No-reference Blur Assessment of Dermatological Images Acquired via Mobile Devices

Vasconcelos, Maria João M.; Rosado, Luís

doi:10.1007/978-3-319-07998-1_40

Cited by 10 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is similar to the work of Vasconcelos and Rosado. 20 This simulates image blurring caused by the object of focus being outside of the depth of field or by motion of the camera along the optical axis.…”

Section: Blurmentioning

confidence: 99%

Quantifying acceptable artefact ranges for dermatologic classification algorithms

Petrie

Larson

Heath

et al. 2021

Skin Health and Disease

View full text Add to dashboard Cite

Background: Many classifiers have been developed that can distinguish different types of skin lesions (e.g., benign nevi, melanoma) with varying degrees of success. [1][2][3][4][5] However, even successfully trained classifiers may perform poorly on images that include artefacts. While problems created by hair and ink markings have been published, quantitative measurements of blur, colour and lighting variations on classification accuracy has not yet been reported to our knowledge. Objectives: We created a system that measures the impact of various artefacts on machine learning accuracy. Our objectives were to (1) quantitatively identify the most egregious artefacts and (2) demonstrate how to assess a classification algorithm's accuracy when input images include artefacts. Methods: We injected artefacts into dermatologic images using techniques that could be controlled with a single variable. This allows us to quantitatively evaluate the impact on the accuracy. We trained two convolutional neural networks on two different binary classification tasks and measured the impact on dermoscopy images over a range of parameter values. The area under the curve and specificity-at-a-given-sensitivity values were measured for each artefact induced at each parameter. Results: General blur had the strongest negative effect on the melanoma versus other task. Conversely, shifting the hue towards blue had a more pronounced effect on the suspicious versus follow task. Conclusions: Classifiers should either mitigate artefacts or detect them. Images should be excluded from diagnosis/recommendation when artefacts are present in amounts outside the machine perceived quality range. Failure to do so will reduce accuracy and impede approval from regulatory agencies.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Blurmentioning

confidence: 99%

Quantifying acceptable artefact ranges for dermatologic classification algorithms

Petrie

Larson

Heath

et al. 2021

Skin Health and Disease

View full text Add to dashboard Cite

show abstract

“…and learning based on natural scene statistics metrics are some of the categories these metrics may fall into [22]. Also transform-based, statistics, directional or geometric based features are some metrics that are widely used to discriminate the quality of an image where no reference image is provided [23]. In Reference [24] the authors have explored a no reference methodology for uneven illumination assessment of 30 dermoscopic images with different degrees of real uneven illumination.…”

Section: Related Workmentioning

confidence: 99%

“…Afterwards, several image features for assessing blur distortion were extracted for both IGray and IBlur images. The complete set of the considered focus metrics was already reported in a previous study [23], it being possible to categorize them into five broad groups according to their working principles—Gradient based, Laplacian based, Statistical based, Discrete Cosine Transform (DCT)/Discrete Fourier Transform (DFT) based and Other principles (see Table 5 for a detailed summary).…”

Section: System Architecturementioning

confidence: 99%

Automatic Focus Assessment on Dermoscopic Images Acquired with Smartphones

Alves

Moreira

Alves

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Over recent years, there has been an increase in popularity of the acquisition of dermoscopic skin lesion images using mobile devices, more specifically using the smartphone camera. The demand for self-care and telemedicine solutions requires suitable methods to guide and evaluate the acquired images’ quality in order to improve the monitoring of skin lesions. In this work, a system for automated focus assessment of dermoscopic images was developed using a feature-based machine learning approach. The system was designed to guide the user throughout the acquisition process by means of a preview image validation approach that included artifact detection and focus validation, followed by the image quality assessment of the acquired picture. This paper also introduces two different datasets, dermoscopic skin lesions and artifacts, which were collected using different mobile devices to develop and test the system. The best model for automatic preview assessment attained an overall accuracy of 77.9% while focus assessment of the acquired picture reached a global accuracy of 86.2%. These findings were validated by implementing the proposed methodology within an android application, demonstrating promising results as well as the viability of the proposed solution in a real life scenario.

show abstract

“…In [95], a new methodology to detect reflections on dermatological images acquired by mobile phones is presented. In this work, the authors start to apply a filter to the original RGB image to attenuate the mean luminance and enhance the contours and use the difference between the L channel and a variation from the H channel, from the L*a*b* and HSV color spaces, respectively, to enhance the reflection regions.…”

Section: Reflection Detectionmentioning

confidence: 99%

Improved Skin Lesion Diagnostics for General Practice by Computer-Aided Diagnostics

Rosado¹,

Vasconcelos²,

Castro³

et al. 2015

Dermoscopy Image Analysis

View full text Add to dashboard Cite

No-reference Blur Assessment of Dermatological Images Acquired via Mobile Devices

Cited by 10 publications

References 18 publications

Quantifying acceptable artefact ranges for dermatologic classification algorithms

Quantifying acceptable artefact ranges for dermatologic classification algorithms

Automatic Focus Assessment on Dermoscopic Images Acquired with Smartphones

Improved Skin Lesion Diagnostics for General Practice by Computer-Aided Diagnostics

Contact Info

Product

Resources

About