Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs

Kandemir, Melih; Zhang, Chong; Hamprecht, Fred A.

doi:10.1007/978-3-319-10470-6_29

Cited by 47 publications

(55 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…26 images are diagnosed as malignant, 32 as benign. For a fair comparison we used the feature sets made publicly available 1 by Kandemir et al [10]. Each image was divided into 49 equally-sized instances.…”

Section: Breast Cancer Tma Imagesmentioning

confidence: 99%

“…Since instance location information is not available in the feature set, we focus on image-level performance evaluation. We follow the 4-fold cross validation protocol used in [10]. For the proposed method we first applied the set cover search with m = 20.…”

Section: Breast Cancer Tma Imagesmentioning

confidence: 99%

“…Multiple instance learning (MIL) has recently been applied to histopathology image analysis for both segmentation and classification tasks [10,16]. While training a tumour detector usually requires a large amount of high quality manual annotation [1], MIL methods can potentially infer tumour regions with image-level annotation, i.e., binary labels indicating whether tumour is present in the image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Instance Cancer Detection by Boosting Regularised Trees

Zhang

McKenna

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we first search a set of region-level prototypes by solving a submodular set cover problem. Regularised regression trees are then constructed and combined on the set of prototypes using a multiple instance boosting framework. The method compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.

show abstract

Section: Breast Cancer Tma Imagesmentioning

confidence: 99%

Section: Breast Cancer Tma Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Instance Cancer Detection by Boosting Regularised Trees

Zhang

McKenna

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…A two-stage Expectation Maximization based algorithm combined with a deep convolutional neural network (CNN) works well to classify instances on multiple medical datasets [5]. In Kandemir et al's work [7], a Gaussian process with relational learning is introduced to exploit the similarity between instances of Barretts cancer dataset. To relate the instances and the bags, different permutation-invariant pooling approaches with CNN have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Deep Instance-Level Hard Negative Mining Model for Histopathology Images

Wiliem

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i.e., patches) and the task is to predict a single class label to the WSI. However, in many reallife applications such as computational pathology, discovering the key instances that trigger the bag label is of great interest because it provides reasons for the decision made by the system. In this paper, we propose a deep convolutional neural network (CNN) model that addresses the primary task of a bag classification on a histopathology image and also learns to identify the response of each instance to provide interpretable results to the final prediction. We incorporate the attention mechanism into the proposed model to operate the transformation of instances and learn attention weights to allow us to find key patches. To perform a balanced training, we introduce adaptive weighing in each training bag to explicitly adjust the weight distribution in order to concentrate more on the contribution of hard samples. Based on the learned attention weights, we further develop a solution to boost the classification performance by generating the bags with hard negative instances. We conduct extensive experiments on colon and breast cancer histopathology data and show that our framework achieves state-of-the-art performance.

show abstract

“…With these extracted descriptors, supervised classification models such as support vector machine (SVM) [12, 13, 18, 19, 22–24, 27, 29, 31], subspace learning [10, 11, 14–16, 26], multiple instance learning [17, 25] and sparse representation [21, 32] are applied. However, the classification performance is often largely affected by the small number of training data available for bioimage research.…”

Section: Introductionmentioning

confidence: 99%

Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors

et al. 2016

View full text Add to dashboard Cite

BackgroundBioimage classification is a fundamental problem for many important biological studies that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new bioimage classification method that can be generally applicable to a wide variety of classification problems. We propose to use a high-dimensional multi-modal descriptor that combines multiple texture features. We also design a novel subcategory discriminant transform (SDT) algorithm to further enhance the discriminative power of descriptors by learning convolution kernels to reduce the within-class variation and increase the between-class difference.ResultsWe evaluate our method on eight different bioimage classification tasks using the publicly available IICBU 2008 database. Each task comprises a separate dataset, and the collection represents typical subcellular, cellular, and tissue level classification problems. Our method demonstrates improved classification accuracy (0.9 to 9%) on six tasks when compared to state-of-the-art approaches. We also find that SDT outperforms the well-known dimension reduction techniques, with for example 0.2 to 13% improvement over linear discriminant analysis.ConclusionsWe present a general bioimage classification method, which comprises a highly descriptive visual feature representation and a learning-based discriminative feature transformation algorithm. Our evaluation on the IICBU 2008 database demonstrates improved performance over the state-of-the-art for six different classification tasks.

show abstract

Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs

Cited by 47 publications

References 3 publications

Multiple Instance Cancer Detection by Boosting Regularised Trees

Multiple Instance Cancer Detection by Boosting Regularised Trees

Deep Instance-Level Hard Negative Mining Model for Histopathology Images

Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors

Contact Info

Product

Resources

About