Rethinking extent of resection of contrast-enhancing and non-enhancing tumor: different survival impacts on adult-type diffuse gliomas in 2021 World Health Organization classification.

OBJECTIVES: Extent of resection (EOR) of contrast-enhancing (CE) and non-enhancing (NE) tumors may have different impacts on survival according to types of adult-type diffuse gliomas in the molecular era. This study aimed to evaluate the impact of EOR of CE and NE tumors in glioma according to the 2021 World Health Organization classification. METHODS: This retrospective study included 1193 adult-type diffuse glioma patients diagnosed between 2001 and 2021 (183 oligodendroglioma, 211 isocitrate dehydrogenase [IDH]-mutant astrocytoma, and 799 IDH-wildtype glioblastoma patients) from a single institution. Patients had complete information on IDH mutation, 1p/19q codeletion, and O6-methylguanine-methyltransferase (MGMT) status. Cox survival analyses were performed within each glioma type to assess predictors of overall survival, including clinical, imaging data, histological grade, MGMT status, adjuvant treatment, and EOR of CE and NE tumors. Subgroup analyses were performed in patients with CE tumor. RESULTS: Among 1193 patients, 935 (78.4%) patients had CE tumors. In entire oligodendrogliomas, gross total resection (GTR) of NE tumor was not associated with survival (HR = 0.56, p = 0.223). In 86 (47.0%) oligodendroglioma patients with CE tumor, GTR of CE tumor was the only independent predictor of survival (HR = 0.16, p = 0.004) in multivariable analysis. GTR of CE and NE tumors was independently associated with better survival in IDH-mutant astrocytoma and IDH-wildtype glioblastoma (all ps < 0.05). CONCLUSIONS: GTR of both CE and NE tumors may significantly improve survival within IDH-mutant astrocytomas and IDH-wildtype glioblastomas. In oligodendrogliomas, the EOR of CE tumor may be crucial in survival; aggressive GTR of NE tumor may be unnecessary, whereas GTR of the CE tumor is recommended. CLINICAL RELEVANCE STATEMENT: Surgical strategies on contrast-enhancing (CE) and non-enhancing (NE) tumors should be reassessed considering the different survival outcomes after gross total resection depending on CE and NE tumors in the 2021 World Health Organization classification of adult-type diffuse gliomas. KEY POINTS: The survival impact of extent of resection of contrast-enhancing (CE) and non-enhancing (NE) tumors was evaluated in adult-type diffuse gliomas. Gross total resection of both CE and NE tumors may improve survival in isocitrate dehydrogenase (IDH)-mutant astrocytomas and IDH-wildtype glioblastomas, while only gross total resection of the CE tumor improves survival in oligodendrogliomas. Surgical strategies should be reconsidered according to types in adult-type diffuse gliomas.

Screening in Patients With Dense Breasts: Comparison of Mammography, Artificial Intelligence, and Supplementary Ultrasound.

BACKGROUND. Screening mammography has decreased performance in patients with dense breasts. Supplementary screening ultrasound is a recommended option in such patients, although it has yielded mixed results in prior investigations. OBJECTIVE. The purpose of this article is to compare the performance characteristics of screening mammography alone, standalone artificial intelligence (AI), ultrasound alone, and mammography in combination with AI and/or ultrasound in patients with dense breasts. METHODS. This retrospective study included 1325 women (mean age, 53 years) with dense breasts who underwent both screening mammography and supplementary breast ultrasound within a 1-month interval from January 2017 to December 2017; prior mammography and prior ultrasound examinations were available for comparison in 91.2% and 91.8%, respectively. Mammography and ultrasound examinations were interpreted by one of 15 radiologists (five staff; 10 fellows); clinical reports were used for the present analysis. A commercial AI tool was used to retrospectively evaluate mammographic examinations for presence of cancer. Screening performances were compared among mammography, AI, ultrasound, and test combinations, using generalized estimating equations. Benign diagnoses required 24 months or longer of imaging stability. RESULTS. Twelve cancers (six invasive ductal carcinoma; six ductal carcinoma in situ) were diagnosed. Mammography, standalone AI, and ultrasound showed cancer detection rates (per 1000 patients) of 6.0, 6.8, and 6.0 (all p > .05); recall rates of 4.4%, 11.9%, and 9.2% (all p < .05); sensitivity of 66.7%, 75.0%, and 66.7% (all p > .05); specificity of 96.2%, 88.7%, and 91.3% (all p < .05); and accuracy of 95.9%, 88.5%, and 91.1% (all p < .05). Mammography with AI, mammography with ultrasound, and mammography with both ultrasound and AI showed cancer detection rates of 7.5, 9.1, and 9.1 (all p > .05); recall rates of 14.9, 11.7, and 21.4 (all p < .05); sensitivity of 83.3%, 100.0%, and 100.0% (all p > .05); specificity of 85.8%, 89.1%, and 79.4% (all p < .05); and accuracy of 85.7%, 89.2%, and 79.5% (all p < .05). CONCLUSION. Mammography with supplementary ultrasound showed higher accuracy, higher specificity, and lower recall rate in comparison with mammography with AI and in comparison with mammography with both ultrasound and AI. CLINICAL IMPACT. The findings fail to show benefit of AI with respect to screening mammography performed with supplementary breast ultrasound in patients with dense breasts.

