Automatic label‐free detection of breast cancer using nonlinear multimodal imaging and the convolutional neural network ResNet50. Issue 1 (30th December 2019)

• Record Type: Journal Article
• Authors: Ali, Nairveen; Quansah, Elsie; Köhler, Katarina; Meyer, Tobias; Schmitt, Michael; Popp, Jürgen; Niendorf, Axel; Bocklitz, Thomas
• Is Part Of: Translational biophotonics. Volume 1:Issue 1/2(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-12-30
• Subjects: breast cancer imaging -- coherent anti‐stokes Raman scattering -- computer aided diagnosis -- convolutional neural network -- deep learning -- image analysis -- nonlinear multimodal imaging -- second‐harmonic generation -- two‐photon excited fluorescence; Imaging systems in medicine -- Periodicals; Biosensors -- Optical properties -- Periodicals; Photonics -- Periodicals; Imaging systems in medicine; Photonics; Optics and Photonics; Translational Medical Research; Periodicals; Periodical; 621.365
• DOI: 10.1002/tbio.201900003
• Languages: English
• ISSNs: 2627-1850

Abstract

Abstract: Breast cancer is the main cause of all female cancer deaths worldwide. Because of the lack of early symptoms, the early detection of breast cancer becomes challenging. This detection is performed by screening techniques in organized preventive examinations. A promising imaging technology that can detect biomolecular alterations and can support the screening technologies by enhancing their low sensitivity, is nonlinear multimodal imaging. To detect these biomolecular alterations, machine‐learning algorithms are utilized. Our analysis started by preprocessing the images and comparing them to the pathological diagnosis. We trained two classification models utilizing the deep convolutional neural network ResNet50. This network was either used as feature extractor or to be fine‐tuned as a classification model. Beside these two classification approaches, two data validation techniques were investigated: the leave‐one‐patient‐out cross‐validation (LOPO‐CV) and the training‐test validation. The best reported result of breast cancer detection was introduced by the fine‐tuned ResNet50 network and LOPO‐CV accounting to 86.23% mean‐sensitivity. Abstract : An automatic detection of breast cancer based on nonlinear multimodal imaging by applied machine learning is presented. To do so, classical machine learning and deep learning algorithms were successfully implemented to classify normal, fat and cancerous tissue. The main part of our analysis was built upon the pretrained convolutional neural network ResNet50, which showed promising results, if the pretrained ResNet50 network was fine‐tuned on the breast cancer dataset.