Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT.

OBJECTIVES: The purpose of this study was to evaluate the incremental value of artificial intelligence (AI) compared to the diagnostic accuracy of radiologists alone in detecting incidental acute pulmonary embolism (PE) on routine portal venous contrast-enhanced chest computed tomography (CT). METHODS: CTs of 3089 consecutive patients referred to the radiology department for a routine contrast-enhanced chest CT between 27-5-2020 and 31-12-2020, were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The diagnostic performance of the AI was compared to the initial report. To determine the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, another experienced cardiothoracic radiologist with knowledge of the initial report and the AI output adjudicated. RESULTS: The prevalence of acute incidental PE in the reference standard was 2.2% (67 of 3089 patients). In 25 cases, AI detected initially unreported PE. This included three cases concerning central/lobar PE. Sensitivity of the AI algorithm was significantly higher than the outcome of the initial report (respectively 95.5% vs. 62.7%, p < 0.001), whereas specificity was very high for both (respectively 99.6% vs 99.9%, p = 0.012). The AI algorithm only showed a slightly higher amount of false-positive findings (11 vs. 2), resulting in a significantly lower PPV (85.3% vs. 95.5%, p = 0.047). CONCLUSION: The AI algorithm showed high diagnostic accuracy in diagnosing incidental PE, detecting an additional 25 cases of initially unreported PE, accounting for 37.3% of all positive cases. CLINICAL RELEVANCE STATEMENT: Radiologist support from AI algorithms in daily practice can prevent missed incidental acute PE on routine chest CT, without a high burden of false-positive cases. KEY POINTS: • Incidental pulmonary embolism is often missed by radiologists in non-diagnostic scans with suboptimal contrast opacification within the pulmonary trunk. • An artificial intelligence algorithm showed higher sensitivity detecting incidental pulmonary embolism on routine portal venous chest CT compared to the initial report. • Implementation of artificial intelligence support in routine daily practice will reduce the number of missed incidental pulmonary embolism.

An artificial intelligence algorithm for pulmonary embolism detection on polychromatic computed tomography: performance on virtual monochromatic images.

OBJECTIVES: Virtual monochromatic images (VMI) are increasingly used in clinical practice as they improve contrast-to-noise ratio. However, due to their different appearances, the performance of artificial intelligence (AI) trained on conventional CT images may worsen. The goal of this study was to assess the performance of an established AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPI) to detect pulmonary embolism (PE) on VMI. METHODS: Paired 60 kiloelectron volt (keV) VMI and CPI of 114 consecutive patients suspected of PE, obtained with a detector-based spectral CT scanner, were retrospectively analyzed by an established AI algorithm. The CT pulmonary angiography (CTPA) were classified as positive or negative for PE on a per-patient level. The reference standard was established using a comprehensive method that combined the evaluation of the attending radiologist and three experienced cardiothoracic radiologists aided by two different detection tools. Sensitivity, specificity, positive and negative predictive values and likelihood ratios of the algorithm on VMI and CPI were compared. RESULTS: The prevalence of PE according to the reference standard was 35.1% (40 patients). None of the diagnostic accuracy measures of the algorithm showed a significant difference between CPI and VMI. Sensitivity was 77.5% (95% confidence interval (CI) 64.6-90.4%) and 85.0% (73.9-96.1%) (p = 0.08) on CPI and VMI respectively and specificity 96.0% (91.4-100.0%) and 94.6% (89.4-99.7%) (p = 0.32). CONCLUSIONS: Diagnostic performance of the AI algorithm that was trained on CPI did not drop on VMI, which is reassuring for its use in clinical practice. CLINICAL RELEVANCE STATEMENT: A commercially available AI algorithm, trained on conventional polychromatic CTPA, could be safely used on virtual monochromatic images. This supports the sustainability of AI-aided detection of PE on CT despite ongoing technological advances in medical imaging, although monitoring in daily practice will remain important. KEY POINTS: • Diagnostic accuracy of an AI algorithm trained on conventional polychromatic images to detect PE did not drop on virtual monochromatic images. • Our results are reassuring as innovations in hardware and reconstruction in CT are continuing, whilst commercial AI algorithms that are trained on older generation data enter healthcare.

Re-attendance in supplemental breast MRI screening rounds of the DENSE trial for women with extremely dense breasts.

