Large cell anaplastic lymphoma associated with breast implant: a rare case report presentation and discussion of possible management

A Deep Learning Model to Predict Breast Implant Texture Types Using Ultrasonography Images: Feasibility Development Study

BACKGROUND

Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell texture types of breast implants, has been identified as a possible etiologic factor for lymphoma, specifically breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the shell texture type of the implant is critical to diagnosing BIA-ALCL. However, distinguishing the shell texture type can be difficult due to the loss of human memory and medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment.

OBJECTIVE

This study aims to determine the feasibility of using a deep learning model to classify the shell texture type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources.

METHODS

A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images captured from both Canon and GE devices, images of ruptured implants, and images without implants, as well as publicly available images. The Canon images were trained using ResNet-50. The model's performance on the Canon dataset was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using the GE and publicly available datasets. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (PRAUC) were calculated based on the contribution of the pixels with Gradient-weighted Class Activation Mapping (Grad-CAM). To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess the model's robustness to uncertainty, Shannon entropy was calculated for 4 image groups: Canon, GE, ruptured implants, and without implants.

RESULTS

The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset. The model achieved an AUROC of 0.985 and a PRAUC of 0.748 for images captured with GE devices. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for the publicly available dataset. This model maintained the PRAUC values for quantitative validation when masking up to 90% of the least-contributing pixels and the remnant pixels in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (0.066), GE (0072), ruptured implants (0.371), and no implants (0.777).

CONCLUSIONS

We have demonstrated the feasibility of using deep learning to predict the shell texture type of breast implants. This approach quantifies the shell texture types of breast implants, supporting the first step in the diagnosis of BIA-ALCL.

A Study on Breast Augmentation Using Fat Grafting With Stromal Vascular Fraction

BACKGROUND

Stromal vascular fraction (SVF) and fat grafting are emerging alternatives to implants for breast augmentation. However, the lack of controlled clinical data has led to conflicting results regarding the effectiveness of surgical treatments. This study aimed to identify the key factors affecting the outcomes of fat grafting with SVF and to recognize novel methods to improve the retention rate.

PATIENTS AND METHODS

In total, 384 women underwent breast augmentation using fat grafting with SVF. The patients were preoperatively and postoperatively managed and recalled for follow-up at 3, 6, and 18 months.

RESULTS

The average volume of the injection in the left breast was 162.35 mL (range, 50-260 mL). The postoperative retention rates were 78.65% in 384 patients at 3 months, 77.17% in 273 patients at 6 months, and 77.48% in 102 patients at 18 months. The retention rates were compared based on the number of SVF cells; patients with more than 60 million cells had a retention rate of 70.77%, and those with less than 60 million cells had a retention rate of 85.60% at 18 months. The retention rates at the 18-month follow-up were 65.62% and 85.09% in stiff and soft breasts, respectively. A higher number of cells in the SVF was associated with a greater retention volume, and the retention volume was greater in patients with soft breasts.Given the higher use of the right arm, after 18 months of the surgery, the retention rate of the right breast (60.35%) was lower than that of the left breast (77.48%) ( P < 0.05; t = -13.199).

CONCLUSIONS

Limiting arm movement, increasing the number of cells in the SVF, and improving the skin tension might enhance the retention rate in patients undergoing breast augmentation.

Primary Lymphomas of the Breast: A Review

Lymphomas of the breast are rare neoplasms that arise from breast lymphoid tissue and are characterised by neoplastic B or T cells. Breast lymphomas arising from B cells include, but are not limited to, diffuse large B cell lymphoma, follicular lymphoma, extra-nodal marginal zone lymphoma and Burkitt lymphoma. Anaplastic large cell lymphoma (ALCL) is of a T cell origin and both anaplastic lymphoma kinase (ALK)-positive and ALK-negative presentations have been noted in the breast. In addition, there is a more recently identified presentation of ALK-negative ALCL that arises around textured breast implants and is usually confined to a periprosthetic fibrous capsule. Here, we discuss the clinical presentations, histological and immunohistochemical features and treatment options for each type of primary breast lymphoma. We hope that this review will highlight the importance of the timely and accurate diagnosis of breast lymphoma in order to tailor the most appropriate treatment. We also wish to raise awareness of the breast implant-associated lymphomas, with the goal of stimulating work that will aid our understanding of their epidemiology and pathogenesis.

Existing and Emerging Breast Cancer Detection Technologies and Its Challenges: A Review

Breast cancer is the most leading cancer occurring in women and is a significant factor in female mortality. Early diagnosis of breast cancer with Artificial Intelligent (AI) developments for breast cancer detection can lead to a proper treatment to affected patients as early as possible that eventually help reduce the women mortality rate. Reliability issues limit the current clinical detection techniques, such as Ultra-Sound, Mammography, and Magnetic Resonance Imaging (MRI) from screening images for precise elucidation. The capability to detect a tumor in early diagnosis, expensive, relatively long waiting time due to pandemic and painful procedure for a patient to perform. This article aims to review breast cancer screening methods and recent technological advancements systematically. In addition, this paper intends to explore the progression and challenges of AI in breast cancer detection. The next state of the art between image and signal processing will be presented, and their performance is compared. This review will facilitate the researcher to insight the view of breast cancer detection technologies advancement and its challenges.

Deep Vision for Breast Cancer Classification and Segmentation

Simple Summary

Breast cancer misdiagnoses increase individual and system stressors as well as costs and result in increased morbidity and mortality. Digital mammography studies are typically about 80% sensitive and 90% specific. Improvement in classification of breast cancer imagery is possible using deep vision methods, and these methods may be further used to identify autonomously regions of interest most closely associated with anomalies to support clinician analysis. This research explores deep vision techniques for improving mammography classification and for identifying associated regions of interest. The findings from this research contribute to the future of automated assistive diagnoses of breast cancer and the isolation of regions of interest.

Abstract

(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies 299 × 299 pixel de-noised mammography images as negative or non-negative using models built on 55,890 pre-processed training images and applied to 15,364 unseen test images. A small image representation from the fitted training model is returned to evaluate the portion of the loss function gradient with respect to the image that maximizes the classification probability. This gradient is then re-mapped back to the original images, highlighting the areas of the original image that are most influential for classification (perhaps masses or boundary areas). (3) Results: initial classification results were 97% accurate, 99% specific, and 83% sensitive. Gradient techniques for unsupervised region of interest mapping identified areas most associated with the classification results clearly on positive mammograms and might be used to support clinician analysis. (4) Conclusions: deep vision techniques hold promise for addressing the overdiagnoses and treatment, underdiagnoses, and automated region of interest identification on mammography.