Comparative effectiveness study of face-to-face and teledermatology workflows for diagnosing skin cancer

Marwaha, Sangeeta; Fevrier, Helene; Alexeeff, Stacey; Crowley, Eileen; Haiman, Michael; Pham, N.; Tuerk, Melanie J; Wukda, Danny; Hartmann, Michael; Herrinton, Lisa J.

doi:10.1016/j.jaad.2019.01.067

Cited by 43 publications

(36 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, mobile phones are implemented as a part of teledermatological systems that are now becoming a reality. The comparison of four different teledermatological workflows reported in [ 5 ] demonstrated that teledermatology is efficient in diagnosis, reaching a sensitivity greater than 90% and a specificity greater than 80%. One of the limitations of such systems is the image acquisition device that defines the quality of the captured lesion images: a system equipped with a dermoscope outperformed these based on smartphones by achieving a greater probability of correct cancer detection and lower probability of unnecessary biopsy [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Skin Lesion Detection Algorithms in Whole Body Images

Strzelecki

Strąkowska

Kozłowski

et al. 2021

Sensors

View full text Add to dashboard Cite

Melanoma is one of the most lethal and rapidly growing cancers, causing many deaths each year. This cancer can be treated effectively if it is detected quickly. For this reason, many algorithms and systems have been developed to support automatic or semiautomatic detection of neoplastic skin lesions based on the analysis of optical images of individual moles. Recently, full-body systems have gained attention because they enable the analysis of the patient’s entire body based on a set of photos. This paper presents a prototype of such a system, focusing mainly on assessing the effectiveness of algorithms developed for the detection and segmentation of lesions. Three detection algorithms (and their fusion) were analyzed, one implementing deep learning methods and two classic approaches, using local brightness distribution and a correlation method. For fusion of algorithms, detection sensitivity = 0.95 and precision = 0.94 were obtained. Moreover, the values of the selected geometric parameters of segmented lesions were calculated and compared for all algorithms. The obtained results showed a high accuracy of the evaluated parameters (error of area estimation <10%), especially for lesions with dimensions greater than 3 mm, which are the most suspected of being neoplastic lesions.

show abstract

Section: Introductionmentioning

confidence: 99%

Skin Lesion Detection Algorithms in Whole Body Images

Strzelecki

Strąkowska

Kozłowski

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The literature suggests that with the use of high-quality images, biopsy rates are similar or lower with TD. [9][10][11] However, a recent Cochrane review suggested that some lower-concern lesions are more likely to be excised, referred for F2F assessment or followed up if assessed via TD. 5 In our evaluation we note that the TD assessments were by experienced consultants whereas the F2F appointments were with doctors of mixed seniority.…”

mentioning

confidence: 99%

A service evaluation between 2‐week wait (2WW) skin cancer referrals via teledermatology and the standard face‐to‐face pathway at a teaching hospital

et al. 2019

View full text Add to dashboard Cite

with MADM compared with DM controls without malignancy (P < 0.01), as expected, but NLRs were not significantly different in patients who died compared to those who remained alive (P = 0.11).Abundant research has shown NLR to be related to disease activity of inflammatory diseases, including DM, and to the prognosis of various cancers. 5 However, our results suggest that NLR does not have prognostic value in patients with MADM and is not able to predict the presence or development of malignancy in patients with DM. Thus, calculating an NLR in newly diagnosed patients with DM does not appear to be a useful exercise.The benefits of our study include a well-defined cohort not yet on immunomodulatory therapy, and comparison with matched DM controls without malignancy. Limitations include a relatively small cohort and variable timing of CBC and DM diagnosis.In summary, our results suggest calculating NLR is not useful to predict presence/development of underlying malignancy in patients with newly diagnosed DM, or for predicting prognosis of patients with MADM. However, NLR differences in patients with MADM who died compared with matched DM controls is notable, and the small number of patients who died (n = 4) suggest our results may be inconclusive concerning risk of death (Table 1). Further research aimed at identifying clinical risk factors of malignancy development and/or prognosis in patients with DM, including NLR, is needed. Figure 1 Flow chart of the teledermatology (TD) and face-to-face (F2F) pathways. 2WW, 2-week wait. References

show abstract

“…Many studies have shown that for SCS, up to 50% of teledermatology referrals can be downgraded to routine appointments or patients discharged with reassurance 87–89 . Up to 40% of teledermatology referrals for skin lesions are sent straight to biopsy lists without necessitating face‐to‐face appointments beforehand, so waiting times are reduced 87–89 . Furthermore, for large lesions, patients can be referred directly to dermatosurgeons or plastic surgeons.…”

Section: Innovative Methods In Dermato‐oncologymentioning

confidence: 99%

“…Sensitivity has been found to be comparable between teledermoscopy and face‐to‐face evaluations, although specificity was higher in face‐to‐face evaluations 86 . Many studies have shown that for SCS, up to 50% of teledermatology referrals can be downgraded to routine appointments or patients discharged with reassurance 87–89 . Up to 40% of teledermatology referrals for skin lesions are sent straight to biopsy lists without necessitating face‐to‐face appointments beforehand, so waiting times are reduced 87–89 .…”

Section: Innovative Methods In Dermato‐oncologymentioning

confidence: 99%