTRasym) and Lorentzian line shape fitting. The APTW CEST signals at baseline, C2, and C4 were compared for 51 participants to evaluate the saturation power levels and analysis methods. The APTW CEST signals and their changes during NAST were then compared for the 26 participants with pathology reports for treatment response assessment. Results A significant APTW CEST signal decrease was observed during NAST when acquisition at 0.9-µT saturation power was paired with Lorentzian line shape fitting analysis and when the acquisition at 2.0 µT was paired with MTRasym analysis. Using 0.9-µT saturation power and Lorentzian line shape fitting, the APTW CEST signal at C2 was significantly different from baseline in participants with pathologic complete response (pCR) (3.19% vs 2.43%; P = .03) but not with non-pCR (2.76% vs 2.50%; P > .05). The APTW CEST signal change was not significant between pCR and non-pCR at all time points. Conclusion Quantitative APTW CEST MRI depended on optimizing acquisition saturation powers and analysis methods. APTW CEST MRI monitored treatment effects but did not differentiate participants with TNBC who had pCR from those with non-pCR. © RSNA, 2021 Clinical trial registration no. NCT02744053 Supplemental material is available for this article.Keywords Molecular Imaging-Cancer, Molecular Imaging-Clinical Translation, MR-Imaging, Breast, Technical Aspects, Tumor Response, Technology Assessment.

Functional Tumor Volume by Fast Dynamic Contrast-Enhanced MRI for Predicting Neoadjuvant Systemic Therapy Response in Triple-Negative Breast Cancer.

BACKGROUND: Dynamic contrast-enhanced (DCE) MRI is useful for diagnosis and assessment of treatment response in breast cancer. Fast DCE MRI offers a higher sampling rate of contrast enhancement curves in comparison to conventional DCE MRI, potentially characterizing tumor perfusion kinetics more accurately for measurement of functional tumor volume (FTV) as a predictor of treatment response. PURPOSE: To investigate FTV by fast DCE MRI as a predictor of neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC). STUDY TYPE: Prospective. POPULATION/SUBJECTS: Sixty patients with biopsy-confirmed TNBC between December 2016 and September 2020. FIELD STRENGTH/SEQUENCE: A 3.0 T/3D fast spoiled gradient echo-based DCE MRI ASSESSMENT: Patients underwent MRI at baseline and after four cycles (C4) of NAST, followed by definitive surgery. DCE subtraction images were analyzed in consensus by two breast radiologists with 5 (A.H.A.) and 2 (H.S.M.) years of experience. Tumor volumes (TV) were measured on early and late subtractions. Tumors were segmented on 1 and 2.5-minute early phases subtractions and FTV was determined using optimized signal enhancement thresholds. Interpolated enhancement curves from segmented voxels were used to determine optimal early phase timing. STATISTICAL TESTS: Tumor volumes were compared between patients who had a pathologic complete response (pCR) and those who did not using the area under the receiver operating curve (AUC) and Mann-Whitney U test. RESULTS: About 26 of 60 patients (43%) had pCR. FTV at 1 minute after injection at C4 provided the best discrimination between pCR and non-pCR, with AUC (95% confidence interval [CI]) = 0.85 (0.74,0.95) (P < 0.05). The 1-minute timing was optimal for FTV measurements at C4 and for the change between C4 and baseline. TV from the early phase at C4 also yielded a good AUC (95%CI) of 0.82 (0.71,0.93) (P < 0.05). DATA CONCLUSION: FTV and TV measured at 1 minute after injection can predict response to NAST in TNBC. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: 4.

Tumor necrosis by pretreatment breast MRI: association with neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC).

