Alessandro Bruno - Faculty of Media and Communication, Department - NCCA (National Centre for Computer Animation) at Bournemouth University, Poole, Dorset, United Kingdom
Edoardo Ardizzone - Department of Engineering at Palermo University
Salvatore Vitabile - Department of Biomedicine, Neuroscience and Advanced Diagnostic at Palermo University, Palermo, Italy
Massimo Midiri - Department of Biomedicine, Neuroscience and Advanced Diagnostic at Palermo University, Palermo, Italy

Background: Deep learning methods have become popular for their high‑performance rate in the classification and detection of events in computer vision tasks. Transfer learning paradigm is widely adopted to apply pretrained convolutional neural network (CNN) on medical domains overcoming the problem of the scarcity of public datasets. Some investigations to assess transfer learning knowledge inference abilities in the context of mammogram screening and possible combinations with unsupervised techniques are in progress. Methods: We propose a novel technique for the detection of suspicious regions in mammograms that consist of the combination of two approaches based on scale invariant feature transform (SIFT) keypoints and transfer learning with pretrained CNNs such as PyramidNet and AlexNet fine‑tuned on digital mammograms generated by different mammography devices. Preprocessing, feature extraction, and selection steps characterize the SIFT‑based method, while the deep learning network validates the candidate suspicious regions detected by the SIFT method. Results: The experiments conducted on both mini‑MIAS dataset and our new public dataset Suspicious Region Detection on Mammogram from PP (SuReMaPP) of ۳۸۴ digital mammograms exhibit high performances compared to several state‑of‑the‑art methods. Our solution reaches ۹۸% of sensitivity and ۹۰% of specificity on SuReMaPP and ۹۴% of sensitivity and ۹۱% of specificity on mini‑MIAS. Conclusions: The experimental sessions conducted so far prompt us to further investigate the powerfulness of transfer learning over different CNNs and possible combinations with unsupervised techniques. Transfer learning performances’ accuracy may decrease when the training and testing images come out from mammography devices with different properties.

Classification, computer‑assisted image processing, computing methodologies, deep learning, digital mammography