Using the Kaiser Score as a clinical decision rule for breast lesion classification: Does computer-assisted curve type analysis improve diagnosis?

PURPOSE

We aimed to investigate the effect of using visual or automatic enhancement curve type assessment on the diagnostic performance of the Kaiser Score (KS), a clinical decision rule for breast MRI.

METHOD

This IRB-approved retrospective study analyzed consecutive conventional BI-RADS 0, 4 or 5 patients who underwent biopsy after 1.5T breast MRI according to EUSOBI recommendations between 2013 and 2015. The KS includes five criteria (spiculations; signal intensity (SI)-time curve type; margins of the lesion; internal enhancement; and presence of edema) resulting in scores from 1 (=lowest) to 11 (=highest risk of breast cancer). Enhancement curve types (Persistent, Plateau or Wash-out) were assessed by two radiologists independently visually and using a pixel-wise color-coded computed parametric map of curve types. KS diagnostic performance differences between readings were compared by ROC analysis.

RESULTS

In total 220 lesions (147 benign, 73 malignant) including mass (n = 148) and non-mass lesions (n = 72) were analyzed. KS reading performance in distinguishing benign from malignant lesions did not differ between visual analysis and parametric map (P = 0.119; visual: AUC 0.875, sensitivity 95 %, specificity 63 %; and map: AUC 0.901, sensitivity 97 %, specificity 65 %). Additionally, analyzing mass and non-mass lesions separately, showed no difference between parametric map based and visual curve type-based KS analysis as well (P = 0.130 and P = 0.787).

CONCLUSIONS

The performance of the Kaiser Score is largely independent of the curve type assessment methodology, confirming its robustness as a clinical decision rule for breast MRI in any type of breast lesion in clinical routine.

Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI

PURPOSE

Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning.

METHODS

Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses.

RESULTS

The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively.

CONCLUSION

Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

Deep learning analysis provides accurate COVID-19 diagnosis on chest computed tomography

INTRODUCTION

Computed Tomography is an essential diagnostic tool in the management of COVID-19. Considering the large amount of examinations in high case-load scenarios, an automated tool could facilitate and save critical time in the diagnosis and risk stratification of the disease.

METHODS

A novel deep learning derived machine learning (ML) classifier was developed using a simplified programming approach and an open source dataset consisting of 6868 chest CT images from 418 patients which was split into training and validation subsets. The diagnostic performance was then evaluated and compared to experienced radiologists on an independent testing dataset. Diagnostic performance metrics were calculated using Receiver Operating Characteristics (ROC) analysis. Operating points with high positive (>10) and low negative (<0.01) likelihood ratios to stratify the risk of COVID-19 being present were identified and validated.

RESULTS

The model achieved an overall accuracy of 0.956 (AUC) on an independent testing dataset of 90 patients. Both rule-in and rule out thresholds were identified and tested. At the rule-in operating point, sensitivity and specificity were 84.4 % and 93.3 % and did not differ from both radiologists (p > 0.05). At the rule-out threshold, sensitivity (100 %) and specificity (60 %) differed significantly from the radiologists (p < 0.05). Likelihood ratios and a Fagan nomogram provide prevalence independent test performance estimates.

CONCLUSION

Accurate diagnosis of COVID-19 using a basic deep learning approach is feasible using open-source CT image data. In addition, the machine learning classifier provided validated rule-in and rule-out criteria could be used to stratify the risk of COVID-19 being present.

Impact of androgen deprivation therapy on apparent diffusion coefficient and T2w MRI for histogram and texture analysis with respect to focal radiotherapy of prostate cancer

PURPOSE

Accurate prostate cancer (PCa) detection is essential for planning focal external beam radiotherapy (EBRT). While biparametric MRI (bpMRI) including T2-weighted (T2w) and diffusion-weighted images (DWI) is an accurate tool to localize PCa, its value is less clear in the case of additional androgen deprivation therapy (ADT). The aim of this study was to investigate the value of a textural feature (TF) approach on bpMRI analysis in prostate cancer patients with and without neoadjuvant ADT with respect to future dose-painting applications.

METHODS

28 PCa patients (54-80 years) with (n = 14) and without (n = 14) ADT who underwent bpMRI with T2w and DWI were analyzed retrospectively. Lesions, central gland (CG), and peripheral zone (PZ) were delineated by an experienced urogenital radiologist based on localized pre-therapeutic histopathology. Histogram parameters and 20 Haralick TF were calculated. Regional differences (i. e., tumor vs. PZ, tumor vs. CG) were analyzed for all imaging parameters. Receiver-operating characteristic (ROC) analysis was performed to measure diagnostic performance to distinguish PCa from benign prostate tissue and to identify the features with best discriminative power in both patient groups.

RESULTS

The obtained sensitivities were equivalent or superior when utilizing the TF in the no-ADT group, while specificity was higher for the histogram parameters. However, in the ADT group, TF outperformed the conventional histogram parameters in both specificity and sensitivity. Rule-in and rule-out criteria for ADT patients could exclusively be defined with the aid of TF.

