Image Descriptors for Weakly Annotated Histopathological Breast Cancer Data

Abstract

Introduction: Cancerous Tissue Recognition (CTR) methodologies are continuously integrating advancements at the forefront of machine learning and computer vision, providing a variety of inference schemes for histopathological data. Histopathological data, in most cases, come in the form of high-resolution images, and thus methodologies operating at the patch level are more computationally attractive. Such methodologies capitalize on pixel level annotations (tissue delineations) from expert pathologists, which are then used to derive labels at the patch level. In this work, we envision a digital connected health system that augments the capabilities of the clinicians by providing powerful feature descriptors that may describe malignant regions.Material and Methods: We start with a patch level descriptor, termed Covariance-Kernel Descriptor (CKD), capable of compactly describing tissue architectures associated with carcinomas. To leverage the recognition capability of the CKDs to larger slide regions, we resort to a multiple instance learning framework. In that direction, we derive the Weakly Annotated Image Descriptor (WAID) as the parameters of classifier decision boundaries in a Multiple Instance Learning framework. The WAID is computed on bags of patches corresponding to larger image regions for which binary labels (malignant vs. benign) are provided, thus obviating the necessity for tissue delineations.Results: The CKD was seen to outperform all the considered descriptors, reaching classification accuracy (ACC) of 92.83%. and area under the curve (AUC) of 0.98. The CKD captures higher order correlations between features and was shown to achieve superior performance against a large collection of computer vision features on a private breast cancer dataset. The WAID outperform all other descriptors on the Breast Cancer Histopathological database (BreakHis) where correctly classified malignant (CCM) instances reached 91.27 and 92.00% at the patient and image level, respectively, without resorting to a deep learning scheme achieves state-of-the-art performance.Discussion: Our proposed derivation of the CKD and WAID can help medical experts accomplish their work accurately and faster than the current state-of-the-art.

A critical review of the role of technology and context in digital health research

“…The fourth-largest group, accounting for 14% of the articles, represents the computational view, focusing on the processing capabilities of the technology. For example, Stanitsas et al 34 envision the augmentation of clinicians’ capabilities to describe malignant regions in breast cancer image data. While mammography is widespread in use, interpreting images based on manually segmenting data to consider whether a lesion is cancerous or not remains time-consuming.…”

“…Computer-aided diagnostics has the potential to assist medical experts in doing their job more efficiently and supporting them in their most recurrent tasks, resulting in faster diagnostics. In their research, Stanitsas et al 34 suggest the Covariance-Kernel Descriptor (CKD) and derive the Weakly Annotated Image Descriptor (WAID). They show how CKD outperforms other descriptors and how WAID outperforms other descriptors using the Breast Cancer Histopathological database (BreakHis) in terms of classification accuracy.…”

Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning

“… CMTHis [ 37 ] ⇒ The CMTHis (Canine Mammary Tumor Histopathological Image) [ 37 ] dataset comprises 352 images acquired from 44 clinical cases of canine mammary tumors. FABCD [ 133 ] ⇒ The FABCD (Fully Annotated Breast Cancer Database) [ 133 ] consists of 21 annotated images of carcinomas and 19 images of benign tissue taken from 21 patients [ 130 ]. IICBU2008 [ 87 ] ⇒ The IICBU2008 (Image Informatics and Computational Biology Unit) malignant lymphoma dataset contains 374 H&E stained microscopy images captured using bright field microscopy [ 21 ].…”

“…FABCD [ 133 ] ⇒ The FABCD (Fully Annotated Breast Cancer Database) [ 133 ] consists of 21 annotated images of carcinomas and 19 images of benign tissue taken from 21 patients [ 130 ].…”

“…and DenseNet [67] BreaKHis [33], ICIAR2018 [78], PCam [121], Bioimaging2015 [122] 8594 87 [130] To visualize a health system for clinicians Employed region covariance [131], SVM, multiple instance learning [132] FABCD [133], BreaKHis [33] 7949 70…”