Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence
The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/12/1/12 |
| _version_ | 1827369817893502976 |
|---|---|
| author | José Fabrício de Carvalho Leal Daniel Holanda Barroso Natália Santos Trindade Vinícius Lima de Miranda Rodrigo Gurgel-Gonçalves |
| author_facet | José Fabrício de Carvalho Leal Daniel Holanda Barroso Natália Santos Trindade Vinícius Lima de Miranda Rodrigo Gurgel-Gonçalves |
| author_sort | José Fabrício de Carvalho Leal |
| collection | DOAJ |
| description | The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81–96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services. |
| first_indexed | 2024-03-08T09:58:07Z |
| format | Article |
| id | doaj.art-bb25f706244b438ca59e8263a5a55b67 |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-08T09:58:07Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-bb25f706244b438ca59e8263a5a55b672024-01-29T13:46:28ZengMDPI AGBiomedicines2227-90592023-12-011211210.3390/biomedicines12010012Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial IntelligenceJosé Fabrício de Carvalho Leal0Daniel Holanda Barroso1Natália Santos Trindade2Vinícius Lima de Miranda3Rodrigo Gurgel-Gonçalves4Graduate Program in Tropical Medicine, Center for Tropical Medicine, Faculty of Medicine, University of Brasília–UnB, Brasília 70904-970, BrazilPostgraduate Program in Medical Sciences, Faculty of Medicine, University of Brasília–UnB, Brasília 70904-970, BrazilLaboratory of Medical Parasitology and Vector Biology, Faculty of Medicine, University of Brasília–UnB, Brasília 70904-970, BrazilLaboratory of Medical Parasitology and Vector Biology, Faculty of Medicine, University of Brasília–UnB, Brasília 70904-970, BrazilGraduate Program in Tropical Medicine, Center for Tropical Medicine, Faculty of Medicine, University of Brasília–UnB, Brasília 70904-970, BrazilThe polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81–96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services.https://www.mdpi.com/2227-9059/12/1/12dermatologyleishmaniasisdiagnosisAlexNetmachine learningpictures |
| spellingShingle | José Fabrício de Carvalho Leal Daniel Holanda Barroso Natália Santos Trindade Vinícius Lima de Miranda Rodrigo Gurgel-Gonçalves Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence Biomedicines dermatology leishmaniasis diagnosis AlexNet machine learning pictures |
| title | Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence |
| title_full | Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence |
| title_fullStr | Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence |
| title_full_unstemmed | Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence |
| title_short | Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence |
| title_sort | automated identification of cutaneous leishmaniasis lesions using deep learning based artificial intelligence |
| topic | dermatology leishmaniasis diagnosis AlexNet machine learning pictures |
| url | https://www.mdpi.com/2227-9059/12/1/12 |
| work_keys_str_mv | AT josefabriciodecarvalholeal automatedidentificationofcutaneousleishmaniasislesionsusingdeeplearningbasedartificialintelligence AT danielholandabarroso automatedidentificationofcutaneousleishmaniasislesionsusingdeeplearningbasedartificialintelligence AT nataliasantostrindade automatedidentificationofcutaneousleishmaniasislesionsusingdeeplearningbasedartificialintelligence AT viniciuslimademiranda automatedidentificationofcutaneousleishmaniasislesionsusingdeeplearningbasedartificialintelligence AT rodrigogurgelgoncalves automatedidentificationofcutaneousleishmaniasislesionsusingdeeplearningbasedartificialintelligence |