Generalizable attention U-Net for segmentation of fibroglandular tissue and background parenchymal enhancement in breast DCE-MRI.

OBJECTIVES: Development of automated segmentation models enabling standardized volumetric quantification of fibroglandular tissue (FGT) from native volumes and background parenchymal enhancement (BPE) from subtraction volumes of dynamic contrast-enhanced breast MRI. Subsequent assessment of the developed models in the context of FGT and BPE Breast Imaging Reporting and Data System (BI-RADS)-compliant classification. METHODS: For the training and validation of attention U-Net models, data coming from a single 3.0-T scanner was used. For testing, additional data from 1.5-T scanner and data acquired in a different institution with a 3.0-T scanner was utilized. The developed models were used to quantify the amount of FGT and BPE in 80 DCE-MRI examinations, and a correlation between these volumetric measures and the classes assigned by radiologists was performed. RESULTS: To assess the model performance using application-relevant metrics, the correlation between the volumes of breast, FGT, and BPE calculated from ground truth masks and predicted masks was checked. Pearson correlation coefficients ranging from 0.963 ± 0.004 to 0.999 ± 0.001 were achieved. The Spearman correlation coefficient for the quantitative and qualitative assessment, i.e., classification by radiologist, of FGT amounted to 0.70 (p < 0.0001), whereas BPE amounted to 0.37 (p = 0.0006). CONCLUSIONS: Generalizable algorithms for FGT and BPE segmentation were developed and tested. Our results suggest that when assessing FGT, it is sufficient to use volumetric measures alone. However, for the evaluation of BPE, additional models considering voxels' intensity distribution and morphology are required. CRITICAL RELEVANCE STATEMENT: A standardized assessment of FGT density can rely on volumetric measures, whereas in the case of BPE, the volumetric measures constitute, along with voxels' intensity distribution and morphology, an important factor. KEY POINTS: • Our work contributes to the standardization of FGT and BPE assessment. • Attention U-Net can reliably segment intricately shaped FGT and BPE structures. • The developed models were robust to domain shift.

How low can we go? CT dose reduction in the assessment of the medial clavicular epiphysis in forensic age estimation: a prospective postmortem CT study.

BACKGROUND: Projection radiography and, more recently, computed tomography (CT) play an important role in forensic age estimation. Both in terms of general criminal responsibility and government regulations concerning refugee care, it is important to differentiate correctly between youths and adults. A disadvantage of age estimation in CT is the ionizing radiation exposure. PURPOSE: To investigate how far the CT dose can be reduced without losing diagnostic confidence in assessing the different stages of ossification of the medial clavicle. MATERIAL AND METHODS: We prospectively scanned 25 postmortem cases with a fixed parameters protocol (FPP) and a care dose modulation protocol (CDMP) for different scan parameters. Two radiologists assessed the diagnostic image quality using a 5-point Likert scale. Inter-reader agreement was evaluated with Cohen's kappa. Differences in doses between FPP and CDMP were assessed with the one-tailed t-test. RESULTS: The best combination of diagnostic image quality and lowest radiation dose was obtained using a CDMP with 100 kV and 40 mAs and an FPP with 100 kV and 30 mAs. Doses for 120 kV were significantly higher (one-tailed P < 0.001). The diagnostic image quality for 80 kV was insufficient overall. DISCUSSION: Our results confirm that CT imaging at 100 kV allows a sufficient image quality that is diagnostic for age estimation in the ossification of the medial clavicle.

Mammographic calcifications undergoing percutaneous biopsy: outcome in women with and without a personal history of breast cancer.