Methods for Clinical Evaluation of Artificial Intelligence Algorithms for Medical Diagnosis.

Adequate clinical evaluation of artificial intelligence (AI) algorithms before adoption in practice is critical. Clinical evaluation aims to confirm acceptable AI performance through adequate external testing and confirm the benefits of AI-assisted care compared with conventional care through appropriately designed and conducted studies, for which prospective studies are desirable. This article explains some of the fundamental methodological points that should be considered when designing and appraising the clinical evaluation of AI algorithms for medical diagnosis. The specific topics addressed include the following: (a) the importance of external testing of AI algorithms and strategies for conducting the external testing effectively, (b) the various metrics and graphical methods for evaluating the AI performance as well as essential methodological points to note in using and interpreting them, (c) paired study designs primarily for comparative performance evaluation of conventional and AI-assisted diagnoses, (d) parallel study designs primarily for evaluating the effect of AI intervention with an emphasis on randomized clinical trials, and (e) up-to-date guidelines for reporting clinical studies on AI, with an emphasis on guidelines registered in the EQUATOR Network library. Sound methodological knowledge of these topics will aid the design, execution, reporting, and appraisal of clinical evaluation of AI.

Revisiting prognostic factors in glioma with leptomeningeal metastases: a comprehensive analysis of clinical and molecular factors and treatment modalities.

PURPOSE: To comprehensively investigate prognostic factors, including clinical and molecular factors and treatment modalities, in adult glioma patients with leptomeningeal metastases (LM). METHODS: Total 226 patients with LM (from 2001 to 2021 among 1495 grade 2 to 4 glioma patients, 88.5% of LM patients being IDH-wildtype) with complete information on IDH mutation, 1p/19q codeletion, and MGMT promoter methylation status were enrolled. Predictors of overall survival (OS) of entire patients were determined by time-dependent Cox analysis, including clinical, molecular, and treatment data. Subgroup analyses were performed for patients with LM at initial diagnosis and LM diagnosed at recurrence (herein, initial and recurrent LM). Identical analyses were performed in IDH-wildtype glioblastoma patients. RESULTS: Median OS was 17.0 (IQR 9.7-67.1) months, with shorter median OS in initial LM than recurrent LM patients (12.2 vs 20.6 months, P < 0.001). In entire patients, chemotherapy and antiangiogenic therapy were predictors of longer OS, while male sex and initial LM were predictors of shorter OS. In initial LM, higher KPS, chemotherapy, and antiangiogenic therapy were predictors of longer OS, while male sex was a predictor of shorter OS. In recurrent LM, chemotherapy and longer interval between initial glioma and LM diagnoses were predictors of longer OS, while male sex was a predictor of shorter OS. A similar trend was observed in IDH-wildtype glioblastoma. CONCLUSION: Active chemotherapy and antiangiogenic therapy demonstrated survival benefit in glioma patients with LM. There is consistent female survival advantage, whereas longer interval between initial glioma diagnosis and LM development suggests longer OS in recurrent LM.

Multiparametric MRI-based radiomics model for predicting human papillomavirus status in oropharyngeal squamous cell carcinoma: optimization using oversampling and machine learning techniques.

OBJECTIVES: To develop and validate a multiparametric MRI-based radiomics model with optimal oversampling and machine learning techniques for predicting human papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC). METHODS: This retrospective, multicenter study included consecutive patients with newly diagnosed and pathologically confirmed OPSCC between January 2017 and December 2020 (110 patients in the training set, 44 patients in the external validation set). A total of 293 radiomics features were extracted from three sequences (T2-weighted images [T2WI], contrast-enhanced T1-weighted images [CE-T1WI], and ADC). Combinations of three feature selection, five oversampling, and 12 machine learning techniques were evaluated to optimize its diagnostic performance. The area under the receiver operating characteristic curve (AUC) of the top five models was validated in the external validation set. RESULTS: A total of 154 patients (59.2 ± 9.1 years; 132 men [85.7%]) were included, and oversampling was employed to account for data imbalance between HPV-positive and HPV-negative OPSCC (86.4% [133/154] vs. 13.6% [21/154]). For the ADC radiomics model, the combination of random oversampling and ridge showed the highest diagnostic performance in the external validation set (AUC, 0.791; 95% CI, 0.775-0.808). The ADC radiomics model showed a higher trend in diagnostic performance compared to the radiomics model using CE-T1WI (AUC, 0.604; 95% CI, 0.590-0.618), T2WI (AUC, 0.695; 95% CI, 0.673-0.717), and a combination of both (AUC, 0.642; 95% CI, 0.626-0.657). CONCLUSIONS: The ADC radiomics model using random oversampling and ridge showed the highest diagnostic performance in predicting the HPV status of OPSCC in the external validation set. CLINICAL RELEVANCE STATEMENT: Among multiple sequences, the ADC radiomics model has a potential for generalizability and applicability in clinical practice. Exploring multiple oversampling and machine learning techniques was a valuable strategy for optimizing radiomics model performance. KEY POINTS: • Previous radiomics studies using multiparametric MRI were conducted at single centers without external validation and had unresolved data imbalances. • Among the ADC, CE-T1WI, and T2WI radiomics models and the ADC histogram models, the ADC radiomics model was the best-performing model for predicting human papillomavirus status in oropharyngeal squamous cell carcinoma. • The ADC radiomics model with the combination of random oversampling and ridge showed the highest diagnostic performance.

