Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules

Feng, Xinyang; Yang, Jie; Laine, Andrew F.; Angelini, Elsa D.

doi:10.1007/978-3-319-66179-7_65

Cited by 133 publications

(101 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Their average IOU improvement across different tests over the baseline of just using CAM is 20%. Feng et al (2017) propose a 2-stage approach consisting of a coarse image segmentation followed by a fine instance-level segmentation. The first stage makes use of CAM via an image classification model, which learns whether a slice has a nodule or not.…”

Section: Image Level Labelsmentioning

confidence: 99%

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Tajbakhsh¹,

Jeyaseelan²,

Li³

et al. 2020

Medical Image Analysis

731

358

View full text Add to dashboard Cite

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire. Recently, a large body of research has studied the problem of medical image segmentation with imperfect datasets, tackling two major dataset limitations: scarce annotations where only limited annotated data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations. In this article, we provide a detailed review of the solutions above, summarizing both the technical novelties and empirical results. We further compare the benefits and requirements of the surveyed methodologies and provide our recommended solutions to the problems of scarce and weak annotations. We hope this review increases the community awareness of the techniques to handle imperfect datasets.

show abstract

Section: Image Level Labelsmentioning

confidence: 99%

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Tajbakhsh¹,

Jeyaseelan²,

Li³

et al. 2020

Medical Image Analysis

731

358

View full text Add to dashboard Cite

show abstract

“…One interesting observation is that the [35,40), [40,45) are the two age bins with fewest number of subjects, so we use the number of subjects in this age segment as the base level and allow repeated scans from same subjects. The other age bins having multiple scans per subject are the two age bins at the tail end: [85, 90) and [90, 100], because of the relative lower number in these two age bins.…”

Section: Study Populationmentioning

confidence: 99%

“…Class activation mapping [38,39] is a commonly-used method for interpreting the classification using CNNs and has been previously used in CNN based medical image analysis [40] to marry potential disease pathology with classification findings. In this work, we use the idea of a class activation map in a regression setting by highlighting the small-valued gradient in grad-CAM framework.…”

Section: Age Activation Mapmentioning

confidence: 99%

Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging

Feng

Lipton

Yang

et al. 2020

Neurobiology of Aging

Self Cite

View full text Add to dashboard Cite

Numerous studies have established that estimated brain age, as derived from statistical models trained on healthy populations, constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases. In this work, we curate a large-scale heterogeneous dataset (N = 10,158, age range 18 -97) of structural brain MRIs in a healthy population from multiple publiclyavailable sources, upon which we train a deep learning model for brain age estimation. The availability of the large-scale dataset enables a more uniform age distribution across adult life-span for effective age estimation with no bias toward certain age groups. We demonstrate that the age estimation accuracy, evaluated with mean absolute error (MAE) and correlation coefficient (r ), outperforms previously reported methods in both a hold-out test set reflective of the custom population (MAE = 4.06 years, r = 0.970) and an independent life-span evaluation dataset (MAE = 4.21 years, r = 0.960) on which a previous study has evaluated. We further demonstrate the utility of the estimated age in life-span aging analysis of cognitive functions. Furthermore, we conduct extensive ablation tests and employ feature-attribution techniques to analyze which regions contribute the most predictive value, demonstrating the prominence of the frontal lobe as well as pattern shift across life-span.In summary, we achieve superior age estimation performance confirming the efficacy of deep learning and the added utility of training with data both in larger number and more uniformly distributed than in previous studies. We demonstrate the regional contribution to our brain age predictions through multiple routes and confirm the association of divergence between estimated and chronological brain age with neuropsychological measures. OASIS-1 Open Access Series of ImagingStudies-1 https://www.oasis-brains.org OASIS-2 Open Access Series of Imaging Studies-2 https://www.oasis-brains.org SALD Southwest University Adult life-span Dataset http://fcon_1000.projects.nitrc.org/indi/retro/sald.html SLIM Southwest University Longitudinal Imaging Multimodal Brain Data Repository http://fcon_1000.projects.nitrc.org/indi/retro/southwestuni_qiu_index.html PPMI Parkinson's Progression Markers Initiative SchizConnect SchizConnect http://schizconnect.org/ DLBS Dallas life-span Brain Study

show abstract

“…Such ROI localisation is important for explaining the classification made by the CAD system in clinical settings (e.g., for a scan classified as malignant, doctors are likely to know where the lesions are located). Solving this lesion localisation problem is a research problem that is being actively investigated in the field (Dubost et al, 2017;Feng et al, 2017;Maicas et al, 2018b;Wang et al, 2017b;Yang et al, 2017). The approach proposed by Maicas et al (2018b) achieves SOTA detection performance by properly defining saliency for the problem of weakly supervised lesion localisation, which assures that salient regions represent malignant lesions in the image.…”

Section: Post-hoc Approachesmentioning

confidence: 99%

Pre and post-hoc diagnosis and interpretation of malignancy from breast DCE-MRI

Maicas

Bradley

Nascimento

et al. 2019

Medical Image Analysis

View full text Add to dashboard Cite

We propose a new method for breast cancer screening from DCE-MRI based on a post-hoc approach that is trained using weakly annotated data (i.e., labels are available only at the image level without any lesion delineation). Our proposed post-hoc method automatically diagnosis the whole volume and, for positive cases, it localizes the malignant lesions that led to such diagnosis. Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy -this approach is trained using strongly annotated data (i.e., it needs a delineation and classification of all lesions in an image). Another goal of this paper is to establish the advantages and disadvantages of both approaches when applied to breast screening from DCE-MRI. Relying on experiments on a breast DCE-MRI dataset that contains scans of 117 patients, our results show that the post-hoc method is more accurate for diagnosing the whole volume per patient, achieving an AUC of 0.91, while the pre-hoc method achieves an AUC of 0.81. However, the performance for localising the malignant lesions remains challenging for the post-hoc method due to the weakly labelled dataset employed during training.

show abstract

Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules

Cited by 133 publications

References 14 publications

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging

Pre and post-hoc diagnosis and interpretation of malignancy from breast DCE-MRI

Contact Info

Product

Resources

About