Breast Tumor Cellularity Assessment using Deep Neural Networks

Abstract

Breast cancer is one of the main causes of death worldwide. Histopathological cellularity assessment of residual tumors in post-surgical tissues is used to analyze a tumor's response to a therapy. Correct cellularity assessment increases the chances of getting an appropriate treatment and facilitates the patient's survival. In current clinical practice, tumor cellularity is manually estimated by pathologists; this process is tedious and prone to errors or low agreement rates between assessors. In this work, we evaluated three strong novel Deep Learning-based approaches for automatic assessment of tumor cellularity from posttreated breast surgical specimens stained with hematoxylin and eosin. We validated the proposed methods on the BreastPathQ SPIE challenge dataset that consisted of 2395 image patches selected from whole slide images acquired from 64 patients. Compared to expert pathologist scoring, our best performing method yielded the Cohen's kappa coefficient of 0.70 (vs. 0.42 previously known in literature) and the intra-class correlation coefficient of 0.89 (vs. 0.83). Our results suggest that Deep Learning-based methods have a significant potential to alleviate the burden on pathologists, enhance the diagnostic workflow, and, thereby, facilitate better clinical outcomes in breast cancer treatment.

Obtaining spatially resolved tumor purity maps using deep multiple instance learning in a pan-cancer study

“…68,69 Furthermore, they can enhance spatial-omics technologies. [70][71][72][73] Weak tumor purity labels innately necessitated an MIL approach Previous studies based on patch-based models worked on few cancer types with relatively few patients (like 10 patients 46 or 64 patients 47,48 ) since they required pixel-level annotations (rarely available). However, using genomic tumor purity values as sample-level weak labels enabled us to conduct a pan-cancer study on 10 different TCGA cohorts, where each cohort had more than 400 patients.…”

“…The patchbased models require pathologists' pixel-level annotations showing whether each pixel is cancerous or normal. Although different studies employed this approach for tumor purity prediction, [44][45][46][47][48][49] they had limited coverage since pixel-level annotations are rarely available, expensive, and tedious. On the other hand, the MIL models do not require pixel-level annotations.…”

3D Convolutional Neural Networks for Stalled Brain Capillary Detection

“…Backbones pre-trained on Imagenet [34] have demonstrated great results for transfer learning into a different domain with increased accuracy and/or faster convergence [35], including applications to medical image analysis [13][14][15][16]. To leverage pre-training on massive 2D image datasets for 3D image analysis, we developed a method for weight transfer from 2D to 3D CNNs.…”

“…For 3D ResNet18 it has dimensions of (10, 13, 13, 512), i.e. 512 feature volumes with shapes (10,13,13) that transform into a 1D vector of 512 values after 3D global max pooling.…”

“…This creates an opportunity to use the crowdsourced annotations for training deep learning models, which rely on the availability of large labeled datasets [11]. Specifically, the growing availability of annotated data has recently enabled efficient applications of deep learning to the analysis of biomedical images [12], demonstrating state-of-the-art results in object detection, segmentation, and classification [13][14][15][16]. In multiphoton microscopic images, deep learning have been recently used for segmenting blood vessels [8,17] and segmenting and classifying cancer cells [18][19][20].…”