A Proposed Dedicated Breast PET Lexicon: Standardization of Description and Reporting of Radiotracer Uptake in the Breast

Multiparametric Approach to Breast Cancer With Emphasis on Magnetic Resonance Imaging in the Era of Personalized Breast Cancer Treatment

ABSTRACT

A multiparametric approach to breast cancer imaging offers the advantage of integrating the diverse contributions of various parameters. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is the most important MRI sequence for breast imaging. The vascularity and permeability of lesions can be estimated through the use of semiquantitative and quantitative parameters. The increased use of ultrafast DCE-MRI has facilitated the introduction of novel kinetic parameters. In addition to DCE-MRI, diffusion-weighted imaging provides information associated with tumor cell density, with advanced diffusion-weighted imaging techniques such as intravoxel incoherent motion, diffusion kurtosis imaging, and time-dependent diffusion MRI opening up new horizons in microscale tissue evaluation. Furthermore, T2-weighted imaging plays a key role in measuring the degree of tumor aggressiveness, which may be related to the tumor microenvironment. Magnetic resonance imaging is, however, not the only imaging modality providing semiquantitative and quantitative parameters from breast tumors. Breast positron emission tomography demonstrates superior spatial resolution to whole-body positron emission tomography and allows comparable delineation of breast cancer to MRI, as well as providing metabolic information, which often precedes vascular and morphological changes occurring in response to treatment. The integration of these imaging-derived factors is accomplished through multiparametric imaging. In this article, we explore the relationship among the key imaging parameters, breast cancer diagnosis, and histological characteristics, providing a technical and theoretical background for these parameters. Furthermore, we review the recent studies on the application of multiparametric imaging to breast cancer and the significance of the key imaging parameters.

Clinical Applications of Dedicated Breast Positron Emission Tomography

Breast-specific positron imaging systems provide higher sensitivity than whole-body PET for breast cancer detection. The clinical applications for breast-specific positron imaging are similar to breast MRI including preoperative local staging and neoadjuvant therapy response assessment. Breast-specific positron imaging may be an alternative for patients who cannot undergo breast MRI. Further research is needed in expanding the field-of-view for posterior breast lesions, increasing biopsy capability, and reducing radiation dose. Efforts are also necessary for developing appropriate use criteria, increasing availability, and advancing insurance coverage.

Molecular Breast Imaging and Positron Emission Mammography

There is growing interest in application of functional imaging modalities for adjunct breast imaging due to their unique ability to evaluate molecular/pathophysiologic changes, not visible by standard anatomic breast imaging. This has led to increased use of nuclear medicine dedicated breast-specific single photon and coincidence imaging systems for multiple indications, such as supplemental screening, staging of newly diagnosed breast cancer, evaluation of response to neoadjuvant treatment, diagnosis of local disease recurrence in the breast, and problem solving. Studies show that these systems maybe especially useful for specific subsets of patients, not well served by available anatomic breast imaging modalities.

Performance of dedicated breast PET in breast cancer screening: comparison with digital mammography plus digital breast tomosynthesis and ultrasound

OBJECTIVE

To compare the diagnostic performance of dedicated breast positron emission tomography (dbPET) in breast cancer screening with digital mammography plus digital breast tomosynthesis (DM-DBT) and breast ultrasound (US).

METHODS

Women who participated in opportunistic whole-body PET/computed tomography cancer screening programs with breast examinations using dbPET, DM-DBT, and US between 2016-2020, whose results were determined pathologically or by follow-up for at least 1 year, were included. DbPET, DM-DBT, and US assessments were classified into four diagnostic categories: A (no abnormality), B (mild abnormality), C (need for follow-up), and D (recommend further examination). Category D was defined as screening positive. Each modality's recall rate, sensitivity, specificity, and positive predictive value (PPV) were calculated per examination to evaluate their diagnostic performance for breast cancer.