PURPOSE: To compare the positive predictive values (PPVs) of BI-RADS categories used to assess pure mammographic calcifications in women with and without a previous history of breast cancer (PHBC). MATERIALS AND METHODS: In this retrospective study, all consecutive pure mammographic calcifications (n = 320) undergoing a stereotactic biopsy between 2016 and 2018 were identified. Mammograms were evaluated in consensus by two radiologists according to BI-RADS and blinded to patient history and pathology results. Final pathologic results were used as the standard of reference. PPV of BI-RADS categories were compared between the two groups. Data were evaluated using standard statistics, Mann-Whitney U tests and Chi-square tests. RESULTS: Two hundred sixty-eight patients (274 lesions, median age 54 years, inter-quartile range, 50-65 years) with a PHBC (n = 46) and without a PHBC (n = 222) were included. Overall PPVs were the following: BI-RADS 2, 0% (0 of 56); BI-RADS 3, 9.1% (1 of 11); BI-RADS 4a, 16.2% (6 of 37); BI-RADS 4b, 37.5% (48 of 128); BI-RADS 4c, 47.3% (18 of 38) and BI-RADS 5, 100% (4 of 4). The PPV of BI-RADS categories was similar in patients with and without a PHBC (P = .715). Calcifications were more often malignant in patients with a PHBC older than 10 years (47.3%, 9 of 19) compared to 1-2 years (25%, 1 of 4), 2-5 years (20%, 2 of 10) and 5-10 years (0%, of 13) from the first breast cancer (P = .005). CONCLUSION: PPV of mammographic calcifications is similar in women with or without PHBC when BI-RADS classification is strictly applied. A higher risk of malignancy was observed in patients with a PHBC longer than 10 years.

Dedicated breast computed-tomography in women with a personal history of breast cancer: A proof-of-concept study.

PURPOSE: To compare the subjective image quality assessment using B-CT and digital mammography in women with personal history of breast cancer (PHBC). METHOD: In this retrospective study 32 patients with PHBC were included. Each patient had undergone a B-CT examination and a previous mammogram in a time interval of less than 18 months between the two examinations. Two radiologists evaluated the two examinations independently with regard to the presence of lesions, BI-RADS classification, level of confidence for the overall exam interpretation, scar evaluation and image quality including image degradation due to clip artifacts. Level of confidence and image quality were assessed using a 5-point Likert scale. A p-value of less than 0.01 was considered statistically significant. RESULTS: Thirty-seven operated and 27 non-operated breasts were included. Confidence for the overall interpretation with B-CT was equal or superior to mammography in 63 cases (98.4 %) for reader 1 and in 58 cases (90.6 %) for reader 2 (p <.001). Confidence for scar evaluation with B-CT was equal or superior to mammography in all cases for reader 1 and in 34 cases (91.9 %) for readers 2 (p <.001). One case with local recurrence in B-CT was identified by both readers and no false positive findings were reported. A moderate to high image degradation due to beam-hardening artifacts has been reported by both readers in 29.4 % of cases due to surgical clips in the B-CT volume. CONCLUSIONS: B-CT in patients with PHBC provides high quality images that can be evaluated with confidence equal or superior to mammography.

Clinical assessment of image quality, usability and patient comfort in dedicated spiral breast computed tomography.

OBJECTIVE: To investigate aspects of image quality, feasibility and patient comfort in dedicated spiral breast computed tomography (B-CT) in a large patient cohort. METHODS: This retrospective study was approved by the institutional review board. 2418 B-CT scans from 1222 women examined between 04/16/2019 and 04/13/2022 were analyzed. Patients evaluated their comfort during the examination, radiographers carrying out the scans evaluated the patient's mobility and usability of the B-CT device, whereas radiologists assessed lesion contrast, detectability of calcifications, breast coverage and overall image quality. For semi-quantitative assessment, a Likert-Scale was used and statistical significance and correlations were calculated using ANOVAs and Spearman tests. RESULTS: Comfort, mobility and usability of the B-CT were rated each with either "no" or "negligible" complaints in >99%. Image quality was rated with "no" or "negligible complaints" in 96.7%. Lesion contrast and detectability of calcifications were rated either "optimal" or "good" in 92.6% and 98.4%. "Complete" and "almost complete" breast coverage were reported in 41.9%, while the pectoral muscle was found not to be covered in 56.0%. Major parts of the breast were not covered in 2.1%. Some variables were significantly correlated, such as age with comfort (ρ = -0.168, p < .001) and mobility (ρ = -0.172, p < .001) as well as patient weight with lesion contrast (ρ = 0.172, p < .001) and breast coverage (ρ = -0.109, p < .001). CONCLUSIONS: B-CT provides high image quality and contrast of soft tissue lesions as well as calcifications, while covering the pre-pectoral areas of the breast remains challenging. B-CT is easy to operate for the radiographer and comfortable for the majority of women.