PURPOSE: To determine if tumor necrosis by pretreatment breast MRI and its quantitative imaging characteristics are associated with response to NAST in TNBC. METHODS: This retrospective study included 85 TNBC patients (mean age 51.8 ± 13 years) with MRI before NAST and definitive surgery during 2010-2018. Each MRI included T2-weighted, diffusion-weighted (DWI), and dynamic contrast-enhanced (DCE) imaging. For each index carcinoma, total tumor volume including necrosis (TTV), excluding necrosis (TV), and the necrosis-only volume (NV) were segmented on early-phase DCE subtractions and DWI images. NV and %NV were calculated. Percent enhancement on early and late phases of DCE and apparent diffusion coefficient were extracted from TTV, TV, and NV. Association between necrosis with pathological complete response (pCR) was assessed using odds ratio (OR). Multivariable analysis was used to evaluate the prognostic value of necrosis with T stage and nodal status at staging. Mann-Whitney U tests and area under the curve (AUC) were used to assess performance of imaging metrics for discriminating pCR vs non-pCR. RESULTS: Of 39 patients (46%) with necrosis, 17 had pCR and 22 did not. Necrosis was not associated with pCR (OR, 0.995; 95% confidence interval [CI] 0.4-2.3) and was not an independent prognostic factor when combined with T stage and nodal status at staging (P = 0.46). None of the imaging metrics differed significantly between pCR and non-pCR in patients with necrosis (AUC < 0.6 and P > 0.40). CONCLUSION: No significant association was found between necrosis by pretreatment MRI or the quantitative imaging characteristics of tumor necrosis and response to NAST in TNBC.

MetNet: Computer-aided segmentation of brain metastases in post-contrast T1-weighted magnetic resonance imaging.

PURPOSE: Brain metastases are manually contoured during stereotactic radiosurgery (SRS) treatment planning, which is time-consuming, potentially challenging, and laborious. The purpose of this study was to develop and investigate a 2-stage deep learning (DL) approach (MetNet) for brain metastasis segmentation in pre-treatment magnetic resonance imaging (MRI). MATERIALS AND METHODS: We retrospectively analyzed postcontrast 3D T1-weighted spoiled gradient echo MRIs from 934 patients who underwent SRS between August 2009 and August 2018. Neuroradiologists manually identified brain metastases in the MRIs. The treating radiation oncologist or physicist contoured the brain metastases. We constructed a 2-stage DL ensemble consisting of detection and segmentation models to segment the brain metastases on the MRIs. We evaluated the performance of MetNet by computing sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC) with respect to metastasis size, as well as free-response receiver operating characteristics. RESULTS: The 934 patients (mean [±standard deviation] age 59 ± 13 years, 474 women) were randomly split into 80% training and 20% testing groups (748:186). For patients with metastases 1-52 mm (n = 766), 648 (85%) were detected and segmented with a mean segmentation DSC of 81% ± 15%. Patient-averaged sensitivity was 88% ± 19%, PPV was 58% ± 25%, and DSC was 85% ± 13% with 3 ± 3 false positives (FPs) per patient. When considering only metastases ≥6 mm, patient-averaged sensitivity was 99% ± 5%, PPV was 67% ± 28%, and DSC was 87% ± 13% with 1 ± 2 FPs per patient. CONCLUSION: MetNet can segment brain metastases across a broad range of metastasis sizes with high sensitivity, low FPs, and high segmentation accuracy in postcontrast T1-weighted MRI, potentially aiding treatment planning for SRS.

Should abbreviated breast MRI be compliant with American College of Radiology requirements for MRI accreditation?

OBJECTIVE: To evaluate non-inferiority and diagnostic performance of an American College of Radiology compliant abbreviated MRI protocol (AB-MRI) compared with standard-of-care breast MRI (SOC-BMRI) in patients with increased breast cancer risk. MATERIAL AND METHODS: Women with increased lifetime breast cancer risk by American Cancer Society guidelines underwent breast MRI at a single institution between October 2015 and February 2018. AB-MRI was acquired at 3.0 T with T2-weighted extended fast spin echo triple-echo Dixon and pre- and post-contrast 3D dual-echo fast spoiled gradient echo two-point Dixon sequences with an 8-channel breast coil 1-7 days after SOC-BMRI. Three readers independently reviewed AB-MRI and assigned BI-RADS categories for maximum intensity projection images (AB1), dynamic contrast-enhanced (DCE) images (AB2), and DCE and non-contrast T2 and fat-only images (AB3). These scores were compared to those from SOC-BMRI. RESULTS: Cancer yield was 14 per 1000 (women-years) in 73 women aged 26-75 years (mean 53.5 years). AB-MRI acquisition times (mean 9.63 min) and table times (mean 15.07 min) were significantly shorter than those of SOC-BMRI (means 19.46 and 36.3 min, respectively) (p < .001). Accuracy, sensitivity, specificity, and positive and negative predictive values were identical for AB3 and SOC-BMRI (93%, 100%, 93%, 16.7%, and 100%, respectively). AB-MRI with AB1 and AB2 had significantly lower specificity (AB1 = 73.6%, AB2 = 77.8%), positive predictive values (AB1 = 5%, AB2 = 5.9%), and accuracy (AB1 = 74%, AB2 = 78%) than those of SOC-BMRI (p = .002 for AB1, p = .01 for AB2). CONCLUSION: AB-MRI was acquired significantly faster than SOC-BMRI and its diagnostic performance was non-inferior. Inclusion of T2 and fat-only images was necessary to achieve non-inferiority by multireader evaluation.