Comparison of imaging findings of macrotrabecular-massive hepatocellular carcinoma using CT and gadoxetic acid-enhanced MRI.

OBJECTIVES: To investigate the imaging findings of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC) on CT and MRI, and examine their diagnostic performance and prognostic significance. METHODS: We retrospectively enrolled 220 consecutive patients who underwent hepatic resection between June 2009 and December 2013 for single treatment-naïve HCC, who have preoperative CT and gadoxetic acid-enhanced MRI. Independent reviews of histopathology and imaging were performed by two reviewers. Previously reported imaging findings, LI-RADS category, and CT attenuation of MTM-HCC were investigated. The diagnostic performance of the MTM-HCC diagnostic criteria was compared across imaging modalities. RESULTS: MTM-HCC was associated with ≥ 50% arterial phase hypovascular component, intratumoral artery, arterial phase peritumoral enhancement, and non-smooth tumor margin on CT and MRI (p < .05). Arterial phase hypovascular components were less commonly observed on MRI subtraction images than on CT or MRI, while non-rim arterial phase hyperenhancement and LR-5 were more commonly observed on MRI subtraction images than on MRI (p < .05). MTM-HCC showed lower tumor attenuation in the CT arterial phase (p = .01). Rhee's criteria, defined as ≥ 50% hypovascular component and ≥ 2 ancillary findings (intratumoral artery, arterial phase peritumoral enhancement, and non-smooth tumor margin), showed similar diagnostic performance for MRI (sensitivity, 41%; specificity, 97%) and CT (sensitivity, 31%; specificity, 94%). Rhee's criteria on CT were independent prognostic factors for overall survival. CONCLUSION: The MRI diagnostic criteria for MTM-HCC are applicable on CT, showing similar diagnostic performance and prognostic significance. For MTM-HCC, arterial phase subtraction images can aid in the HCC diagnosis by depicting subtle arterial hypervascularity. KEY POINTS: • MTM-HCC on CT demonstrated previously described MRI findings, including arterial phase hypovascular component, intratumoral artery, arterial phase peritumoral enhancement, and necrosis. • The MRI diagnostic criteria for MTM-HCC were also applicable to CT, showing comparable diagnostic performance and prognostic significance. • On arterial phase subtraction imaging, MTM-HCC more frequently demonstrated non-rim enhancement and LR-5 and less frequently LR-M than MRI arterial phase, which may aid in the diagnosis of HCC.

Intelligent noninvasive meningioma grading with a fully automatic segmentation using interpretable multiparametric deep learning.

OBJECTIVES: To establish a robust interpretable multiparametric deep learning (DL) model for automatic noninvasive grading of meningiomas along with segmentation. METHODS: In total, 257 patients with pathologically confirmed meningiomas (162 low-grade, 95 high-grade) who underwent a preoperative brain MRI, including T2-weighted (T2) and contrast-enhanced T1-weighted images (T1C), were included in the institutional training set. A two-stage DL grading model was constructed for segmentation and classification based on multiparametric three-dimensional U-net and ResNet. The models were validated in the external validation set consisting of 61 patients with meningiomas (46 low-grade, 15 high-grade). Relevance-weighted Class Activation Mapping (RCAM) method was used to interpret the DL features contributing to the prediction of the DL grading model. RESULTS: On external validation, the combined T1C and T2 model showed a Dice coefficient of 0.910 in segmentation and the highest performance for meningioma grading compared to the T2 or T1C only models, with an area under the curve (AUC) of 0.770 (95% confidence interval: 0.644-0.895) and accuracy, sensitivity, and specificity of 72.1%, 73.3%, and 71.7%, respectively. The AUC and accuracy of the combined DL grading model were higher than those of the human readers (AUCs of 0.675-0.690 and accuracies of 65.6-68.9%, respectively). The RCAM of the DL grading model showed activated maps at the surface regions of meningiomas indicating that the model recognized the features at the tumor margin for grading. CONCLUSIONS: An interpretable multiparametric DL model combining T1C and T2 can enable fully automatic grading of meningiomas along with segmentation. KEY POINTS: • The multiparametric DL model showed robustness in grading and segmentation on external validation. • The diagnostic performance of the combined DL grading model was higher than that of the human readers. • The RCAM interpreted that DL grading model recognized the meaningful features at the tumor margin for grading.

