Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty

Belharbi, Soufiane; Rony, Jérôme; Dolz, José; Ayed, Ismail Ben; McCaffrey, Luke; Granger, Éric

doi:10.1109/tmi.2021.3123461

Cited by 43 publications

(19 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visual results are presented in Fig2, 3, 4. The long version of this work can be found in (Belharbi et al, 2022).…”

Section: Methodsmentioning

confidence: 99%

Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images

Belharbi¹,

Rony²,

Dolz³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Trained using only image class label, deep weakly supervised methods allow image classification and ROI segmentation for interpretability. Despite their success on natural images, they face several challenges over histology data where ROI are visually similar to background making models vulnerable to high pixel-wise false positives. These methods lack mechanisms for modeling explicitly non-discriminative regions which raises false-positive rates. We propose novel regularization terms, which enable the model to seek both non-discriminative and discriminative regions, while discouraging unbalanced segmentations and using only image class label. Our method is composed of two networks: a localizer that yields segmentation mask, followed by a classifier. The training loss pushes the localizer to build a segmentation mask that holds most discrimiantive regions while simultaneously modeling background regions. Comprehensive experiments 1 over two histology datasets showed the merits of our method in reducing false positives and accurately segmenting ROI.

show abstract

“…Visual results are presented in Fig2, 3, 4. The long version of this work can be found in (Belharbi et al, 2022).…”

Section: Methodsmentioning

confidence: 99%

Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images

Belharbi¹,

Rony²,

Dolz³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is also applied to reinforce the presence of background [47]. Authors in [5,4] model the presence of background in an image using the response of a classifier. Over background regions, classifier is constrained to be the most uncertain in classification due to the lack of positive evidence for the corresponding class.…”

Section: Related Workmentioning

confidence: 99%

Negative Evidence Matters in Interpretable Histology Image Classification

Belharbi¹,

Pedersoli²,

Ayed³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Using only global annotations such as the image class labels, weakly-supervised learning methods allow CNN classifiers to jointly classify an image, and yield the regions of interest associated with the predicted class. However, without any guidance at the pixel level, such methods may yield inaccurate regions. This problem is known to be more challenging with histology images than with natural ones, since objects are less salient, structures have more variations, and foreground and background regions have stronger similarities. Therefore, methods in computer vision literature for visual interpretation of CNNs may not directly apply. In this work, we propose a simple yet efficient method based on a composite loss function that leverages information from the fully negative samples, i.e. samples that do not contain positive parts. Our new loss function contains two complementary terms: the first exploits positive evidence collected from the CNN classifier, while the second leverages the fully negative samples from the training dataset. In particular, we equip a pre-trained classifier with a decoder that allows refining the regions of interest. The same classifier is exploited to collect both the positive and negative evidence at the pixel level to train the decoder. This enables to take advantages of the fully negative samples that occurs naturally in the data, without any additional supervision signals and using only the image class as supervision. Compared to several recent related methods, over the public benchmark GlaS for colon cancer and a Camelyon16 patch-based benchmark for breast cancer using three different backbones, we show the substantial improvements introduced by our method. Our results shows the benefits of using both negative and positive evidence, i.e., the one obtained from a classifier and the one naturally available in datasets. We provide an ablation study of both terms. Our code is publicly available 1 .

show abstract

“…The task of the positive patch localization, which described in the previous section is still based on the classification of patches, and it is a more challenging task to further obtain pixel-level segmentation results based on the weak labels. A few current studies (Xu et al 2019, Qu et al 2020, Belharbi et al 2021, Lerousseau et al 2020 have made attempts in this new direction, but they still face many problems such as lack of details and precision on the segmentation results. Overall, for the weakly supervised learning paradigm, how to obtain the most detailed segmentation results as possible with weak labels is another promising study direction.…”

Section: For Weakly Supervised Learning Paradigmmentioning

confidence: 99%

Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis

Qu¹,

Liu²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Histopathological images contain abundant phenotypic information and pathological patterns, which are the gold standards for disease diagnosis and essential for the prediction of patient prognosis and treatment outcome. In recent years, computer-automated analysis techniques for histopathological images have been urgently required in clinical practice, and deep learning methods represented by convolutional neural networks have gradually become the mainstream in the field of digital pathology. However, obtaining large numbers of fine-grained annotated data in this field is a very expensive and difficult task, which hinders the further development of traditional supervised algorithms based on large numbers of annotated data. More recent studies have started to liberate from the traditional supervised paradigm, and the most representative ones are the studies on weakly supervised learning paradigm based on weak annotation, semi-supervised learning paradigm based on limited annotation, and self-supervised learning paradigm based on pathological image representation learning. These new methods have led a new wave of automatic pathological image diagnosis and analysis targeted at annotation efficiency. With a survey of over 130 papers, we present a comprehensive and systematic review of the latest studies on weakly supervised learning, semi-supervised learning, and selfsupervised learning in the field of computational pathology from both technical and methodological perspectives. Finally, we present the key challenges and future trends for these techniques.

show abstract

Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty

Cited by 43 publications

References 72 publications

Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images

Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images

Negative Evidence Matters in Interpretable Histology Image Classification

Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis

Contact Info

Product

Resources

About