Accuracy of an Artificial Intelligence System for Interval Breast Cancer Detection at Screening Mammography.

Background Artificial intelligence (AI) systems can be used to identify interval breast cancers, although the localizations are not always accurate. Purpose To evaluate AI localizations of interval cancers (ICs) on screening mammograms by IC category and histopathologic characteristics. Materials and Methods A screening mammography data set (median patient age, 57 years [IQR, 52-64 years]) that had been assessed by two human readers from January 2011 to December 2018 was retrospectively analyzed using a commercial AI system. The AI outputs were lesion locations (heatmaps) and the highest per-lesion risk score (range, 0-100) assigned to each case. AI heatmaps were considered false positive (FP) if they occurred on normal screening mammograms or on IC screening mammograms (ie, in patients subsequently diagnosed with IC) but outside the cancer boundary. A panel of consultant radiology experts classified ICs as normal or benign (true negative [TN]), uncertain (minimal signs of malignancy [MS]), or suspicious (false negative [FN]). Several specificity and sensitivity thresholds were applied. Mann-Whitney U tests, Kruskal-Wallis tests, and χ2 tests were used to compare groups. Results A total of 2052 screening mammograms (514 ICs and 1548 normal mammograms) were included. The median AI risk score was 50 (IQR, 32-82) for TN ICs, 76 (IQR, 41-90) for ICs with MS, and 89 (IQR, 81-95) for FN ICs (P = .005). Higher median AI scores were observed for invasive tumors (62 [IQR, 39-88]) than for noninvasive tumors (33 [IQR, 20-55]; P < .01) and for high-grade (grade 2-3) tumors (62 [IQR, 40-87]) than for low-grade (grade 0-1) tumors (45 [IQR, 26-81]; P = .02). At the 96% specificity threshold, the AI algorithm flagged 121 of 514 (23.5%) ICs and correctly localized the IC in 93 of 121 (76.9%) cases, with 48 FP heatmaps on the mammograms for ICs (rate, 0.093 per case) and 74 FP heatmaps on normal mammograms (rate, 0.048 per case). The AI algorithm correctly localized a lower proportion of TN ICs (54 of 427; 12.6%) than ICs with MS (35 of 76; 46%) and FN ICs (four of eight; 50% [95% CI: 13, 88]; P < .001). The AI algorithm localized a higher proportion of node-positive than node-negative cancers (P = .03). However, no evidence of a difference by cancer type (P = .09), grade (P = .27), or hormone receptor status (P = .12) was found. At 89.8% specificity and 79% sensitivity thresholds, AI detection increased to 181 (35.2%) and 256 (49.8%) of the 514 ICs, respectively, with FP heatmaps on 158 (10.2%) and 307 (19.8%) of the 1548 normal mammograms. Conclusion Use of a standalone AI system improved early cancer detection by correctly identifying some cancers missed by two human readers, with no differences based on histopathologic features except for node-positive cancers. © RSNA, 2024 Supplemental material is available for this article.

Deep learning-based segmentation of multisite disease in ovarian cancer.

