A convolutional neural network based system for detection of actinic keratosis in clinical images of cutaneous field cancerization. (January 2023)

• Record Type: Journal Article
• Authors: Spyridonos, Panagiota; Gaitanis, Georgios; Likas, Aristidis; Bassukas, Ioannis D.
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 1
• Publication Date: 2023-01
• Subjects: CNN -- Transfer learning -- Classification -- Keratosis -- Actinic -- Skin disease -- Field cancerization; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104059
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Automatic detection of multiple actinic keratoses in sun affected skin areas. Evaluation of cutaneous cancerization fields using cross-polarized clinical photography. Superpixel-based detection system, using an end-to-end hybrid convolutional neural network classifier. Convolutional neural network optimal configuration using support vector machines. Abstract: Areas of cutaneous field cancerization (CFC) occur in sun-damaged skin and are prone to skin cancer development. Actinic keratosis (AK) is the pathognomonic lesion of CFC. Therefore, the reliable and non-invasive AK burden assessment is essential to assist clinicians in delivering patient-tailored therapeutic interventions and support the objective evaluation of emerging therapeutic modalities. Herein, we introduce a system for automated AK detection in CFC areas. For the differentiation of AK from healthy skin areas and co-localized benign growths (Seborrheic Keratosis/Lentigo Solaris; SK/LS), cross-polarized digital photographs of afflicted skin surfaces were taken, and a convolutional neural network (AKCNN) whose convolution part was optimally transferred from a pre-trained VGG16 was implemented. For the detection of multifocal AK in wide skin regions, superpixels were employed to generate region patches for the subsequent evaluation. AKCNN was implemented and evaluated in 19739, 43067, and 12, 205 image patches of AK, SK/LS, and healthy skin, respectively, originating from 46 patients. AKCNN performance was assessed in two ways: (a) patch classification using the macro averaged F1 score and (b) AK burden evaluation in broad skin areas using an adapted region-based F1 ( a F 1 ) score. Using raw clinical images, AKCNN exhibited a macro F1 of 0.78 at patch level and a region-based a F 1 of 0.81, with good tolerance against image scaling. The proposed system efficiently uses cross-polarized clinical photography to assess the AK burden within the CFC.