DermX: An end-to-end framework for explainable automated dermatological diagnosis

Jalaboi, Raluca; Faye, Frederik; Orbes-Arteaga, Mauricio; Jøgensen, Dan; Winther, Ole; Galimzianova, Alfiia

doi:10.1016/j.media.2022.102647

Cited by 5 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ImageQX architecture is inspired by the DermX architecture introduced by Jalaboi et al to intrinsically learn the expert explanations, as illustrated in Figure 1 . 17 EfficientNet-B0 was used as the feature extractor to increase the image processing speed and reduce the network size. 18 To increase the convergence speed, we used weights pretrained on the ImageNet dataset, 19 made available by the Pytorch framework.…”

Section: Methodsmentioning

confidence: 99%

Explainable Image Quality Assessments in Teledermatological Photography

Jalaboi

Winther

Galimzianova³

2023

Telemedicine and e-Health

Self Cite

View full text Add to dashboard Cite

Background and Objectives: Image quality is a crucial factor in the effectiveness and efficiency of teledermatological consultations. However, up to 50% of images sent by patients have quality issues, thus increasing the time to diagnosis and treatment. An automated, easily deployable, explainable method for assessing image quality is necessary to improve the current teledermatological consultation flow. We introduce ImageQX, a convolutional neural network for image quality assessment with a learning mechanism for identifying the most common poor image quality explanations: bad framing, bad lighting, blur, low resolution, and distance issues. Methods: ImageQX was trained on 26,635 photographs and validated on 9,874 photographs, each annotated with image quality labels and poor image quality explanations by up to 12 board-certified dermatologists. The photographic images were taken between 2017 and 2019 using a mobile skin disease tracking application accessible worldwide. Results: Our method achieves expert-level performance for both image quality assessment and poor image quality explanation. For image quality assessment, ImageQX obtains a macro F1-score of 0.73 ± 0.01, which places it within standard deviation of the pairwise inter-rater F1-score of 0.77 ± 0.07. For poor image quality explanations, our method obtains F1-scores of between 0.37 ± 0.01 and 0.70 ± 0.01, similar to the inter-rater pairwise F1-score of between 0.24 ± 0.15 and 0.83 ± 0.06. Moreover, with a size of only 15 MB, ImageQX is easily deployable on mobile devices. Conclusion: With an image quality detection performance similar to that of dermatologists, incorporating ImageQX into the teledermatology flow can enable a better, faster flow for remote consultations.

show abstract

Section: Methodsmentioning

confidence: 99%

Explainable Image Quality Assessments in Teledermatological Photography

Jalaboi

Winther

Galimzianova³

2023

Telemedicine and e-Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…To quantify the level of transparency in our XAI and the baseline classifier, we employed a methodology that involves measuring explanation faithfulness. This is achieved through the use of contrastive examples 34 , 46 . After obtaining the Grad-CAM heatmaps for each image, we randomised all pixels indicated as important for the predictions to create contrastive images.…”

Section: Resultsmentioning

confidence: 99%

“…Utilising the annotations optimises our XAI to be aligned with dermatologists’ perspective on melanoma diagnosis. We follow the attention inference architecture introduced by Li et al 40 and extended by Jalaboi et al 34 Our classifier has two components: a classification component Comp C and a guided attention component Comp A to help localise the relevant features. In Comp C , instead of predicting the diagnosis directly, the classifier predicts the characteristics from our ontology.…”

Section: Methodsmentioning

confidence: 99%

“…Lucieri et al 23 used the clinically well-established and expert annotated concepts from the PH2 32 and derm7pt 33 datasets to create an XAI that provides lesion-level explanations based on concept vectors. Jalaboi et al 34 employed a specialised light-weight convolutional neural network architecture that was designed to include localisations into training on clinical images of skin lesions. Additionally, they composed an ontology of clinically established terms to explain why the annotated regions are diagnostically relevant.…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, we aimed to develop an XAI that is from its core aligned with dermatologists’ perspective on melanoma diagnosis. Extending on prior work on explainability in dermatology 34 , 40 , we developed our XAI to provide dermatologist-like localised explanations (Fig. 2a, b ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Chanda,

Hauser,

Hobelsberger

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists’ decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists’ diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists’ confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists’ willingness to adopt such XAI systems, promoting future use in the clinic.

show abstract