RESULTS

Out of 2156 screenings, 18 breast cancer cases were diagnosed during the follow-up period (10 invasive cancers and eight ductal carcinomas in situ [DCIS]). The recall rates for dbPET, DM-DBT, and US were 17.8%, 19.2%, and 9.4%, respectively. The recall rate of dbPET was highest in the first year and subsequently decreased to 11.4%. dbPET, DM-DBT, and US had sensitivities of 72.2%, 88.9%, and 83.3%; specificities of 82.6%, 81.4%, and 91.2%; and PPVs of 3.4%, 3.9%, and 7.4%, respectively. The sensitivities of dbPET, DM-DBT, and US for invasive cancers were 90%, 100%, and 90%, respectively. There were no significant differences between the modalities. One case of dbPET-false-negative invasive cancer was identified in retrospect. DbPET had 50% sensitivity for DCIS, while that of both DM-DBT and US was 75%. Furthermore, the specificity of dbPET in the first year was the lowest among all periods, and modalities increased over the years to 88.7%. The specificity of dbPET was significantly higher than that of DM-DBT (p < 0.01) in the last 3 years.

CONCLUSIONS

DbPET had a compatible sensitivity to DM-DBT and breast US for invasive breast cancer. The specificity of dbPET was improved and became higher than that of DM-DBT. DbPET may be a feasible screening modality.

Deep learning model with collage images for the segmentation of dedicated breast positron emission tomography images

BACKGROUND

Dedicated breast positron emission tomography (dbPET) has high contrast and resolution optimized for detecting small breast cancers, leading to its noisy characteristics. This study evaluated the application of deep learning to the automatic segmentation of abnormal uptakes on dbPET to facilitate the assessment of lesions. To address data scarcity in model training, we used collage images composed of cropped abnormal uptakes and normal breasts for data augmentation.

METHODS

This retrospective study included 1598 examinations between April 2015 and August 2020. A U-Net-based model with an uptake shape classification head was trained using either the original or augmented dataset comprising collage images. The Dice score, which measures the pixel-wise agreement between a prediction and its ground truth, of the models was compared using the Wilcoxon signed-rank test. Moreover, the classification accuracies were evaluated.

RESULTS

After applying the exclusion criteria, 662 breasts were included; among these, 217 breasts had abnormal uptakes (mean age: 58 ± 14 years). Abnormal uptakes on the cranio-caudal and mediolateral maximum intensity projection images of 217 breasts were annotated and labeled as focus, mass, or non-mass. The inclusion of collage images into the original dataset yielded a Dice score of 0.884 and classification accuracy of 91.5%. Improvement in the Dice score was observed across all subgroups, and the score of images without breast cancer improved significantly from 0.750 to 0.834 (effect size: 0.76, P = 0.02).

CONCLUSIONS

Deep learning can be applied for the automatic segmentation of dbPET, and collage images can improve model performance.

A case of breast cancer: Suppression of lactation-related FDG uptake 2 days after cabergoline administration

We present a case of a 35-year-old woman with breast cancer in lactation 3 months after childbirth, in which a lactation inhibitor was useful for 18F-FDG PET/CT examination. Via ultrasonography and biopsy with histopathology, we diagnosed the lesion in the upper region of the left breast as invasive ductal carcinoma. She stopped breastfeeding and was administered cabergoline to suppress lactation. Two days after the administration, 18F-FDG PET/CT revealed segmental uptake (10 cm in diameter) and no lactation-related uptakes. Dynamic MRI also revealed a segmental enhancement of the same size as 18F-FDG PET/CT. The lactation inhibitor was useful to delineate the extent of the lesion during the 18F-FDG PET/CT examination.

Reproducibility assessment of uptake on dedicated breast PET for noise discrimination

OBJECTIVES

Dedicated breast PET (dbPET) systems have improved the detection of small breast cancers but have increased false-positive diagnoses due to an increased chance of noise detection. This study examined whether reproducibility assessment using paired images helped to improve noise discrimination and diagnostic performance in dbPET.

