DANIELLA LUMARA PEREIRA MENDES DE OLIVEIRA PERES

DANIELLA LUMARA PEREIRA MENDES DE OLIVEIRA PERES

Página do item completo

Resultados de Busca

Agora exibindo 1 - 6 de 6

Classification of oral cancer using Random Forest
2024 - PERES, DANIELLA L.; SILVA. DANIELA F.T.; GERMANO, GLEICE; BACHMANN, LUCIANO; MATOS, LEANDRO L. de; FELIPE, JOAQUIM C.; PEREIRA, THIAGO M.; ZEZELL, DENISE M.
The role of the student chapter in scientific outreach
2024 - PRADO, FELIPE M.; PERES, DANIELLA L.; STASI, RAFFAEL; ANJOS, VINICIUS P. dos; CAVALERO, JULIA G.; ZEZELL, DENISE M.
This paper reviews the activities conducted by a student chapter of optics and photonics in Brazil during the 2023–2024 academic year. The initiative played a significant role within its host institution, contributing to scientific outreach and academic enrichment. The paper assesses key initiatives and their impact on both the broader community and the institution itself. We highlight several events organized during this period, which engaged over 1,500 participants. Additionally, the paper examines the benefits derived from these activities for the institutions, the participants, and the general public, emphasizing their contribution to the dissemination of optics and photonics within the community.
Rapid identification of breast cancer in different stages using micro-FTIR and supervised machine learning methods
2024 - GERMANO, GLEICE; VALLE, MATHEUS D.; PERES, DANIELLA L.P.M. de O.; SILVA, DANIELA de F.T. da; PEREIRA, THIAGO M.; ZEZELL, DENISE M.
According to the World Health Organization, breast cancer is the second most common cancer in the world; 11.5% of the total cases of cancer in both genders and 15.4% of deaths in females are reported. Accurate determination of the intrinsic subtype and disease stage of breast cancer will help in the adoption of optimal treatment strategies, thus improving overall outcomes. The aim of the present work, therefore, is to apply micro-FTIR spectroscopy combined with different supervised machine learning methods to classify various types and stages of breast cancer and to identify the chemometric areas that best distinguish between them. In the work reported here, PCA-LDA and PLS-DA models were carried out in the raw data in the fingerprint region (1800–900 cm−1) and the region characteristic for proteins (1750–1400 cm−1). Therefore, the analysis of these results reveals significant differences in the amide I and amide II regions, thus proving that both PCA-LDA and PLS-DA are useful frameworks for performing discrimination analyses.
A deep neural network approach for oral squamous cell carcinoma identification
2024 - PERES, DANIELLA L.; GERMANO, GLEICE; SILVA, DANIELA F.T.; BACHMANN, LUCIANO; MATOS, LEANDRO L. de; FELIPE, JOAQUIM C.; PEREIRA, THIAGO M.; ZEZELL, DENISE M.
Early detection and diagnosis of oral squamous cell carcinoma (OSCC) are essential for improving patient outcomes. This study presents the development of a deep neural network model trained to classify OSCC using hyperspectral FTIR spectroscopy imaging. The network's performance was evaluated using accuracy, precision, recall, and F1-score metrics. The model demonstrated high effectiveness in classifying unfolded OSCC hyperspectral images, showing potential as a valuable tool for supporting diagnostic processes in clinical settings.
Identification of basal cell carcinoma skin cancer using FTIR and Machine learning
2023 - PERES, DANIELLA L.; FAROOQ, SAJID; RAFFAELI, ROCIO; CROCE, MARIA V.; CROCE, ADELA E.; ZEZELL, DENISE M.
Here we applied ATR-FTIR spectroscopy combined with computational modeling based on 3D-discriminant analysis (3D-PCA-QDA). Our results present an exceptional performance of 3D-discriminant algorithms to diagnose BCC skin cancer, indicating the accuracy up to 99%.
Monitoring changes in urine from diabetic rats using ATR-FTIR and Machine Learning
2023 - FAROOQ, SAJID; PERES, DANIELLA L.; CAIXETA, DOUGLAS C.; LIMA, CASSIO; SILVA, ROBINSON S. da; ZEZELL, DENISE M.
Here, we aim to better characterize diabetes mellitus (DM) by analyzing 149 urine spectral samples, comprising of diabetes versus healthy control groups employing ATR-FTIR spectroscopy, combined with a 3D discriminant analysis machine learning approach. Our results depict that the model is highly precise with accuracy close to 100%.