Pretreatment MRI-detected extramural venous invasion as a prognostic and predictive biomarker for neoadjuvant chemoradiotherapy in non-metastatic rectal cancer: a propensity score matched analysis.

OBJECTIVES: This study evaluated pretreatment magnetic resonance imaging (MRI)-detected extramural venous invasion (pmrEMVI) as a predictor of survival after neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC). MATERIALS AND METHODS: Medical records of 1184 patients with rectal adenocarcinoma who underwent TME between January 2011 and December 2016 were reviewed. MRI data were collected from a computerized radiologic database. Cox proportional hazards analysis was used to assess local, systemic recurrence, and disease-free survival risk based on pretreatment MRI-assessed tumor characteristics. After propensity score matching (PSM) for pretreatment MRI features, nCRT therapeutic outcomes according to pmrEMVI status were evaluated. Cox proportional hazards analysis was used to identify risk factors for early recurrence in patients receiving nCRT. RESULTS: Median follow-up was 62.8 months. Among all patients, the presence of pmrEMVI was significantly associated with worse disease-free survival (DFS; HR 1.827, 95% CI 1.285-2.597, p = 0.001) and systemic recurrence (HR 2.080, 95% CI 1.400-3.090, p < 0.001) but not local recurrence. Among patients with pmrEMVI, nCRT provided no benefit for oncological outcomes before or after PSM. Furthermore, pmrEMVI( +) was the only factor associated with early recurrence on multivariate analysis in patients receiving nCRT. CONCLUSIONS: pmrEMVI is a poor prognostic factor for DFS and SR in patients with non-metastatic rectal cancer and also serves as a predictive biomarker of poor DFS and SR following nCRT in LARC. Therefore, for patients who are positive for pmrEMVI, consideration of alternative treatment strategies may be warranted. CLINICAL RELEVANCE STATEMENT: This study demonstrated the usefulness of pmrEMVI as a predictive biomarker for nCRT, which may assist in initial treatment decision-making in patients with non-metastatic rectal cancer. KEY POINTS: • Pretreatment MRI-detected extramural venous invasion (pmrEMVI) was significantly associated with worse disease-free survival and systemic recurrence in patients with non-metastatic rectal cancer. • pmrEMVI is a predictive biomarker of poor DFS following nCRT in patients with LARC. • The presence of pmrEMVI was the only factor associated with early recurrence on multivariate analysis in patients receiving nCRT.

Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports.

OBJECTIVES: To evaluate the performance of natural language processing (NLP) models to predict isocitrate dehydrogenase (IDH) mutation status in diffuse glioma using routine MR radiology reports. MATERIALS AND METHODS: This retrospective, multi-center study included consecutive patients with diffuse glioma with known IDH mutation status from May 2009 to November 2021 whose initial MR radiology report was available prior to pathologic diagnosis. Five NLP models (long short-term memory [LSTM], bidirectional LSTM, bidirectional encoder representations from transformers [BERT], BERT graph convolutional network [GCN], BioBERT) were trained, and area under the receiver operating characteristic curve (AUC) was assessed to validate prediction of IDH mutation status in the internal and external validation sets. The performance of the best performing NLP model was compared with that of the human readers. RESULTS: A total of 1427 patients (mean age ± standard deviation, 54 ± 15; 779 men, 54.6%) with 720 patients in the training set, 180 patients in the internal validation set, and 527 patients in the external validation set were included. In the external validation set, BERT GCN showed the highest performance (AUC 0.85, 95% CI 0.81-0.89) in predicting IDH mutation status, which was higher than LSTM (AUC 0.77, 95% CI 0.72-0.81; p = .003) and BioBERT (AUC 0.81, 95% CI 0.76-0.85; p = .03). This was higher than that of a neuroradiologist (AUC 0.80, 95% CI 0.76-0.84; p = .005) and a neurosurgeon (AUC 0.79, 95% CI 0.76-0.84; p = .04). CONCLUSION: BERT GCN was externally validated to predict IDH mutation status in patients with diffuse glioma using routine MR radiology reports with superior or at least comparable performance to human reader. CLINICAL RELEVANCE STATEMENT: Natural language processing may be used to extract relevant information from routine radiology reports to predict cancer genotype and provide prognostic information that may aid in guiding treatment strategy and enabling personalized medicine. KEY POINTS: • A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set. • The best NLP models were superior or at least comparable to human readers in both internal and external validation sets. • Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.

MRI radiomics may predict early tumor recurrence in patients with sinonasal squamous cell carcinoma.

