Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study

Shavlokhova, Veronika; Sandhu, Sameena; Flechtenmacher, Christa; Kövesházi, István; Neumeier, Florian; Padrón-Laso, Víctor; Jonke, Žan; Saravi, Babak; Vollmer, Michael; Vollmer, Andreas; Hoffmann, Jürgen; Engel, Michael; Ristow, Oliver

doi:10.3390/jcm10225326

Cited by 30 publications

(29 citation statements)

References 44 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs are composed of many hidden layers, such as convolutional layers, pooling layers, fully connected layers, and normalizing layers. A ConvNet is designed to mimic the organization of the visual cortex and the pattern of connectivity of the neurons in the human brain [ 13 ]. In dentistry, interest in this area of research has increased significantly in recent years [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Based Prediction of Oroantral Communication after Tooth Extraction Utilizing Preoperative Panoramic Radiography

et al. 2022

Self Cite

View full text Add to dashboard Cite

Oroantral communication (OAC) is a common complication after tooth extraction of upper molars. Profound preoperative panoramic radiography analysis might potentially help predict OAC following tooth extraction. In this exploratory study, we evaluated n = 300 consecutive cases (100 OAC and 200 controls) and trained five machine learning algorithms (VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50) to predict OAC versus non-OAC (binary classification task) from the input images. Further, four oral and maxillofacial experts evaluated the respective panoramic radiography and determined performance metrics (accuracy, area under the curve (AUC), precision, recall, F1-score, and receiver operating characteristics curve) of all diagnostic approaches. Cohen’s kappa was used to evaluate the agreement between expert evaluations. The deep learning algorithms reached high specificity (highest specificity 100% for InceptionV3) but low sensitivity (highest sensitivity 42.86% for MobileNetV2). The AUCs from VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50 were 0.53, 0.60, 0.67, 0.51, and 0.56, respectively. Expert 1–4 reached an AUC of 0.550, 0.629, 0.500, and 0.579, respectively. The specificity of the expert evaluations ranged from 51.74% to 95.02%, whereas sensitivity ranged from 14.14% to 59.60%. Cohen’s kappa revealed a poor agreement for the oral and maxillofacial expert evaluations (Cohen’s kappa: 0.1285). Overall, present data indicate that OAC cannot be sufficiently predicted from preoperative panoramic radiography. The false-negative rate, i.e., the rate of positive cases (OAC) missed by the deep learning algorithms, ranged from 57.14% to 95.24%. Surgeons should not solely rely on panoramic radiography when evaluating the probability of OAC occurrence. Clinical testing of OAC is warranted after each upper-molar tooth extraction.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-Based Prediction of Oroantral Communication after Tooth Extraction Utilizing Preoperative Panoramic Radiography

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…SVM achieved the best performance for classifying color and texture features. Veronika et al [ 10 ] presented a MobileNet model for diagnosing squamous cell carcinoma through pooled samples of 20 patients. The model achieved a sensitivity and specificity of 47% and 96%, respectively.…”

Section: Related Workmentioning

confidence: 99%

“… Comparison of the performance of our system with previous studies for diagnosing oral squamous cell carcinomas [ 6 , 10 , 16 , 37 , 38 , 39 ]. …”

Section: Figurementioning

confidence: 99%

Early Diagnosis of Oral Squamous Cell Carcinoma Based on Histopathological Images Using Deep and Hybrid Learning Approaches