OBJECTIVES: Supplemental MRI screening improves early breast cancer detection and reduces interval cancers in women with extremely dense breasts in a cost-effective way. Recently, the European Society of Breast Imaging recommended offering MRI screening to women with extremely dense breasts, but the debate on whether to implement it in breast cancer screening programs is ongoing. Insight into the participant experience and willingness to re-attend is important for this discussion. METHODS: We calculated the re-attendance rates of the second and third MRI screening rounds of the DENSE trial. Moreover, we calculated age-adjusted odds ratios (ORs) to study the association between characteristics and re-attendance. Women who discontinued MRI screening were asked to provide one or more reasons for this. RESULTS: The re-attendance rates were 81.3% (3458/4252) and 85.2% (2693/3160) in the second and third MRI screening round, respectively. A high age (> 65 years), a very low BMI, lower education, not being employed, smoking, and no alcohol consumption were correlated with lower re-attendance rates. Moderate or high levels of pain, discomfort, or anxiety experienced during the previous MRI screening round were correlated with lower re-attendance rates. Finally, a plurality of women mentioned an examination-related inconvenience as a reason to discontinue screening (39.1% and 34.8% in the second and third screening round, respectively). CONCLUSIONS: The willingness of women with dense breasts to re-attend an ongoing MRI screening study is high. However, emphasis should be placed on improving the MRI experience to increase the re-attendance rate if widespread supplemental MRI screening is implemented. CLINICAL RELEVANCE STATEMENT: For many women, MRI is an acceptable screening method, as re-attendance rates were high - even for screening in a clinical trial setting. To further enhance the (re-)attendance rate, one possible approach could be improving the overall MRI experience. KEY POINTS: • The willingness to re-attend in an ongoing MRI screening study is high. • Pain, discomfort, and anxiety in the previous MRI screening round were related to lower re-attendance rates. • Emphasis should be placed on improving MRI experience to increase the re-attendance rate in supplemental MRI screening.

Assessing Quantitative Parenchymal Features at Baseline Dynamic Contrast-enhanced MRI and Cancer Occurrence in Women with Extremely Dense Breasts.

Background Automated identification of quantitative breast parenchymal enhancement features on dynamic contrast-enhanced (DCE) MRI scans could provide added value in assessment of breast cancer risk in women with extremely dense breasts. Purpose To automatically identify quantitative properties of the breast parenchyma on baseline DCE MRI scans and assess their association with breast cancer occurrence in women with extremely dense breasts. Materials and Methods This study represents a secondary analysis of the Dense Tissue and Early Breast Neoplasm Screening trial. MRI was performed in eight hospitals between December 2011 and January 2016. After segmentation of fibroglandular tissue, quantitative features (including volumetric density, volumetric morphology, and enhancement characteristics) of the parenchyma were extracted from baseline MRI scans. Principal component analysis was used to identify parenchymal measures with the greatest variance. Multivariable Cox proportional hazards regression was applied to assess the association between breast cancer occurrence and quantitative parenchymal features, followed by stratification of significant features into tertiles. Results A total of 4553 women (mean age, 55.7 years ± 6 [SD]) with extremely dense breasts were included; of these women, 122 (3%) were diagnosed with breast cancer. Five principal components representing 96% of the variance were identified, and the component explaining the greatest independent variance (42%) consisted of MRI features relating to volume of enhancing parenchyma. Multivariable analysis showed that volume of enhancing parenchyma was associated with breast cancer occurrence (hazard ratio [HR], 1.09; 95% CI: 1.01, 1.18; P = .02). Additionally, women in the high tertile of volume of enhancing parenchyma showed a breast cancer occurrence twice that of women in the low tertile (HR, 2.09; 95% CI: 1.25, 3.61; P = .005). Conclusion In women with extremely dense breasts, a high volume of enhancing parenchyma on baseline DCE MRI scans was associated with increased occurrence of breast cancer as compared with a low volume of enhancing parenchyma. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Grimm in this issue.

Challenges and Changes of the Breast Cancer Screening Paradigm.

Since four decades mammography is used for early breast cancer detection in asymptomatic women and still remains the gold standard imaging modality. However, population screening programs can be personalized and women can be divided into different groups based on risk factors and personal preferences. The availability of new and evolving imaging modalities, for example, digital breast tomosynthesis, dynamic-contrast-enhanced magnetic resonance imaging (MRI), abbreviated MRI protocols, diffusion-weighted MRI, and contrast-enhanced mammography leads to new challenges and perspectives regarding the feasibility and potential harms of breast cancer screening. The aim of this review is to discuss the current guidelines for different risk groups, to analyze the recent published studies about the diagnostic performance of the imaging modalities and to discuss new developments and future perspectives. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 6.

Optimizing carboplatin dosing by an improved prediction of carboplatin clearance using a CT-enhanced estimate of renal function.

AIMS: Carboplatin is generally dosed based on a modified Calvert formula, in which the Cockcroft-Gault-based creatinine clearance (CRCL) is used as proxy for the glomerular filtration rate (GFR). The Cockcroft-Gault formula (CG) overpredicts CRCL in patients with an aberrant body composition. The CT-enhanced estimate of RenAl FuncTion (CRAFT) was developed to compensate for this overprediction. We aimed to evaluate whether carboplatin clearance is better predicted by CRCL based on the CRAFT compared to the CG. METHODS: Data of four previously conducted trials was used. The CRAFT was divided by serum creatinine to derive CRCL. The difference between CRAFT- and CG-based CRCL was assessed by population pharmacokinetic modelling. Furthermore, the difference in calculated carboplatin dose was assessed in a heterogeneous dataset. RESULTS: In total, 108 patients were included in the analysis. Addition of the CRAFT- and CG-based CRCL as covariate on carboplatin clearance led, respectively, to an improved model fit with a 26-point drop in objective function value and a worsened model fit with an increase of 8 points. In 19 subjects with serum creatinine <50 µmol/L, the calculated carboplatin dose was 233 mg higher using the CG. CONCLUSIONS: Carboplatin clearance is better predicted by CRAFT vs. CG-based CRCL. In subjects with low serum creatinine, the calculated carboplatin dose using CG exceeds the dose using CRAFT, which might explain the need for dose capping when using the CG. Therefore, the CRAFT might be an alternative for dose capping while still dosing accurately.

