Deep learning for automatic calcium scoring in population based cardiovascular screening

Background

High volumes of standardized coronary artery calcium (CAC) scans are generated in screening that need to be scored accurately and efficiently to risk stratify individuals.

Purpose

To evaluate the performance of deep learning based software for automatic coronary calcium scoring in a screening setting.

Methods

Participants from the Robinsca trial that underwent low-dose ECG-triggered cardiac CT for calcium scoring were included. CAC was measured with fully automated deep learning prototype and compared to the original manual assessment of the Robinsca trial. Detection rate, positive Agatston score and risk categorization (0–99, 100–399, ≥400) were compared using McNemar test, ICC, and Cohen's kappa. False negative (FN), false positive (FP) rate and diagnostic accuracy were determined for preventive treatment initiation (cut-off ≥100 AU).

Results

In total, 997 participants were included between December 2015 and June 2016. Median age was 61.0 y (IQR: 11.0) and 54.4% was male. A high agreement for detection was found between deep learning based and manual scoring, κ=0.87 (95% CI 0.85–0.89). Median Agatston score was 58.4 (IQR: 12.3–200.2) and 61.2 (IQR: 13.9–212.9) for deep learning based and manual assessment respectively, ICC was 0.958 (95% CI 0.951–0.964). Reclassification rate was 2.0%, with a very high agreement with κ=0.960 (95% CI: 0.943–0.997), p<0.001. FN rate was 0.7% and FP rate was 0.1% and diagnostic accuracy was 99.2% for initiation of preventive treatment.

Conclusion

Deep learning based software for automatic CAC scoring can be used in a cardiovascular CT screening setting with high accuracy for risk categorization and initiation of preventive treatment.

Funding Acknowledgement

Type of funding sources: Public grant(s) – EU funding. Main funding source(s): Robinsca trial was supported by advanced grant of European Research Council

Diffusion weighted imaging of the breast: Performance of standardized breast tumor tissue selection methods in clinical decision making

Objectives

In breast diffusion weighted imaging (DWI) protocol standardization, it is recently shown that no breast tumor tissue selection (BTTS) method outperformed the others. The purpose of this study is to analyze the feasibility of three fixed-size breast tumor tissue selection (BTTS) methods based on the reproducibility, accuracy and time-measurement in comparison to the largest oval and manual delineation in breast diffusion weighted imaging data.

Methods

This study is performed with a consecutive dataset of 116 breast lesions (98 malignant) of at least 1.0 cm, scanned in accordance with the EUSOBI breast DWI working group recommendations. Reproducibility of the maximum size manual (BTTS1) and of the maximal size round/oval (BTTS2) methods were compared with three smaller fixed-size circular BTTS methods in the middle of each lesion (BTTS3, 0.12 cm³ volume) and at lowest apparent diffusion coefficient (ADC) (BTTS4, 0.12 cm³; BTTS5, 0.24 cm³). Mean ADC values, intraclass-correlation-coefficients (ICCs), area under the curve (AUC) and measurement times (sec) of the 5 BTTS methods were assessed by two observers.

Results

Excellent inter- and intra-observer agreement was found for any BTTS (with ICC 0.88–0.92 and 0.92–0.94, respectively). Significant difference in ADCmean between any pair of BTTS methods was shown (p = <0.001–0.009), except for BTTS2 vs. BTTS3 for observer 1 (p = 0.10). AUCs were comparable between BTTS methods, with highest AUC for BTTS2 (0.89–0.91) and lowest for BTTS4 (0.76–0.85). However, as an indicator of clinical feasibility, BTTS2-3 showed shortest measurement times (10–15 sec) compared to BTTS1, 4–5 (19–39 sec).

Conclusion

The performance of fixed-size BTTS methods, as a potential tool for clinical decision making, shows equal AUC but shorter ADC measurement time compared to manual or oval whole lesion measurements. The advantage of a fixed size BTTS method is the excellent reproducibility. A central fixed breast tumor tissue volume of 0.12 cm³ is the most feasible method for use in clinical practice.

Diagnostic performance of breast tumor tissue selection in diffusion weighted imaging: A systematic review and meta-analysis

Background

Several methods for tumor delineation are used in literature on breast diffusion weighted imaging (DWI) to measure the apparent diffusion coefficient (ADC). However, in the process of reaching consensus on breast DWI scanning protocol, image analysis and interpretation, still no standardized optimal breast tumor tissue selection (BTTS) method exists. Therefore, the purpose of this study is to assess the impact of BTTS methods on ADC in the discrimination of benign from malignant breast lesions in DWI in terms of sensitivity, specificity and area under the curve (AUC).

