Digital diaphanoscopy data processing for differentiation of maxillary sinus pathologies

Bryanskaya, Ekaterina O.; Dremin, Viktor; Novikova, Irina N.; Nikolaeva, Yu.O.; Pil'nikov, Vladislav G.; Bakotina, A.V.; Овчинников, А. Ю.; Панченков, Д. Н.; Baranov, A.V. Baranov; Artyushenko, Viacheslav; Dunaev, Andrey V.

doi:10.1109/iclo54117.2022.9839976

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the results obtained, the boundaries in the intensity parameter and asymmetry coefficient values for a healthy sinus and a sinus with pathology are clearly traced. LDA was chosen as an approach to construct the classification model [22]. The discriminant function can be represented in the following formula:…”

Section: The Linear Discriminant Analysis Applicationmentioning

confidence: 99%

“…Machine learning approaches have great potential in supporting this application. Quantitative parameters of the registered diaphanograms obtained earlier could be used as diagnostic criteria to build a classification model [22,23], in particular utilizing linear discriminant analysis (LDA) [24]. In addition, the application of pattern recognition theory, namely convolutional neural networks (CNN), seems promising for the differentiation of the condition of the maxillary sinuses (presence or absence of pathology) due to the method's resistance to small shifts and rotations of objects in the input images possible during diagnostic procedure [25][26][27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Bryanskaya

Dremin

Shupletsov

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Maxillary sinus pathologies remain among the most common ENT diseases requiring timely diagnosis for successful treatment. Standard ENT inspection approaches indicate low sensitivity in detecting maxillary sinus pathologies. In this paper, we report on capabilities of digital diaphanoscopy combined with machine learning tools in the detection of such pathologies. We provide a comparative analysis of two machine learning approaches applied to digital diapahnoscopy data, namely, convolutional neural networks and linear discriminant analysis. The sensitivity and specificity values obtained for both employed approaches exceed the reported accuracy indicators for traditional screening diagnosis methods (such as nasal endoscopy or ultrasound), suggesting the prospects of their usage for screening maxillary sinuses alterations. The analysis of the obtained values showed that the linear discriminant analysis, being a simpler approach as compared to neural networks, allows one to detect the maxillary sinus pathologies with the sensitivity and specificity of 0.88 and 0.98, respectively.

show abstract

Section: The Linear Discriminant Analysis Applicationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Bryanskaya

Dremin

Shupletsov

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…Magnetic Resonance Imaging, a non-invasive imaging technique, employs a strong magnetic field and radiofrequency pulses to create detailed images of the soft tissues within the body. MRI has become the gold standard for evaluating soft tissue structures, making it particularly well-suited for the assessment of skull base pathologies [8]. One of the key advantages of MRI is its excellent contrast resolution, allowing for clear visualization of different tissues and their pathological changes.…”

Section: Magnetic Resonance Imaging (Mri)mentioning

confidence: 99%

Comparative analysis of diagnostic accuracy between MRI and CT scans in detecting skull base ENT pathologies

Iqbal,

Khursheed,

Ibrahim

et al. 2023

View full text Add to dashboard Cite

Skull base ENT (Ear, Nose, and Throat) pathologies present a diagnostic challenge due to their intricate location. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans are commonly used diagnostic tools for detecting these pathologies. This study aims to associate the diagnostic exactness of MRI and CT scans in detecting skull base ENT pathologies. Aim: The primary objective of our current research is to assess and associate the diagnostic accuracy of MRI and CT scans in detecting skull base ENT pathologies, including tumors, infections, and congenital anomalies. Methods: Researchers led the retrospective study of medical records from the cohort of patients with suspected skull base ENT pathologies who underwent both MRI and CT scans. Imaging reports were reviewed by experienced radiologists blinded to the clinical outcomes. Diagnostic accuracy metrics, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were calculated for each modality. McNemar's test was utilized to assess statistical significance of differences in diagnostic accuracy between MRI and CT. Results: An overall of 150 individuals were involved in our research. MRI demonstrated a sensitivity of 87%, specificity of 92%, PPV of 85%, and NPV of 93% in detecting skull base ENT pathologies. CT scans showed a sensitivity of 72%, specificity of 78%, PPV of 70%, and NPV of 80%. The diagnostic accuracy of MRI was significantly higher than that of CT for detecting these pathologies (p < 0.05). Subgroup analyses were performed for different types of pathologies, providing valuable insights into the strengths and limitations of each imaging modality. Conclusion: This comparative analysis highlights the superior diagnostic accuracy of MRI over CT scans in detecting skull base ENT pathologies. MRI offers higher sensitivity and specificity, making it a valuable tool for clinicians in the evaluation and management of individuals with these conditions. However, CT may still have a role in specific cases where MRI is contraindicated or for initial screening. Clinicians should consider these findings when selecting the most appropriate imaging modality for patients with suspected skull base ENT pathologies.

show abstract

Digital diaphanoscopy data processing for differentiation of maxillary sinus pathologies

Cited by 2 publications

References 3 publications

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Digital diaphanoscopy of maxillary sinus pathologies supported by machine learning

Comparative analysis of diagnostic accuracy between MRI and CT scans in detecting skull base ENT pathologies

Contact Info

Product

Resources

About