METHODS

This study included 21 patients with newly diagnosed breast cancer who underwent [¹⁸F]FDG-dbPET and contrast-enhanced breast MRI. A 10-min dbPET data scan was acquired per breast, and two sets of reconstructed images were generated (named dbPET-1 and dbPET-2, respectively), each of which consisted of randomly allocated 5-min data from the 10-min data. Uptake spots higher than the background were indexed for the study with visual assessment. All indexed uptakes on dbPET-1 were evaluated using dbPET-2 for reproducibility. MRI findings based on the Breast Imaging-Reporting and Data System (BI-RADS) 2013 were used as the gold standard. Uptake spots that corresponded to BI-RADS 1 on MRI were considered noise, while those with BI-RADS 4b-6 were considered malignancies. The diagnostic performance of dbPET for malignancy was evaluated using four different criteria: any uptake on dbPET-1 regarded as positive (criterion A), a subjective visual assessment of dbPET-1 (criterion B), reproducibility assessment between dbPET-1 and dbPET-2 (criterion C), and a combination of B and C (criterion D).

RESULTS

A total of 213 indexed uptake spots were identified on dbPET-1, including 152, 15, 6, 6, and 34 lesions classified as BI-RADS MRI categories 1, 2, 4b, 4c, and 5, respectively. Overall, 31.9% of the index uptake values were reproducible. All malignant lesions were reproducible, whereas 93.4% of noise was not reproducible. The sensitivities for malignancy for criteria A, B, C, and D were 100%, 91.3%, 100%, and 91.3%, respectively, with positive predictive values (PPVs) of 21.4%, 68.9%, 67.6%, and 82.4%, respectively.

CONCLUSIONS

Our results demonstrated that reproducibility assessment helped reduce false-positive findings caused by noise on dbPET without lowering the sensitivity for malignancy. While subjective visual assessment was also efficient in increasing PPV, it occasionally missed malignant uptake.

Universal Liver Imaging Lexicon: Imaging Atlas for Research and Clinical Practice

The use of standardized terms in assessing and reporting disease processes has well-established benefits, such as clear communication between radiologists and other health care providers, improved diagnostic accuracy and reproducibility, and the enhancement and facilitation of research. Recently, the Liver Imaging Reporting and Data System (LI-RADS) Steering Committee released a universal liver imaging lexicon. The current version of the lexicon includes 81 vetted and precisely defined terms that are relevant to acquisition of images using all major liver imaging modalities and contrast agents, as well as lesion- and organ-level features. Most terms in the lexicon are applicable to all patients undergoing imaging of the liver, and only a minority of the terms are strictly intended to be used for patients with high risk factors for hepatocellular carcinoma. This pictorial atlas familiarizes readers with the liver imaging lexicon and includes discussion of general concepts, providing sample definitions, schematics, and clinical examples for a subset of the terms in the liver imaging lexicon. The authors discuss general, technical, and imaging feature terms used commonly in liver imaging, with the goal of illustrating their use for clinical and research applications. Work of the U.S. Government published under an exclusive license with the RSNA. Online supplemental material is available for this article.

Feasibility of Dedicated Breast Positron Emission Tomography Image Denoising Using a Residual Neural Network

Objectives

This study aimed to create a deep learning (DL)-based denoising model using a residual neural network (Res-Net) trained to reduce noise in ring-type dedicated breast positron emission tomography (dbPET) images acquired in about half the emission time, and to evaluate the feasibility and the effectiveness of the model in terms of its noise reduction performance and preservation of quantitative values compared to conventional post-image filtering techniques.

