Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
This study is to compare 2D- and 3D-imaging and routine clinical care in early melanoma detection in a prospective large-scale real-world data set.
This study is to compare the accuracy of combining human and artificial intelligence with its independent application in early melanoma detection. The Artificial Intelligence (AI)-powered 3D Total Body Photography (TBP) VectraĀ® WB360 system's utility and clinical performance in detecting melanoma in the real-world setting will be compared to the gold standard with clinical assessments by experienced dermatologists, to currently widespread used 2D imaging tools (FotoFinder ATBMĀ® Master) and to the Smartphone-based algorithm application (e.g. SkinVisionĀ®). Here included are specific questions regarding the patients' subjective experience, acceptance and evaluation of modern technological examination.
Additionally, the overall psychological burden and worry of melanoma risk or disease, anxiety, depression will be compared in different groups of patients and psychological support need and real uptake of support and its predictors will be investigated in all participants.
To validate the MELVEC (Melanoma Detection in Switzerland with VectraĀ®) test procedure, an analysis of the measurement repeatability of computer-guided risk assessment scores for early melanoma detection will be performed. A potential benefit of this validation analysis is the optimization of study procedure for future follow-up visits and further enrolled patients in the MELVEC study. Additionally, results will shed light on the reliability of the convolutional neural networks (CNNs) investigated and help formulate recommendations for their current use. Furthermore, results will provide important data for the manufacturers regarding the systems' reliability in clinical application to help future improvement of the respective algorithms.
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| 3D imaging Total Body Photography VectraĀ® WB360 | Device | 3D Total Body Photography VectraĀ® WB360 (Canfield Scientific, Parsippany, New Jersey, USA) and its digital dermoscopic camera (VISIOMEDĀ® D200evo dermatoscope) and scoring of pigmented skin lesions. All participants of this study will undergo 3D TBP at baseline and the follow-up visits up to month 24. | ||
| 2D imaging FotoFinder ATBMĀ® Master imaging system | Device | 2D imaging with FotoFinderĀ® Mole Analyzer and scoring of pigmented skin lesions. All participants of this study will undergo 2D imaging FotoFinder ATBMĀ® Master imaging system at baseline and the follow-up visits up to month 24. | ||
| Smartphone application (SkinVisionĀ®) | Device | Smartphone application for all dermatoscopically documented pigmented skin lesions in all study participations and record of risk assessment of the health application (low, medium or high risk) to compare the app's accuracy in risk assessment with the AI tools and the dermatologist. The SkinVisionĀ® smartphone app is CE certified.of skin lesions. All participants of this study will undergo Smartphone application (SkinVisionĀ®) at baseline and the follow-up visits up to month 12. | ||
| Standard-of-care clinical assessment of the skin | Other |
| Measure | Description | Time Frame |
|---|---|---|
| Analyses of histopathology reports of all excised suspectable lesions | The primary outcome, the sensitivity of human and artificial intelligence in detecting melanoma, will be measured at every study visit in case of a suspected melanoma by analysing histopathology reports of all excised suspectable lesions. The diagnosis of melanoma will be confirmed by histology. The biopsied pigmented skin lesions will be categorized as benign (melanocytic nevi / dysplastic nevi) or malignant (melanoma). | up to 24 months |
| Analyses of dermatologists' assessment of each pigmented skin lesion as benign (melanocytic nevi / dysplastic nevi) or malignant (melanoma) before and after (without and with knowledge of) computer-guided risk assessment scores | Analyses of dermatologists' assessment of each pigmented skin lesion as benign (melanocytic nevi / dysplastic nevi) or malignant (melanoma) before and after computer-guided risk assessment scores by VectraĀ® WB360 and FotoFinderĀ® Mole Analyzer and smartphone app. | up to 24 months |
| Analyses of 2D FotoFinderĀ® Mole Analyzer scoring of pigmented skin lesions (0.0 - 1.0) | The primary outcome, the sensitivity of human and artificial intelligence in detecting melanoma, will be measured at every study visit in case of a suspected melanoma by 2D FotoFinderĀ® Mole Analyzer scoring of pigmented skin lesions (0.0 - 1.0). Scores 0.0 - 1.0; 0 indicating no suspicion for melanoma, 1 indicating a high suspicion for melanoma). | up to 24 months |
| Analyses of 3D VectraĀ® WB360 imaging scoring of pigmented skin lesions (0- 10) | The primary outcome, the sensitivity of human and artificial intelligence in detecting melanoma, will be measured at every study visit in case of a suspected melanoma by analysing 3D VectraĀ® WB360 imaging scoring of pigmented skin lesions (0- 10). Score 0 - 10; 0 indicating no suspicion for melanoma, 10 indicating a high suspicion for melanoma). | up to 24 months |
| Measure | Description | Time Frame |
|---|---|---|
| Change in Distress thermometer (Patient-reported outcome) | Distress thermometer on a scale from 0-10 to address psychological distress: German version of the NCCN Distress Thermometer is used with Problem List (PL) as the screening tool for self-reported psychosocial distress, and to identify the causes of expressed distress. | up to 24 months |
| Measure | Description | Time Frame |
|---|---|---|
| Comparison of automated naevus counts from 3D total-body photography | Comparison of automated naevus counts from 3D total-body photography generated by collegues in Australia | Up to 3 years |
| Impact of sun damage on diagnostic accuracy of DEXI algorithm in melanoma recognition |
Inclusion Criteria:
Written informed consent of the patient
Sufficient fluency in German language skills to complete all questionnaires of the study without external assistance
High-risk criteria for melanoma. For "high risk" one of the following criteria needs to be fulfilled:
Exclusion Criteria:
Not provided
Not provided
Not provided
Patients will be recruited during melanoma consultations and the consultation in the outpatient clinic at the Department of Dermatology at the University Hospital Basel from Q4/2020 until Q4/2021.
