Recent advances in artificial intelligence (AI), especially convolutional neural networks (CNNs), alongside the digitization of histopathological images, have made the computer-aided diagnosis of breast cancer a reality. However, deep learning-based approaches are computationally expensive and have huge parameters, which makes them less affordable for edge devices. In order to make them affordable for edge devices, the whole classification model needs to be compressed while maintaining accuracy. Providing a low-cost solution for histopathological diagnosis in the recent edge-computing world is of utmost importance. Therefore, in this study, we propose “MobiHisNet,” an efficient and lightweight CNN model for histopathological image classification (HIC) based on MobileNet. MobiHisNet was successfully deployed on a Raspberry Pi, as well as three mobile devices, demonstrating its ability to run on a lightweight and portable processor. Our studies indicated that a depth parameter ( $\gamma = 0.5$ ) and a 16-bit quantization are the optimum parameters for the proposed model while balancing the accuracy, inference time, and memory peak requirements. Compared to the state-of-the-art, pretrained models, MobiHisNet has fewer parameters and calculations, resulting in faster image classification. This renders it more viable for production purposes and applications on edge devices. In addition, MobiHisNet is computationally faster than VGG16, ResNet50, Xception, and InceptionV3 by twenty-seven, eight, six, and five times, respectively. This also outperforms all the baseline models with the moderate model size and FLOP counts. Experiments on breast cancer HIC (BreakHis) data sets show superior performance of MobiHisNet on edge devices in terms of higher accuracy, lesser complexity, and lesser memory requirements. Thus, it has a high potential for deployment in mobile edge devices.

Machine learning (ML) has emerged as a powerful tool for pattern recognition. Traditional ML algorithms have limited ability to reveal the most sophisticated features of cancer histopathological images, but their robustness and fault tolerance can be enhanced by using fuzzy modeling to capture the uncertainty in image data. Therefore, this study proposes a novel CoMHisP framework based on a fuzzy support vector machine with within-class density information (FSVM-WD). It utilizes a novel feature extraction technique by optimizing the block size to extract image micro-patterns and computing center of mass (CoM) for each pixel to extract feature vectors. The performance of the proposed framework is evaluated using a CMTHis dataset comprising histopathological images of canine mammary tumor (CMT), a prevalent neoplastic disease in female dogs, and an established model for human breast cancer. Data analysis reveals that stain normalization and magnification influence the performance of the CoMHisP framework, with the best results achieved at lower magnifications after stain normalization. The proposed framework achieves a classification accuracy of 97.25% (±1.80%) using a FSVM-WD classifier, outperforming both traditional ML and deep FE-VGGNET16-based feature descriptors. To the best of our knowledge, this is the first time a CoM-based feature descriptor has been proposed for histopathological image analysis of CMTs and its performance was evaluated using a fuzzy SVM-based classifier. The proposed method performs well with datasets of limited size and low-magnification images and therefore has the potential to provide rapid and accurate diagnosis in low-cost clinical settings.

Spontaneously occurring canine mammary tumours (CMTs) are the most common neoplasms of unspayed female dogs leading to thrice higher mortality rates than human breast cancer. These are also attractive models for human breast cancer studies owing to clinical and molecular similarities. Thus, they are important candidates for biomarker studies and understanding cancer pathobiology. The study was designed to explore underlying molecular networks and pathways in CMTs for deciphering new prognostic factors and therapeutic targets. To gain an insight into various pathways and networks associated with the development and pathogenesis of CMTs, comparative cDNA microarray expression profiling was performed using CMT tissues and healthy mammary gland tissues. Upon analysis, 1700 and 1287 differentially expressed genes (DEGs, P ≤ 0.05) were identified in malignant and benign tissues, respectively. DEGs identified from microarray analysis were further annotated using the Ingenuity Systems Pathway Analysis (IPA) tool for detection of deregulated canonical pathways, upstream regulators, and networks associated with malignant, as well as, benign disease. Top scoring key networks in benign and malignant mammary tumours were having central nodes of VEGF and BUB1B, respectively. Cyclins & cell cycle regulation and TREM1 signalling were amongst the top activated canonical pathways in CMTs. Other cancer related significant pathways like apoptosis signalling, dendritic cell maturation, DNA recombination and repair, Wnt/β-catenin signalling, etc. were also found to be altered. Furthermore, seven proteins (ANXA2, APOCII, CDK6, GATC, GDI2, GNAQ and MYH9) highly up-regulated in malignant tissues were identified by two-dimensional gel electrophoresis (2DE) and MALDI-TOF PMF studies which were in concordance with microarray data. Thus, the study has uncovered ample number of candidate genes associated with CMTs which need to be further validated as therapeutic targets and prognostic markers.

