Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology

Hirokawa, Mitsuyoshi; Niioka, Hirohiko; Suzuki, Ayana; Abe, Masatoshi; Arai, Yusuke; Nagahara, Hajime; Miyauchi, Akira; Akamizu, Takashi

doi:10.1002/cncy.22669

Cited by 17 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Digital thyroid fine needle aspiration biopsy images are employed in these studies. EfficientNetV2-L image classification works in thyroid fine needle aspiration cytology, according to Hirokawa et al [20]. Kezalarian [21] studied AI's role in follicular cancer vs. adenoma, whereas Alabrak et al proposed a CNN model with good accuracy, sensitivity, specificity, and AUC-score [22].…”

Section: Related and Recent Workmentioning

confidence: 99%

Enhancing Thyroid Cancer Diagnostics Through Hybrid Machine Learning and Metabolomics Approaches

Raj

2024

IJACSA

View full text Add to dashboard Cite

Thyroid cancer, a prevalent endocrine malignancy, necessitates advanced diagnostic techniques for accurate and early detection. This study introduces an innovative approach that integrates hybrid Machine Learning (ML) algorithms with metabolomics, offering a novel pathway in thyroid cancer diagnostics. Our methodology employs a range of hybrid ML models, combining the strengths of various algorithms to analyze complex metabolomic data effectively. These models include ensemble methods, neural network-based hybrids, and integrations of unsupervised and supervised learning techniques, tailored to decipher the intricate patterns within metabolic profiles associated with thyroid cancer. The study demonstrates how these hybrid ML algorithms can efficiently process and interpret metabolomic data, leading to enhanced diagnostic accuracy. By leveraging the distinct characteristics of each ML model, our approach not only improves the detection of thyroid cancer but also contributes to a deeper understanding of its metabolic underpinnings. The findings of this study pave the way for more personalized and precise medical interventions in thyroid cancer management, showcasing the potential of hybrid ML models in revolutionizing cancer diagnostics. Our system analyzes thyroid cancer metabolomic data using ensemble methods, neural network-based hybrids, and unsupervised and supervised learning integrations. The research shows hybrid ML models may revolutionize cancer diagnoses by improving accuracy. LSTM+CNN, LSTM+GRU, and CNN+GRU have high accuracy rates, helping us comprehend thyroid cancer's biochemical roots. Hybrid ML models enhance thyroid cancer diagnosis and management, enabling more tailored and accurate medical treatments. The hybrid machine learning models like LSTM+CNN, LSTM+GRU, and CNN+GRU beat CNN, VGG-19, Inception-ResNet-v2, decision support, and random forests (99.45%).

show abstract

Section: Related and Recent Workmentioning

confidence: 99%

Enhancing Thyroid Cancer Diagnostics Through Hybrid Machine Learning and Metabolomics Approaches

Raj

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…However, then biopsy is fundamental to make the diagnosis. Fine needle aspiration (FNA) cytology using a 21-25 gauge needle under US guidance has been widely used as an initial step in diagnosis by cytologic examination[ 20 , 21 , 34 , 45 , 60 ]. However, due to its high false-negative results, low sensitivity of 54%-61% vs 77%-80% of core needle biopsy (CNB), and specificity of 87% vs 100% of CNB[ 20 , 21 ] or often inconclusive results, this option tends to be omitted recently in favor of CNB.…”

Section: Diagnosismentioning

confidence: 99%

“…Machine learning with deep learning along with artificial intelligence implementation has provided preliminary encouraging results for diagnosis, imaging assessment, treatment and outcome prediction. It now remains to be used in clinical practice[ 10 , 34 ]. A multidisciplinary approach must be followed with an individualized therapeutic plan based on surveillance and epidemiology end results (SEER)[ 3 , 9 , 35 - 37 ].…”

