We propose a framework for localization and classification of masses in breast ultrasound (BUS) images. We have experimentally found that training convolutional neural network based mass detectors with large, weakly annotated datasets presents a non-trivial problem, while overfitting may occur with those trained with small, strongly annotated datasets. To overcome these problems, we use a weakly annotated dataset together with a smaller strongly annotated dataset in a hybrid manner. We propose a systematic weakly and semi-supervised training scenario with appropriate training loss selection. Experimental results show that the proposed method can successfully localize and classify masses with less annotation effort. The results trained with only 10 strongly annotated images along with weakly annotated images were comparable to results trained from 800 strongly annotated images, with the 95% confidence interval of difference -3.00%–5.00%, in terms of the correct localization (CorLoc) measure, which is the ratio of images with intersection over union with ground truth higher than 0.5. With the same number of strongly annotated images, additional weakly annotated images can be incorporated to give a 4.5% point increase in CorLoc, from 80.00% to 84.50% (with 95% confidence intervals 76.00%–83.75% and 81.00%–88.00%). The effects of different algorithmic details and varied amount of data are presented through ablative analysis.

Despite the recent success of text detection and recognition methods, existing evaluation metrics fail to provide a fair and reliable comparison among those methods. In addition, there exists no end-to-end evaluation metric that takes characteristics of OCR tasks into account. Previous end-to-end metric contains cascaded errors from the binary scoring process applied in both detection and recognition tasks. Ignoring partially correct results raises a gap between quantitative and qualitative analysis, and prevents fine-grained assessment. Based on the fact that character is a key element of text, we hereby propose a Character-Level Evaluation metric (CLEval). In CLEval, the instance matching process handles split and merge detection cases, and the scoring process conducts character-level evaluation. By aggregating character-level scores, the CLEval metric provides a fine-grained evaluation of end-to-end results composed of the detection and recognition as well as individual evaluations for each module from the end-performance perspective. We believe that our metrics can play a key role in developing and analyzing state-of-the-art text detection and recognition methods. The evaluation code is publicly available at https://github.com/clovaai/CLEval.

Retinal artery–vein (AV) classification is a prerequisite for quantitative analysis of retinal vessels, which provides a biomarker for neurologic, cardiac, and systemic diseases, as well as ocular diseases. Although convolutional neural networks have presented remarkable performance on AV classification, it often comes with a topological error, like an abrupt class flipping on the same vessel segment or a weakness for thin vessels due to their indistinct appearances. In this paper, we present a new method for AV classification where the underlying vessel topology is estimated to give consistent prediction along the actual vessel structure. We cast the vessel topology estimation as iterative vascular connectivity prediction, which is implemented as deep-learning-based pairwise classification. In consequence, a whole vessel graph is separated into sub-trees, and each of them is classified as an artery or vein in whole via a voting scheme. The effectiveness and efficiency of the proposed method is validated by conducting experiments on two retinal image datasets acquired using different imaging techniques called DRIVE and IOSTAR.

A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve better performance. A typical architecture places detection and recognition modules into separate branches, and a RoI pooling is commonly used to let the branches share a visual feature. However, there still exists a chance of establishing a more complimentary connection between the modules when adopting recognizer that uses attention-based decoder and detector that represents spatial information of the character regions. This is possible since the two modules share a common sub-task which is to find the location of the character regions. Based on the insight, we construct a tightly coupled single pipeline model. This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage. The use of character score map helps the recognizer attend better to the character center points, and the recognition loss propagation to the detector module enhances the localization of the character regions. Also, a strengthened sharing stage allows feature rectification and boundary localization of arbitrary-shaped text regions. Extensive experiments demonstrate state-of-the-art performance in publicly available straight and curved benchmark dataset.