Methods

Low-count (LC) and full-count (FC) PET images with acquisition durations of 3 and 7 minutes, respectively, were reconstructed. A Res-Net was trained to create a noise reduction model using fifteen patients' data. The inputs to the network were LC images and its outputs were denoised PET (LC + DL) images, which should resemble FC images. To evaluate the LC + DL images, Gaussian and non-local mean (NLM) filters were applied to the LC images (LC + Gaussian and LC + NLM, respectively). To create reference images, a Gaussian filter was applied to the FC images (FC + Gaussian). The usefulness of our denoising model was objectively and visually evaluated using test data set of thirteen patients. The coefficient of variation (CV) of background fibroglandular tissue or fat tissue were measured to evaluate the performance of the noise reduction. The SUV_max and SUV_peak of lesions were also measured. The agreement of the SUV measurements was evaluated by Bland-Altman plots.

Results

The CV of background fibroglandular tissue in the LC + DL images was significantly lower (9.10±2.76) than the CVs in the LC (13.60± 3.66) and LC + Gaussian images (11.51± 3.56). No significant difference was observed in both SUV_max and SUV_peak of lesions between LC + DL and reference images. For the visual assessment, the smoothness rating for the LC + DL images was significantly better than that for the other images except for the reference images.

Conclusion

Our model reduced the noise in dbPET images acquired in about half the emission time while preserving quantitative values of lesions. This study demonstrates that machine learning is feasible and potentially performs better than conventional post-image filtering in dbPET denoising.

Proposal to Improve the Image Quality of Short-Acquisition Time-Dedicated Breast Positron Emission Tomography Using the Pix2pix Generative Adversarial Network

This study aimed to evaluate the ability of the pix2pix generative adversarial network (GAN) to improve the image quality of low-count dedicated breast positron emission tomography (dbPET). Pairs of full- and low-count dbPET images were collected from 49 breasts. An image synthesis model was constructed using pix2pix GAN for each acquisition time with training (3776 pairs from 16 breasts) and validation data (1652 pairs from 7 breasts). Test data included dbPET images synthesized by our model from 26 breasts with short acquisition times. Two breast radiologists visually compared the overall image quality of the original and synthesized images derived from the short-acquisition time data (scores of 1−5). Further quantitative evaluation was performed using a peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the visual evaluation, both readers revealed an average score of >3 for all images. The quantitative evaluation revealed significantly higher SSIM (p < 0.01) and PSNR (p < 0.01) for 26 s synthetic images and higher PSNR for 52 s images (p < 0.01) than for the original images. Our model improved the quality of low-count time dbPET synthetic images, with a more significant effect on images with lower counts.

Deep learning for image classification in dedicated breast positron emission tomography (dbPET)

OBJECTIVE

This study aimed to investigate and determine the best deep learning (DL) model to predict breast cancer (BC) with dedicated breast positron emission tomography (dbPET) images.

METHODS

Of the 1598 women who underwent dbPET examination between April 2015 and August 2020, a total of 618 breasts on 309 examinations for 284 women who were diagnosed with BC or non-BC were analyzed in this retrospective study. The Xception-based DL model was trained to predict BC or non-BC using dbPET images from 458 breasts of 109 BCs and 349 non-BCs, which consisted of mediallateral and craniocaudal maximum intensity projection images, respectively. It was tested using dbPET images from 160 breasts of 43 BC and 117 non-BC. Two expert radiologists and two radiology residents also interpreted them. Sensitivity, specificity, and area under the receiver operating characteristic curves (AUCs) were calculated.

RESULTS

Our DL model had a sensitivity and specificity of 93% and 93%, respectively, while radiologists had a sensitivity and specificity of 77-89% and 79-100%, respectively. Diagnostic performance of our model (AUC = 0.937) tended to be superior to that of residents (AUC = 0.876 and 0.868, p = 0.073 and 0.073), although not significantly different. Moreover, no significant differences were found between the model and experts (AUC = 0.983 and 0.941, p = 0.095 and 0.907).

CONCLUSIONS

Our DL model could be applied to dbPET and achieve the same diagnostic ability as that of experts.