# Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images

arXiv: https://arxiv.org/abs/1710.03778 · HTML: https://mlsanity.com/paper/1710.03778/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2017.

## Built on by (most cited first, 18 of 18)

- [AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultrasound Images](https://mlsanity.com/paper/2204.12077/) (2022)
- [Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation](https://mlsanity.com/paper/2209.07193/) (2022)
- [M2SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation](https://mlsanity.com/paper/2303.10894/) (2023)
- [Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation](https://mlsanity.com/paper/2101.09321/) (2021)
- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction](https://mlsanity.com/paper/2105.14773/) (2021)
- [Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images](https://mlsanity.com/paper/2108.04345/) (2021)
- [Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Images](https://mlsanity.com/paper/2306.06982/) (2023)
- [A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images](https://mlsanity.com/paper/2109.14919/) (2021)
- [Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images](https://mlsanity.com/paper/2402.13778/) (2024)
- [Learning a Clinically-Relevant Concept Bottleneck for Lesion Detection in Breast Ultrasound](https://mlsanity.com/paper/2407.00267/) (2024)
- [Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound](https://mlsanity.com/paper/2503.20685/) (2025)
- [Improving Segmentation and Detection of Lesions in CT Scans Using Intensity Distribution Supervision](https://mlsanity.com/paper/2307.05804/) (2023)
- [LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillation](https://mlsanity.com/paper/2311.11086/) (2023)
- [U-Net-and-a-half: Convolutional network for biomedical image segmentation using multiple expert-driven annotations](https://mlsanity.com/paper/2108.04658/) (2021)
- [Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Tool Segmentation in Robot-Assisted Cardiovascular Catheterization](https://mlsanity.com/paper/2404.07594/) (2024)
- [Joint localization and classification of breast tumors on ultrasound images using a novel auxiliary attention-based framework](https://mlsanity.com/paper/2210.05762/) (2022)
- [Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey](https://mlsanity.com/paper/2504.11588/) (2025)

## Abstract (arXiv)

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.