Section: Introductionmentioning

confidence: 99%

Update on current diagnosis and management of anaplastic thyroid carcinoma

Pavlidis,

Galanis,

Pavlidis

2023

World J Clin Oncol

View full text Add to dashboard Cite

Well-differentiated thyroid carcinoma has a favorable prognosis with a 5-year survival rate of over 95%. However, the undifferentiated or anaplastic type accounting for < 0.2%, usually in elderly individuals, exhibits a dismal prognosis with rapid growth and disappointing outcomes. It is the most aggressive form of thyroid carcinoma, with a median survival of 5 mo and poor quality of life (airway obstruction, dysphagia, hoarseness, persistent pain). Early diagnosis and staging are crucial. Diagnostic tools include biopsy (fine needle aspiration, core needle, open surgery), high-resolution ultrasound, computed tomography, magnetic resonance imaging, [(18)F]fluoro-D-glucose positron emission tomo-graphy/computed tomography, liquid biopsy and microRNAs. The BRAF gene (BRAF-V600E and BRAF wild type) is the most often found molecular factor. Others include the genes RET, KRAS, HRAS, and NRAS . Recent management policy is based on surgery, even debulking, chemotherapy (cisplatin or doxorubicin), radiotherapy (adjuvant or definitive), targeted biological agents and immunotherapy. The last two options constitute novel hopeful management modalities improving the overall survival in these otherwise condemned patients. Anti-programmed death-ligand 1 antibody immunotherapy, stem cell targeted therapies, nanotechnology achievements and artificial intelligence imple-mentation provide novel promising alternatives. Genetic mutations determine molecular pathways, thus indicating novel treatment strategies such as anti-BRAF, anti-vascular endothelial growth factor-A, and anti-epidermal growth factor receptor. Treatment with the combination of the BRAF inhibitor dabrafenib and the MEK inhibitor trametinib has been approved by the Food and Drug Administration in cases with BRAF-V600E gene mutations and is currently the standard care. This neoadjuvant treatment followed by surgery ensures a two-year overall survival of 80%. Prognostic factors for improved outcomes have been found to be younger age, earlier tumor stage and radiation therapy. A multidisciplinary approach is necessary, and the therapeutic plan should be individualized based on surveillance and epidemiology end results.

show abstract

“…The EfficientNet network proposed by the Google Brain team in 2019 ensures the model’s accuracy while reducing its parameter scale [ 21 ]. The EfficientNetV2 network was proposed in 2021 as an update to the EfficientNet network, which has made remarkable achievements in the diagnosis and prognosis of various human diseases [ 16 , 22 – 24 ].…”

Section: Introductionmentioning

confidence: 99%

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

Xu,

Wang,

Dai

et al. 2024

J Digit Imaging. Inform. med.

View full text Add to dashboard Cite

We aimed to develop and validate a deep learning-based system using pre-therapy computed tomography (CT) images to detect epidermal growth factor receptor (EGFR)-mutant status in patients with non-small cell lung cancer (NSCLC) and predict the prognosis of advanced-stage patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors (TKI). This retrospective, multicenter study included 485 patients with NSCLC from four hospitals. Of them, 339 patients from three centers were included in the training dataset to develop an EfficientNetV2-L-based model (EME) for predicting EGFR-mutant status, and the remaining patients were assigned to an independent test dataset. EME semantic features were extracted to construct an EME-prognostic model to stratify the prognosis of EGFR-mutant NSCLC patients receiving EGFR-TKI. A comparison of EME and radiomics was conducted. Additionally, we included patients from The Cancer Genome Atlas lung adenocarcinoma dataset with both CT images and RNA sequencing data to explore the biological associations between EME score and EGFR-related biological processes. EME obtained an area under the curve (AUC) of 0.907 (95% CI 0.840–0.926) on the test dataset, superior to the radiomics model (P = 0.007). The EME and radiomics fusion model showed better (AUC, 0.941) but not significantly increased performance (P = 0.895) compared with EME. In prognostic stratification, the EME-prognostic model achieved the best performance (C-index, 0.711). Moreover, the EME-prognostic score showed strong associations with biological pathways related to EGFR expression and EGFR-TKI efficacy. EME demonstrated a non-invasive and biologically interpretable approach to predict EGFR status, stratify survival prognosis, and correlate biological pathways in patients with NSCLC.

show abstract

Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology

Cited by 17 publications

References 36 publications

Enhancing Thyroid Cancer Diagnostics Through Hybrid Machine Learning and Metabolomics Approaches

Enhancing Thyroid Cancer Diagnostics Through Hybrid Machine Learning and Metabolomics Approaches

Update on current diagnosis and management of anaplastic thyroid carcinoma

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

Contact Info

Product

Resources

About