Not provided
| Name | Affiliation | Role |
|---|---|---|
| Lara Valeska Maul, Dr. med. | Department of Dermatology, University Hospital Basel | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Department of Dermatology, University Hospital Basel | Basel | 4031 | Switzerland |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 38411348 | Derived | Goessinger EV, Niederfeilner JC, Cerminara S, Maul JT, Kostner L, Kunz M, Huber S, Koral E, Habermacher L, Sabato G, Tadic A, Zimmermann C, Navarini A, Maul LV. Patient and dermatologists' perspectives on augmented intelligence for melanoma screening: A prospective study. J Eur Acad Dermatol Venereol. 2024 Dec;38(12):2240-2249. doi: 10.1111/jdv.19905. Epub 2024 Feb 27. | |
| 38158385 |
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D008545 | Melanoma |
| ID | Term |
|---|---|
| D018358 | Neuroendocrine Tumors |
| D017599 | Neuroectodermal Tumors |
| D009373 | Neoplasms, Germ Cell and Embryonal |
| D009370 | Neoplasms by Histologic Type |
Not provided
Not provided
Not provided
Not provided
Not provided
Clinical skin examination with dermatoscope by an experienced dermatologist and risk assessment of pigmented lesions (melanoma vs. naevus). All participants of this study will undergo Standard-of-care clinical assessment of the skin at baseline and the follow-up visits up to month 24.
| Analyses of Smartphone app Skin VisionĀ® scoring of pigmented skin lesions (low, medium or high risk) | The primary outcome, the sensitivity of human and artificial intelligence in detecting melanoma, will be measured at every study visit in case of a suspected melanoma by analysing Smartphone app Skin VisionĀ® scoring of pigmented skin lesions (low, medium or high risk). | up to 12 months |
| Change in FACIT G7 Functional Assessment of Cancer Therapy - General - (7 item version). | The FACIT Measurement System is a collection of QOL questionnaires targeted to the management of chronic illness. | up to 24 months |
| Change in Hospital Anxiety and Depression Scale (HADS) | The HADS is a 14-item self-administered questionnaire widely used to detect anxiety and depression in physically ill patients and is validated for the German language. The questionnaire has two subscales (anxiety and depression) with seven items each and a total score for each subscale (values from 0-21). Subscale scores between 0-7 indicate normal anxiety and depression levels, scores between 8-10 indicate borderline levels of anxiety and depression, and scores between 11-21 indicate clinical levels of anxiety or depression | up to 24 months |
| Change in Melanoma Worry Scale (MWS) | MWS comprises four items, score 1 to 4, with possible scores ranging from 4 to 17, a higher score indicating higher levels of worry | up to 24 months |
| Change in support need and uptake | Support need and uptake will be collected by questions regarding participants' prospective intention to use psycho-oncological support services ("Do you intend to use the in-house psycho-oncological support service in the next months?", answer options: yes, maybe, no), the recommendation by the dermatologist for psychological support as well as patients' real uptake (hospital record). | up to 24 months |
| Patients' subjective experience and evaluation of modern technological examination | Study specific questions concerning the individuals' perceptions focusing the benefits by potentially improved sensitivity and specificity and possible disadvantages of the additional technology (3D TBP) in melanoma screening will be asked. The psychological impact of 3D TBP usage in melanoma screening and its effect on patients' cancer worry will be evaluated. | up to 24 months |
Determination of the impact of sun damage on diagnostic accuracy of DEXI algorithm in melanoma recognition |
| Up to 3 years |
| Patient perception of AI utilisation in skin cancer screening via questionaire | Including willingness to pay for 3D TBP | Up to 3 years |
| Comparison of the diagnostic accuracy of different algorithms by using ROC-AUC curves | Investigating how different algorithms might change diagnostic accuracy | Up to 3 years |
| Derived |
| Goessinger EV, Cerminara SE, Mueller AM, Gottfrois P, Huber S, Amaral M, Wenz F, Kostner L, Weiss L, Kunz M, Maul JT, Wespi S, Broman E, Kaufmann S, Patpanathapillai V, Treyer I, Navarini AA, Maul LV. Consistency of convolutional neural networks in dermoscopic melanoma recognition: A prospective real-world study about the pitfalls of augmented intelligence. J Eur Acad Dermatol Venereol. 2024 May;38(5):945-953. doi: 10.1111/jdv.19777. Epub 2023 Dec 29. |
| 37453242 | Derived | Cerminara SE, Cheng P, Kostner L, Huber S, Kunz M, Maul JT, Bohm JS, Dettwiler CF, Geser A, Jakopovic C, Stoffel LM, Peter JK, Levesque M, Navarini AA, Maul LV. Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening? Eur J Cancer. 2023 Sep;190:112954. doi: 10.1016/j.ejca.2023.112954. Epub 2023 Jun 24. |
| D009369 | Neoplasms |
| D009380 | Neoplasms, Nerve Tissue |
| D018326 | Nevi and Melanomas |
| D012878 | Skin Neoplasms |
| D009371 | Neoplasms by Site |
| D012871 | Skin Diseases |
| D017437 | Skin and Connective Tissue Diseases |