Zabit Hameed

Breast cancer is a common malignancy and a leading cause of cancer-related deaths in women worldwide. Its early diagnosis can significantly reduce the morbidity and mortality rates in women. To this end, histopathological diagnosis is usually followed as the gold standard approach. However, this process is tedious, labor-intensive, and may be subject to inter-reader variability. Accordingly, an automatic diagnostic system can assist to improve the quality of diagnosis. This paper presents a deep learning approach to automatically classify hematoxylin-eosin-stained breast cancer microscopy images into normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma using our collected dataset. Our proposed model exploited six intermediate layers of the Xception (Extreme Inception) network to retrieve robust and abstract features from input images. First, we optimized the proposed model on the original (unnormalized) dataset using 5-fold cross-validation. Then, we investigated its performance on four normalized datasets resulting from Reinhard, Ruifrok, Macenko, and Vahadane stain normalization. For original images, our proposed framework yielded an accuracy of 98% along with a kappa score of 0.969. Also, it achieved an average AUC-ROC score of 0.998 as well as a mean AUC-PR value of 0.995. Specifically, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. For normalized images, the proposed architecture performed better for Makenko normalization compared to the other three techniques. In this case, the proposed model achieved an accuracy of 97.79% together with a kappa score of 0.965. Also, it attained an average AUC-ROC score of 0.997 and a mean AUC-PR value of 0.991. Especially, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. These results demonstrate that our proposed model outperformed the baseline AlexNet as well as state-of-the-art VGG16, VGG19, Inception-v3, and Xception models with their default settings. Furthermore, it can be inferred that although stain normalization techniques offered competitive performance, they could not surpass the results of the original dataset.

This paper presents a comparably simpler yet effective deep learning approach for sentiment analysis of Twitter topics. We automatically collected positive and negative tweets and labeled them manually, and thus created a new dataset. We then leveraged BiGRU model with an ensemble approach for the binary classification of tweets. Our finalized BiGRU model offered an accuracy of 84.8% as well as an averaged F1-measure of 84.8%(±0.3). Moreover, the ensemble approach, using an averaged prediction of 5-fold strategy, provided the accuracy of 86.3% along with the averaged F1-measure of 86.3%(±0.05). Consequently, the ensemble approach offered better performance even on a smaller dataset used in this study.

This study presents a computationally efficient deep learning model for binary sentiment classification, which aims to decide the sentiment polarity of people’s opinions, attitudes, and emotions expressed in written text. To achieve this, we exploited three widely practiced datasets based on public opinions about movies.We utilized merely one bidirectional long short-term memory (BiLSTM) layer along with a global pooling mechanism and achieved an accuracy of 80.500%, 85.780%, and 90.585% on MR, SST2 and IMDb datasets, respectively.We concluded that the performance metrics of our proposed approach are competitive with the recently published models, having comparatively complex architectures. Also, it is inferred that the proposed single-layered BiLSTM based architecture is computationally efficient and can be recommended for the real-time applications in the field of sentiment analysis.

Sentiment analysis is a crucial task in natural language processing (NLP), aiming at the extraction of opinions expressed in the texts. This paper aims at a computationally efficient approach for the classification of positive and negative sentiments by using publicly available datasets about movie reviews, namely, Movie Review (MR) and Stanford Sentiment Tree (SST2) datasets. We exploited merely one bidirectional long short-term memory (BiLSTM) layer with a global maximum pooling layer and got F1 scores of 85.78 and 80.21 for SST2 and MR datasets, respectively. We concluded that our results are competitive with recently published methods with complex architectures. Also, our approach requires minimal computational cost and thus may help in real-time applications in general opinion categorization.

Epilepsy is a brain disorder characterised by the recurrent and unpredictable interruptions of normal brain function, called epileptic seizures. The present study attempts to derive new diagnostic indices which may delineate between ictal and interictal states of epilepsy. To achieve this, the nonlinear modeling approach of global principal dynamic modes (PDMs) is adopted to examine the functional connectivity of the temporal and frontal lobes with the occipital brain segment using an ensemble of paediatric EEGs having the presence of epileptic seizure. The distinct spectral characteristics of global PDMs are found to be in line with the neural rhythms of brain dynamics. Moreover, we find that the linear trends of associated nonlinear functions (ANFs) associated with the 2nd and 4th global PDMs (representing delta, theta and alpha bands) of Fp1–F3 may differentiate between ictal and interictal states of epilepsy. These findings suggest that global PDMs and their associated ANFs may offer potential utility as diagnostic neural measures for ictal and interictal states of epilepsy.