Methods and findings

In this systematic review and meta-analysis, adhering to the PRISMA statement, 61 studies, with 65 study subsets, in females with benign or malignant primary breast lesions (6291 lesions) were assessed. Studies on DWI, quantified by ADC, scanned on 1.5 and 3.0 Tesla and using b-values 0/50 and ≥ 800 s/mm² were included. PubMed and EMBASE were searched for studies up to 23-10-2019 (n = 2897). Data were pooled based on four BTTS methods (by definition of measured region of interest, ROI): BTTS1: whole breast tumor tissue selection, BTTS2: subtracted whole breast tumor tissue selection, BTTS3: circular breast tumor tissue selection and BTTS4: lowest diffusion breast tumor tissue selection. BTTS methods 2 and 3 excluded necrotic, cystic and hemorrhagic areas. Pooled sensitivity, specificity and AUC of the BTTS methods were calculated. Heterogeneity was explored using the inconsistency index (I²) and considering covariables: field strength, lowest b-value, image of BTTS selection, pre-or post-contrast DWI, slice thickness and ADC threshold. Pooled sensitivity, specificity and AUC were: 0.82 (0.72–0.89), 0.79 (0.65–0.89), 0.88 (0.85–0.90) for BTTS1; 0.91 (0.89–0.93), 0.84 (0.80–0.87), 0.94 (0.91–0.96) for BTTS2; 0.89 (0.86–0.92), 0.90 (0.85–0.93), 0.95 (0.93–0.96) for BTTS3 and 0.90 (0.86–0.93), 0.84 (0.81–0.87), 0.86 (0.82–0.88) for BTTS4, respectively. Significant heterogeneity was found between studies (I² = 95).

Conclusions

None of the breast tissue selection (BTTS) methodologies outperformed in differentiating benign from malignant breast lesions. The high heterogeneity of ADC data acquisition demands further standardization, such as DWI acquisition parameters and tumor tissue selection to substantially increase the reliability of DWI of the breast.

Enhanced pulmonary uptake on 18F-FES-PET/CT scans after irradiation of the thoracic area: related to fibrosis?

Rationale

The use of 16α-[¹⁸F]fluoro-17β-estradiol (FES) positron emission tomography (PET) in clinical dilemmas and for therapy decision-making in lesions expressing estrogen receptors is growing. However, on a considerable number of FES PET scans, previously performed in a research and clinical setting in our institution, FES uptake was noticed in the lungs without an oncologic substrate. We hypothesized that this uptake was related to pulmonary fibrosis as a result of radiation therapy. This descriptive study therefore aimed to investigate whether radiation therapy in the thoracic area is possibly related to enhanced pulmonary, non-tumor FES uptake.

Methods

All FES-PET/CT scans performed in our institution from 2008 to 2017 were retrospectively analyzed. Scans from patients who had received irradiation in the thoracic area prior to the scan were compared to scans of patients who had never received irradiation in the thoracic area. The primary outcome was the presence of enhanced non-tumor FES uptake in the lungs, defined as visually increased FES uptake in the absence of an oncologic substrate on the concordant (contrast-enhanced) CT scan. All CT scans were evaluated for the presence of fibrosis or oncologic substrates.

Results

A total of 108 scans were analyzed: 70 scans of patients with previous irradiation in the thoracic area and 38 of patients without. Enhanced non-tumor FES uptake in the lungs was observed in 39/70 irradiated patients (56%), versus in 9/38 (24%) of non-irradiated patients. Fibrosis was present in 37 of the 48 patients with enhanced non-tumor FES uptake (77%), versus in 15 out of 60 (25%) patients without enhanced non-tumor uptake, irrespective of radiotherapy (p < 0.001).

Conclusion

After irradiation of the thorax, enhanced non-tumor uptake on FES-PET can be observed in the radiation field in a significant proportion of patients. This seems to be related to fibrosis. When observing enhanced FES uptake in the lungs, this should not be interpreted as metastases. Information on recent radiation therapy or history of pulmonary fibrosis should therefore be taken into consideration.

Respiratory level tracking with visual biofeedback for consistent breath-hold level with potential application in image-guided interventions

BACKGROUND

To present and evaluate a new respiratory level biofeedback system that aids the patient to return to a consistent breath-hold level with potential application in image-guided interventions.