Fully automated breast segmentation on spiral breast computed tomography images.

INTRODUCTION: The quantification of the amount of the glandular tissue and breast density is important to assess breast cancer risk. Novel photon-counting breast computed tomography (CT) technology has the potential to quantify them. For accurate analysis, a dedicated method to segment the breast components-the adipose and glandular tissue, skin, pectoralis muscle, skinfold section, rib, and implant-is required. We propose a fully automated breast segmentation method for breast CT images. METHODS: The framework consists of four parts: (1) investigate, (2) segment the components excluding adipose and glandular tissue, (3) assess the breast density, and (4) iteratively segment the glandular tissue according to the estimated density. For the method, adapted seeded watershed and region growing algorithm were dedicatedly developed for the breast CT images and optimized on 68 breast images. The segmentation performance was qualitatively (five-point Likert scale) and quantitatively (Dice similarity coefficient [DSC] and difference coefficient [DC]) demonstrated according to human reading by experienced radiologists. RESULTS: The performance evaluation on each component and overall segmentation for 17 breast CT images resulted in DSCs ranging 0.90-0.97 and in DCs 0.01-0.08. The readers rated 4.5-4.8 (5 highest score) with an excellent inter-reader agreement. The breast density varied by 3.7%-7.1% when including mis-segmented muscle or skin. CONCLUSION: The automatic segmentation results coincided with the human expert's reading. The accurate segmentation is important to avoid the significant bias in breast density analysis. Our method enables accurate quantification of the breast density and amount of the glandular tissue that is directly related to breast cancer risk.

Contrast Media-Enhanced Breast Computed Tomography With a Photon-Counting Detector: Initial Experiences on In Vivo Image Quality and Correlation to Histology.

OBJECTIVES: The aim of this study was to investigate the feasibility, the image quality, and the correlation with histology of dedicated spiral breast computed tomography (B-CT) equipped with a photon-counting detector in patients with suspicious breast lesions after application of iodinated contrast media. MATERIALS AND METHODS: The local ethics committee approved this prospective study. Twelve women with suspicious breast lesions found in mammography or B-CT underwent contrast-enhanced spiral B-CT and supplementary ultrasound. For all lesions, biopsy-proven diagnosis and histological workup after surgical resection were obtained including the size of cancer/ductal carcinoma in situ, which were correlated to sizes measured in B-CT. Signal-to-noise ratio and contrast-to-noise ratio were evaluated for tumor, glandular tissue, and fatty tissue. RESULTS: Of the 12 patients, 15 suspicious lesions were found, 14 were malignant, and 1 benign lesion corresponded to a chronic inflammation. All lesions showed strong contrast media uptake with a signal-to-noise ratio of 119.7 ± 52.5 with a contrast-to-noise ratio between glandular tissue and breast cancer lesion of 12.6 ± 5.9. The correlation of the size of invasive tumors measured in B-CT compared with histological size was significant and strong R = 0.77 ( P < 0.05), whereas the correlation with the size of the peritumoral ductal carcinoma in situ was not significant R = 0.80 ( P = 0.11). CONCLUSIONS: Contrast-enhanced B-CT shows high contrast between breast cancer and surrounding glandular tissue; therefore, it is a promising technique for cancer detection and staging depicting both soft tissue lesions and microcalcifications, which might be a substantial advantage over breast MRI.

Breast Computed Tomography: Diagnostic Performance of the Maximum Intensity Projection Reformations as a Stand-Alone Method for the Detection and Characterization of Breast Findings.