PURPOSE: To determine if pelvic/ovarian and omental lesions of ovarian cancer can be reliably segmented on computed tomography (CT) using fully automated deep learning-based methods. METHODS: A deep learning model for the two most common disease sites of high-grade serous ovarian cancer lesions (pelvis/ovaries and omentum) was developed and compared against the well-established "no-new-Net" framework and unrevised trainee radiologist segmentations. A total of 451 CT scans collected from four different institutions were used for training (n = 276), evaluation (n = 104) and testing (n = 71) of the methods. The performance was evaluated using the Dice similarity coefficient (DSC) and compared using a Wilcoxon test. RESULTS: Our model outperformed no-new-Net for the pelvic/ovarian lesions in cross-validation, on the evaluation and test set by a significant margin (p values being 4 × 10-7, 3 × 10-4, 4 × 10-2, respectively), and for the omental lesions on the evaluation set (p = 1 × 10-3). Our model did not perform significantly differently in segmenting pelvic/ovarian lesions (p = 0.371) compared to a trainee radiologist. On an independent test set, the model achieved a DSC performance of 71 ± 20 (mean ± standard deviation) for pelvic/ovarian and 61 ± 24 for omental lesions. CONCLUSION: Automated ovarian cancer segmentation on CT scans using deep neural networks is feasible and achieves performance close to a trainee-level radiologist for pelvic/ovarian lesions. RELEVANCE STATEMENT: Automated segmentation of ovarian cancer may be used by clinicians for CT-based volumetric assessments and researchers for building complex analysis pipelines. KEY POINTS: • The first automated approach for pelvic/ovarian and omental ovarian cancer lesion segmentation on CT images has been presented. • Automated segmentation of ovarian cancer lesions can be comparable with manual segmentation of trainee radiologists. • Careful hyperparameter tuning can provide models significantly outperforming strong state-of-the-art baselines.

Clinically Interpretable Radiomics-Based Prediction of Histopathologic Response to Neoadjuvant Chemotherapy in High-Grade Serous Ovarian Carcinoma.

Background: Pathological response to neoadjuvant treatment for patients with high-grade serous ovarian carcinoma (HGSOC) is assessed using the chemotherapy response score (CRS) for omental tumor deposits. The main limitation of CRS is that it requires surgical sampling after initial neoadjuvant chemotherapy (NACT) treatment. Earlier and non-invasive response predictors could improve patient stratification. We developed computed tomography (CT) radiomic measures to predict neoadjuvant response before NACT using CRS as a gold standard. Methods: Omental CT-based radiomics models, yielding a simplified fully interpretable radiomic signature, were developed using Elastic Net logistic regression and compared to predictions based on omental tumor volume alone. Models were developed on a single institution cohort of neoadjuvant-treated HGSOC (n = 61; 41% complete response to NCT) and tested on an external test cohort (n = 48; 21% complete response). Results: The performance of the comprehensive radiomics models and the fully interpretable radiomics model was significantly higher than volume-based predictions of response in both the discovery and external test sets when assessed using G-mean (geometric mean of sensitivity and specificity) and NPV, indicating high generalizability and reliability in identifying non-responders when using radiomics. The performance of a fully interpretable model was similar to that of comprehensive radiomics models. Conclusions: CT-based radiomics allows for predicting response to NACT in a timely manner and without the need for abdominal surgery. Adding pre-NACT radiomics to volumetry improved model performance for predictions of response to NACT in HGSOC and was robust to external testing. A radiomic signature based on five robust predictive features provides improved clinical interpretability and may thus facilitate clinical acceptance and application.

Improving the image quality of DWI in breast cancer: comparison of multi-shot DWI using multiplexed sensitivity encoding to conventional single-shot echo-planar imaging DWI.

OBJECTIVE: To compare diffusion-weighted images (DWI) acquired using single-shot echo-planar imaging (ss-EPI) and multiplexed sensitivity encoding (MUSE) in breast cancer. METHODS: 20 females with pathologically confirmed breast cancer (age 51 ± 12 years) were imaged with ss-EPI-DWI and MUSE-DWI. ADC, normalised ADC (nADC), blur and distortion metrics and qualitative image quality scores were compared. The Crété-Roffet and Mattes mutual information metrics were used to evaluate blurring and distortion, respectively. In a breast phantom, six permutations of MUSE-DWI with varying parallel acceleration factor and number of shots were compared. Differences in ADC and nADC were compared using the coefficient of variation in the phantom and a paired t-test in patients. Differences in blur, distortion and qualitative metrics were analysed using a Wilcoxon signed-rank test. RESULTS: There was a low coefficient of variation (<2%) in ADC between ss-EPI-DWI and all MUSE-DWI permutations acquired using the phantom. 22 malignant and three benign lesions were identified in 20 patients. ADC values measured using MUSE were significantly lower compared to ss-EPI for malignant but not benign lesions (p < 0.001, p = 0.21). nADC values were not significantly different (p = 0.62, p = 0.28). Blurring and distortion improved with number of shots and acceleration factor, and significantly improved with MUSE in patients (p < 0.001, p = 0.002). Qualitatively, image quality improved using MUSE. CONCLUSION: MUSE improves the image quality of breast DWI compared to ss-EPI. ADVANCES IN KNOWLEDGE: MUSE-DWI has superior image quality and reduced blurring and distortion compared to ss-EPI-DWI in breast cancer.

