1
|
Hossain SI, de Goër de Herve J, Hassan MS, Martineau D, Petrosyan E, Corbin V, Beytout J, Lebert I, Durand J, Carravieri I, Brun-Jacob A, Frey-Klett P, Baux E, Cazorla C, Eldin C, Hansmann Y, Patrat-Delon S, Prazuck T, Raffetin A, Tattevin P, Vourc'h G, Lesens O, Nguifo EM. Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images. Comput Methods Programs Biomed 2022; 215:106624. [PMID: 35051835 DOI: 10.1016/j.cmpb.2022.106624] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/12/2021] [Revised: 12/22/2021] [Accepted: 01/05/2022] [Indexed: 05/14/2023]
Abstract
BACKGROUND AND OBJECTIVE Lyme disease which is one of the most common infectious vector-borne diseases manifests itself in most cases with erythema migrans (EM) skin lesions. Recent studies show that convolutional neural networks (CNNs) perform well to identify skin lesions from images. Lightweight CNN based pre-scanner applications for resource-constrained mobile devices can help users with early diagnosis of Lyme disease and prevent the transition to a severe late form thanks to appropriate antibiotic therapy. Also, resource-intensive CNN based robust computer applications can assist non-expert practitioners with an accurate diagnosis. The main objective of this study is to extensively analyze the effectiveness of CNNs for diagnosing Lyme disease from images and to find out the best CNN architectures considering resource constraints. METHODS First, we created an EM dataset with the help of expert dermatologists from Clermont-Ferrand University Hospital Center of France. Second, we benchmarked this dataset for twenty-three CNN architectures customized from VGG, ResNet, DenseNet, MobileNet, Xception, NASNet, and EfficientNet architectures in terms of predictive performance, computational complexity, and statistical significance. Third, to improve the performance of the CNNs, we used custom transfer learning from ImageNet pre-trained models as well as pre-trained the CNNs with the skin lesion dataset HAM10000. Fourth, for model explainability, we utilized Gradient-weighted Class Activation Mapping to visualize the regions of input that are significant to the CNNs for making predictions. Fifth, we provided guidelines for model selection based on predictive performance and computational complexity. RESULTS Customized ResNet50 architecture gave the best classification accuracy of 84.42% ±1.36, AUC of 0.9189±0.0115, precision of 83.1%±2.49, sensitivity of 87.93%±1.47, and specificity of 80.65%±3.59. A lightweight model customized from EfficientNetB0 also performed well with an accuracy of 83.13%±1.2, AUC of 0.9094±0.0129, precision of 82.83%±1.75, sensitivity of 85.21% ±3.91, and specificity of 80.89%±2.95. All the trained models are publicly available at https://dappem.limos.fr/download.html, which can be used by others for transfer learning and building pre-scanners for Lyme disease. CONCLUSION Our study confirmed the effectiveness of even some lightweight CNNs for building Lyme disease pre-scanner mobile applications to assist people with an initial self-assessment and referring them to expert dermatologist for further diagnosis.
Collapse
Affiliation(s)
- Sk Imran Hossain
- Université Clermont Auvergne, CNRS, ENSMSE, LIMOS, F-63000 Clermont-Ferrand, France
| | - Jocelyn de Goër de Herve
- Université Clermont Auvergne, INRAE, VetAgro Sup, UMR EPIA, 63122 Saint-Genès-Champanelle, France; Université de Lyon, INRAE, VetAgro Sup, UMR EPIA, F-69280 Marcy l'Etoile, France
| | - Md Shahriar Hassan
- Université Clermont Auvergne, CNRS, ENSMSE, LIMOS, F-63000 Clermont-Ferrand, France
| | - Delphine Martineau
- Infectious and Tropical Diseases Department, CHU Clermont-Ferrand, Clermont-Ferrand, France
| | - Evelina Petrosyan
- Infectious and Tropical Diseases Department, CHU Clermont-Ferrand, Clermont-Ferrand, France
| | - Violaine Corbin
- Infectious and Tropical Diseases Department, CHU Clermont-Ferrand, Clermont-Ferrand, France
| | - Jean Beytout
- CHU Clermont-Ferrand, Inserm, Neuro-Dol, CNRS 6023 Laboratoire Microorganismes: Génome Environnement (LMGE), Université Clermont Auvergne, Clermont-Ferrand, France
| | - Isabelle Lebert
- Université Clermont Auvergne, INRAE, VetAgro Sup, UMR EPIA, 63122 Saint-Genès-Champanelle, France; Université de Lyon, INRAE, VetAgro Sup, UMR EPIA, F-69280 Marcy l'Etoile, France
| | - Jonas Durand
- Tous Chercheurs Laboratory, UMR 1136 'Interactions Arbres Micro-Organismes', INRAE, Centre INRAE Grand Est-Nancy, F-54280 Champenoux, France
| | | | - Annick Brun-Jacob
- Tous Chercheurs Laboratory, UMR 1136 'Interactions Arbres Micro-Organismes', INRAE, Centre INRAE Grand Est-Nancy, F-54280 Champenoux, France
| | - Pascale Frey-Klett
- INRAE, US 1371 Laboratory of Excellence ARBRE, Centre INRAE Grand Est-Nancy, Champenoux F-54280, France
| | - Elisabeth Baux
- Infectious Diseases Department, University Hospital of Nancy, Nancy, France
| | - Céline Cazorla
- Infectious Disease Department, University Hospital of Saint Etienne, Saint-Etienne, France
| | - Carole Eldin