OBJECTIVES: This study aimed to evaluate the diagnostic performance of the maximum intensity projection (MIP) reformations of breast computed tomography (B-CT) images as a stand-alone method for the detection and characterization of breast imaging findings. MATERIALS AND METHODS: A total of 160 women undergoing B-CT between August 2018 and December 2020 were retrospectively included; 80 patients with known breast imaging findings were matched with 80 patients without imaging findings according to age and amount of fibroglandular tissue (FGT). A total of 71 benign and 9 malignant lesions were included. Images were evaluated using 15-mm MIP in 3 planes by 2 radiologists with experience in B-CT. The presence of lesions and FGT were evaluated, using the BI-RADS classification. Interreader agreement and descriptive statistics were calculated. RESULTS: The interreader agreement of the 2 readers for finding a lesion (benign or malignant) was 0.86 and for rating according to BI-RADS classification was 0.82. One of 9 cancers (11.1%) was missed by both readers due to dense breast tissue. BI-RADS 1 was correctly applied to 73 of 80 patients (91.3%) by reader 1 and to 74 of 80 patients (92.5%) by reader 2 without recognizable lesions. BI-RADS 2 or higher with a lesion in at least one of the breasts was correctly applied in 69 of 80 patients (86.3%) by both readers. For finding a malignant lesion, sensitivity was 88.9% (95% confidence interval [CI], 51.75%-99.72%) for both readers, and specificity was 99.3% (95% CI, 96.4%-100%) for reader 1 and 100% (95% CI, 97.20%-100.00%) for reader 2. CONCLUSIONS: Evaluation of B-CT images using the MIP reformations may help to reduce the reading time with high diagnostic performance and confidence.

Breast density in dedicated breast computed tomography: Proposal of a classification system and interreader reliability.

ABSTRACT: The aim of this study was to develop a new breast density classification system for dedicated breast computed tomography (BCT) based on lesion detectability analogous to the ACR BI-RADS breast density scale for mammography, and to evaluate its interrater reliability.In this retrospective study, 1454 BCT examinations without contrast media were screened for suitability. Excluding datasets without additional ultrasound and exams without any detected lesions resulted in 114 BCT examinations. Based on lesion detectability, an atlas-based BCT density (BCTD) classification system of breast parenchyma was defined using 4 categories. Interrater reliability was examined in 40 BCT datasets between 3 experienced radiologists.Among the included lesions were 63 cysts (55%), 18 fibroadenomas (16%), 7 lesions of fatty necrosis (6%), and 6 breast cancers (5%) with a median diameter of 11 mm. X-ray absorption was identical between lesions and breast tissue; therefore, the lack of fatty septae was identified as the most important criteria for the presence of lesions in glandular tissue. Applying a lesion diameter of 10 mm as desired cut-off for the recommendation of an additional ultrasound, an atlas of 4 BCTD categories was defined resulting in a distribution of 17.5% for density A, 39.5% (B), 31.6% (C), and 11.4% (D) with an intraclass correlation coefficient (ICC) among 3 readers of 0.85 to 0.87.We propose a dedicated atlas-based BCTD classification system, which is calibrated to lesion detectability. The new classification system exhibits a high interrater reliability and may be used for the decision whether additional ultrasound is recommended.

Biennial screening mammography: How many women ask for more? Estimate of the interval mammogram rate in an organised population-based screening programme.

OBJECTIVES: To estimate the interval mammogram rate, i.e. the undertaking of an additional mammography between scheduled screening rounds, and identify factors influencing this phenomenon. METHODS: Data from our screening programme for the year 2014, excluding prevalent rounds, were analysed. Information about the number of women who underwent  interval mammograms was obtained reviewing the questionnaires and searching the department database. Data on age, breast density, family history of breast cancer, number of screening rounds, previous recalls, general practitioner, and city of residence (used as a proxy of local socio-economic differences) were evaluated using chi-square test. RESULTS: Of 2780 screened women (incident rounds), 2566 had complete data (92%). The interval mammogram rate was 384/2566 (15%, 95% confidence interval 14-17%). Women classified with American College of Radiology c or d breast density categories showed a higher interval mammography probability than those with a and b density (p < 0.001); women in their second round showed a higher probability of interval mammogram compared to women in their fifth, sixth, or seventh round (p ≤ 0.004). No significant differences were found between women with and without an interval mammogram when considering previous recalls for a negative work-up (p = 0.241), positive breast cancer family history (p = 0.538), and city of residence (p = 0.177). CONCLUSIONS: The interval mammogram rate was relatively low (15%). Higher breast density and first of years of adherence to the programme were associated with higher interval mammogram rate.