OBJECTIVES: Sinonasal squamous cell carcinoma (SCC) follows a poor prognosis with high tendency for local recurrence. We aimed to evaluate whether MRI radiomics can predict early local failure in sinonasal SCC. METHODS: Sixty-eight consecutive patients with node-negative sinonasal SCC (January 2005-December 2020) were enrolled, allocated to the training (n = 47) and test sets (n = 21). Early local failure, which occurred within 12 months of completion of initial treatment, was the primary endpoint. For clinical features (age, location, treatment modality, and clinical T stage), binary logistic regression analysis was performed. For 186 extracted radiomic features, different feature selections and classifiers were combined to create two prediction models: (1) a pure radiomics model; and (2) a combined model with clinical features and radiomics. The areas under the receiver operating characteristic curves (AUCs) were calculated and compared using DeLong's method. RESULTS: Early local failure occurred in 38.3% (18/47) and 23.8% (5/21) in the training and test sets, respectively. We identified several radiomic features which were strongly associated with early local failure. In the test set, both the best-performing radiomics model and the combined model (clinical + radiomic features) yielded higher AUCs compared to the clinical model (AUC, 0.838 vs. 0.438, p = 0.020; 0.850 vs. 0.438, p = 0.016, respectively). The performances of the best-performing radiomics model and the combined model did not differ significantly (AUC, 0.838 vs. 0.850, p = 0.904). CONCLUSION: MRI radiomics integrated with a machine learning classifier may predict early local failure in patients with sinonasal SCC. CLINICAL RELEVANCE STATEMENT: MRI radiomics intergrated with machine learning classifiers may predict early local failure in sinonasal squamous cell carcinomas more accurately than the clinical model. KEY POINTS: • A subset of radiomic features which showed significant association with early local failure in patients with sinonasal squamous cell carcinomas was identified. • MRI radiomics integrated with machine learning classifiers can predict early local failure with high accuracy, which was validated in the test set (area under the curve = 0.838). • The combined clinical and radiomics model yielded superior performance for early local failure prediction compared to that of the radiomics (area under the curve 0.850 vs. 0.838 in the test set), without a statistically significant difference.

Artificial intelligence assistance for women who had spot compression view: reducing recall rates for digital mammography.

BACKGROUND: Mammography yields inevitable recall for indeterminate findings that need to be confirmed with additional views. PURPOSE: To explore whether the artificial intelligence (AI) algorithm for mammography can reduce false-positive recall in patients who undergo the spot compression view. MATERIAL AND METHODS: From January to December 2017, 236 breasts from 225 women who underwent the spot compression view due to focal asymmetry, mass, or architectural distortion on standard digital mammography were included. Three readers who were blinded to the study purpose, patient information, previous mammograms, following spot compression views, and any clinical or pathologic reports retrospectively reviewed 236 standard mammograms and determined the necessity of patient recall and the probability of malignancy per breast, first without and then with AI assistance. The performances of AI and the readers were evaluated with the recall rate, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. RESULTS: Among 236 examinations, 8 (3.4%) were cancers and 228 (96.6%) were benign. The recall rates of all three readers significantly decreased with AI assistance (P < 0.05). The reader-averaged recall rates significantly decreased with AI assistance regardless of breast composition (fatty breasts: 32.7% to 24.1%m P = 0.002; dense breasts: 33.6% to 21.2%, P < 0.001). The reader-averaged AUC increased with AI assistance and was comparable to that of standalone AI (0.835 vs. 0.895; P = 0.234). The reader-averaged specificity (71.2% to 79.8%, P < 0.001) and accuracy (71.3% to 79.7%, P < 0.001) significantly improved with AI assistance. CONCLUSION: AI assistance significantly reduced false-positive recall without compromising cancer detection in women with focal asymmetry, mass, or architectural distortion on standard digital mammography regardless of mammographic breast density.

Preliminary study for prediction of benign vertebral compression fracture age by quantitative water fraction using modified Dixon sequences: an imaging biomarker of fracture age.

PURPOSE: This study aimed to evaluate whether quantitative water fraction parameters could predict fracture age in patients with benign vertebral compression fractures (VCFs). METHODS: A total of 38 thoracolumbar VCFs in 27 patients imaged using modified Dixon sequences for water fraction quantification on 3-T MRI were retrospectively reviewed. To calculate quantitative parameters, a radiologist independently measured the regions of interest in the bone marrow edema (BME) of the fractures. Furthermore, five features (BME, trabecular fracture line, condensation band, cortical or end plate fracture line, and paravertebral soft-tissue change) were analyzed. The fracture age was evaluated based on clear-onset symptoms and previously available images. A correlation analysis between the fracture age and water fraction was evaluated using a linear regression model, and a multivariable analysis of the dichotomized fracture age model was performed. RESULTS: The water fraction ratio was the only significant factor and was negatively correlated with the fracture age of VCFs in multiple linear regression (p = 0.047), whereas the water fraction was not significantly correlated (p = 0.052). Water fraction and water fraction ratio were significant factors in differentiating the fracture age of 1 year in multiple logistic regression (odds ratio 0.894, p = 0.003 and odds ratio 0.986, p = 0.019, respectively). Using a cutoff of 0.524 for the water fraction, the area under the curve, sensitivity, and specificity were 0.857, 85.7%, and 87.1%, respectively. CONCLUSIONS: Water fraction is a good imaging biomarker for the fracture healing process. The water fraction ratio of the compression fractures can be used to predict the fracture age of benign VCFs.

