Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images
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.
Code (1)
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Self-Transfer Learning for Fully Weakly Supervised Object Localization
Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches…
Medical Image AnalysisObjectObject LocalizationTransfer Learning+2Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net
This study presents a novel deep learning architecture for multi-class classification and localization of abnormalities in medical imaging illustrated through experiments on mammograms. The proposed network combines two …
ClassificationGeneral ClassificationMulti-class ClassificationWeakly-supervised LearningRevisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
Despite remarkable progress, weakly supervised segmentation methods are still inferior to their fully supervised counterparts. We obverse that the performance gap mainly comes from the inability of producing dense and in…
ClassificationGeneral ClassificationObjectObject Localization+4Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produ…
ObjectObject LocalizationSegmentationSemantic Segmentation+2FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localizatio…
image-classificationImage ClassificationImage SegmentationSemantic Segmentation+1