Breast cancer (BC) is currently the most common form of cancer diagnosed worldwide with an incidence estimated at 2.26 million in 2020. Additionally, BC is the leading cause of cancer death. Many subtypes of breast cancer exist with distinct biological features and which respond differently to various treatment modalities and have different clinical outcomes. To ensure that sufferers receive lifesaving patients-tailored treatment early, it is crucial to accurately distinguish dangerous malignant (ductal carcinoma, lobular carcinoma, mucinous carcinoma, and papillary carcinoma) subtypes of tumors from adenosis, fibroadenoma, phyllodes tumor, and tubular adenoma benign harmless subtypes. An excellent automated method for detecting malignant subtypes of tumors is desirable since doctors do not identify 10% to 30% of breast cancers during regular examinations. While several computerized methods for breast cancer classification have been proposed, deep convolutional neural networks (DCNNs) have demonstrated superior performance. In this work, we proposed an ensemble of four variants of DCNNs combined with the support vector machines classifier to classify breast cancer histopathological images into eight subtypes classes: four benign and four malignant. The proposed method utilizes the power of DCNNs to extract highly predictive multi-scale pooled image feature representation (MPIFR) from four resolutions (40×, 100×, 200×, and 400×) of BC images that are then classified using SVM. Eight pre-trained DCNN architectures (Inceptionv3, InceptionResNetv2, ResNet18, ResNet50, DenseNet201, EfficientNetb0, shuffleNet, and SqueezeNet) were individually trained and an ensemble of the four best-performing models (ResNet50, ResNet18, DenseNet201, and EfficientNetb0) was utilized for feature extraction. One-versus-one SVM classification was then utilized to model an 8-class breast cancer image classifier. Our work is novel because while some prior work has utilized CNNs for 2- and 4-class breast cancer classification, only one other prior work proposed a solution for 8-class BC histopathological image classification. A 6B-Net deep CNN model was utilized, achieving an accuracy of 90% for 8-class BC classification. In rigorous evaluation, the proposed MPIFR method achieved an average accuracy of 97.77%, with 97.48% sensitivity, and 98.45% precision on the BreakHis histopathological BC image dataset, outperforming the prior state-of-the-art for histopathological breast cancer multi-class classification and a comprehensive set of DCNN baseline models.

In this study, we explore the development of controlled PLGA-CS-PEG microspheres, which are used to encapsulate model anticancer drugs (prodigiosin (PGS) or paclitaxel (PTX)) for controlled breast cancer treatment. The PLGA microspheres are blended with hydrophilic polymers (chitosan and polyethylene glycol) in the presence of polyvinyl alcohol (PVA) that were synthesized via a water-oil-water (W/O/W) solvent evaporation technique. Chitosan (CS) and polyethylene glycol (PEG) were used as surface-modifying additives to improve the biocompatibility and reduce the adsorption of plasma proteins onto the microsphere surfaces. These PLGA-CS-PEG microspheres are loaded with varying concentrations (5 and 8 mg/mL) of PGS or PTX, respectively. Scanning electron microscopy (SEM) revealed the morphological properties while Fourier transform infrared spectroscopy (FTIR) was used to elucidate the functional groups of drug-loaded PLGA-CS-PEG microparticles. A thirty-day, in vitro, encapsulated drug (PGS or PTX) release was carried out at 37 °C, which corresponds to human body temperature, and at 41 °C and 44 °C, which correspond to hyperthermic temperatures. The thermodynamics and kinetics of in vitro drug release were also elucidated using a combination of mathematical models and the experimental results. The exponents of the Korsmeyer–Peppas model showed that the kinetics of drug release was well characterized by anomalous non-Fickian drug release. Endothermic and nonspontaneous processes are also associated with the thermodynamics of drug release. Finally, the controlled in vitro release of cancer drugs (PGS and PTX) is shown to decrease the viability of MDA-MB-231 cells. The implications of the results are discussed for the development of drug-encapsulated PLGA-CS-PEG microparticles for the controlled release of cancer drugs in treatment of triple negative breast cancer.