Consistency of Artificial Intelligence (AI)-based Diagnostic Support Software in Short-term Digital Mammography Reimaging After Core Needle Biopsy.

To evaluate the consistency in the performance of Artificial Intelligence (AI)-based diagnostic support software in short-term digital mammography reimaging after core needle biopsy. Of 276 women who underwent short-term (<3 mo) serial digital mammograms followed by breast cancer surgery from Jan. to Dec. 2017, 550 breasts were included. All core needle biopsies for breast lesions were performed between serial exams. All mammography images were analyzed using a commercially available AI-based software providing an abnormality score (0-100). Demographic data for age, interval between serial exams, biopsy, and final diagnosis were compiled. Mammograms were reviewed for mammographic density and finding. Statistical analysis was performed to evaluate the distribution of variables according to biopsy and to test the interaction effects of variables with the difference in AI-based score according to biopsy. AI-based score of 550 exams (benign or normal in 263 and malignant in 287) showed significant difference between malignant and benign/normal exams (0.48 vs. 91.97 in first exam and 0.62 vs. 87.13 in second exam, P<0.0001). In comparison of serial exams, no significant difference was found in AI-based score. AI-based score difference between serial exams was significantly different according to biopsy performed or not (-0.25 vs. 0.07, P = 0.035). In linear regression analysis, there was no significant interaction effect of all clinical and mammographic characteristics with mammographic examinations performed after biopsy or not. The results from AI-based diagnostic support software for digital mammography was relatively consistent in short-term reimaging even after core needle biopsy.

Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis.

BACKGROUND AND PURPOSE: To investigate the diagnostic performance of fully automated radiomics-based models for multiclass classification of a single enhancing brain tumor among glioblastoma, central nervous system lymphoma, and metastasis. MATERIALS AND METHODS: The training and test sets were comprised of 538 cases (300 glioblastomas, 73 lymphomas, and 165 metastases) and 169 cases (101 glioblastomas, 29 lymphomas, and 39 metastases), respectively. After fully automated segmentation, radiomic features were extracted. Three conventional machine learning classifiers, including least absolute shrinkage and selection operator (LASSO), adaptive boosting (Adaboost), and support vector machine with the linear kernel (SVC), combined with one of four feature selection methods, including forward sequential feature selection, F score, mutual information, and LASSO, were trained. Additionally, one ensemble classifier based on the three classifiers was used. The diagnostic performance of the optimized models was tested in the test set using the accuracy, F1-macro score, and the area under the receiver operating characteristic curve (AUCROC). RESULTS: The best performance was achieved when the LASSO was used as a feature selection method. In the test set, the best performance was achieved by the ensemble classifier, showing an accuracy of 76.3% (95% CI, 70.0-82.7), a F1-macro score of 0.704, and an AUCROC of 0.878. CONCLUSION: Our fully automated radiomics-based models for multiclass classification might be useful for differential diagnosis of a single enhancing brain tumor with a good diagnostic performance and generalizability.

Retrospective Evaluation of Treatment Response in Patients with Nonmetastatic Pancreatic Cancer Using CT and CA 19-9.

Background Imaging studies have limitations in evaluating pancreatic ductal adenocarcinoma (PDAC) treatment response. Purpose To investigate the effectiveness of combined CT and carbohydrate antigen 19-9 (CA 19-9) evaluation at 8 weeks after first-line treatment to predict overall survival (OS) of patients with nonmetastatic PDAC. Materials and Methods Patients with nonmetastatic PDAC who received first-line treatment with either chemotherapy or concurrent chemoradiation in a single-center PDAC cohort registry were retrospectively enrolled in the study between January 2013 and December 2016. Follow-up CT images obtained 8 weeks after treatment were evaluated according to Response Evaluation Criteria in Solid Tumors. Patients with partial response (PR) or stable disease (SD) were defined as CT responders, and those with progressive disease (PD) were defined as CT nonresponders. Patients with a normalized CA 19-9 level at 8-week follow-up were defined as CA 19-9 responders, and those with a nonnormalized or nonelevated CA 19-9 level were defined as CA 19-9 nonresponders. OS was compared using the Kaplan-Meier method with Breslow analysis. Results A total of 197 patients (mean age ± standard deviation, 65 years ± 10; 107 men) were evaluated. Patients with PD (n = 17) showed shorter OS than those with SD (n = 147; P < .001) or PR (n = 33; P = .003). OS did not differ between the patients with PR and those with SD (P = .60). When the CT and CA 19-9 responses were integrated, OS was longest in CT and CA 19-9 responders (group 1, n = 27; median OS, 26.6 months [95% CI: 9.0, 44.1]), followed by CT responders but CA 19-9 nonresponders (group 2, n = 153; median OS, 15.9 months [95% CI: 13.3, 18.5]; P = .007 vs group 1) and CT and CA 19-9 nonresponders (group 3, n = 17; median OS, 6.5 months [95% CI: 0.8, 12.2]; P < .001 vs group 2). Conclusion Integrated evaluation with CT and carbohydrate antigen 19-9 response allowed more accurate stratification of survival in patients with pancreatic ductal adenocarcinoma in the early treatment period than did evaluation according to Response Evaluation Criteria in Solid Tumors. © RSNA, 2022 Online supplemental material is available for this article.