Diagnostic value of a spiral breast computed tomography system equipped with photon counting detector technology in patients with implants: An observational study of our initial experiences.

To evaluate the value of a breast computed tomography (CT) (B-CT) in assessing breast density, pathologies and implant integrity in women with breast implants.This retrospective study was approved by the local ethics committee. B-CT images of 21 women with implants (silicone/saline; 20 bilateral, 1 unilateral) who underwent opportunistic screening or diagnostic bilateral B-CT were included. Breast density, implant integrity, extensive capsular fibrosis, soft tissue lesions and micro-/macrocalcifications were rated. In 18 of the 21 women, an additional ultrasound and in two patients breast magnetic resonance imaging was available for comparison. The average dose was calculated for each breast using verified Monte Carlo simulations on 3D image data sets.Breast density was nearly completely fatty (ACR a) in two patients, scattered fibroglandular (ACR b) in five, heterogeneously dense (ACR c) in ten and very dense (ACR d) in four women. In three women showed a unilateral positive Linguine sign indicative of an inner capsule rupture. Extensive capsular fibrosis was found in three women. In three women, soft tissue lesions were depicted, which revealed to be cysts (n = 2) and lymph nodes (n = 1) on subsequent sonography. Diffuse, non-clustered microcalcifications were found in nine women. Eleven women showed cutaneous or intramammary macrocalcifications. Average dose was 6.45 mGy (range 5.81-7.28 mGy).In women with implants, B-CT presents a promising modality for evaluating breast density, implant integrity, extensive capsular fibrosis, soft tissue lesions and micro-/macrocalcifications without the need of breast compression utilizing a lower dose compared to doses reported for conventional four-view mammography.

[New Trends in Breast Imaging]. / Neue Wege in der Senologischen Bildgebung.

New Trends in Breast Imaging Abstract. The examination of the breast, especially as a screening examination for breast cancer, has so far been carried out primarily by means of mammography and occasionally supplementary ultrasound. These check-ups have become established because early diagnosis of breast cancer increases the chances of recovery. Breast cancer is the most common cancer in women (approximately every 8th woman is affected). While the MRI examination, which offers a high level of sensitivity and specificity, has so far established itself as a further clarification, new examination methods have emerged in the recent past, which on the one hand make the examination more pleasant for women (e. g. no compression of the mammary gland tissue, as is the case with mammography) and which could potentially be diagnostically equivalent. In particular, this article mentions automatic breast ultrasound (ABUS) and computer tomography of the breast (breast CT). In the future, programs with artificial intelligence could also help confirm the diagnoses or increase accuracy so that no relevant lesion is overlooked.

Fully automatic classification of breast MRI background parenchymal enhancement using a transfer learning approach.

Marked enhancement of the fibroglandular tissue on contrast-enhanced breast magnetic resonance imaging (MRI) may affect lesion detection and classification and is suggested to be associated with higher risk of developing breast cancer. The background parenchymal enhancement (BPE) is qualitatively classified according to the BI-RADS atlas into the categories "minimal," "mild," "moderate," and "marked." The purpose of this study was to train a deep convolutional neural network (dCNN) for standardized and automatic classification of BPE categories.This IRB-approved retrospective study included 11,769 single MR images from 149 patients. The MR images were derived from the subtraction between the first post-contrast volume and the native T1-weighted images. A hierarchic approach was implemented relying on 2 dCNN models for detection of MR-slices imaging breast tissue and for BPE classification, respectively. Data annotation was performed by 2 board-certified radiologists. The consensus of the 2 radiologists was chosen as reference for BPE classification. The clinical performances of the single readers and of the dCNN were statistically compared using the quadratic Cohen's kappa.Slices depicting the breast were classified with training, validation, and real-world (test) accuracies of 98%, 96%, and 97%, respectively. Over the 4 classes, the BPE classification was reached with mean accuracies of 74% for training, 75% for the validation, and 75% for the real word dataset. As compared to the reference, the inter-reader reliabilities for the radiologists were 0.780 (reader 1) and 0.679 (reader 2). On the other hand, the reliability for the dCNN model was 0.815.Automatic classification of BPE can be performed with high accuracy and support the standardization of tissue classification in MRI.

