María Díaz de León Derby

María Díaz de León Derby

Auto-generated profile, based on publicly available information

María Díaz de León Derby

Department of Bioengineering, University of California, Berkeley, Berkeley, California, United States of America

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MDMaría Díaz de León Derby
María Díaz de León Derby
CDCharles B. Delahunt
Charles B. Delahunt
ESEthan Spencer
Ethan Spencer
JCJean T. Coulibaly
Jean T. Coulibaly
KSKigbafori D. Silué
Kigbafori D. Silué
DFDaniel A. Fletcher
Daniel A. Fletcher
Schistosomiasis currently affects over 250 million people and remains a public health burden despite ongoing global control efforts. Conventional microscopy is a practical tool for diagnosis and screening of Schistosoma haematobium , but identification of eggs requires a skilled microscopist. Here we present a machine learning (ML)-based strategy for automated detection of S. haematobium that combines two imaging contrasts, brightfield (BF) and darkfield (DF), to improve diagnostic performance. We collected BF and DF images of S. haematobium eggs in patient samples from two different field studies in Côte d’Ivoire using a mobile phone-based microscope, the SchistoScope. We then trained separate egg-detection ML models and compared the patient-level performance of BF and DF models alone to Boolean combinations of BF and DF models, using annotations from trained microscopists as the gold standard. We found that models trained on DF images, and almost all BF and DF combinations, performed significantly better than models trained on BF images only. When models were trained on images from the first field study, patient-level classification performance for images from the second study met the WHO Diagnostic Target Product Profile (TPP) sensitivity and specificity for the monitoring and evaluation use case. When we used images from both field studies for the training set, performance of the models was improved. This work shows that multi-contrast imaging can increase information available for classification tasks, while retaining the portability, power, and time-to-results of the TPP’s desired diagnostic. The imaging contrasts used here require no additional sample preparation and do not increase the complexity of the imaging system, and we used off-the-shelf ML models to simplify software engineering. Multi-contrast machine learning offers a practical means to improve performance of automated diagnostics for S. haematobium , one that could be applied to other microscopy-based diagnostics. Author summary: Schistosomiasis is a neglected tropical disease that impacts hundreds of millions of people worldwide. Patients with Schistosoma haematobium shed parasite eggs in their urine, which can be used as a diagnostic marker of disease. However, identification of those eggs in patient samples normally requires a microscope and trained microscopist. In this work, we show that machine learning models trained on two imaging contrasts, brightfield and darkfield, can improve performance of automated schistosomiasis diagnosis. Using a mobile phone-based microscope (the SchistoScope), we captured brightfield and darkfield images of patient samples during two visits to Côte d’Ivoire and then trained models to detect eggs in the brightfield and darkfield images. When training on images from one visit and testing on images from the other visit, we find that combining the brightfield and darkfield model outputs improved the diagnostic sensitivity and specificity compared to brightfield alone, meeting the target metrics for monitoring and evaluation of schistosomiasis control programs outlined by the World Health Organization. This use of multi-contrast machine learning with a mobile microscope has the potential to improve diagnostic testing for schistosomiasis and could be extended to other neglected tropical diseases.

14 July 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MDMaría Díaz de León Derby
María Díaz de León Derby
JCJean T. Coulibaly
Jean T. Coulibaly
EDElena Dacal
Elena Dacal
KSKigbafori D. Silue
Kigbafori D. Silue
DCDaniel Cuadrado
Daniel Cuadrado
IBIsaac Bogoch
Isaac Bogoch
Background: Schistosomiasis affects over 200 million people and causes significant urogenital and gastrointestinal morbidity. Mass drug administration (MDA) with praziquantel is used to mitigate severe illness and reduce infection rates. Portable microscopy, combined with artificial intelligence (AI), offers a novel method for schistosomiasis screening in low-resource settings. This study tested whether re-training AI models for Schistosoma egg detection with local field data, a process we call “edge-tuning”, could improve the model’s performance on the following field day. Methods: This study in Côte d’Ivoire evaluated a portable microscope (NTDscope) for Schistosoma haematobium screening. Urine samples from 100 community members were analyzed using AI models on the NTDscope and traditional light microscopy. Starting AI models, trained on images from a previous version of the NTDscope, were edge-tuned after the first day of sample collection using cloud-based image annotation and re-training. Starting and edge-tuned models were evaluated at confidence thresholds optimizing for sensitivity, specificity, or egg counting. Findings: For all thresholds, edge-tuned models performed better than starting AI models. Compared to manual counting of eggs on the NTDscope, sensitivity of the starting AI model on day 2 ranged from 59.3%-75.5%, with specificity ranging from 46.7%-85.7%. After edge-tuning, sensitivity increased to 77.8%-100%, with specificity from 78.6%-100%. Compared to light microscopy, edge-tuned AI models had comparable performance to manual counting from NTDscope images. Interpretation: Portable microscopy is an effective solution for rapid, on-site schistosomiasis screening. AI- based egg detection increases diagnostic throughput while maintaining good performance. This study demonstrates that edge-tuning AI models with local data significantly improves their performance and can be performed in low-resource settings, making the combined technologies effective tools for monitoring schistosomiasis programs in endemic areas.