Pediatric body composition based on automatic segmentation of computed tomography scans: a pilot study.

BACKGROUND: Body composition during childhood may predispose to negative health outcomes later in life. Automatic segmentation may assist in quantifying pediatric body composition in children. OBJECTIVE: To evaluate automatic segmentation for body composition on pediatric computed tomography (CT) scans and to provide normative data on muscle and fat areas throughout childhood using automatic segmentation. MATERIALS AND METHODS: In this pilot study, 537 children (ages 1-17 years) who underwent abdominal CT after high-energy trauma at a Dutch tertiary center (2002-2019) were retrospectively identified. Of these, the CT images of 493 children (66% boys) were used to establish normative data. Muscle (psoas, paraspinal and abdominal wall) and fat (subcutaneous and visceral) areas were measured at the third lumbar vertebral (L3) level by automatic segmentation. A representative subset of 52 scans was also manually segmented to evaluate the performance of automatic segmentation. RESULTS: For manually-segmented versus automatically-segmented areas (52 scans), mean Dice coefficients were high for muscle (0.87-0.90) and subcutaneous fat (0.88), but lower for visceral fat (0.60). In the control group, muscle area was comparable for both sexes until the age of 13 years, whereafter, boys developed relatively more muscle. From a young age, boys were more prone to visceral fat storage than girls. Overall, boys had significantly higher visceral-to-subcutaneous fat ratios (median 1.1 vs. 0.6, P<0.01) and girls higher fat-to-muscle ratios (median 1.0 vs. 0.7, P<0.01). CONCLUSION: Automatic segmentation of L3-level muscle and fat areas allows for accurate quantification of pediatric body composition. Using automatic segmentation, the development in muscle and fat distribution during childhood (in otherwise healthy) Dutch children was demonstrated.

Supplemental MRI Screening for Women with Extremely Dense Breast Tissue.

BACKGROUND: Extremely dense breast tissue is a risk factor for breast cancer and limits the detection of cancer with mammography. Data are needed on the use of supplemental magnetic resonance imaging (MRI) to improve early detection and reduce interval breast cancers in such patients. METHODS: In this multicenter, randomized, controlled trial in the Netherlands, we assigned 40,373 women between the ages of 50 and 75 years with extremely dense breast tissue and normal results on screening mammography to a group that was invited to undergo supplemental MRI or to a group that received mammography screening only. The groups were assigned in a 1:4 ratio, with 8061 in the MRI-invitation group and 32,312 in the mammography-only group. The primary outcome was the between-group difference in the incidence of interval cancers during a 2-year screening period. RESULTS: The interval-cancer rate was 2.5 per 1000 screenings in the MRI-invitation group and 5.0 per 1000 screenings in the mammography-only group, for a difference of 2.5 per 1000 screenings (95% confidence interval [CI], 1.0 to 3.7; P<0.001). Of the women who were invited to undergo MRI, 59% accepted the invitation. Of the 20 interval cancers that were diagnosed in the MRI-invitation group, 4 were diagnosed in the women who actually underwent MRI (0.8 per 1000 screenings) and 16 in those who did not accept the invitation (4.9 per 1000 screenings). The MRI cancer-detection rate among the women who actually underwent MRI screening was 16.5 per 1000 screenings (95% CI, 13.3 to 20.5). The positive predictive value was 17.4% (95% CI, 14.2 to 21.2) for recall for additional testing and 26.3% (95% CI, 21.7 to 31.6) for biopsy. The false positive rate was 79.8 per 1000 screenings. Among the women who underwent MRI, 0.1% had either an adverse event or a serious adverse event during or immediately after the screening. CONCLUSIONS: The use of supplemental MRI screening in women with extremely dense breast tissue and normal results on mammography resulted in the diagnosis of significantly fewer interval cancers than mammography alone during a 2-year screening period. (Funded by the University Medical Center Utrecht and others; DENSE ClinicalTrials.gov number, NCT01315015.).

Deep Learning for Automated Triaging of 4581 Breast MRI Examinations from the DENSE Trial.

