Image-guided procedures for breast masses

RiIG Modeled WCP Image-Based CNN Architecture and Feature-Based Approach in Breast Tumor Classification from B-Mode Ultrasound

This study presents two new approaches based on Weighted Contourlet Parametric (WCP) images for the classification of breast tumors from B-mode ultrasound images. The Rician Inverse Gaussian (RiIG) distribution is considered for modeling the statistics of ultrasound images in the Contourlet transform domain. The WCP images are obtained by weighting the RiIG modeled Contourlet sub-band coefficient images. In the feature-based approach, various geometrical, statistical, and texture features are shown to have low ANOVA p-value, thus indicating a good capacity for class discrimination. Using three publicly available datasets (Mendeley, UDIAT, and BUSI), it is shown that the classical feature-based approach can yield more than 97% accuracy across the datasets for breast tumor classification using WCP images while the custom-made convolutional neural network (CNN) can deliver more than 98% accuracy, sensitivity, specificity, NPV, and PPV values utilizing the same WCP images. Both methods provide superior classification performance, better than those of several existing techniques on the same datasets.

Analysis of Diagnostic Methods for Focal Lesions in Breast Glands with Use of Open Surgical Biopsies and Core-Needle Biopsies in Poland

Background

Numerous studies confirm the benefits of using core-needle biopsy (CNB) for diagnosing patients with suspected breast cancer, thus reducing the costs and the stress, and allowing optimum treatment planning. The present study examined the number of patients in Poland who had been diagnosed with breast cancer through inpatient open surgical biopsy (OSB) and CNB by province.

Material/Methods

This retrospective study used a health needs map to identify patients in 2014 and partially in 2015 who had had OSB or CNB of the breast performed on an inpatient basis due to benign breast lesions and whose diagnosis had been changed from benign to malignant.

Results

Among the total number of hospitalizations (13 718 cases with OSB) due to benign lesions of the breast, 1506 patients had their diagnosis changed to malignant, constituting 8.59% of new breast cancer diagnoses across the country. The resulting diagnosis change from benign to malignant varied significantly across provinces, from 5.3% to 23.4%. Among the total of 7205 hospitalizations in 2014 with CNB performed using different methods, there were 1574 malignancies, amounting to 8.9% of new diagnoses in Poland. The use of inpatient CNB to diagnose breast cancer differed significantly across provinces, from 0.6% to 34.4%.

Conclusions

OSBs are too often used to diagnose focal lesions in breast glands in Poland. In some regions, CNBs are too frequently performed on an inpatient rather than outpatient basis, thereby requiring an analysis of the quality of and access to modern diagnostic methods.

Initial Experience of Utilizing Real-Time Intra-Procedural PET/CT Biopsy

OBJECTIVES

Nonreal-time Positron Emission Tomography/Computed Tomography (PET/CT) biopsies that use the image co-registration of a prior PET with an intra-procedural CT have been reported. The aim of this study was to report the initial experience of performing real-time intra-procedural PET/CT-guided biopsies.

MATERIALS AND METHODS

All patients (n = 4) had a prior PET/CT examination of the concerning lesion and no significant CT correlate. On the day of the biopsy, 5 mCi of 18F-fluorodeoxyglucose (FDG) or NaF18 was intravenously injected. After 60 min of biodistribution of the molecular probe, PET/CT images were obtained in a limited one bed position over the region of the concerning lesion to be biopsied.

RESULTS

One patient had a mesenteric mass and the other three had bone lesions, one located in the rib and two in the iliac bone. The pathology report revealed that two lesions (50%) were malignant and two lesions (50%) were benign. The results of the biopsy changed management in all cases. There was 0% complication rate.

CONCLUSIONS

No additional software or hardware is required to perform real-time intra-procedural PET/CT-guided biopsies. It can optimize the yield, especially in cases where there are no anatomical abnormalities. Real-time intra-procedural PET/CT biopsy may have benefits over conventional biopsy techniques in terms of accuracy.

MR imaging in the evaluation of equivocal clinical and imaging findings of the breast

Because of its high negative predictive value in excluding breast cancer, magnetic resonance (MR) imaging plays a role in the evaluation of selected clinical and imaging findings of the breast, especially when biopsy is not technically feasible. Case selection is very important in ensuring the efficacy of this use of MR imaging because of potential false-positive and (albeit less likely) false-negative results. This article examines the clinical scenarios and imaging findings in which MR imaging is contributory to patient management after conventional workup with equivocal results.

Clinician's guide to imaging and pathologic findings in benign breast disease

The discussion of abnormal results of breast imaging and abnormal pathologic findings can be challenging for health care professionals and often is stressful for patients. Although most imaging findings and biopsy results are negative and do not infer a substantial increase in breast cancer risk, the subsequent conversation between the patient and her practitioner is more effective and informative with a thorough review of the pathologic results and an appreciation of the importance of radiologic-histologic concordance. This article provides insight into and understanding of breast imaging and biopsy techniques and of histologic findings as a means to timely and appropriate decision making and action by the patient and her health care professional.

Radiological features of breast benign lesions in patients with hyperprolactinemia

Background: The study was conducted to determine whether prolactin (PRL) influences radiological features of benign breast lesions. Methods: During the 4-year period, we observed 50 patients with nipple discharge: 23 with normal serum prolactin levels (group 1) and 27 with hyperprolactinemia (group 2a before hyperprolactinemia treatment and group 2b after hyperprolactinemia treatment). Patients observed during this study underwent breast ultrasonography (US) and mammography. Radiological findings in group 1, group 2a and group 2b were compared. Results: The most frequent radiological findings in group 2a were dilated lactiferous ducts and cystic lesions with statistical significances p<0.001 and p<0.01 in comparison to other radiological findings. In group 1 significantly less presence of dilated lactiferous ducts was observed (p<0.05) and proportional lower frequency of solid lumps compared to group 2a. Our results showed significantly lower incidence (p<0.001) of dilated lactiferous ducts, after hyperprolactinemia treatment (group 2b). In group 2b less presence of solid lumps and enlarged axillary lymph nodes is also observed in comparison to group 2a. Frequency of cystic lesions significantly decreased (p<0.05) and pseudocysts completely withdrew in patients with normalized serum prolactin levels. Conclusion: Prolactin significantly influences radiological presentation of benign breast diseases. Treatment of hyperprolactinemia results in withdrawal of mammary duct ectasia, pseudocystic formations, cystic lesions and solid lumps. Breast ultra-sonography and mammography should be considered as routine diagnostic procedures in patients with hyperprolactinemia.