Diagnostic validation of a portable whole slide imaging scanner for lymphoma diagnosis in resource-constrained setting: A cross-sectional study

Mremi, Alex; Achola, Caroline; Mbwambo, Daniel; Magorosa, Erick; Legason, Ismail D.; Vavoulis, Dimitris; Mouden, Claire El; Schuh, Anna; Mnango, Leah

doi:10.1016/j.jpi.2023.100188

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The graphs depict the validation accuracies of EficientNet, Googl_eNet and ResNet60 for batch size4 (A) and sample size 20 (C,D) . Validation accuracies for the models with attention heads 10 and 50 for EfficientNet and 16 and 64 for GoogLaNet and RasNat60, with a batch size of 4 (C) and a sample size of ( 20 ) (D) .…”

Section: Resultsmentioning

confidence: 99%

An AI based, open access screening tool for early diagnosis of Burkitt lymphoma

Nambiar,

Rajesh,

Nair

et al. 2024

Front. Med.

View full text Add to dashboard Cite

Burkitt Lymphoma (BL) is a highly treatable cancer. However, delayed diagnosis of BL contributes to high mortality in BL endemic regions of Africa. Lack of enough pathologists in the region is a major reason for delayed diagnosis. The work described in this paper is a proof-of-concept study to develop a targeted, open access AI tool for screening of histopathology slides in suspected BL cases. Slides were obtained from a total of 90 BL patients. 70 Tonsillectomy samples were used as controls. We fine-tuned 6 pre-trained models and evaluated the performance of all 6 models across different configurations. An ensemble-based consensus approach ensured a balanced and robust classification. The tool applies novel features to BL diagnosis including use of multiple image magnifications, thus enabling use of different magnifications of images based on the microscope/scanner available in remote clinics, composite scoring of multiple models and utilizing MIL with weak labeling and image augmentation, enabling use of relatively low sample size to achieve good performance on the inference set. The open access model allows free access to the AI tool from anywhere with an internet connection. The ultimate aim of this work is making pathology services accessible, efficient and timely in remote clinics in regions where BL is endemic. New generation of low-cost slide scanners/microscopes is expected to make slide images available immediately for the AI tool for screening and thus accelerate diagnosis by pathologists available locally or online.

show abstract

Section: Resultsmentioning

confidence: 99%

An AI based, open access screening tool for early diagnosis of Burkitt lymphoma

Nambiar,

Rajesh,

Nair

et al. 2024

Front. Med.

View full text Add to dashboard Cite

show abstract

“…The global impact of telepathology is underscored by its ability to bridge the gap in pathology services, particularly in under-resourced regions. Studies from Zambia, Uganda, and Rwanda highlighted the role of telepathology in enhancing diagnostic capabilities and providing educational support [ 16 , 18 , 27 , 56 , 58 ]. The implementation of telepathology in these regions demonstrates a significant improvement in cancer diagnosis, management of infectious diseases, and access to specialized pathology consultations.…”

Section: Reviewmentioning

confidence: 99%

The State of Telepathology in Africa in the Age of Digital Pathology Advancements: A Bibliometric Analysis and Literature Review

El Jiar,

Eliahiai,

Chaib

et al. 2024

Cureus

View full text Add to dashboard Cite

Telepathology emerges as a vital tool, offering significant promise for enhancing pathology services in Africa, a region historically challenged by healthcare access and resource limitations. This review explores the development, adoption, and impacts of telepathology in Africa through a comprehensive bibliometric analysis and literature review. A methodical search in PubMed for publications up to 2024 revealed 119 pertinent studies, out of which 47 met the inclusion criteria for a focused review on telepathology's role in African healthcare settings. This research has charted a clear trajectory of growing interest in telepathology, as evidenced by the annual increase in related publications and robust international collaboration. It underscores the expanding utility of telepathology in diagnostics, education, and research within Africa, particularly in domains like dermatopathology, neuropathology, and, notably, oncology. The integration of artificial intelligence into telepathology presents new frontiers for enhancing diagnostic accuracy and efficiency. However, the review also identifies persistent challenges such as infrastructural inadequacies, a shortage of skilled professionals, and regulatory hurdles. The study highlights the indispensable role of international partnerships in advancing telepathology in the region. This review proposes a strategic pivot toward "leapfrogging," an approach that allows Africa to skip traditional developmental hurdles by directly adopting cutting-edge technologies and practices.

show abstract

The future of lymphoma diagnosis, prognosis, and treatment monitoring in countries with limited access to pathology services

Chamba,

Mawalla

2023

Seminars in Hematology

View full text Add to dashboard Cite

Diagnostic validation of a portable whole slide imaging scanner for lymphoma diagnosis in resource-constrained setting: A cross-sectional study

Cited by 3 publications

References 28 publications

An AI based, open access screening tool for early diagnosis of Burkitt lymphoma

An AI based, open access screening tool for early diagnosis of Burkitt lymphoma

The State of Telepathology in Africa in the Age of Digital Pathology Advancements: A Bibliometric Analysis and Literature Review

The future of lymphoma diagnosis, prognosis, and treatment monitoring in countries with limited access to pathology services

Contact Info

Product

Resources

About