Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

Wu, Nan; Phang, Jason; Park, Jungkyu; Shen, Yiqiu; Huang, Zhe; Zorin, Masha; Jastrzębski, Stanisław; Févry, Thibault; Katsnelson, Joe; Kim, Eric; Wolfson, S. Sabina; Parikh, Ujas; Gaddam, Sushma; Lin, Leng Leng Young; Ho, Kara; Weinstein, Joshua D.; Reig, Beatriu; Gao, Yiming; Toth, Hildegard K.; Pysarenko, Kristine; Lewin, Alan A.; Lee, Jiyon; Airola, Krystal; Mema, Eralda; Chung, Sung‐Kee; Hwang, Esther; Samreen, Naziya; Kim, S. Gene; Heacock, Laura; Moy, Linda; Cho, Kyunghyun; Geras, Krzysztof J.

doi:10.48550/arxiv.1903.08297

Cited by 9 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• The proposed model is able to localize breast lesions in a weakly supervised manner, unlike existing approaches that rely on pixel-level lesion annotations (Ribli et al, 2018;Févry et al, 2019;Wu et al, 2019b). In Section 3.5, we demonstrate that the regions highlighted by the saliency maps indeed correlate with the objects of interest.…”

Section: Introductionmentioning

confidence: 84%

“…Generating the Saliency Maps. To process high-resolution images while keeping GPU memory consumption manageable, we parameterize f g as a ResNet-22 (Wu et al, 2019b) whose architecture is shown in Figure 2. In comparison to canonical ResNet architectures (He et al, 2016a), ResNet-22 has one more residual block and only a quarter of the filters in each convolution layer.…”

Section: Model Parameterizaitonmentioning

confidence: 99%

“…We trained and tested our model on the NYU Breast Cancer Screening Dataset consisting of 229,426 high-resolution screening mammograms (Wu et al, 2019c). On a held-out test set of 14,148 exams, GMIC achieves an AUC of 0.93 in identifying breasts with malignant findings, outperforming baseline approaches including ResNet-34 (He et al, 2016a), Faster R-CNN (Févry et al, 2019) and DMV-CNN (Wu et al, 2019b).…”

Section: Introductionmentioning

confidence: 99%

“…sis of screening mammography (Zhu et al, 2017;Kim et al, 2018;Kyono et al, 2018;Ribli et al, 2018;Wu et al, 2019b;McKinney et al, 2020). An overwhelming majority of existing studies on this task utilize models that were originally designed for natural images.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

Shen¹,

Wu²,

Phang³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a final prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, consisting of more than one million images, our model achieves an AUC of 0.93 in classifying breasts with malignant findings, outperforming ResNet-34 and Faster R-CNN. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11. The proposed model is available online.This paper is an extension of work originally presented at the 10th International Workshop on Machine Learning in Medical Imaging (Shen et al., 2019).mammogram per the American College of Radiology Breast Imaging Reporting and Data System (BI-RADS), with specific follow-up recommendations for each category (Liberman and Menell, 2002).Screening mammography interpretation is a particularly challenging task because mammograms are in very high resolutions while most asymptomatic cancer lesions are small, sparsely distributed over the breast and may present as subtle changes in the breast tissue pattern. While randomized clinical trials have shown that screening mammography has significantly reduced breast cancer mortality (Duffy et al., 2002;Kopans, 2002), it is associated with limitations such as false positive recalls for additional imaging and subsequent false positive biopsies which result in benign, non-cancerous findings. About 10% to 20% of women who have an abnormal screening mammogram are recommended to undergo a biopsy. Only 20% to 40% of these biopsies yield a diagnosis of cancer (Kopans, 2015).To tackle these limitations, convolutional neural networks (CNN) have been applied to assist radiologists in the analy-

show abstract

Section: Introductionmentioning

confidence: 84%

Section: Model Parameterizaitonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

Shen¹,

Wu²,

Phang³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Breast cancer is the second leading cause of cancer-related deaths among women (Bray et al, 2018) and screening mammography is the main tool for its early detection (Marmot et al, 2013). CNN classifiers have shown promise in diagnosis from mammograms (Zhu et al, 2017;Kim et al, 2018;Ribli et al, 2018;Wu et al, 2019b;McKinney et al, 2020;Shen et al, 2019Shen et al, , 2021. Accurate localization of suspicious lesions is crucial to aid clinicians in interpreting model outputs, and can provide guidance for future diagnostic procedures.…”

Section: Introductionmentioning

confidence: 99%

Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis

Liu,

Shen,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the last few years, deep learning classifiers have shown promising results in image-based medical diagnosis. However, interpreting the outputs of these models remains a challenge. In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output, i.e. the location of a lesion. Alternatively, segmentation or detection models can be trained with pixel-wise annotations indicating the locations of malignant lesions. Unfortunately, acquiring such labels is labor-intensive and requires medical expertise. To overcome this difficulty, weaklysupervised localization can be utilized. These methods allow neural network classifiers to output saliency maps highlighting the regions of the input most relevant to the classification task (e.g. malignant lesions in mammograms) using only image-level labels (e.g. whether the patient has cancer or not) during training. When applied to high-resolution images, existing methods produce lowresolution saliency maps. This is problematic in applications in which suspicious lesions are small in relation to the image size. In this work, we introduce a novel neural network architecture to perform weakly-supervised segmentation of high-resolution images. The proposed model selects regions of interest via coarse-level localization, and then performs fine-grained segmentation of those regions. We apply this model to breast cancer diagnosis with screening mammography, and validate it on a large clinically-realistic dataset. Measured by Dice similarity score, our approach outperforms existing methods by a large margin in terms of localization performance of benign and malignant lesions, relatively improving the performance by 39.6% and 20.0%, respectively. Code and the weights of some of the models are available at https://github.com/nyukat/GLAM.

show abstract

Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

Shen

Phang

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.

show abstract

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

Cited by 9 publications

References 0 publications

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis

Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

Contact Info

Product

Resources

About