US, Mammography, and Histopathologic Evaluation to Identify Low Nuclear Grade Ductal Carcinoma in Situ.

Background Low nuclear grade ductal carcinoma in situ (DCIS) identified at biopsy can be upgraded to intermediate to high nuclear grade DCIS at surgery. Methods that confirm low nuclear grade are needed to consider nonsurgical approaches for these patients. Purpose To develop a preoperative model to identify low nuclear grade DCIS and to evaluate factors associated with low nuclear grade DCIS at biopsy that was not upgraded to intermediate to high nuclear grade DCIS at surgery. Materials and Methods In this retrospective study, 470 women (median age, 50 years; interquartile range, 44-58 years) with 477 pure DCIS lesions at surgical histopathologic evaluation were included (January 2010 to December 2015). Patients were divided into the training set (n = 330) or validation set (n = 147) to develop a preoperative model to identify low nuclear grade DCIS. Features at US (mass, nonmass) and at mammography (morphologic characteristics, distribution of microcalcification) were reviewed. The upgrade rate of low nuclear grade DCIS was calculated, and multivariable regression was used to evaluate factors for associations with low nuclear grade DCIS that was not upgraded later. Results A preoperative model that included lesions manifesting as a mass at US without microcalcification and no comedonecrosis at biopsy was used to identify low nuclear grade DCIS, with a high area under the receiver operating characteristic curve of 0.97 (95% CI: 0.94, 1.00) in the validation set. The upgrade rate of low nuclear grade DCIS at biopsy was 38.8% (50 of 129). Ki-67 positivity (odds ratio, 0.04; 95% CI: 0.0003, 0.43; P = .005) was inversely associated with constant low nuclear grade DCIS. Conclusion The upgrade rate of low nuclear grade ductal carcinoma in situ (DCIS) at biopsy to intermediate to high nuclear grade DCIS at surgery occurred in more than a third of patients; low nuclear grade DCIS at final histopathologic evaluation could be identified if the mass was viewed at US without microcalcifications and had no comedonecrosis at histopathologic evaluation of biopsy. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Rahbar in this issue. An earlier incorrect version appeared online. This article was corrected on April 14, 2022.

Impact of intratumoral heterogeneity on the metabolic profiling of breast cancer tissue using high-resolution magic angle spinning magnetic resonance spectroscopy.

High-resolution magic angle spinning (HR-MAS) magnetic resonance spectroscopy (MRS) is a useful metabolic profiling technique for human tissue. However, the impact of intratumoral heterogeneity on the metabolite levels of breast cancers is not yet established. The purpose of this prospective study was to investigate whether the tumor cell fraction of core needle biopsy (CNB) specimens of breast cancers affect metabolic profiles assessed with HR-MAS MRS. From June 2015 to December 2016, 46 patients with 47 breast cancers were enrolled. HR-MAS MRS was used for the metabolic profiling of 285 CNB specimens from the 47 cancers. Multiple CNB samples (range 2-8) for the HR-MAS MRS experiment were obtained from surgical specimens under ultrasound guidance following surgical removal of the tumor. Tumor cell fraction was expressed as a percentage of the tumor cell volume relative to the total tumor volume contained in each CNB sample. Metabolite quantification levels were compared according to primary tumor characteristics using the t-test. Multivariate analyses were performed including primary tumor characteristics and tumor cell percentages as variables. Correlations between tumor cell percentage and metabolite levels in the CNB specimens were assessed according to the immunohistochemical status of the primary tumor. In univariate analysis, levels of choline-containing compounds, glutamate, glutamine, glycine, serine, and taurine were correlated with primary tumor characteristics. In multivariate analysis, most metabolite levels were not affected by tumor cell percentage. Tumor cell percentage showed poor correlation with metabolite levels in hormone receptor-positive cancer and triple-negative cancer, and poor to fair correlation with metabolite levels in HER2-positive cancer. This study showed that differences in the tumor cell fraction of CNB samples do not affect predictions on the primary cancer from which the samples are obtained.

A New Reporting System for Diagnosis of Hepatocellular Carcinoma in Chronic Hepatitis B With Clinical and Gadoxetic Acid-Enhanced MRI Features.