Background Supplemental screening with MRI has proved beneficial in women with extremely dense breasts. Most MRI examinations show normal anatomic and physiologic variation that may not require radiologic review. Thus, ways to triage these normal MRI examinations to reduce radiologist workload are needed. Purpose To determine the feasibility of an automated triaging method using deep learning (DL) to dismiss the highest number of MRI examinations without lesions while still identifying malignant disease. Materials and Methods This secondary analysis of data from the Dense Tissue and Early Breast Neoplasm Screening, or DENSE, trial evaluated breast MRI examinations from the first screening round performed in eight hospitals between December 2011 and January 2016. A DL model was developed to differentiate between breasts with lesions and breasts without lesions. The model was trained to dismiss breasts with normal phenotypical variation and to triage lesions (Breast Imaging Reporting and Data System [BI-RADS] categories 2-5) using eightfold internal-external validation. The model was trained on data from seven hospitals and tested on data from the eighth hospital, alternating such that each hospital was used once as an external test set. Performance was assessed using receiver operating characteristic analysis. At 100% sensitivity for malignant disease, the fraction of examinations dismissed from radiologic review was estimated. Results A total of 4581 MRI examinations of extremely dense breasts from 4581women (mean age, 54.3 years; interquartile range, 51.5-59.8 years) were included. Of the 9162 breasts, 838 had at least one lesion (BI-RADS category 2-5, of which 77 were malignant) and 8324 had no lesions. At 100% sensitivity for malignant lesions, the DL model considered 90.7% (95% CI: 86.7, 94.7) of the MRI examinations with lesions to be nonnormal and triaged them to radiologic review. The DL model dismissed 39.7% (95% CI: 30.0, 49.4) of the MRI examinations without lesions. The DL model had an average area under the receiver operating characteristic curve of 0.83 (95% CI: 0.80, 0.85) in the differentiation between normal breast MRI examinations and MRI examinations with lesions. Conclusion Automated analysis of breast MRI examinations in women with dense breasts dismissed nearly 40% of MRI scans without lesions while not missing any cancers. ClinicalTrials.gov: NCT01315015 © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Joe in this issue.

Exposure-Response Analysis of Osimertinib in EGFR Mutation Positive Non-Small Cell Lung Cancer Patients in a Real-Life Setting.

BACKGROUND: Osimertinib, an irreversible inhibitor of the epidermal growth factor receptor (EGFR) is an important drug in the treatment of EGFR-mutation positive non-small cell lung cancer (NSCLC). Clinical trials with osimertinib could not demonstrate an exposure-efficacy relationship, while a relationship between exposure and toxicity has been found. In this study, we report the exposure-response relationships of osimertinib in a real-life setting. METHODS: A retrospective observational cohort study was performed, including patients receiving 40 - 80 mg osimertinib as ≥ 2 line therapy and from whom pharmacokinetic samples were collected during routine care. Trough plasma concentrations (Cmin,pred) were estimated and used as a measure of osimertinib exposure. A previously defined exploratory pharmacokinetic threshold of 166 µg/L was taken to explore the exposure-efficacy relationship. RESULTS: A total of 145 patients and 513 osimertinib plasma concentration samples were included. Median progression free survival (PFS) was 13.3 (95% confidence interval (CI):10.3 - 19.1) months and 9.3 (95% CI: 7.2 - 11.1) months for patients with Cmin,pred < 166 µg/L and Cmin,pred ≥ 166 µg/L, respectively (p = 0.03). In the multivariate analysis, a Cmin,pred < 166 µg/L resulted in a non-statistically significant hazard ratio of 1.10 (95% CI: 0.60 - 2.01; p = 77). Presence of a EGFR driver-mutation other than the exon 19 del or L858R mutations, led to a shorter PFS with a hazard ratio of 2.89 (95% CI: 1.18 - 7.08; p = 0.02). No relationship between exposure and toxicity was observed (p = 0.91). CONCLUSION: In our real-life cohort, no exposure-response relationship was observed for osimertinib in the current dosing scheme. The feasibility of a standard lower fixed dosing of osimertinib in clinical practice should be studied prospectively.

Reducing False-Positive Screening MRI Rate in Women with Extremely Dense Breasts Using Prediction Models Based on Data from the DENSE Trial.