Lesion Detectability and Radiation Dose in Spiral Breast CT With Photon-Counting Detector Technology: A Phantom Study.

OBJECTIVES: The aim of the article was to evaluate the lesion detectability, image quality, and radiation dose of a dedicated clinical spiral breast computed tomography (CT) system equipped with a photon-counting detector, and to propose optimal scan parameter settings to achieve low patient dose levels and optimal image quality. METHODS: A breast phantom containing inserts mimicking microcalcifications (diameters 196, 290, and 400 µm) and masses (diameters 1.8, 3.18, 4.76, and 6.32 mm) was examined in a spiral breast CT system with systematic variations of x-ray tube currents between 5 and 125 mA, using 2 slabs of 100 and 160 mm. Signal-to-noise ratio and contrast-to-noise ratio measurements were performed by region of interest analysis. Two experienced radiologists assessed the detectability of the inserts. The average absorbed dose was calculated in Monte Carlo simulations. RESULTS: Microcalcifications in diameters of 290 and 400 µm and masses in diameters of 3.18, 4.76, and 6.32 mm were visible for all tube currents between 5 and 125 mA. Soft tissue masses in a diameter of 1.8 mm were visible at tube currents of 25 mA and higher. Microcalcifications with a diameter of 196 µm were detectable at a tube current of 25 mA and higher in the small, and at a tube current of 40 mA and higher in the large slab. For the small and large breast, at a tube current of 25 and 40 mA, an average dose value of 4.30 ± 0.01 and 5.70 ± 0.02 mGy was calculated, respectively. CONCLUSIONS: Optimizing tube current of spiral breast CT according to the breast size enables the visualization of microcalcifications as small as 196 µm while keeping dose values in the range of conventional mammography.

Atypical ductal hyperplasia: breast DCE-MRI can be used to reduce unnecessary open surgical excision.

PURPOSE: To evaluate the diagnostic performance of dynamic contrast-enhanced (DCE)-MRI in predicting malignancy after percutaneous biopsy diagnosis of atypical ductal hyperplasia (ADH). METHODS AND MATERIALS: In this retrospective study, 68 lesions (66 women) with percutaneous biopsy diagnosis of ADH and pre-operative breast DCE-MRI performed between January 2016 and December 2017 were included. Two radiologists reviewed in consensus mammography, ultrasound, and MR images. The final diagnosis after surgical excision was used as standard of reference. Clinical and imaging features were compared in patients with and without upgrade to malignancy after surgery. The diagnostic performance of DCE-MRI in predicting malignant upgrade was evaluated. RESULTS: A 9-gauge vacuum-assisted biopsy was performed in 40 (58.8%) cases and a 14-gauge core needle biopsy in 28 (41.2%) cases. Upgrade to malignancy was observed in 17/68 (25%) lesions, including 4/17 (23.5%) cases of invasive cancer and 13/17 (76.5%) cases of ductal carcinoma in situ (DCIS). In 16/17 (94.1%) malignant and 20/51 (39.2%) benign lesions, a suspicious enhancement could be recognized in DCE-MRI. The malignant lesion without suspicious enhancement was a low-grade DCIS (4 mm size). Sensitivity, specificity, positive predictive value, and negative predictive value of DCE-MRI on predicting malignancy were respectively 94.1%, 60.7%, 44.4%, and 96.8%. No other clinical or imaging features were significantly different in patients with and without upgrade to malignancy. CONCLUSION: After a percutaneous biopsy diagnosis of ADH, malignancy can be ruled out in most of the cases, if no suspicious enhancement is present in the biopsy area at DCE-MRI. Breast DCE-MRI may be used to avoid surgery in more than half of the patients with final benign diagnosis. KEY POINTS: • Breast DCE-MRI can safely rule out malignancy if no suspicious enhancement is present in the biopsy area after a percutaneous biopsy diagnosis of ADH. • All cases of upgrade to high-grade DCIS and invasive cancers can be identified at breast DCE-MRI after a percutaneous biopsy diagnosis of ADH. • Breast DCE-MRI may be used to avoid surgery in more than half of the patients with final benign diagnosis.

