Extraction of medically interpretable features for classification of malignancy in breast thermography

Abstract

Thermography, with high-resolution cameras, is being re-investigated as a possible breast cancer screening imaging modality, as it does not have the harmful radiation effects of mammography. This paper focuses on automatic extraction of medically interpretable non-vascular thermal features. We design these features to differentiate malignancy from different non-malignancy conditions, including hormone sensitive tissues and certain benign conditions, which have an increased thermal response. These features increase the specificity for breast cancer screening, which had been a long known problem in thermographic screening, while retaining high sensitivity. These features are also agnostic to different cameras and resolutions (up to an extent). On a dataset of around 78 subjects with cancer and 187 subjects without cancer, that have some benign diseases and conditions with thermal responses, we are able to get around 99% specificity while having 100% sensitivity. This indicates a potential break-through in thermographic screening for breast cancer. This shows promise for undertaking a comparison to mammography with larger numbers of subjects with more data variations.

Breast Cancer Identification via Thermography Image Segmentation with a Gradient Vector Flow and a Convolutional Neural Network

“…Next, we review related papers on thermographic breast image classification [1,3,4,6,[20][21][22][23][24][25][26][27][28][29][30], which is the topic of our work. Two different kinds of neural network classifiers have been compared: a feedforward neural network and a radial basis function classifier [20].…”

A Survey on Computer Vision for Assistive Medical Diagnosis From Faces

“…Indeed, not only the thermal-print provides information on the shape of the face [21], but also multiple contributing thermal factors can be assessed (e.g., blood flow, cell metabolism, sweat gland activation), causing local changes in superficial skin temperature. More specifically, different reasons such as inflammatory processes [22], fever [23], [24], cancers [25]or even medications [26] can be responsible for changes in the skin temperature. Due to the increase of thermal camera accuracy and resolution [27], research has been performed lately to evaluate how much information the distribution of heat in the face can provide.…”

Advances in Breast Thermography

“…Computer algorithms based on artificial intelligence and machine learning are making huge inroads in automated diagnostics [38]. Many methods of supervised classification are being developed where a small group of patient data is used to train a probabilistic model that represents the decision criteria based on the extracted features.…”

“…Niramai Thermalytix software is one such advanced software tool with a technology that enables end-to-end fully automated approach for the diagnosis [38][39][40]. The Niramai tool uses complex computer algorithms for the following five key aspects of automated diagnostics.…”

“…The heat patterns found in the thermal images are then analyzed for specific tumor properties. Tumor-specific patterns include multiple important thermal patterns or features that typically help in discriminating malignancy versus benign conditions [38].…”