Background High breast density increases breast cancer risk and lowers mammographic sensitivity. Supplemental MRI screening improves cancer detection but increases the number of false-positive screenings. Thus, methods to distinguish true-positive MRI screening results from false-positive ones are needed. Purpose To build prediction models based on clinical characteristics and MRI findings to reduce the rate of false-positive screening MRI findings in women with extremely dense breasts. Materials and Methods Clinical characteristics and MRI findings in Dutch breast cancer screening participants (age range, 50-75 years) with positive first-round MRI screening results (Breast Imaging Reporting and Data System 3, 4, or 5) after a normal screening mammography with extremely dense breasts (Volpara density category 4) were prospectively collected within the randomized controlled Dense Tissue and Early Breast Neoplasm Screening (DENSE) trial from December 2011 through November 2015. In this secondary analysis, prediction models were built using multivariable logistic regression analysis to distinguish true-positive MRI screening findings from false-positive ones. Results Among 454 women (median age, 52 years; interquartile range, 50-57 years) with a positive MRI result in a first supplemental MRI screening round, 79 were diagnosed with breast cancer (true-positive findings), and 375 had false-positive MRI results. The full prediction model (area under the receiver operating characteristics curve [AUC], 0.88; 95% CI: 0.84, 0.92), based on all collected clinical characteristics and MRI findings, could have prevented 45.5% (95% CI: 39.6, 51.5) of false-positive recalls and 21.3% (95% CI: 15.7, 28.3) of benign biopsies without missing any cancers. The model solely based on readily available MRI findings and age had a comparable performance (AUC, 0.84; 95% CI: 0.79, 0.88; P = .15) and could have prevented 35.5% (95% CI: 30.4, 41.1) of false-positive MRI screening results and 13.0% (95% CI: 8.8, 18.6) of benign biopsies. Conclusion Prediction models based on clinical characteristics and MRI findings may be useful to reduce the false-positive first-round screening MRI rate and benign biopsy rate in women with extremely dense breasts. Clinical trial registration no. NCT01315015 © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Imbriaco in this issue.

Supplemental Breast MRI for Women with Extremely Dense Breasts: Results of the Second Screening Round of the DENSE Trial.

Background In the first (prevalent) supplemental MRI screening round of the Dense Tissue and Early Breast Neoplasm Screening (DENSE) trial, a considerable number of breast cancers were found at the cost of an increased false-positive rate (FPR). In incident screening rounds, a lower cancer detection rate (CDR) is expected due to a smaller pool of prevalent cancers, and a reduced FPR, due to the availability of prior MRI examinations. Purpose To investigate screening performance indicators of the second round (incidence round) of the DENSE trial. Materials and Methods The DENSE trial (ClinicalTrials.gov: NCT01315015) is embedded within the Dutch population-based biennial mammography screening program for women aged 50-75 years. MRI examinations were performed between December 2011 and January 2016. Women were eligible for the second round when they again had a negative screening mammogram 2 years after their first MRI. The recall rate, biopsy rate, CDR, FPR, positive predictive values, and distributions of tumor characteristics were calculated and compared with results of the first round using 95% CIs and χ2 tests. Results A total of 3436 women (median age, 56 years; interquartile range, 48-64 years) underwent a second MRI screening. The CDR was 5.8 per 1000 screening examinations (95% CI: 3.8, 9.0) compared with 16.5 per 1000 screening examinations (95% CI: 13.3, 20.5) in the first round. The FPR was 26.3 per 1000 screening examinations (95% CI: 21.5, 32.3) in the second round versus 79.8 per 1000 screening examinations (95% CI: 72.4, 87.9) in the first round. The positive predictive value for recall was 18% (20 of 110 participants recalled; 95% CI: 12.1, 26.4), and the positive predictive value for biopsy was 24% (20 of 84 participants who underwent biopsy; 95% CI: 16.0, 33.9), both comparable to that of the first round. All tumors in the second round were stage 0-I and node negative. Conclusion The incremental cancer detection rate in the second round was 5.8 per 1000 screening examinations-compared with 16.5 per 1000 screening examinations in the first round. This was accompanied by a strong reduction in the number of false-positive results. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Moy and Gao in this issue.

Deep Learning for Automatic Calcium Scoring in CT: Validation Using Multiple Cardiac CT and Chest CT Protocols.

Background Although several deep learning (DL) calcium scoring methods have achieved excellent performance for specific CT protocols, their performance in a range of CT examination types is unknown. Purpose To evaluate the performance of a DL method for automatic calcium scoring across a wide range of CT examination types and to investigate whether the method can adapt to different types of CT examinations when representative images are added to the existing training data set. Materials and Methods The study included 7240 participants who underwent various types of nonenhanced CT examinations that included the heart: coronary artery calcium (CAC) scoring CT, diagnostic CT of the chest, PET attenuation correction CT, radiation therapy treatment planning CT, CAC screening CT, and low-dose CT of the chest. CAC and thoracic aorta calcification (TAC) were quantified using a convolutional neural network trained with (a) 1181 low-dose chest CT examinations (baseline), (b) a small set of examinations of the respective type supplemented to the baseline (data specific), and (c) a combination of examinations of all available types (combined). Supplemental training sets contained 199-568 CT images depending on the calcium burden of each population. The DL algorithm performance was evaluated with intraclass correlation coefficients (ICCs) between DL and manual (Agatston) CAC and (volume) TAC scoring and with linearly weighted κ values for cardiovascular risk categories (Agatston score; cardiovascular disease risk categories: 0, 1-10, 11-100, 101-400, >400). Results At baseline, the DL algorithm yielded ICCs of 0.79-0.97 for CAC and 0.66-0.98 for TAC across the range of different types of CT examinations. ICCs improved to 0.84-0.99 (CAC) and 0.92-0.99 (TAC) for CT protocol-specific training and to 0.85-0.99 (CAC) and 0.96-0.99 (TAC) for combined training. For assignment of cardiovascular disease risk category, the κ value for all test CT scans was 0.90 (95% confidence interval [CI]: 0.89, 0.91) for the baseline training. It increased to 0.92 (95% CI: 0.91, 0.93) for both data-specific and combined training. Conclusion A deep learning calcium scoring algorithm for quantification of coronary and thoracic calcium was robust, despite substantial differences in CT protocol and variations in subject population. Augmenting the algorithm training with CT protocol-specific images further improved algorithm performance. © RSNA, 2020 See also the editorial by Vannier in this issue.