CONCLUSIONS

The TF approach has the potential for quantitative image-assisted boost volume delineation in PCa patients even if they are undergoing neoadjuvant ADT.

The prognostic role of preoperative serum C-reactive protein in predicting the biochemical recurrence in patients treated with radical prostatectomy

BACKGROUND

To assess the prognostic value of preoperative C-reactive protein (CRP) serum levels for prognostication of biochemical recurrence (BCR) after radical prostatectomy (RP) in a large multi-institutional cohort.

METHODS

Data from 7205 patients treated with RP at five institutions for clinically localized prostate cancer (PCa) were retrospectively analyzed. Preoperative serum levels of CRP within 24 h before surgery were evaluated. A CRP level ⩾0.5 mg dl(-1) was considered elevated. Associations of elevated CRP with BCR were evaluated using univariable and multivariable Cox proportional hazards regression models. Harrel's C-index was used to assess prognostic accuracy (PA).

RESULTS

Patients with higher Gleason score on biopsy and RP, extracapsular extension, seminal vesicle invasion, lymph node metastasis, and positive surgical margins status had a significantly elevated preoperative CRP compared to those without these features. Patients with elevated CRP had a lower 5-year BCR survival proportion as compared to those with normal CRP (55% vs 76%, respectively, P<0.0001). In pre- and postoperative multivariable models that adjusted for standard clinical and pathologic features, elevated CRP was independently associated with BCR (P<0.001). However, the addition of preoperative CRP did not improve the accuracy of the standard pre- and postoperative models for prediction of BCR (70.9% vs 71% and 78.9% vs 78.7%, respectively).

CONCLUSIONS

Preoperative CRP is elevated in patients with pathological features of aggressive PCa and BCR after RP. While CRP has independent prognostic value, it does not add prognostically or clinically significant information to standard predictors of outcomes.

Diffusion-weighted imaging of breast tumours at 3 Tesla and 7 Tesla: a comparison

OBJECTIVES

To compare bilateral diffusion-weighted MR imaging (DWI) at 3 T and 7 T in the same breast tumour patients.

METHODS

Twenty-eight patients were included in this IRB-approved study (mean age 56 ± 16 years). Before contrast-enhanced imaging, bilateral DWI with b = 0 and 850 s/mm(2) was performed in 2:56 min (3 T) and 3:48 min (7 T), using readout-segmented echo planar imaging (rs-EPI) with a 1.4 × 1.4 mm(2) (3 T)/0.9 × 0.9 mm(2) (7 T) in-plane resolution. Apparent diffusion coefficients (ADC), signal-to-noise (SNR) and contrast-to-noise ratios (CNR) were assessed.

RESULTS

Twenty-eight lesions were detected (18 malignant, 10 benign). CNR and SNR were comparable at both field strengths (p > 0.3). Mean ADC values at 7 T were 4-22% lower than at 3 T (p ≤ 0.03). An ADC threshold of 1.275 × 10(-3) mm(2)/s resulted in a diagnostic specificity of 90% at both field strengths. The sensitivity was 94% and 100% at 3 T and 7 T, respectively.

CONCLUSION

7-T DWI of the breast can be performed with 2.4-fold higher spatial resolution than 3 T, without significant differences in SNR if compared to 3 T.

KEY POINTS

• 7 T provides a 2.4-fold higher resolution in breast DWI than 3 T • 7 T DWI has a high diagnostic accuracy comparable to that at 3 T • At 7 T malignant lesions had 22 % lower ADC than at 3 T (p < 0.001).

[Molecular breast imaging. An update]

CLINICAL/METHODICAL ISSUE

The aim of molecular imaging is to visualize and quantify biological, physiological and pathological processes at cellular and molecular levels. Molecular imaging using various techniques has recently become established in breast imaging.

STANDARD RADIOLOGICAL METHODS

Currently molecular imaging techniques comprise multiparametric magnetic resonance imaging (MRI) using dynamic contrast-enhanced MRI (DCE-MRI), diffusion-weighted imaging (DWI), proton MR spectroscopy ((1)H-MRSI), nuclear imaging by breast-specific gamma imaging (BSGI), positron emission tomography (PET) and positron emission mammography (PEM) and combinations of techniques (e.g. PET-CT and multiparametric PET-MRI).

METHODICAL INNOVATIONS

Recently, novel techniques for molecular imaging of breast tumors, such as sodium imaging ((23)Na-MRI), phosphorus spectroscopy ((31)P-MRSI) and hyperpolarized MRI as well as specific radiotracers have been developed and are currently under investigation.

PRACTICAL RECOMMENDATIONS

It can be expected that molecular imaging of breast tumors will enable a simultaneous assessment of the multiple metabolic and molecular processes involved in cancer development and thus an improved detection, characterization, staging and monitoring of response to treatment will become possible.

