The Application of Magnetic Nanoparticles for Sentinel Lymph Node Detection in Clinically Node-Negative Breast Cancer Patients: A Systemic Review and Meta-Analysis

Machine-learning methods based on the texture and non-texture features of MRI for the preoperative prediction of sentinel lymph node metastasis in breast cancer

Background

The establishment of an accurate, stable, and non-invasive prediction model of sentinel lymph node (SLN) metastasis in breast cancer is difficult nowadays. The aim of this work is to identify the optimal machine learning model based on the three-dimensional (3D) image features of magnetic resonance imaging (MRI) for the preoperative prediction of SLN metastasis in breast cancer patients.

Methods

A total of 172 patients with histologically proven breast cancer were enrolled retrospectively, including 74 SLN metastasis patients and 98 non-SLN metastasis patients. All of them underwent diffusion-weighted imaging (DWI) magnetic resonance imaging (MRI) scan. Firstly, a total of 10,320 texture and four non-texture features were extracted from the region of interests (ROIs) of image. Twenty-four feature selection methods and 11 classification methods were then evaluated by using 10-fold cross-validation to identify the optimal machine learning model in terms of the mean area under the curve (AUC), accuracy (ACC), and stability.

Results

The result showed that the model based on the combination of minimum redundancy maximum relevance (MRMR) + random forest (RF) exhibited the optimal predictive performance (AUC: 0.97±0.03; ACC: 0.89±0.05; stability: 2.94). Moreover, we independently investigated the performance of feature selection methods and classification methods, and observed that L1-support vector machine (L1-SVM) (AUC: 0.80±0.08; ACC: 0.76±0.07) and sequential forward floating selection (SFFS) (stability: 3.04) presented the best average predictive performance and stability among all feature selection methods, respectively. RF (AUC: 0.85±0.11; ACC: 0.80±0.09) and SVM (stability: 8.43) showed the best average predictive performance and stability among all classification methods, respectively.

Conclusions

The identified model based on the 3D image features of MRI provides a non-invasive way for the preoperative prediction of SLN metastasis in breast cancer patients.

Hyaluronic acid-empowered nanotheranostics in breast and lung cancers therapy

Nanomedicine application in cancer therapy is an urgency because of inability of current biological therapies for complete removal of tumor cells. The development of smart and novel nanoplatforms for treatment of cancer can provide new insight in tumor suppression. Hyaluronic acid is a biopolymer that can be employed for synthesis of smart nanostructures capable of selective targeting CD44-overexpressing tumor cells. The breast and lung cancers are among the most malignant and common tumors in both females and males that environmental factors, lifestyle and genomic alterations are among the risk factors for their pathogenesis and development. Since etiology of breast and lung tumors is not certain and multiple factors participate in their development, preventative measures have not been completely successful and studies have focused on developing new treatment strategies for them. The aim of current review is to provide a comprehensive discussion about application of hyaluronic acid-based nanostructures for treatment of breast and lung cancers. The main reason of using hyaluronic acid-based nanoparticles is their ability in targeting breast and lung cancers in a selective way due to upregulation of CD44 receptor on their surface. Moreover, nanocarriers developed from hyaluronic acid or functionalized with hyaluronic acid have high biocompatibility and their safety is appreciated. The drugs and genes used for treatment of breast and lung cancers lack specific accumulation at cancer site and their cytotoxicity is low, but hyaluronic acid-based nanostructures provide their targeted delivery to tumor site and by increasing internalization of drugs and genes in breast and lung tumor cells, they improve their therapeutic index. Furthermore, hyaluronic acid-based nanostructures can be used for phototherapy-mediated breast and lung cancers ablation. The stimuli-responsive and smart kinds of hyaluronic acid-based nanostructures such as pH- and light-responsive can increase selective targeting of breast and lung cancers.

New techniques versus standard mapping for sentinel lymph node biopsy in breast cancer: a systematic review and meta-analysis

New tracers for sentinel lymph node biopsy (SLNB), as indocyanine green (ICG), superparamagnetic iron oxide (SPIO) and micro bubbles, have been recently introduced in clinical practice showing promising but variable results. We reviewed the available evidence comparing these new techniques with the standard tracers to evaluate their safety. To identify all available studies, a systematic search was performed in all electronic databases. Data regarding sample size, mean number of SLN harvested for patient, number of metastatic SLN and SLN identification rate of all studies were extracted. No significant differences were found in terms of SLNs identification rates between SPIO, RI and BD but with a higher identification rate with the use of ICG. No significant differences were also found for the number of metastatic lymph nodes identified between SPIO, RI and BD and the mean number of SLNs identified between SPIO and ICG versus conventional tracers. A statistically significant differences in favor of ICG was reported for the comparison between ICG and conventional tracers for the number of metastatic lymph nodes identified. Our meta-analysis demonstrates that the use of both ICG and SPIO for the pre-operative mapping of sentinel lymph nodes in breast cancer treatment is adequately effective.

Role of Nuclear Sentinel Lymph Node Mapping Compared to New Alternative Imaging Methods

With the emergence of sentinel node technology, many patients can be staged histopathologically using lymphatic mapping and selective lymphadenectomy. Structural imaging by using US, CT and MR permits precise measurement of lymph node volume, which is strongly associated with neoplastic involvement. Sentinel lymph node detection has been an ideal field of application for nuclear medicine because anatomical data fails to represent the close connections between the lymphatic system and regional lymph nodes, or, more specifically, to identify the first draining lymph node. Hybrid imaging has demonstrated higher accuracy than standard imaging in SLN visualization on images, but it did not change in terms of surgical detection. New alternatives without ionizing radiations are emerging now from "non-radiological" fields, such as ophthalmology and dermatology, where fluorescence or opto-acoustic imaging, for example, are widely used. In this paper, we will analyze the advantages and limits of the main innovative methods in sentinel lymph node detection, including innovations in lymphoscintigraphy techniques that persist as the gold standard to date.

Iron and Cancer: A Special Issue

Iron is an essential element for all organisms, and iron-containing proteins play critical roles in cellular functions [...]