RESUMO
Actinic keratosis (AK) is a common skin cancer in situ that can progress to invasive SCC. Line-field confocal optical coherence tomography (LC-OCT) has emerged as a non-invasive imaging technique that can aid in diagnosis. Recently, machine-learning algorithms have been developed that can automatically assess the PRO score of AKs based on the dermo-epidermal junction's (DEJ's) protrusion on LC-OCT images. A dataset of 19.898 LC-OCT images from 80 histologically confirmed AK lesions was used to test the performance of a previous validated artificial intelligence (AI)-based LC-OCT assessment algorithm. AI-based PRO score assessment was compared to the imaging experts' visual score. Additionally, undulation of the DEJ, the number of protrusions detected within the image, and the maximum depth of the protrusions were computed. Our results show that AI-automated PRO grading is highly comparable to the visual score, with an agreement of 71.3% for the lesions evaluated. Furthermore, this AI-based assessment was significantly faster than the regular visual PRO score assessment. The results confirm our previous findings of the pilot study in a larger cohort that the AI-based grading of LC-OCT images is a reliable and fast tool to optimize the efficiency of visual PRO score grading. This technology has the potential to improve the accuracy and speed of AK diagnosis and may lead to better clinical outcomes for patients.
RESUMO
BACKGROUND AND OBJECTIVES: The histological PRO score (I-III) helps to assess the malignant potential of actinic keratoses (AK) by grading the dermal-epidermal junction (DEJ) undulation. Line-field confocal optical coherence tomography (LC-OCT) provides non-invasive real-time PRO score quantification. From LC-OCT imaging data, training of an artificial intelligence (AI), using Convolutional Neural Networks (CNNs) for automated PRO score quantification of AK in vivo may be achieved. PATIENTS AND METHODS: CNNs were trained to segment LC-OCT images of healthy skin and AK. PRO score models were developed in accordance with the histopathological gold standard and trained on a subset of 237 LC-OCT AK images and tested on 76 images, comparing AI-computed PRO score to the imaging experts' visual consensus. RESULTS: Significant agreement was found in 57/76 (75%) cases. AI-automated grading correlated best with the visual score for PRO II (84.8%) vs. PRO III (69.2%) vs. PRO I (66.6%). Misinterpretation occurred in 25% of the cases mostly due to shadowing of the DEJ and disruptive features such as hair follicles. CONCLUSIONS: The findings suggest that CNNs are helpful for automated PRO score quantification in LC-OCT images. This may provide the clinician with a feasible tool for PRO score assessment in the follow-up of AK.
Assuntos
Ceratose Actínica , Humanos , Ceratose Actínica/diagnóstico por imagem , Ceratose Actínica/patologia , Inteligência Artificial , Tomografia de Coerência Óptica/métodos , Pele/patologia , Redes Neurais de ComputaçãoRESUMO
BACKGROUND: The objective of the study was to characterize the performance of German dermatology hospitals. METHODS: A structured survey questionnaire was sent out to all dermatology hospitals in October 2019 as part of a cross-sectional analysis based on health care research. RESULTS: Of the 115 hospitals, 95 (82.6 %) responded, including 34 (35.8 %) university hospitals (UC) and 61 (64.2 %) non-university hospitals (NUC), of which 78 % were urban (43 % UC, 57 % NUC) and 22 % rural (10 % UC, 90 % NUC). The dermatology departments comprised an average of 45 inpatient and 11 day-care beds (UC: 52/13, NUC: 40/9). An average of 2,302 inpatients were cared for in 2018 (UC: 2,874, NUC: 1,983), and the case mix index was 0.76 (UC: 0.74, NUC: 0.77, overall range: 0.40-0.96). Mean length of stay was 5.5 days for UC, relevantly lower than 2013 (5.9 days) and 2011 (7.1 days) data, and also significantly lower for NUC at 5.9 (2018) versus 5.1 days (2013). CONCLUSIONS: German dermatology hospitals continue to have a high volume of inpatient care, with a comparison of the last six years again showing a compression with shorter length of stay and higher occupancy density. Dermatological hospitals represent an essential pillar of dermatological care.
Assuntos
Dermatologia , Estudos Transversais , Grupos Diagnósticos Relacionados , Alemanha/epidemiologia , Hospitais Universitários , HumanosRESUMO
BACKGROUND: In Germany, skin diseases are mainly treated in the 115 dermatological hospitals. METHODS: Health care and health economic analysis of dermatological inpatient care and prediction of future care needs based on primary and secondary data. RESULTS: Outpatient and inpatient care for dermatologic treatment indications is predominantly provided by dermatology specialists. Inpatient treatment was provided for 833,491 cases in 2018, corresponding to 4.21 % of all inpatient cases (19,808,687). Most common treatment cases were: epithelial skin cancer (total 87,386, of which dermatology clinics 52,608), followed by melanoma (23,917/17,774), psoriasis (19,291/13,352), erysipelas (73,337/11,260), other dermatitis (12,671/10,842), atopic dermatitis (AD) (11,421/9,734), and herpes zoster (26,249/9,652). With an average length of stay of 5.69 days, dermatology hospitals were in the bottom third. The proportion of inpatient indications cared for in dermatology hospitals was highest for prurigo (95.2 %), pemphigus (94.9 %), parapsoriasis (94.6 %), pemphigoid (90.3 %), eczema other than AD (85.6 %), and AD (85.2 %). While the total number of inpatient treatment cases in Germany has increased by an average of 17.5 % between 2000 and 2018, this is the case for 26.6 % of skin diseases and over 150 % for individual ones. The projection of current to future inpatient care suggests a continued high demand for inpatient care by dermatology hospitals. CONCLUSION: Inpatient dermatological care will continue to be an indispensable component of qualified, socially necessary care in Germany.
Assuntos
Dermatologia , Prurigo , Dermatopatias , Atenção à Saúde , Alemanha/epidemiologia , Humanos , Pacientes Internados , Dermatopatias/epidemiologia , Dermatopatias/terapiaRESUMO
Basal cell carcinoma (BCC) is the most common malignant tumor among fair-skinned individuals, and its incidence had been steadily rising in the past decades. In order to maintain the highest quality of patient care possible, the German S2k guidelines were updated following a systematic literature search and with the participation of all professional societies and associations involved in the management of the disease. Part 2 addresses issues such as proper risk stratification, the various therapeutic approaches, and prevention as well as follow-up of patients with basal cell carcinoma.