Clinical, histopathological, and radiological features of unilateral nasal mass in Saudi Arabia: A retrospective study

Hakami, Khalid; Basurrah, Mohammed Abdullah; Alshehri, AliM; Althagafi, KhalidA; Alotaibi, AbdulazizO; Alharthi, MohammedF

doi:10.4103/sjhs.sjhs_168_19

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tumorous lesions in the nasal cavity and paranasal sinuses are of several histopathological types and are highly heterogeneous [1][2][3]. Non-neoplastic and neoplastic lesions are common in the nasal cavity [2].…”

Section: Introductionmentioning

confidence: 99%

Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images

Kwon,

Park,

Lee

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Nasal endoscopy is routinely performed to distinguish the pathological types of masses. There is a lack of studies on deep learning algorithms for discriminating a wide range of endoscopic nasal cavity mass lesions. Therefore, we aimed to develop an endoscopic-examination-based deep learning model to detect and classify nasal cavity mass lesions, including nasal polyps (NPs), benign tumors, and malignant tumors. The clinical feasibility of the model was evaluated by comparing the results to those of manual assessment. Biopsy-confirmed nasal endoscopic images were obtained from 17 hospitals in South Korea. Here, 400 images were used for the test set. The training and validation datasets consisted of 149,043 normal nasal cavity, 311,043 NP, 9,271 benign tumor, and 5,323 malignant tumor lesion images. The proposed Xception architecture achieved an overall accuracy of 0.792 with the following class accuracies on the test set: normal = 0.978 ± 0.016, NP = 0.790 ± 0.016, benign = 0.708 ± 0.100, and malignant = 0.698 ± 0.116. With an average area under the receiver operating characteristic curve (AUC) of 0.947, the AUC values and F1 score were highest in the order of normal, NP, malignant tumor, and benign tumor classes. The classification performances of the proposed model were comparable with those of manual assessment in the normal and NP classes. The proposed model outperformed manual assessment in the benign and malignant tumor classes (sensitivities of 0.708 ± 0.100 vs. 0.549 ± 0.172, 0.698 ± 0.116 vs. 0.518 ± 0.153, respectively). In urgent (malignant) versus nonurgent binary predictions, the deep learning model achieved superior diagnostic accuracy. The developed model based on endoscopic images achieved satisfactory performance in classifying four classes of nasal cavity mass lesions, namely normal, NP, benign tumor, and malignant tumor. The developed model can therefore be used to screen nasal cavity lesions accurately and rapidly.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images

Kwon,

Park,

Lee

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

The Utility of Clinicopathological Correlation of Sinonasal Masses in a Tertiary Hospital

Hasan¹,

Nady²,

Ibrahim³

et al. 2021

jemds

View full text Add to dashboard Cite

BACKGROUND Sinonasal masses are commonly seen lesions in ENT practice with multiple aetiological factors. We wanted to study the clinico-pathological features of nasal mass specimens in a tertiary hospital and evaluate the utility of routine histopathological examination of the surgically removed nasal tissue specimens. METHODS All the histologically examined specimens of patients clinically presenting with nasal or sinonasal lesions over a period of one year were retrospectively studied and analyzed. RESULTS Out of total 36 patients with masses, 21 were males (58.3 %) and 15 (41.7 %) were females. The age ranged from 10 to 75 years with a mean age of 31.4 years and maximum patients were in the third decade (37.5 %). The most common presenting clinical symptom was nasal obstruction that was seen in 33 patients (91.6 %). Computed tomography (CT) scan was done in 94.5 % of cases prior to the surgical intervention. One fifth of the sinonasal lesions were neoplastic as per histopathology examination. The clinicopathological agreement percentage for detection of the nature of the nasal mass was 88.9 %. The applied interrater reliability in Cohen's kappa coefficient (κ) showed moderate agreement (0.55). CONCLUSIONS The clinical similarity between the histologically different lesions is common and may lead to improper management; so, correlation of clinical, radiologic and pathologic features is of utmost importance for accurate diagnosis and the policy of discarding a surgically removed nasal lesion which clinically appears unremarkable should be totally avoided. KEY WORDS Nasal Polyp, Pathology, Sinonasal Carcinoma

show abstract

Clinical, histopathological, and radiological features of unilateral nasal mass in Saudi Arabia: A retrospective study

Cited by 2 publications

References 0 publications

Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images

Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images

The Utility of Clinicopathological Correlation of Sinonasal Masses in a Tertiary Hospital

Contact Info

Product

Resources

About