12 February 2026 in PLOS Global Public Health
Verified
Journal Article
Open access
MDMaría Díaz de León Derby
María Díaz de León Derby
ZMZaina L. Moussa
Zaina L. Moussa
CNCarlos F. Ng
Carlos F. Ng
ABAbdul M. Bhuiya
Abdul M. Bhuiya
JCJoana P. Cabrera
Joana P. Cabrera
DFDaniel A. Fletcher
Daniel A. Fletcher
Accurate diagnostics are essential for disease control and elimination efforts. However, access to diagnostics for neglected tropical diseases (NTDs) is hindered by limited healthcare infrastructure in many NTD-endemic regions, as well as by reliance on time- and labor-intensive diagnostic methods, such as smear microscopy. New diagnostic tools that are portable, rapid, low-cost, and meet World Health Organization (WHO) sensitivity and specificity targets are urgently needed to accelerate NTD control and elimination programs. Here, we introduce the NTDscope, a portable microscopy platform that enables point-of-care imaging and automated detection of parasites and other pathogens in patient samples. The NTDscope builds on and extends the capabilities of the LoaScope, a device that turned the camera of a mobile phone into a microscope and used on-board image processing to automatically quantify Loa loa microfilariae burden in whole blood samples. The NTDscope replaces the mobile phone of the LoaScope with a system-on-module (SOM) that enables the integration of multiple imaging modalities in a single package designed to improve robustness and expand applications. In this work, we demonstrate the use of the NTDscope as a portable brightfield, darkfield, and fluorescence microscope for samples including microfilariae and helminth eggs. We also show that the device can be used to quantify molecular assays, such as a lateral flow test and a CRISPR-Cas13a-based assay. The ability to combine the diagnostic capabilities of conventional microscopy with molecular assays and machine learning in a single device could expand access to diagnostics for populations in NTD-endemic areas and beyond.

18 March 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MDMaría Díaz de León Derby
María Díaz de León Derby
ZMZaina L. Moussa
Zaina L. Moussa
CNCarlos F. Ng
Carlos F. Ng
ABAbdul M. Bhuiya
Abdul M. Bhuiya
JCJoana P. Cabrera
Joana P. Cabrera
DFDaniel A. Fletcher
Daniel A. Fletcher
Accurate diagnostics are essential for disease control and elimination efforts. However, access to diagnostics for neglected tropical diseases (NTDs) is hindered by limited healthcare infrastructure in many NTD-endemic regions, as well as by reliance on time- and labor-intensive diagnostic methods, such as smear microscopy. New diagnostic tools that are portable, rapid, low-cost, and meet World Health Organization (WHO) sensitivity and specificity targets are urgently needed to accelerate NTD control and elimination programs. Here, we introduce the NTDscope, a portable microscopy platform that enables point-of-care imaging and automated detection of parasites and other pathogens in patient samples. The NTDscope builds on and extends the capabilities of the LoaScope, a device that turned the camera of a mobile phone into a microscope and used on-board image processing to automatically quantify Loa loa microfilariae burden in whole blood samples. The NTDscope replaces the mobile phone of the LoaScope with a system-on-module (SOM) that enables the integration of multiple imaging modalities in a single package designed to improve robustness and expand applications. In this work, we demonstrate use of the NTDscope as a portable brightfield, darkfield, and fluorescence microscope for samples including microfilariae and helminth eggs. We also show that the device can be used to quantify molecular assays, such as a lateral flow test and a CRISPR-Cas13a-based assay. The ability to combine diagnostic capabilities of conventional microscopy with molecular assays and machine learning in a single device could expand access to diagnostics for populations in NTD-endemic areas and beyond. Author summary: Neglected tropical diseases (NTDs) impact one billion of the world’s most vulnerable individuals. Diagnostics are a necessary part of NTD disease control and elimination efforts, but identifying infected individuals remains a challenge. Here we present the NTDscope, a portable multi-contrast microscope designed to diagnose multiple NTDs at the point-of-care. We show that the NTDscope can be used to detect the parasitic worm Loa loa in videos of whole blood samples and parasitic eggs in images of urine and stool samples. The NTDscope can also be used to image thick blood smears in disposable capillaries and serves as a lateral flow assay reader. In addition to brightfield and darkfield imaging, fluorescence imaging on the device enables molecular assays based on CRISPR-Cas enzymes. This portable (<1 kg), field-friendly device—tested in Cameroon, Gabon, Côte d’Ivoire, and Bangladesh—has the potential to become a platform technology that addresses diagnostic needs for multiple NTDs and could serve as a key element of decentralized healthcare in the future.