Spontaneously occurring canine mammary tumours (CMTs) are the most common neoplasms of female unspayed dogs and are of potential importance as models for human breast cancer as well. Mortality rates are thrice higher in dogs as compared to humans with breast cancer, which can partly be attributed to lack of diagnostic techniques for their early detection. Human breast cancer studies reveal role of autoantibodies in early cancer diagnosis and also the usefulness of autoantibody panels in increasing the sensitivity, as well as, specificity of diagnostic assays. Therefore, in this study, we took advantage of high-throughput Luminex technique for developing a multiplex assay to detect autoantibody signatures against 5 canine mammary tumour-associated autoantigens (TAAs). These TAAs were expressed separately as fusion proteins with halo tag at the N-terminus, which allows easy and specific covalent coupling with magnetic microspheres. The multiplex assay, comprising a panel of candidate autoantigens (TPI, PGAM1, MNSOD, CMYC & MUC1) was used for screening circulating autoantibodies in 125 dog sera samples, including 75 mammary tumour sera and 50 healthy dog sera. The area under curve (AUC) of the combined panel of biomarkers is 0.931 (p < 0.0001), which validates the discriminative potential of the panel in differentiating tumour patients from healthy controls. The assay could be conducted in 3hrs using only 1ul of serum sample and could detect clinical cases of canine mammary tumour with sensitivity and specificity of 78.6% and 90%, respectively. In this study, we report for the first time a multiplexed assay for detection of autoantibodies in canine tumours, utilizing luminex technology and halo-tag coupling strategy. Further to the best of our knowledge, autoantibodies to CMYC and MUC1 have been reported for the first time in canines in this study.

Low hemolytic therapeutic peptides have gained an edge over small molecule-based medicines. However, finding low hemolytic peptides in laboratory is time-consuming, costly and necessitates the use of mammalian red blood cells. Therefore, wet-lab researchers often perform in-silico prediction to select low hemolytic peptides before proceeding with in-vitro testing. The in-silico tools available for this purpose have following limitations: (i) They do not provide predictions for peptides having N/C terminal modifications. (ii) Data is food for AI; however, datasets used to create existing tools do not contain peptide data generated over past eight years. (iii) Performance of available tools is also low. Therefore, a novel framework has been proposed in current work. Proposed framework utilizes recent dataset and uses ensemble learning technique to combine the decisions produced by bidirectional long short-term memory, bidirectional temporal convolutional network, and 1-dimensional convolutional neural network deep learning algorithms. Deep learning algorithms are capable of extracting features themselves from data. However, instead of relying solely on deep learning-based features (DLF), handcrafted features (HCF) were also provided so that deep learning algorithms can learn features that are missing from HCF, and a better feature vector can be constructed by concatenating HCF and DLF. Additionally, ablation studies were carried out to understand the roles of an ensemble algorithm, HCF, and DLF in the proposed framework. Ablation studies found that the ensemble algorithm, HCF and DLF are crucial components of proposed framework, and there is a decrease in performance on eliminating any of them. Mean value of performance metrics, namely $A_{cc}$ , $S_{n}$ , $P_{r}$ , $F_{s}$ , $S_{p}$ , $B_{a}$ , and $M{cc}$ obtained by proposed framework for test data is $\approx$ 87, 85, 86, 86, 88, 87, and 73, respectively. To aid scientific community, model developed from proposed framework has been deployed as a web server at https://endl-hemolyt.anvil.app/ .