METHODS

The study was approved by the local ethics committee and written informed consent was waived. Respiratory motion was recorded in eight healthy volunteers in the supine and prone positions, using a depth camera that measures the mean distance to thorax, abdomen and back. Volunteers were provided with real-time visual biofeedback on a screen, as a ball moving up and down with respiratory motion. For validation purposes, a conversion factor from mean distance (in mm) to relative lung volume (in mL) was determined using spirometry. Subsequently, without spirometry, volunteers were given breathing instructions and were asked to return to their initial breath-hold level at expiration ten times, in both positions, with and without visual biofeedback. For both positions, the median and interquartile range (IQR) of the absolute error in lung volume from initial breath-hold were determined with and without biofeedback and compared using Wilcoxon signed rank tests.

RESULTS

Without visual biofeedback, the median difference from initial breath-hold was 124.6 mL (IQR 55.7-259.7 mL) for the supine position and 156.3 mL (IQR 90.9-334.7 mL) for the prone position. With the biofeedback, the difference was significantly decreased to 32.7 mL (IQR 12.8-59.6 mL) (p < 0.001) and 22.3 mL (IQR 7.7-47.0 mL) (p < 0.001), respectively.

CONCLUSIONS

The use of a depth camera to provide visual biofeedback increased the reproducibility of breath-hold expiration level in healthy volunteers, with a potential to eliminate targeting errors caused by respiratory movement during lung image-guided procedures.

Which screening strategy should be offered to women with BRCA1 or BRCA2 mutations? A simulation of comparative cost-effectiveness

Background:

There is no consensus on the most effective strategy (mammography or magnetic resonance imaging (MRI)) for screening women with BRCA1 or BRCA2 mutations. The effectiveness and cost-effectiveness of the Dutch, UK and US screening strategies, which involve mammography and MRI at different ages and intervals were evaluated in high-risk women with BRCA1 or BRCA2 mutations.

Methods:

Into a validated simulation screening model, outcomes and cost parameters were integrated from published and cancer registry data. Main outcomes were life-years gained and incremental cost-effectiveness ratios. The simulation was situated in the Netherlands as well as in the United Kingdom, comparing the Dutch, UK and US strategies with the population screening as a reference. A discount rate of 3% was applied to both costs and health benefits.

Results:

In terms of life-years gained, the strategies from least to most cost-effective were the UK, Dutch and US screening strategy, respectively. However, the differences were small. Applying the US strategy in the Netherlands, the costs were €43 800 and 68 800 for an additional life-year gained for BRCA1 and BRCA2, respectively. At a threshold of €20 000 per life-year gained, implementing the US strategy in the Netherlands has a very low probability of being cost-effective. Stepping back to the less-effective UK strategy would save relatively little in costs and results in life-years lost. When implementing the screening strategies in the United Kingdom, the Dutch, as well as the US screening strategy have a high probability of being cost-effective.

Conclusion:

From a cost-effectiveness perspective, the Dutch screening strategy is preferred for screening high-risk women in the Netherlands as well as in the United Kingdom.

Breast magnetic resonance imaging as a problem-solving modality in mammographic BI-RADS 3 lesions

The probability of a mammographic Breast Imaging Reporting and Data System (BI-RADS) 3 lesion being cancer is considered to be less than 2%. Therefore, the work-up of a mammographic BI-RADS 3 lesion should be biopsy or follow-up mammography after 6 months. However, most patients referred for biopsy have benign disease. Although the negative predictive value (NPV) of magnetic resonance imaging (MRI) is highest of all imaging techniques, it is not yet common practice to use breast MRI as a problem-solving modality to exclude patients for further diagnostic work-up. Therefore, in this meta-analysis the usefulness of breast MRI as a problem-solving modality in mammographic BI-RADS 3 lesions is investigated. After a systematic search only 5 out of 61 studies met the inclusion criteria. The NPV in 2 of those studies was reported to be 100%. It was concluded that MRI can be used as an adjunctive tool to mammographic BI-RADS 3 findings to exclude patients for further diagnostic work-up. The other 3 studies assessed the accuracy of MRI in mammographic BI-RADS 3 microcalcifications. These studies reported an NPV of MRI between 76% and 97%. Therefore, MRI cannot be implemented as a diagnostic tool to evaluate mammographic microcalcifications at this time. The first solid data indicate that breast MRI might be useful as a problem-solving modality to exclude patients with non-calcified mammographic BI-RADS 3 lesions for further diagnostic work-up. However, further research is needed to verify these results.