Automatic Differential Diagnosis of Melanocytic Skin Tumors Using Ultrasound Data
| Autor: | Renaldas Raišutis, Kristina Andrėkutė, Gintarė Linkevičiūtė, Jurgita Makštienė, Skaidra Valiukevičienė |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Adult
Male Pathology medicine.medical_specialty Skin Neoplasms Adolescent Acoustics and Ultrasonics Biophysics Diagnostic system Sensitivity and Specificity 030218 nuclear medicine & medical imaging Diagnosis Differential Lesion Young Adult 030207 dermatology & venereal diseases 03 medical and health sciences 0302 clinical medicine medicine Humans Radiology Nuclear Medicine and imaging Spectral analysis Melanoma Aged Skin Ultrasonography Aged 80 and over Nevus Pigmented Mahalanobis distance Radiological and Ultrasound Technology business.industry Ultrasound Reproducibility of Results Middle Aged medicine.disease Support vector machine classifier Female medicine.symptom Differential diagnosis business |
| Zdroj: | Ultrasound in Medicine & Biology. 42:2834-2843 |
| ISSN: | 0301-5629 |
| DOI: | 10.1016/j.ultrasmedbio.2016.07.026 |
| Popis: | We describe a novel automatic diagnostic system based on quantitative analysis of ultrasound data for differential diagnosis of melanocytic skin tumors. The proposed method has been tested on 160 ultrasound data sets (80 of malignant melanoma and 80 of benign melanocytic nevi). Acoustical, textural and shape features have been evaluated for each segmented lesion. Using parameters selected according to Mahalanobis distance and linear support vector machine classifier, we are able to differentiate malignant melanoma from benign melanocytic skin tumors with 82.4% accuracy (sensitivity = 85.8%, specificity = 79.6%). The results indicate that high-frequency ultrasound has the potential to be used for differential diagnosis of melanocytic skin tumors and to provide supplementary information on lesion penetration depth. The proposed system can be used as an additional tool for clinical decision support to improve the early-stage detection of malignant melanoma. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|