MultiTask Learning AI system to assist BCC diagnosis with dual explanation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914396549152768 |
|---|---|
| author | Matas, Iván Serrano, Carmen Silva, Francisca Serrano, Amalia Toledo-Pastrana, Tomás Acha, Begoña |
| author_facet | Matas, Iván Serrano, Carmen Silva, Francisca Serrano, Amalia Toledo-Pastrana, Tomás Acha, Begoña |
| contents | Basal cell carcinoma (BCC) accounts for about 75% of skin cancers. The adoption of teledermatology protocols in Spanish public hospitals has increased dermatologists' workload, motivating the development of AI tools for lesion prioritization. However, limited transparency in current systems hinders clinical acceptance. This study proposes an AI system for BCC detection from dermoscopic images that integrates dermatologist diagnostic criteria based on specific dermoscopic patterns.
We analyzed 1559 dermoscopic images from 60 primary care centers annotated by four dermatologists for seven BCC patterns. An Expectation-Maximization consensus algorithm was used to build a unified standard reference. A multitask learning model based on MobileNet-V2 was developed to classify lesions and identify clinically relevant patterns, supported by Grad-CAM visual explanations.
The system achieved 90% accuracy in BCC classification (precision 0.90, recall 0.89). Clinically relevant BCC patterns were correctly detected in 99% of positive cases, and the pigment network exclusion criterion was satisfied in 95% of non-BCC cases. Grad-CAM maps showed strong spatial agreement with dermatologist-defined regions.
The proposed system combines accurate BCC detection with transparent pattern-based explanations, helping bridge the gap between AI performance and clinical trust in teledermatology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00104 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MultiTask Learning AI system to assist BCC diagnosis with dual explanation Matas, Iván Serrano, Carmen Silva, Francisca Serrano, Amalia Toledo-Pastrana, Tomás Acha, Begoña Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Information Retrieval Image and Video Processing Basal cell carcinoma (BCC) accounts for about 75% of skin cancers. The adoption of teledermatology protocols in Spanish public hospitals has increased dermatologists' workload, motivating the development of AI tools for lesion prioritization. However, limited transparency in current systems hinders clinical acceptance. This study proposes an AI system for BCC detection from dermoscopic images that integrates dermatologist diagnostic criteria based on specific dermoscopic patterns. We analyzed 1559 dermoscopic images from 60 primary care centers annotated by four dermatologists for seven BCC patterns. An Expectation-Maximization consensus algorithm was used to build a unified standard reference. A multitask learning model based on MobileNet-V2 was developed to classify lesions and identify clinically relevant patterns, supported by Grad-CAM visual explanations. The system achieved 90% accuracy in BCC classification (precision 0.90, recall 0.89). Clinically relevant BCC patterns were correctly detected in 99% of positive cases, and the pigment network exclusion criterion was satisfied in 95% of non-BCC cases. Grad-CAM maps showed strong spatial agreement with dermatologist-defined regions. The proposed system combines accurate BCC detection with transparent pattern-based explanations, helping bridge the gap between AI performance and clinical trust in teledermatology. |
| title | MultiTask Learning AI system to assist BCC diagnosis with dual explanation |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Information Retrieval Image and Video Processing |
| url | https://arxiv.org/abs/2407.00104 |