Dedicated Spiral Breast Computed Tomography With a Single Photon-Counting Detector: Initial Results of the First 300 Women.

OBJECTIVES: The aim of this study was to describe our initial clinical experiences using a dedicated spiral breast computed tomography (B-CT) with a single photon-counting detector. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board. Examinations of 300 consecutive women undergoing B-CT were evaluated on reason of assignment for B-CT instead of mammography, detection rate of breast cancer, and quality criteria of data acquisition. Further evaluated performance indicators were the number of additional ultrasounds examinations due to unclear findings or dense breast tissue and reliability of the technical data acquisition. RESULTS: Five hundred ninety-one B-CT acquisitions in 300 women were performed. The main reason for preference of B-CT over mammography was the lack of breast compression (254 of 300, 84.7%), which was desired due to personal reasons or mastodynia, whereas 10 patients (0.3%) had implants hampering mammography. One hundred two possible lesions were detected in B-CT including 4 cases of breast cancer (1.3% of all patients). Additional ultrasound was performed in 226 patients (102 due to detected lesions and 124 due to dense breast tissue). Three malignant lesions were only detected in an additional ultrasound (1% of all patients). As a quality criterion, the pectoralis muscle was included in 341 of 591 examinations, but complete assessment of breast tissue was only possible in 149, respectively 140 examinations. No movement artifacts were noted. In 99% of all women, the examination could be realized. CONCLUSIONS: The dedicated B-CT provides high-quality images. It can be used as alternative particularly in those patients not otherwise willing to perform mammography because of the breast compression.

A 15 year institutional experience of well-differentiated follicular cell-derived thyroid carcinomas; impact of the new 2017 TNM and WHO Classifications of Tumors of Endocrine Organs on the epidemiological trends and pathological characteristics.

PURPOSE: Our study aimed to describe the evolution of the rate of pathological subtypes of well-differentiated follicular-cell derived thyroid carcinomas (DTCs) in the Department of Pathology, Emergency County Hospital Targu-Mures, Romania over a 15 year period and to assess the impact the new 2017 WHO and TNM classifications of thyroid tumors had on our cases. METHODS: The pathological data were retrieved from the original pathological reports. After applying the exclusion criteria the remaining cases were reviewed on a double-headed microscope and reclassified according to the 2017 WHO and TNM staging system. The follow-up data were collected from the Institute of Oncology Cluj-Napoca, Romania. RESULTS: Our study included 396 cases of DTCs (375 papillary, 11 follicular, and 10 Hürthle cell carcinomas). PTCs revealed a significant increasing trend over the study period, whereas follicular and Hurthle cell carcinomas remain rare; 125/131 of noninvasive encapsulated follicular variant PTC (EFVPTC) were reclassified as noninvasive follicular thyroid neoplasms with papillary-like nuclear features (NIFTPs), resulting in a 33.3% reduction in the number of PTCs. According to 2017 TNM stage-grouping 31% of 271 patients with DTC were downstaged. Follow-up data were available for most of the patients (65.7%, mean period 58.1 months). All patients with noninvasive EFVPTC were disease free at the last clinical assessment. CONCLUSIONS: The increasing rate of PTC was maintained even after exclusion of NIFTP. By applying 2017 TNM criteria, a significant number of DTC cases were downstaged into a more favorable group. Follow-up data highlight the indolent behavior of noninvasive EFVPTCs reclassified as NIFTPs.

Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study.

BACKGROUND: Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification. METHODS: This ethically approved retrospective pilot study included 54 women with benign (n = 38) and malignant (n = 32) solid breast lesions who underwent ABUS. After manual region of interest placement along the lesions' margin as well as the surrounding fat and glandular breast tissue, 47 texture features (TFs) were calculated for each category. Statistical analysis (ANOVA) and a support vector machine (SVM) algorithm were applied to the texture feature to evaluate the accuracy in distinguishing (i) lesions versus normal tissue and (ii) benign versus malignant lesions. RESULTS: Skewness and kurtosis were the only TF significantly different among all the four categories (p < 0.000001). In subsets (i) and (ii), a maximum area under the curve of 0.86 (95% confidence interval [CI] 0.82-0.88) for energy and 0.86 (95% CI 0.82-0.89) for entropy were obtained. Using the SVM algorithm, a maximum area under the curve of 0.98 for both subsets was obtained with a maximum accuracy of 94.4% in subset (i) and 90.7% in subset (ii). CONCLUSIONS: TA in combination with ML might represent a useful diagnostic tool in the evaluation of breast imaging findings in ABUS. Applying ML techniques to TFs might be superior compared to the analysis of single TF.

