Convolutional neural network (CNN) classification of breast cancer in optical coherence tomography (OCT) images

摘要

The purpose of this study was to develop and evaluate the performance of a convolutional neural network (CNN)that uses a novel A-line based classification approach to detect cancer in OCT images of breast specimens. Deep learningalgorithms have been developed for OCT ophthalmology applications using pixel-based classification approaches. In thisstudy, a novel deep learning approach was developed that classifies OCT images of breast tissue.De-identified human breast tissues from mastectomy and breast reduction specimens were excised from patientsat Columbia University Medical Center. A total of 82 specimens from 49 patients were imaged with OCT, including bothnormal tissues and non-neoplastic tissues.The proposed algorithm utilized a hybrid 2D/1D convolutional neural network (CNN) to map each single B-scanto a 1D label vector, which were derived from manual annotation. Each A-line was labelled as one of the following tissuetypes: ductal carcinoma in situ (DCIS), invasive ductal carcinoma (IDC), adipose, and stroma.Five-fold cross-validation Dice scores across tissue types were: 0.82-0.95 for IDC, 0.54-0.75 for DCIS, 0.67-0.91for adipose, and 0.61-0.86 for stroma. In a second experiment, IDC and DCIS were combined as a single tissue class(malignancy) while stroma and adipose were combined as a second tissue class (non-malignancy). In this setup, theexperiment yielded five-fold cross-validation Dice scores between 0.89-0.93, respectively.Future work includes acquiring more patient samples and to compare the algorithm to previous works,including both deep learning and traditional automatic image processing methods for classification of breast tissue inOCT images.