In recent years, convolutional neural networks (CNNs) have found many applications in medical image analysis. Having enough labeled data, CNNs could be trained to learn image features and used for object localization, classification, and segmentation. Although there are many interests in building and improving automated systems for medical image analysis, lack of reliable and publicly available biomedical datasets makes such a task difficult. In this work, the effectiveness of CNNs for the classification of breast lesions in ultrasound (US) images will be studied. First, due to a limited number of training data, we use a custom-built CNN with a few hidden layers and apply regularization techniques to improve the performance. Second, we use transfer learning and adapt some pre-trained models for our dataset. The dataset used in this work consists of a limited number of cases, 641 in total, histopathologically categorized (413 benign and 228 malignant lesions). To assess how the results of our classifier generalize on our data set, a 5-fold cross-validation were employed, where in each fold 80% of data were used for training and the 20% for testing. Accuracy and the area under the ROC curve (AUC) were used as the main performance metrics. Before applying any regularizations techniques, we achieved an overall accuracy of 85.98% for tumor classification, and the AUC equal to 0.94. After applying image augmentation and regularization, the accuracy and the AUC increased to 92.05% and 0.97, respectively. Using a pre-trained model, we achieved an overall accuracy of 87.07% and an AUC equal to 0.96. The obtained results demonstrated the effectiveness of our custom architecture for classification of tumors in this small US imaging dataset, surpassing some traditional learning algorithm based on manual feature selection.

Key words: Tuberculosis; Automatic bacillus identification; Neural network; Support vector machine

Key words: Breast tumors; Breast ultrasound images; Neural network; Support vector machine

Background: Outlining lesion contours in Ultra Sound (US) breast images is an important step in breast cancer diagnosis. Malignant lesions infiltrate the surrounding tissue, generating irregular contours, with spiculation and angulated margins, whereas benign lesions produce contours with a smooth outline and elliptical shape. In breast imaging, the majority of the existing publications in the literature focus on using Convolutional Neural Networks (CNNs) for segmentation and classification of lesions in mammographic images. In this study our main objective is to assess the ability of CNNs in detecting contour irregularities in breast lesions in US images. Methods: In this study we compare the performance of two CNNs with Direct Acyclic Graph (DAG) architecture and one CNN with a series architecture for breast lesion segmentation in US images. DAG and series architectures are both feedforward networks. The difference is that a DAG architecture could have more than one path between the first layer and end layer, whereas a series architecture has only one path from the beginning layer to the end layer. The CNN architectures were evaluated with two datasets. Results: With the more complex DAG architecture, the following mean values were obtained for the metrics used to evaluate the segmented contours: global accuracy: 0.956; IOU: 0.876; F measure: 68.77%; Dice coefficient: 0.892. Conclusion: The CNN DAG architecture shows the best metric values used for quantitatively evaluating the segmented contours compared with the gold-standard contours. The segmented contours obtained with this architecture also have more details and irregularities, like the gold-standard contours.

Due to wearables’ popularity, human activity recognition (HAR) plays a significant role in people’s routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models’ decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR’s high performance with SD comes not only from physical activity learning but also from learning an individual’s signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability.

Optical coherence tomography (OCT) technology enables experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown a relationship between vascular bifurcation and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could benefit experts since the visual analysis of pullback frames is a laborious and time-consuming task. Although convolutional neural networks (CNNs) have shown promising results in classifying medical images, in this paper, we found no studies using CNNs in IVOCT images to classify the vascular bifurcation. In this paper, we evaluated four different CNN architectures in the bifurcation classification task trained with the IVOCT images from nine pullbacks from nine different patients. We used data augmentation to balance the dataset, due to the small number of bifurcation-labeled frames, and also applied transfer learning methods to incorporate the knowledge from a lumen segmentation task into some of the evaluated networks. Our classification outperforms other works in this literature, presenting AUC = 99.72%, obtained by a CNN with transferred knowledge.