Prognostic value of radiological recurrence patterns in ovarian cancer.

OBJECTIVE: To study the prognostic value of CT assessed recurrence patterns on survival outcomes in women with epithelial ovarian cancer. METHODS: CT scans were systematically re-evaluated on predefined anatomical sites for the presence of tumor in all 89 patients diagnosed with epithelial ovarian cancer between January 2008 and December 2013 who underwent cytoreductive surgery at our institution and developed a recurrence. A Cox proportional hazard analysis was used to test the effect of recurrence patterns on survival. RESULTS: The median survival time for patients grouped as predominantly intraperitoneal (n = 62), hematogenous (n = 13) or lymphatic (n = 14) recurrence was 25.8 (95% CI 18.4-33.2), 27.6 (95% CI 18.5-36.6) and 52.9 months (95% CI 42.1-63.7), respectively. Univariate Cox regression analysis identified the following prognostic factors: lymphatic recurrence pattern (HR 0.42, 95% CI 0.21-0.85), ascites at diagnosis (HR 2.35, 95% CI 1.46-3.79), residual tumor at initial surgery (HR 2.16, 95% CI 1.36-3.44) and FIGO stage (I-IIIB: HR 0.59, 95% CI 0.33-1.06). The median time to recurrence was 19.5 month for patients after complete debulking surgery, 13.1 months for patients with residual disease ≤1 cm and 8.2 months for patients with residual disease >1 cm after surgery (P < 0.001). No differences in recurrence patterns between patients with complete and incomplete surgery were found. CONCLUSIONS: Prolonged survival rates were found in ovarian cancer patients with a predominantly lymphatic recurrence compared to patients with a predominantly peritoneal or hematogenous recurrence. Completeness of surgery was associated with time to recurrence. Classification of recurrence patterns can help counsel patients on their prognosis at the time of recurrence.

In vivo growth of 60 non-screening detected lung cancers: a computed tomography study.

Current pulmonary nodule management guidelines are based on nodule volume doubling time, which assumes exponential growth behaviour. However, this is a theory that has never been validated in vivo in the routine-care target population. This study evaluates growth patterns of untreated solid and subsolid lung cancers of various histologies in a non-screening setting.Growth behaviour of pathology-proven lung cancers from two academic centres that were imaged at least three times before diagnosis (n=60) was analysed using dedicated software. Random-intercept random-slope mixed-models analysis was applied to test which growth pattern most accurately described lung cancer growth. Individual growth curves were plotted per pathology subgroup and nodule type.We confirmed that growth in both subsolid and solid lung cancers is best explained by an exponential model. However, subsolid lesions generally progress slower than solid ones. Baseline lesion volume was not related to growth, indicating that smaller lesions do not grow slower compared to larger ones.By showing that lung cancer conforms to exponential growth we provide the first experimental basis in the routine-care setting for the assumption made in volume doubling time analysis.

Incidental perifissural nodules on routine chest computed tomography: lung cancer or not?

OBJECTIVES: Perifissural nodules (PFNs) are a common finding on chest CT, and are thought to represent non-malignant lesions. However, data outside a lung cancer-screening setting are currently lacking. METHODS: In a nested case-control design, out of a total cohort of 16,850 patients ≥ 40 years of age who underwent routine chest CT (2004-2012), 186 eligible subjects with incident lung cancer and 511 controls without were investigated. All non-calcified nodules ≥ 4 mm were semi-automatically annotated. Lung cancer location and subject characteristics were recorded. RESULTS: Cases (56 % male) had a median age of 64 years (IQR 59-70). Controls (60 % male) were slightly younger (p<0.01), median age of 61 years (IQR 51-70). A total of 262/1,278 (21 %) unique non-calcified nodules represented a PFN. None of these were traced to a lung malignancy over a median follow-up of around 4.5 years. PFNs were most often located in the lower lung zones (72 %, p<0.001). Median diameter was 4.6 mm (range: 4.0-8.1), volume 51 mm3 (range: 32-278). Some showed growth rates < 400 days. CONCLUSIONS: Our data show that incidental PFNs do not represent lung cancer in a routine care, heterogeneous population. This confirms prior screening-based results. KEY POINTS: • One-fifth of non-calcified nodules represented a perifissural nodule in our non-screening population. • PFNs fairly often show larger size, and can show interval growth. • When morphologically resembling a PFN, nodules are nearly certainly not a malignancy. • The assumed benign aetiology of PFNs seems valid outside the screening setting.