Injecting and removing suspicious features in breast imaging with CycleGAN: A pilot study of automated adversarial attacks using neural networks on small images.

PURPOSE: To train a CycleGAN on downscaled versions of mammographic data to artificially inject or remove suspicious features, and to determine whether these AI-mediated attacks can be detected by radiologists. MATERIAL AND METHODS: From two publicly available datasets, BCDR and INbreast, we selected 680 images with and without lesions as training data. An internal dataset (n = 302 cancers, n = 590 controls) served as test data. We ran two experiments (256 × 256 px and 512 × 408 px) and applied the trained model to the test data. Three radiologists read a set of images (modified and originals) and rated the presence of suspicious lesions on a scale from 1 to 5 and the likelihood of the image being manipulated. The readout was evaluated by multiple reader multiple case receiver operating characteristics (MRMC-ROC) analysis using the area under the curve (AUC). RESULTS: At the lower resolution, the overall performance was not affected by the CycleGAN modifications (AUC 0.70 vs. 0.76, p = 0.67). However, one radiologist exhibited lower detection of cancer (0.85 vs 0.63, p = 0.06). The radiologists could not discriminate between original and modified images (0.55, p = 0.45). At the higher resolution, all radiologists showed significantly lower detection rate of cancer in the modified images (0.80 vs. 0.37, p < 0.001), however, they were able to detect modified images due to better visibility of artifacts (0.94, p < 0.0001). CONCLUSION: Our proof-of-concept study shows that CycleGAN can implicitly learn suspicious features and artificially inject or remove them in existing images. The applicability of the method is currently limited by the small image size and introduction of artifacts.

Dedicated Breast Computed Tomography With a Photon-Counting Detector: Initial Results of Clinical In Vivo Imaging.

OBJECTIVES: The purpose of this work is to present the data obtained from the first clinical in vivo application of a new dedicated spiral breast computed tomography (B-CT) equipped with a photon-counting detector. MATERIALS AND METHODS: The institutional review board approved this retrospective study. Twelve women referred for breast cancer screening were included and underwent bilateral spiral B-CT acquired in prone position. Additional sonography was performed in case of dense breast tissue or any B-CT findings. In 3 women, previous mammography was available for comparison. Soft tissue (ST) and high-resolution (HR) images were reconstructed. Two independent radiologists performed separately the readout for subjective image quality and for imaging findings detection. Objective image quality evaluation was performed in consensus and included spatial resolution, contrast resolution, signal-to-noise ratio (SNR), and contrast-to-noise ratio. All women were asked to report about positioning comfort and overall comfort during data acquisition. RESULTS: The major pectoral muscle was included in 15 breast CT scans (62.5%); glandular component was partially missing in 2 (8.3%) of the 24 scanned breasts. A thin "ring artifact" was present in all scans but had no influence on image interpretations; no other artifacts were present. Subjective image quality assessment showed excellent agreement between the 2 readers (κ = 1). Three masses were depicted in B-CT and were confirmed as simple cysts in sonography. Additional 5 simple cysts and 2 solid benign lesions were identified only in sonography. A total of 12 calcifications were depicted with a median size of 1.1 mm (interquartile range, 0.7-1.7 mm) on HR and 1.4 mm (interquartile range, 1.1-1.8 mm) on ST images. Median SNRgl, SNRfat, and contrast-to-noise ratio were significantly higher in ST than in HR reconstructions (each, P < 0.001). A mild discomfort due to positioning of the rib cage on the table was reported by 2 women (16.7%); otherwise, no discomfort was reported. CONCLUSIONS: The new dedicated B-CT equipped with a photon-counting detector provides high-quality images with potential for screening of breast cancer along with minor patient discomfort.