- IHU-Méditerranée Infection, Marseille, France; Aix Marseille Univ, IRD, AP-HM, SSA, VITROME, Marseille, France
| | - Yves Hansmann
- Service des Maladies Infectieuses et Tropicales, Hôpitaux Universitaires, 67000 Strasbourg, France
| | - Solene Patrat-Delon
- Infectious Diseases and Intensive Care Unit, Pontchaillou University Hospital, Rennes, France
| | - Thierry Prazuck
- Department of Infectious and Tropical Diseases, CHR Orléans, Orléans, France
| | - Alice Raffetin
- Tick-Borne Diseases Reference Center, North region, Department of Infectious Diseases, Hospital of Villeneuve-Saint-Georges, 40 allée de la Source, 94190 Villeneuve-Saint-Georges; ESGBOR, European Study Group for Lyme Borreliosis
| | - Pierre Tattevin
- Department of Infectious Diseases and Intensive Care Medicine, Centre Hospitalier Universitaire de Rennes, Rennes, France
| | - Gwenaël Vourc'h
- Université Clermont Auvergne, INRAE, VetAgro Sup, UMR EPIA, 63122 Saint-Genès-Champanelle, France; Université de Lyon, INRAE, VetAgro Sup, UMR EPIA, F-69280 Marcy l'Etoile, France
| | - Olivier Lesens
- Infectious and Tropical Diseases Department, CRIOA, CHU Clermont-Ferrand, Clermont-Ferrand, France; UMR CNRS 6023, Laboratoire Microorganismes: Génome Environnement (LMGE), Université Clermont Auvergne, Clermont-Ferrand, France
| | | |
Collapse
|
2
|
Thimonier J, Brun-Jacob A, Mathieu M, Durand J, Frey-Klett P, Hammond C. [The open labs Tous Chercheurs]. Med Sci (Paris) 2020; 36:271-273. [PMID: 32228847 DOI: 10.1051/medsci/2020029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
L’enjeu d’une culture scientifique pour tous est d’importance face à la difficulté des citoyens à critiquer les données de la science avec des arguments rationnels, notamment en ce qui concerne la biologie et la santé (vaccination, procréation médicalement assistée, etc.), car le grand public ne veut plus croire sur parole ce que disent les experts. Dans ce contexte, rapprocher les citoyens de la recherche scientifique représente un réel défi pour l’avenir, que les laboratoires ouverts Tous Chercheurs ont voulu relever.
Collapse
Affiliation(s)
- Jean Thimonier
- Tous Chercheurs, INMED UMR 1249, Inserm et Aix Marseille Université, 163 route de Luminy, 13273 Marseille, France
| | - Annick Brun-Jacob
- Tous Chercheurs, Laboratoire d'Excellence ARBRE, UMR INRAE Université de Lorraine 1136 , Centre INRAE Grand Est-Nancy, 54280 Champenoux, France
| | - Marion Mathieu
- Tous Chercheurs, INMED UMR 1249, Inserm et Aix Marseille Université, 163 route de Luminy, 13273 Marseille, France - UMR 7268 ADES - Aix Marseille Université - EFS - CNRS-, faculté de médecine, département des sciences humaines et sociales, 27 boulevard Jean-Moulin, 13385 Marseille, France
| | - Jonas Durand
- Tous Chercheurs, Laboratoire d'Excellence ARBRE, UMR INRAE Université de Lorraine 1136 , Centre INRAE Grand Est-Nancy, 54280 Champenoux, France
| | - Pascale Frey-Klett
- Tous Chercheurs, Laboratoire d'Excellence ARBRE, UMR INRAE Université de Lorraine 1136 , Centre INRAE Grand Est-Nancy, 54280 Champenoux, France
| | - Constance Hammond
- Tous Chercheurs, INMED UMR 1249, Inserm et Aix Marseille Université, 163 route de Luminy, 13273 Marseille, France
| |
Collapse
|
4
|
Abstract
Ectomycorrhizal interactions established between the root systems of terrestrial plants and hyphae from soil-borne fungi are the most ecologically widespread plant symbioses. The efficient uptake of a broad range of nitrogen (N) compounds by the fungal symbiont and their further transfer to the host plant is a major feature of this symbiosis. Nevertheless, we far from understand which N form is preferentially transferred and what are the key molecular determinants required for this transfer. Exhaustive in silico analysis of N-compound transporter families were performed within the genome of the ectomycorrhizal model fungus Laccaria bicolor. A broad phylogenetic approach was undertaken for all families and gene regulation was investigated using whole-genome expression arrays. A repertoire of proteins involved in the transport of N compounds in L. bicolor was established that revealed the presence of at least 128 gene models in the genome of L. bicolor. Phylogenetic comparisons with other basidiomycete genomes highlighted the remarkable expansion of some families. Whole-genome expression arrays indicate that 92% of these gene models showed detectable transcript levels. This work represents a major advance in the establishment of a transportome blueprint at a symbiotic interface, which will guide future experiments.
Collapse
Affiliation(s)
- Eva Lucic
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| | - Claire Fourrey
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| | - Annegret Kohler
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| | - Francis Martin
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| | - Michel Chalot
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| | - Annick Brun-Jacob
- Research Unit INRA/UHP 1136 'Tree-microbe Interactions', Nancy-University, BP 239, F-54506 Vandoeuvre-les-Nancy Cedex, France
| |
Collapse
|