Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases

Marletta, Stefano; L’Imperio, Vincenzo; Eccher, Albino; Antonini, Pietro; Santonicco, Nicola; Girolami, Ilaria; Tos, Angelo Paolo Dei; Sbaraglia, Marta; Pagni, Fabio; Brunelli, Matteo; Marino, Andrea; Scarpa, Aldo; Munari, Enrico; Fusco, Nicola; Pantanowitz, Liron

doi:10.1016/j.prp.2023.154362

Cited by 24 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of point-of-care testing (POCT) represents the future direction for the diagnosis of the infectious diseases, including malaria, in both endemic and non-endemic settings, according to the WHO global Technical Strategy for Malaria 2016-2030 [9]; it is considered an adequate promising reaction to the need of a prompt diagnosis, together with "on-site" results, which would be an aid for an immediate and accurate anti-malarial treatment and for avoiding the spread of Plasmodia among humans and the vector in areas where malaria was eradicated [9]. Moreover, recently published evidence suggested that artificial intelligence can be of aid in assisting pathologists in the detection of malaria parasites and other microorganisms even if at present these tools remain a descriptive step requiring deeper investigation of their application in diagnostic practice [123,124].…”

Section: Discussionmentioning

confidence: 99%

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non-Endemic Areas

Calderaro,

Piccolo,

Chezzi

2024

IJMS

View full text Add to dashboard Cite

Even if malaria is rare in Europe, it is a medical emergency and programs for its control should ensure both an early diagnosis and a prompt treatment within 24–48 h from the onset of the symptoms. The increasing number of imported malaria cases as well as the risk of the reintroduction of autochthonous cases encouraged laboratories in non-endemic countries to adopt diagnostic methods/algorithms. Microscopy remains the gold standard, but with limitations. Rapid diagnostic tests have greatly expanded the ability to diagnose malaria for rapid results due to simplicity and low cost, but they lack sensitivity and specificity. PCR-based assays provide more relevant information but need well-trained technicians. As reported in the World Health Organization Global Technical Strategy for Malaria 2016–2030, the development of point-of-care testing is important for the improvement of diagnosis with beneficial consequences for prompt/accurate treatment and for preventing the spread of the disease. Despite their limitations, diagnostic methods contribute to the decline of malaria mortality. Recently, evidence suggested that artificial intelligence could be utilized for assisting pathologists in malaria diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non-Endemic Areas

Calderaro,

Piccolo,

Chezzi

2024

IJMS

View full text Add to dashboard Cite

show abstract

“…These data suggest that DL mobile systems may assist clinicians in accurately diagnosing skin lesions. Additionally, AI systems could be a way to speed up the diagnostic process and reduce the high daily workload, and DL approaches have provided highly satisfactory results in image analysis to achieve this goal [57].…”

Section: Discussionmentioning

confidence: 99%

Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence

Leal,

Barroso,

Trindade

et al. 2023

Biomedicines

View full text Add to dashboard Cite

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, pyomerrhitis, 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.

show abstract

“…The development of Point-Of-Care Testing (POCT) represents the future direction for the diagnosis of the infectious diseases, including malaria, in both endemic and non-endemic settings, according to WHO global Technical Strategy for Malaria 2016-2030 [9]; it is considered an adequate promising reaction to the need of a prompt diagnosis, together with "on-site" results, which would be an aid for an immediate and accurate anti-malarial treatment and for avoiding the spread of Plasmodia among humans and the vector in areas where malaria was eradicated [9]. Moreover, recently published evidence suggested that Artificial Intelligence can be of aid in assisting pathologists in the detection of malaria parasites as other microorganisms even if these tools remain at present at descriptive step speculative requiring a deeper investigation on their application in diagnostic practice [123,124].…”

Section: Discussionmentioning

confidence: 99%

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non‐Endemic Areas

Calderaro,

Piccolo,

Chezzi

2023

Preprint

View full text Add to dashboard Cite

Malaria is rare in Europe, but it is a medical emergency and programs for its control should ensure access to early diagnosis and prompt treatment within 24-48 h of the symptom’s onset. The consistent number of imported malaria cases and the risk of reappearance of autochthonous cases stimulated laboratories in non-endemic countries to evaluate diagnostic methods/algorithms: microscopy remains the gold standard, but with limitations. RDTs have greatly expanded the ability to diagnose malaria for rapid results due to simplicity and low cost, but they lack sensitivity and specificity. PCR-based assays provide more relevant information but need well-trained technicians. According to WHO global Technical Strategy for Malaria 2016-2030, the future direction for a rapid diagnosis is the development of Point-Of-Care Testing, which would be helpful for prompt/accurate treatment and for preventing the diseases spread. Despite the limitations of current diagnostic methods, they play important roles in dealing with the global malaria situation, including decreasing its incidence. Recently evidence suggested that Artificial Intelligence could be utilized for assisting pathologists in malaria diagnosis. Future studies need to be conducted to see whether this system can be used for routine malaria diagnostic procedures.

show abstract

Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases

Cited by 24 publications

References 35 publications

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non-Endemic Areas

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non-Endemic Areas

Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non‐Endemic Areas

Contact Info

Product

Resources

About