Breast Tumor Tissue Segmentation with Area-Based Annotation Using Convolutional Neural Network

Abstract

In this paper, we propose a novel approach to segment tumor and normal regions in human breast tissues. Cancer is the second most common cause of death in our society; every eighth woman will be diagnosed with breast cancer in her life. Histological diagnosis is key in the process where oncotherapy is administered. Due to the time-consuming analysis and the lack of specialists alike, obtaining a timely diagnosis is often a difficult process in healthcare institutions, so there is an urgent need for improvement in diagnostics. To reduce costs and speed up the process, an automated algorithm could aid routine diagnostics. We propose an area-based annotation approach generalized by a new rule template to accurately solve high-resolution biological segmentation tasks in a time-efficient way. These algorithm and implementation rules provide an alternative solution for pathologists to make decisions as accurate as manually. This research is based on an individual database from Semmelweis University, containing 291 high-resolution, bright field microscopy breast tumor tissue images. A total of 70% of the 128 × 128-pixel resolution images (206,174 patches) were used for training a convolutional neural network to learn the features of normal and tumor tissue samples. The evaluation of the small regions results in high-resolution histopathological image segmentation; the optimal parameters were calculated on the validation dataset (29 images, 10%), considering the accuracy and time factor as well. The algorithm was tested on the test dataset (61 images, 20%), reaching a 99.10% f1 score on pixel level evaluation within 3 min on average. Besides the quantitative analyses, the system’s accuracy was measured qualitatively by a histopathologist, who confirmed that the algorithm was also accurate in regions not annotated before.

An AI-based cell segmentation pipeline for studying immune markers from brightfield microscopy images

“…There are several methods which classify areas of whole slide images into different categories. These methods use convolutional neural networks (CNNs) for classifying areas in tumor and other areas in lung and breast tissue [5,14,15]. Software packages like the HALO image analysis software (Indica Labs, Albuquerque, US) and cellprofiler [16] are gold standard and allow analysis of microscopy images with manual setting of parameter according to the image.…”

Rotationally Adjustable Hyperthermia Applicators: A Computational Comparative Study of Circular and Linear Array Applicators

“…MH has been used to increase the effectiveness of other cancer therapies such as radiotherapy or chemotherapy, as well as a sole treatment technique [ 3 ]. The steps of proper hyperthermia treatment planning (HTP) can be summarized as follows: After the patient is diagnosed with a malignant tumor, detailed imaging of the body part is obtained and the tissues are segmented [ 4 , 5 ]. Next, the accurate microwave dielectric and thermal properties of the tissues are assigned to each tissue type [ 6 , 7 , 8 , 9 , 10 ].…”