Evaluation of feasibility and image quality of a new radial quantitative T2 weighted imaging sequence for liver MRI.

OBJECTIVES: To evaluate the clinical feasibility of a new T2 weighted sequence to calculate T2 relaxation times (T2RT) of liver lesions using two-dimensional radial turbo spin echo (2DRTSE) and to evaluate this sequence by performing image quality and relaxation time comparison of multiple liver lesions. MATERIALS AND METHODS: This prospective analysis of 2DRTSE sequences (using 22 echoes) was performed in 19 patients with 36 liver lesions. Two radiologists independently obtained T2RTs for liver lesions and scored image quality and image artifacts. Lesions were classified as cyst, hemangioma, solid, or necrotic. T2RT values were compared. Inter-reader agreement was evaluated. RESULTS: The 2DRTSE images were considered good quality with few artifacts by both radiologists. Nineteen patients were included in the study, with a total of 36 liver lesions. Two of the liver lesions were classified as cysts, 7 as hemangiomas, 4 as necrotic lesions, and 23 as solid lesions. The concordance correlation coefficient was 0.996 for the calculated T2RT of each liver lesion between the two readers, indicating good agreement. There was statically significant difference of the calculated T2RT for each lesion type. CONCLUSION: The 2DRTSE sequence can be performed and provides good T2W image quality and a quantitative T2RT map of the entire abdomen. The liver lesions can be distinguished based on the calculated T2RT using this technique. 2DRTSE could potentially supplant the current T2-weighted imaging sequence with the benefit of quantitative T2RTs.

Computer-aided Detection of Brain Metastases in T1-weighted MRI for Stereotactic Radiosurgery Using Deep Learning Single-Shot Detectors.

Background Brain metastases are manually identified during stereotactic radiosurgery (SRS) treatment planning, which is time consuming and potentially challenging. Purpose To develop and investigate deep learning (DL) methods for detecting brain metastasis with MRI to aid in treatment planning for SRS. Materials and Methods In this retrospective study, contrast material-enhanced three-dimensional T1-weighted gradient-echo MRI scans from patients who underwent gamma knife SRS from January 2011 to August 2018 were analyzed. Brain metastases were manually identified and contoured by neuroradiologists and treating radiation oncologists. DL single-shot detector (SSD) algorithms were constructed and trained to map axial MRI slices to a set of bounding box predictions encompassing metastases and associated detection confidences. Performances of different DL SSDs were compared for per-lesion metastasis-based detection sensitivity and positive predictive value (PPV) at a 50% confidence threshold. For the highest-performing model, detection performance was analyzed by using free-response receiver operating characteristic analysis. Results Two hundred sixty-six patients (mean age, 60 years ± 14 [standard deviation]; 148 women) were randomly split into 80% training and 20% testing groups (212 and 54 patients, respectively). For the testing group, sensitivity of the highest-performing (baseline) SSD was 81% (95% confidence interval [CI]: 80%, 82%; 190 of 234) and PPV was 36% (95% CI: 35%, 37%; 190 of 530). For metastases measuring at least 6 mm, sensitivity was 98% (95% CI: 97%, 99%; 130 of 132) and PPV was 36% (95% CI: 35%, 37%; 130 of 366). Other models (SSD with a ResNet50 backbone, SSD with focal loss, and RetinaNet) yielded lower sensitivities of 73% (95% CI: 72%, 74%; 171 of 234), 77% (95% CI: 76%, 78%; 180 of 234), and 79% (95% CI: 77%, 81%; 184 of 234), respectively, and lower PPVs of 29% (95% CI: 28%, 30%; 171 of 581), 26% (95% CI: 26%, 26%; 180 of 681), and 13% (95% CI: 12%, 14%; 184 of 1412). Conclusion Deep-learning single-shot detector models detected nearly all brain metastases that were 6 mm or larger with limited false-positive findings using postcontrast T1-weighted MRI. © RSNA, 2020 See also the editorial by Kikinis and Wells in this issue.