Gerbode defect following endocarditis and misinterpreted as severe pulmonary arterial hypertension.

A Gerbode-type defect is a ventricular septal defect communicating directly between the left ventricle and right atrium. It is usually congenital, but rarely is acquired, as a complication of endocarditis. This can be anatomically possible because the normal tricuspid valve is more apically displaced than the mitral valve. However, identification of an actual communication is often extremely difficult, so a careful and meticulous echocardiogram should be done in order to prevent echocardiographic misinterpretation of this defect as pulmonary arterial hypertension. The large systolic pressure gradient between the left ventricle and the right atrium would expectedly result in a high velocity systolic Doppler flow signal in right atrium and it can be sometimes mistakably diagnosed as tricuspid regurgitant jet simulating pulmonary arterial hypertension. We present a rare case of young woman, with endocarditis who presented with severe pulmonary arterial hypertension. The preoperative diagnosis of left ventricle to right atrial communication (acquired Gerbode defect) was suspected initially by echocardiogram and confirmed at the time of the surgery. A point of interest, apart from the diagnostic problem, was the explanation for its mechanism and presentation. The probability of a bacterial etiology of the defect is high in this case.

The Role of CT Angiography of Coronaries in Early Diagnosis of Coronary Artery Plaques in Albanian People with No History of Cardiovascular Disease in Correlation with Traditional Risk Factors.

OBJECTIVE: To evaluate the role of CT angiography of coronaries (CTAC) in the diagnosis of subclinical atherosclerosis by detection of coronary artery plaques (CAP) in a group of consecutive albanian individuals with no history of coronary artery disease (CAD) or acute coronary syndrome and to investigate the relation between the prevalence of CAP, traditional risk factors and the expected 10-year risk of fatal cardiovascular event (CVE) based on our own experience. METHOD AND TECHNIQUE: This is a prospective study including 456 patients with no history of CAD who underwent CTAC in our hospital from September 2009 to March 2013. Risk estimation of fatal CVE was assessed using Systematic Coronary Risk Evaluation (SCORE) and then CT scan was performed with a 64 detector CT, including Ca Score and angiography of coronaries with iv contrast. RESULTS: From 456 patients 61.4% were low risk and 32.9% were at intermediate risk according to SCORE. The prevalence of CAP diagnosed by CTAC was calculated as 55.7 % overall. Though the presence and severity of CAP increased significantly with the increase of SCORE, it was found to be 44.1% in the low risk patients and 80% in the intermediate risk group, with a presence of 17% and 25% of stenotic plaques (>50%) respectively. Significant correlation was found between all traditional risk factors and CAP. CONCLUSION: Although a direct relation between the prevalence of CAP, risk factors and the related 10-year risk of fatal CVE was found, there was a significant prevalence of CAP in low -intermediate risk group with a considerable presence of stenotic lesions. Also 8.3% of patients with no risk factors and 18% of the patients with Ca score 0 had CAP in CT angiography, one resulting with severe stenosis. Our results suggest once more that CT angiography is a reliable, very accurate noninvasive technique for the diagnosis of early CAD, especially in the low-intermediate risk patients compared to the traditional evaluation schemes and Ca score, thus should be considered in this group as a diagnostic guide for optimal therapy planning.