Triple-negative breast cancer (TNBC) treatment is challenging and frequently characterized by an aggressive phenotype and low prognosis in comparison to other subtypes. This paper presents fabricated implantable drug-loaded microporous poly-di-methyl-siloxane (PDMS) devices for the delivery of targeted therapeutic agents [Luteinizing Hormone-Releasing Hormone conjugated paclitaxel (PTX-LHRH) and Luteinizing Hormone-Releasing Hormone conjugated prodigiosin (PG-LHRH)] for the treatment and possible prevention of triple-negative cancer recurrence. In vitro assessment using the Alamar blue assay demonstrated a significant reduction (p < 0.05) in percentage of cell growth in a time-dependent manner in the groups treated with PG, PG-LHRH, PTX, and PTX-LHRH. Subcutaneous triple-negative xenograft breast tumors were then induced in athymic female nude mice that were four weeks old. Two weeks later, the tumors were surgically but partially removed, and the device implanted. Mice were observed for tumor regrowth and organ toxicity. The animal study revealed that there was no tumor regrowth, six weeks post-treatment, when the LHRH targeted drugs (LHRH-PTX and LHRH-PGS) were used for the treatment. The possible cytotoxic effects of the released drugs on the liver, kidney, and lung are assessed using quantitative biochemical assay from blood samples of the treatment groups. Ex vivo histopathological results from organ tissues showed that the targeted cancer drugs released from the implantable drug-loaded device did not induce any adverse effect on the liver, kidneys, or lungs, based on the results of qualitative toxicity studies. The implications of the results are discussed for the targeted and localized treatment of triple negative breast cancer.

Breast cancer accounts for 30% of all female cancers. Accurately distinguishing dangerous malignant tumors from benign harmless ones is key to ensuring patients receive lifesaving treatments on time. However, as doctors currently do not identify 10% to 30% of breast cancers during regular assessment, automated methods to detect malignant tumors are desirable. Although several computerized methods for breast cancer classification have been proposed, convolutional neural networks (CNNs) have demonstrably outperformed other approaches. In this paper, we propose an automated method for the binary classification of breast cancer tumors as either malignant or benign that utilizes a bag of deep multi-resolution convolutional features (BoDMCF) extracted from histopathological images at four resolutions (40×, 100×, 200× and 400×) by three pre-trained state-of-the-art deep CNN models: ResNet-50, EfficientNetb0, and Inception-v3. The BoDMCF extracted by the pre-trained CNNs were pooled using global average pooling and classified using the support vector machine (SVM) classifier. While some prior work has utilized CNNs for breast cancer classification, they did not explore using CNNs to extract and pool a bag of deep multi-resolution features. Other prior work utilized CNNs for deep multi-resolution feature extraction from chest X-ray radiographs to detect other conditions such as pneumoconiosis but not for breast cancer detection from histopathological images. In rigorous evaluation experiments, our deep BoDMCF feature approach with global pooling achieved an average accuracy of 99.92%, sensitivity of 0.9987, specificity (or recall) of 0.9797, positive prediction value (PPV) or precision of 0.99870, F1-Score of 0.9987, MCC of 0.9980, Kappa of 0.8368, and AUC of 0.9990 on the publicly available BreaKHis breast cancer image dataset. The proposed approach outperforms the prior state of the art for histopathological breast cancer classification as well as a comprehensive set of CNN baselines, including ResNet18, InceptionV3, DenseNet201, EfficientNetb0, SqueezeNet, and ShuffleNet, when classifying images at any individual resolutions (40×, 100×, 200× or 400×) or when SVM is used to classify a BoDMCF extracted using any single pre-trained CNN model. We also demonstrate through a carefully constructed set of experiments that each component of our approach contributes non-trivially to its superior performance including transfer learning (pre-training and fine-tuning), deep feature extraction at multiple resolutions, global pooling of deep multiresolution features into a powerful BoDMCF representation, and classification using SVM.