2022

View full text Add to dashboard Cite

Oral squamous cell carcinoma (OSCC) is one of the most common head and neck cancer types, which is ranked the seventh most common cancer. As OSCC is a histological tumor, histopathological images are the gold diagnosis standard. However, such diagnosis takes a long time and high-efficiency human experience due to tumor heterogeneity. Thus, artificial intelligence techniques help doctors and experts to make an accurate diagnosis. This study aimed to achieve satisfactory results for the early diagnosis of OSCC by applying hybrid techniques based on fused features. The first proposed method is based on a hybrid method of CNN models (AlexNet and ResNet-18) and the support vector machine (SVM) algorithm. This method achieved superior results in diagnosing the OSCC data set. The second proposed method is based on the hybrid features extracted by CNN models (AlexNet and ResNet-18) combined with the color, texture, and shape features extracted using the fuzzy color histogram (FCH), discrete wavelet transform (DWT), local binary pattern (LBP), and gray-level co-occurrence matrix (GLCM) algorithms. Because of the high dimensionality of the data set features, the principal component analysis (PCA) algorithm was applied to reduce the dimensionality and send it to the artificial neural network (ANN) algorithm to diagnose it with promising accuracy. All the proposed systems achieved superior results in histological image diagnosis of OSCC, the ANN network based on the hybrid features using AlexNet, DWT, LBP, FCH, and GLCM achieved an accuracy of 99.1%, specificity of 99.61%, sensitivity of 99.5%, precision of 99.71%, and AUC of 99.52%.

show abstract

“…It is a technique where there is the potential to use artificial intelligence approaches to interpretation in the future. 69 …”

Section: Feasibility Of Use In Cipnmentioning

confidence: 99%

The Value of In Vivo Reflectance Confocal Microscopy as an Assessment Tool in Chemotherapy-Induced Peripheral Neuropathy: A Pilot Study

et al. 2022

View full text Add to dashboard Cite

Background There is a lack of standardized objective and reliable assessment tools for chemotherapy-induced peripheral neuropathy (CIPN). In vivo reflectance confocal microscopy (RCM) imaging offers a non-invasive method to identify peripheral neuropathy markers, namely Meissner’s corpuscles (MC). This study investigated the feasibility and value of RCM in CIPN. Patients and Methods Reflectance confocal microscopy was performed on the fingertip to evaluate MC density in 45 healthy controls and 9 patients with cancer (prior, during, and post-chemotherapy). Quantification was completed by 2 reviewers (one blinded), with maximum MC count/3 × 3 mm image reported. Quantitative Sensory Testing (QST; thermal and mechanical detection thresholds), Grooved pegboard test, and patient-reported outcomes measures (PROMS) were conducted for comparison. Results In controls (25 females, 20 males; 24-81 years), females exhibited greater mean MC density compared with males (49.9 ± 7.1 vs 30.9 ± 4.2 MC/3 × 3 mm; P = .03). Differences existed across age by decade (P < .0001). Meissner’s corpuscle density was correlated with mechanical detection (ρ = −0.51), warm detection (ρ = −0.47), cold pain (ρ = 0.49) thresholds (P < .01); and completion time on the Grooved pegboard test in both hands (P ≤ .02). At baseline, patients had reduced MC density vs age and gender-matched controls (P = .03). Longitudinal assessment of MC density revealed significant relationships with QST and PROMS. Inter-rater reliability of MC count showed an intraclass correlation of 0.96 (P < .0001). Conclusions The findings support the clinical utility of RCM in CIPN as it provides meaningful markers of sensory nerve dysfunction. Novel, prospective assessment demonstrated the ability to detect subclinical deficits in patients at risk of CIPN and potential to monitor neuropathy progression.

show abstract

Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study

Cited by 30 publications

References 44 publications

Artificial Intelligence-Based Prediction of Oroantral Communication after Tooth Extraction Utilizing Preoperative Panoramic Radiography

Artificial Intelligence-Based Prediction of Oroantral Communication after Tooth Extraction Utilizing Preoperative Panoramic Radiography

Early Diagnosis of Oral Squamous Cell Carcinoma Based on Histopathological Images Using Deep and Hybrid Learning Approaches

The Value of In Vivo Reflectance Confocal Microscopy as an Assessment Tool in Chemotherapy-Induced Peripheral Neuropathy: A Pilot Study

Contact Info

Product

Resources

About