Surgical management of multiple bilateral fibroadenoma of the breast: the Ribeiro technique modified by Rezai

BACKGROUND

Fibroadenomas are hyperplasia arising from the terminal ductulo-lobular unit and adjacent tissue of the breast. As single fibroadenoma, even giant ones are easily manageable, however multiple fibroadenomas pose a particular challenge.

CASE REPORT

In 1971, Liacyr Ribeiro described his new technique for reduction mammaplasty. Four years later, the first 20 cases were published. This technique was introduced by Rezai in oncoplastic surgery. With free hand design, preoperative marking is performed- and the inferior pedicle modulated.

RESULTS

Selective resection of more than seventy fibroadenomas was performed on two patients. The technique allowed a modelling of the breast like a mastopexy through the inferior pedicle.

CONCLUSION

Multiple fibroadenomas of the breast are safely removable with the Ribeiro technique modified by Rezai.

High-intensity xenon plasma discharge lamp for bulk-sensitive high-resolution photoemission spectroscopy

We have developed a highly brilliant xenon (Xe) discharge lamp operated by microwave-induced electron cyclotron resonance (ECR) for ultrahigh-resolution bulk-sensitive photoemission spectroscopy (PES). We observed at least eight strong radiation lines from neutral or singly ionized Xe atoms in the energy region of 8.4-10.7 eV. The photon flux of the strongest Xe I resonance line at 8.437 eV is comparable to that of the He Ialpha line (21.218 eV) from the He-ECR discharge lamp. Stable operation for more than 300 h is achieved by efficient air-cooling of a ceramic tube in the resonance cavity. The high bulk sensitivity and high-energy resolution of PES using the Xe lines are demonstrated for some typical materials.

Is the ?blooming sign? a promising additional tool to determine malignancy in MR mammography?

The aim of this study was to evaluate potential diagnostic relevance of blooming effect for verification of suspicious breast lesions in MR mammography (MRM). The MRM examinations of 1035 patients, all following the same imaging protocol (from 1994 to 2001) were retrospectively evaluated by two experienced radiologists in consensus. A total of 817 lesions showed a focal enhancement; of these, 793 were histologically verified after surgical intervention so that 514 malignant and 279 benign lesions could be evaluated. Using a 1.5-T Gyroscan ACS II-imager (Philips, Hamburg, Germany) and a double breast coil with the patient lying in a prone position, 0.1 mmol/kgbw Magnevist (Schering, Berlin, Germany) were injected into the cubital vein to obtain dynamic axial and coronal T1-weighted fast-field-echo images every minute up to 7 min after bolus injection. Blooming sign describes a progradient unsharpness of lesion borders initially sharply shaped and fast enhancing 7 min after bolus injection; 324 of 514 (63.0%) malignant lesions and 41 of 279 (14.7%) benign lesions revealed a blooming sign (sensitivity 63.0%, specificity 85.3%, accuracy 70.9%, positive predictive value 88.8%, negative predictive value 56.0%). Forty-one of 279 benign lesions showed a blooming sign; of these, there were 4 of 86 (4.7%) fibroadenomas, 2 of 21 (9.5%) phylloides tumours, 11 of 38 (28.9%) papillomas, 3 of 9 (33.3%) radial scars, 2 of 19 (10.5%) mastitis, 1 of 4 (25%) galactophoritis, 1 of 3 (33.3%) ADH and 19 of 99 (17.2%) mastopathic proliferations, respectively. Blooming sign is a phenomenon which should be taken into account when diagnosing MR mammographies because it might increase the ability to discriminate uncertain breast lesions; however, this effect can only be used as an additional item to other well-known effects such as plateau, washout and cancer corner.

[Acute effects of the natural atmospheric ozone exposure on lung function of clinically normal smokers and non-smokers]

The influence of moderate ambient ozone exposure on spirometric lung function and bronchial responsiveness was analyzed in 13 healthy adult nonsmokers and 11 asymptomatic smokers. The study was divided into an initial investigation at low atmospheric ozone concentrations of about 80 (range 68-102) micrograms/m3 and a subsequent similar testing at moderately elevated ozone concentrations above 140 (range 145-205) micrograms/m3. Overall there was a slight but significant impairment in forced expiratory volumes (p less than 0.002) at elevated compared with low ozone concentrations. Furthermore, a significant increase in bronchial responsiveness was shown, with a decrease in threshold dose for inhaled metacholine to produce a 50% fall in specific airway conductance (p less than 0.02). In both smokers and nonsmokers there was a similar change in lung function at ambient ozone concentrations, with more pronounced bronchial irritation in the smokers group. It is concluded that even moderately elevated ambient ozone concentrations can induce slight but significant ventilatory obstruction and an obvious increase in bronchial responsiveness in healthy adults. Although the minor impairment of lung function did not cause manifest acute respiratory problems, it still reduced maximal physical ventilation capacity. The results further support the assumption that air pollution may act as a primary trigger in the development of obstructive airway disease.