Positron emission tomography (PET) and magnetic resonance imaging (MRI) for assessing tumour resectability in advanced epithelial ovarian/fallopian tube/primary peritoneal cancer.

BACKGROUND: Ovarian cancer is the leading cause of death from gynaecological cancer in developed countries. Surgery and chemotherapy are considered its mainstay of treatment and the completeness of surgery is a major prognostic factor for survival in these women. Currently, computed tomography (CT) is used to preoperatively assess tumour resectability. If considered feasible, women will be scheduled for primary debulking surgery (i.e. surgical efforts to remove the bulk of tumour with the aim of leaving no visible (macroscopic) tumour). If primary debulking is not considered feasible (i.e. the tumour load is too extensive), women will receive neoadjuvant chemotherapy to reduce tumour load and subsequently undergo (interval) surgery. However, CT is imperfect in assessing tumour resectability, so additional imaging modalities can be considered to optimise treatment selection. OBJECTIVES: To assess the diagnostic accuracy of fluorodeoxyglucose-18 (FDG) PET/CT, conventional and diffusion-weighted (DW) MRI as replacement or add-on to abdominal CT, for assessing tumour resectability at primary debulking surgery in women with stage III to IV epithelial ovarian/fallopian tube/primary peritoneal cancer. SEARCH METHODS: We searched MEDLINE and Embase (OVID) for potential eligible studies (1946 to 23 February 2017). Additionally, ClinicalTrials.gov, WHO-ICTRP and the reference list of all relevant studies were searched. SELECTION CRITERIA: Diagnostic accuracy studies addressing the accuracy of preoperative FDG-PET/CT, conventional or DW-MRI on assessing tumour resectability in women with advanced stage (III to IV) epithelial ovarian/fallopian tube/primary peritoneal cancer who are scheduled to undergo primary debulking surgery. DATA COLLECTION AND ANALYSIS: Two authors independently screened titles and abstracts for relevance and inclusion, extracted data and performed methodological quality assessment using QUADAS-2. The limited number of studies did not permit meta-analyses. MAIN RESULTS: Five studies (544 participants) were included in the analysis. All studies performed the index test as replacement of abdominal CT. Two studies (366 participants) addressed the accuracy of FDG-PET/CT for assessing incomplete debulking with residual disease of any size (> 0 cm) with sensitivities of 1.0 (95% CI 0.54 to 1.0) and 0.66 (95% CI 0.60 to 0.73) and specificities of 1.0 (95% CI 0.80 to 1.0) and 0.88 (95% CI 0.80 to 0.93), respectively (low- and moderate-certainty evidence). Three studies (178 participants) investigated MRI for different target conditions, of which two investigated DW-MRI and one conventional MRI. The first study showed that DW-MRI determines incomplete debulking with residual disease of any size with a sensitivity of 0.94 (95% CI 0.83 to 0.99) and a specificity of 0.98 (95% CI 0.88 to 1.00) (low- and moderate-certainty evidence). For abdominal CT, the sensitivity for assessing incomplete debulking was 0.66 (95% CI 0.52 to 0.78) and the specificity 0.77 (95% CI 0.63 to 0.87) (low- and low-certainty evidence). The second study reported a sensitivity of DW-MRI of 0.75 (95% CI 0.35 to 0.97) and a specificity of 0.96 (95% CI 0.80 to 1.00) (very low-certainty evidence) for assessing incomplete debulking with residual disease > 1 cm. In the last study, the sensitivity for assessing incomplete debulking with residual disease of > 2 cm on conventional MRI was 0.91 (95% CI 0.59 to 1.00) and the specificity 0.97 (95% CI 0.87 to 1.00) (very low-certainty evidence). Overall, the certainty of evidence was very low to moderate (according to GRADE), mainly due to small sample sizes and imprecision. AUTHORS' CONCLUSIONS: Studies suggested a high specificity and moderate sensitivity for FDG-PET/CT and MRI to assess macroscopic incomplete debulking. However, the certainty of the evidence was insufficient to advise routine addition of FDG-PET/CT or MRI to clinical practice..In a research setting, adding an alternative imaging method could be considered for women identified as suitable for primary debulking by abdominal CT, in an attempt to filter out false-negatives (i.e. debulking, feasible based on abdominal CT, unfeasible at actual surgery).

The effect of volumetric breast density on the risk of screen-detected and interval breast cancers: a cohort study.