Comparison of free breathing and respiratory triggered diffusion-weighted imaging sequences for liver imaging.

BACKGROUND: Diffusion-weighted imaging (DWI) has become a useful tool in the detection, characterization, and evaluation of response to treatment of many cancers, including malignant liver lesions. DWI offers higher image contrast between lesions and normal liver tissue than other sequences. DWI images acquired at two or more b-values can be used to derive an apparent diffusion coefficient (ADC). DWI in the body has several technical challenges. This include ghosting artifacts, mis-registration and susceptibility artifacts. New DWI sequences have been developed to overcome some of these challenges. Our goal is to evaluate 3 new DWI sequences for liver imaging. AIM: To qualitatively and quantitatively compare 3 DWI sequences for liver imaging: free-breathing (FB), simultaneous multislice (SMS), and prospective acquisition correction (PACE). METHODS: Magnetic resonance imaging (MRI) was performed in 20 patients in this prospective study. The MR study included 3 separate DWI sequences: FB-DWI, SMS-DWI, and PACE-DWI. The image quality, mean ADC, standard deviations (SD) of ADC, and ADC histogram were compared. Wilcoxon signed-rank tests were used to compare qualitative image quality. A linear mixed model was used to compare the mean ADC and the SDs of the ADC values. All tests were 2-sided and P values of < 0.05 were considered statistically significant. RESULTS: There were 56 lesions (50 malignant) evaluated in this study. The mean qualitative image quality score of PACE-DWI was 4.48. This was significantly better than that of SMS-DWI (4.22) and FB-DWI (3.15) (P < 0.05). Quantitatively, the mean ADC values from the 3 different sequences did not significantly differ for each liver lesion. FB-DWI had a markedly higher variation in the SD of the ADC values than did SMS-DWI and PACE-DWI. We found statistically significant differences in the SDs of the ADC values for FB-DWI vs PACE-DWI (P < 0.0001) and for FB-DWI vs SMS-DWI (P = 0.03). The SD of the ADC values was not statistically significant for PACE-DWI and SMS-DWI (P = 0.18). The quality of the PACE-DWI ADC histograms were considered better than the SMS-DWI and FB-DWI. CONCLUSION: Compared to FB-DWI, both PACE-DWI and SMS-DWI provide better image quality and decreased quantitative variability in the measurement of ADC values of liver lesions.

Multimodal Imaging of Pathologic Response to Chemoradiation in Esophageal Cancer.

PURPOSE: To examine the value of early changes in quantitative diffusion-weighted imaging and 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) for discriminating complete pathologic response (pCR) to chemoradiation in esophageal cancer. METHODS AND MATERIALS: Twenty esophageal cancer patients treated with chemoradiation followed by surgery were prospectively enrolled. Patients underwent magnetic resonance imaging and FDG-PET/CT scans at baseline, interim (2 weeks after chemoradiation start), and first follow-up. On the basis of pathologic findings at surgery, patients were categorized into tumor regression groups (TRG1, TRG2, and TRG3+). Distributions of summary statistics in apparent diffusion coefficient (ADC) and FDG-PET at baseline and relative changes at interim and follow-up scans were compared between pCR/TRG1 and non-pCR/TRG2+ groups and across readers. Receiver operating characteristics were evaluated for summary measures to characterize discrimination of pCR from non-pCR. RESULTS: Relative changes in tumor volume ADC (ΔADC) mean and 25th and 10th percentiles from baseline to interim were able to completely discriminate (area under the curve = 1, P < .0011) between pCR and non-pCR (thresholds = 27.7%, 29.2%, and 32.1%, respectively) and were found to have high interreader reliability (95% limits of agreement of 1.001, 0.944, and 0.940, respectively). Relative change in total lesion glycolysis (TLG) from baseline to interim was significantly different among pCR and non-pCR groups (P=.0117) and yielded an area under the curve of 0.947 (95% confidence interval 0.8505-1.043). An optimal threshold of 59% decrease in TLG provided optimal sensitivity (specificity) of 1.000 (0.867). Changes in ADC summary measures were negatively correlated with that of TLG (Spearman, -0.495, P=.027). CONCLUSIONS: Quantitative volume ΔADC and TLG during treatment may serve as early imaging biomarkers for discriminating pathologic response to chemoradiation in esophageal cancer. Validation of these data in larger, prospective, multicenter studies is essential.