BACKGROUND: Current major guidelines for diagnosis of hepatocellular carcinoma (HCC) based on imaging findings are different from each other and do not include clinical risk factors as a diagnostic criteria. PURPOSE: To developed and validated a new diagnostic score system using MRI and clinical features as applied in chronic hepatitis B patients. STUDY TYPE: Retrospective observational study. SUBJECT: A total of 418 treatment-naïve patients (out of 902 patients) with chronic hepatitis B having 556 lesions suspected for HCC which were eligible for curative treatment. FIELD STRENGTH/SEQUENCE: T1W GRE in- and opposed-phase, T2W FSE, DWI, and T1W 3D-GRE dynamic contrast-enhanced sequences at 1.5  T and 3  T. ASSESSMENT: Six radiologists with 7-22 years of experience independently evaluated MR images based on Liver Imaging Reporting and Data System (LI-RADS) version 2018. STATISTICAL TESTS: Based on logistic regression analysis of MRI features and clinical factors, a risk score system was devised in derivation cohorts (268 patients, 352 lesions) and externally validated (150 patients, 204 lesions). The performance of the new score system was assessed by Harell's c-index. Using cutoff value of 12, maintaining positive predictive value ≥95%, the diagnostic performances of the score system were compared with those of LR-5. RESULTS: The 15-point diagnostic scoring system used MRI features (lesion size, nonrim arterial phase hyperenhancement, portal venous phase hypointensity, hepatobiliary phase hypointensity, and diffusion restriction) and clinical factors (alpha-fetoprotein and platelet). It showed good discrimination in the derivation (c-index, 0.946) and validation cohorts (c-index, 0.907). Using a risk score of 12 as a cut-off, this system yielded higher sensitivity than LR-5 (derivation cohort, 76.8% vs. 52.1%; validation cohort, 73.4% vs. 49.5%) without significant decrease in specificity (derivation cohort, 93.1% vs. 97.2%, P = 0.074; validation cohort, 91.7% vs. 96.1%, P = 0.299). DATA CONCLUSION: A new score system showed improved sensitivity in chronic hepatitis B patients compared to LI-RADS without significant compromise in specificity. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Preoperative magnetic resonance imaging-based prognostic model for mass-forming intrahepatic cholangiocarcinoma.

BACKGROUND & AIMS: As most staging systems for intrahepatic cholangiocarcinoma (iCCA) are based on pathological results, preoperative prognostic prediction is limited. This study aimed to develop and validate a prognostic model for the overall survival of patients with mass-forming iCCA (MF-iCCA) using preoperative magnetic resonance imaging (MRI) and clinical findings. METHODS: We enrolled a total of 316 patients who underwent preoperative MRI and surgical resection for treatment-naive MF-iCCA from six institutions, between January 2009 and December 2015. The subjects were randomly assigned to a training set (n = 208) or validation set (n = 108). The MRIs were independently reviewed by three abdominal radiologists. Using MRI and clinical findings, an MRI prognostic score was established. We compared the discrimination performance of MRI prognostic scores with those of conventional pathological staging systems. RESULTS: We developed an MRI prognostic score consisting of serum CA19-9 and three MRI findings (tumour multiplicity, lymph node metastasis and bile duct invasion). The MRI prognostic score demonstrated good discrimination performance in both the training set (C-index, 0.738; 95% confidence interval [CI], 0.698-0.780) and validation set (C-index, 0.605; 95% CI, 0.526-0.680). In the validation set, MRI prognostic score showed no significant difference with AJCC 8th TNM stage, MEGNA score and Nathan's stage. CONCLUSIONS: Our MRI prognostic score for overall survival of MF-iCCA showed comparable discriminatory performance with pathological staging systems and might be used to determine an optimal treatment strategy.

Sex as a prognostic factor in adult-type diffuse gliomas: an integrated clinical and molecular analysis according to the 2021 WHO classification.

PURPOSE: To investigate whether type-specific sex differences in survival exist independently of clinical and molecular factors in adult-type diffuse gliomas according to the 2021 World Health Organization (WHO) classification. METHODS: A retrospective chart and imaging review of 1325 patients (mean age, 54 ± 15 years; 569 females) with adult-type diffuse gliomas (oligodendroglioma, IDH-mutant, and 1p/19q-codeleted, n = 183; astrocytoma, IDH-mutant, n = 211; glioblastoma, IDH-wildtype, n = 800; IDH-wildtype diffuse glioma, NOS, n = 131) was performed. The demographic information, extent of resection, imaging data, and molecular data including O6-methylguanine-methyltransferase promoter methylation (MGMT) promotor methylation were collected. Sex differences in survival were analyzed using Cox analysis. RESULTS: In patients with glioblastoma, IDH-wildtype, female sex remained as an independent predictor of better overall survival (hazard ratio = 0.91, P = 0.031), along with age, histological grade 4, MGMT promoter methylation status, and gross total resection. Female sex showed a higher prevalence of MGMT promoter methylation (40.2% vs 32.0%, P = 0.017) but there was no interaction effect between female sex and MGMT promoter methylation status (P-interaction = 0.194), indicating independent role of female sex. The median OS for females were 19.2 months (12.3-35.0) and 16.2 months (10.5-30.6) for males. No sex difference in survival was seen in other types of adult-type diffuse gliomas. CONCLUSION: There was a female survival advantage in glioblastoma, IDH-wildtype, independently of clinical data or MGMT promoter methylation status. There was no sex difference in survival in other types of adult-type diffuse gliomas, suggesting type-specific sex effects solely in glioblastoma, IDH-wildtype.