BACKGROUND: In the light of the breast density legislation in the USA, it is important to know a woman's breast cancer risk, but particularly her risk of a tumor that is not detected through mammographic screening (interval cancer). Therefore, we examined the associations of automatically measured volumetric breast density with screen-detected and interval cancer risk, separately. METHODS: Volumetric breast measures were assessed automatically using Volpara version 1.5.0 (Matakina, New Zealand) for the first available digital mammography (DM) examination of 52,814 women (age 50 - 75 years) participating in the Dutch biennial breast cancer screening program between 2003 and 2011. Breast cancer information was obtained from the screening registration system and through linkage with the Netherlands Cancer Registry. We excluded all screen-detected breast cancers diagnosed as a result of the first digital screening examination. During a median follow-up period of 4.2 (IQR 2.0-6.2) years, 523 women were diagnosed with breast cancer of which 299 were screen-detected and 224 were interval breast cancers. The associations between volumetric breast measures and breast cancer risk were determined using Cox proportional hazards analyses. RESULTS: Percentage dense volume was found to be positively associated with both interval and screen-detected breast cancers (hazard ratio (HR) 8.37 (95% CI 4.34-16.17) and HR 1.39 (95% CI 0.82-2.36), respectively, for Volpara density grade category (VDG) 4 compared to VDG1 (p for heterogeneity < 0.001)). Dense volume (DV) was also found to be positively associated with both interval and screen-detected breast cancers (HR 4.92 (95% CI 2.98-8.12) and HR 2.30 (95% CI 1.39-3.80), respectively, for VDG-like category (C)4 compared to C1 (p for heterogeneity = 0.041)). The association between percentage dense volume categories and interval breast cancer risk (HR 8.37) was not significantly stronger than the association between absolute dense volume categories and interval breast cancer risk (HR 4.92). CONCLUSIONS: Our results suggest that both absolute dense volume and percentage dense volume are strong markers of breast cancer risk, but that they are even stronger markers for predicting the occurrence of tumors that are not detected during mammography breast cancer screening.

Implementation of a Multicenter Biobanking Collaboration for Next-Generation Sequencing-Based Biomarker Discovery Based on Fresh Frozen Pretreatment Tumor Tissue Biopsies.

BACKGROUND: The discovery of novel biomarkers that predict treatment response in advanced cancer patients requires acquisition of high-quality tumor samples. As cancer evolves over time, tissue is ideally obtained before the start of each treatment. Preferably, samples are freshly frozen to allow analysis by next-generation DNA/RNA sequencing (NGS) but also for making other emerging systematic techniques such as proteomics and metabolomics possible. Here, we describe the first 469 image-guided biopsies collected in a large collaboration in The Netherlands (Center for Personalized Cancer Treatment) and show the utility of these specimens for NGS analysis. PATIENTS AND METHODS: Image-guided tumor biopsies were performed in advanced cancer patients. Samples were fresh frozen, vital tumor cellularity was estimated, and DNA was isolated after macrodissection of tumor-rich areas. Safety of the image-guided biopsy procedures was assessed by reporting of serious adverse events within 14 days after the biopsy procedure. RESULTS: Biopsy procedures were generally well tolerated. Major complications occurred in 2.1%, most frequently consisting of pain. In 7.3% of the percutaneous lung biopsies, pneumothorax requiring drainage occurred. The majority of samples (81%) contained a vital tumor percentage of at least 30%, from which at least 500 ng DNA could be isolated in 91%. Given our preset criteria, 74% of samples were of sufficient quality for biomarker discovery. The NGS results in this cohort were in line with those in other groups. CONCLUSION: Image-guided biopsy procedures for biomarker discovery to enable personalized cancer treatment are safe and feasible and yield a highly valuable biobank. The Oncologist 2017;22:33-40Implications for Practice: This study shows that it is safe to perform image-guided biopsy procedures to obtain fresh frozen tumor samples and that it is feasible to use these biopsies for biomarker discovery purposes in a Dutch multicenter collaboration. From the majority of the samples, sufficient DNA could be yielded to perform next-generation sequencing. These results indicate that the way is paved for consortia to prospectively collect fresh frozen tumor tissue.

Volumetric breast density affects performance of digital screening mammography.

PURPOSE: To determine to what extent automatically measured volumetric mammographic density influences screening performance when using digital mammography (DM). METHODS: We collected a consecutive series of 111,898 DM examinations (2003-2011) from one screening unit of the Dutch biennial screening program (age 50-75 years). Volumetric mammographic density was automatically assessed using Volpara. We determined screening performance measures for four density categories comparable to the American College of Radiology (ACR) breast density categories. RESULTS: Of all the examinations, 21.6% were categorized as density category 1 ('almost entirely fatty') and 41.5, 28.9, and 8.0% as category 2-4 ('extremely dense'), respectively. We identified 667 screen-detected and 234 interval cancers. Interval cancer rates were 0.7, 1.9, 2.9, and 4.4‰ and false positive rates were 11.2, 15.1, 18.2, and 23.8‰ for categories 1-4, respectively (both p-trend < 0.001). The screening sensitivity, calculated as the proportion of screen-detected among the total of screen-detected and interval tumors, was lower in higher density categories: 85.7, 77.6, 69.5, and 61.0% for categories 1-4, respectively (p-trend < 0.001). CONCLUSIONS: Volumetric mammographic density, automatically measured on digital mammograms, impacts screening performance measures along the same patterns as established with ACR breast density categories. Since measuring breast density fully automatically has much higher reproducibility than visual assessment, this automatic method could help with implementing density-based supplemental screening.