Dataset Information

Differentiating malignant and benign eyelid lesions using deep learning.

ABSTRACT: Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion, and no lesion. Two pre-trained convolutional neural network (CNN) models, DenseNet-161 and EfficientNetV2-M architectures, were fine-tuned to classify images into three or two (malignant versus benign) categories. For a ternary classification, the mean diagnostic accuracies of the CNNs were 82.1% and 83.0% using DenseNet-161 and EfficientNetV2-M, respectively, which were inferior to those of the nine clinicians (87.0-89.5%). For the binary classification, the mean accuracies were 87.5% and 92.5% using DenseNet-161 and EfficientNetV2-M models, which was similar to that of the clinicians (85.8-90.0%). The mean AUC of the two CNN models was 0.908 and 0.950, respectively. Gradient-weighted class activation map successfully highlighted the eyelid tumors on clinical photographs. Deep learning models showed a promising performance in discriminating malignant versus benign eyelid lesions on clinical photographs, reaching the level of human observers.

SUBMITTER: Lee MJ

PROVIDER: S-EPMC10011394 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Differentiating malignant and benign eyelid lesions using deep learning.

Lee Min Joung MJ Yang Min Kyu MK Khwarg Sang In SI Oh Eun Kyu EK Choi Youn Joo YJ Kim Namju N Choung Hokyung H Seo Chang Won CW Ha Yun Jong YJ Cho Min Ho MH Cho Bum-Joo BJ

Scientific reports 20230313 1

Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion ...[more]

PMID: 36914694

Similar Datasets

Project description:PurposeTo compare the diagnostic efficiencies of deep learning single-modal and multi-modal for the classification of benign and malignant breast mass lesions.MethodsWe retrospectively collected data from 203 patients (207 lesions, 101 benign and 106 malignant) with breast tumors who underwent breast magnetic resonance imaging (MRI) before surgery or biopsy between January 2014 and October 2020. Mass segmentation was performed based on the three dimensions-region of interest (3D-ROI) minimum bounding cube at the edge of the lesion. We established single-modal models based on a convolutional neural network (CNN) including T2WI and non-fs T1WI, the dynamic contrast-enhanced (DCE-MRI) first phase was pre-contrast T1WI (d1), and Phases 2, 4, and 6 were post-contrast T1WI (d2, d4, d6); and Multi-modal fusion models with a Sobel operator (four_mods:T2WI, non-fs-T1WI, d1, d2). Training set (n = 145), validation set (n = 22), and test set (n = 40). Five-fold cross validation was performed. Accuracy, sensitivity, specificity, negative predictive value, positive predictive value, and area under the ROC curve (AUC) were used as evaluation indicators. Delong's test compared the diagnostic performance of the multi-modal and single-modal models.ResultsAll models showed good performance, and the AUC values were all greater than 0.750. Among the single-modal models, T2WI, non-fs-T1WI, d1, and d2 had specificities of 77.1%, 77.2%, 80.2%, and 78.2%, respectively. d2 had the highest accuracy of 78.5% and showed the best diagnostic performance with an AUC of 0.827. The multi-modal model with the Sobel operator performed better than single-modal models, with an AUC of 0.887, sensitivity of 79.8%, specificity of 86.1%, and positive prediction value of 85.6%. Delong's test showed that the diagnostic performance of the multi-modal fusion models was higher than that of the six single-modal models (T2WI, non-fs-T1WI, d1, d2, d4, d6); the difference was statistically significant (p = 0.043, 0.017, 0.006, 0.017, 0.020, 0.004, all were greater than 0.05).ConclusionsMulti-modal fusion deep learning models with a Sobel operator had excellent diagnostic value in the classification of breast masses, and further increase the efficiency of diagnosis.

Project description:ObjectivesTo develop and validate a dual-energy CT (DECT)-based model for noninvasively differentiating between benign and malignant breast lesions detected on DECT.Materials and methodsThis study prospectively enrolled patients with suspected breast cancer who underwent dual-phase contrast-enhanced DECT from July 2022 to July 2023. Breast lesions were randomly divided into the training and test cohorts at a ratio of 7:3. Clinical characteristics, DECT-based morphological features, and DECT quantitative parameters were collected. Univariate analyses and multivariate logistic regression were performed to determine independent predictors of benign and malignant breast lesions. An individualized model was constructed. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic ability of the model, whose calibration and clinical usefulness were assessed by calibration curve and decision curve analysis.ResultsThis study included 200 patients (mean age, 49.9 ± 11.9 years; age range, 22-83 years) with 222 breast lesions. Age, lesion shape, and the effective atomic number (Zeff) in the venous phase were significant independent predictors of breast lesions (all p < 0.05). The discriminative power of the model incorporating these three factors was high, with AUCs of 0.844 (95%CI 0.764-0.925) and 0.791 (95% CI 0.647-0.935) in the training and test cohorts, respectively. The constructed model showed a preferable fitting (all p > 0.05 by the Hosmer-Lemeshow test) and provided enhanced net benefits than simple default strategies within a wide range of threshold probabilities in both cohorts.ConclusionThe DECT-based model showed a favorable diagnostic performance for noninvasive differentiation between benign and malignant breast lesions detected on DECT.Critical relevance statementThe combination of clinical and morphological characteristics and DECT-derived parameter have the potential to identify benign and malignant breast lesions and it may be useful for incidental breast lesions on DECT to decide if further work-up is needed.Key pointsIt is important to characterize incidental breast lesions on DECT for patient management. DECT-based model can differentiate benign and malignant breast lesions with good performance. DECT-based model is a potential tool for distinguishing breast lesions detected on DECT.

Project description:BackgroundComputer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fully-automatic diagnosis using deep learning is rarely reported.PurposeTo evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deep-learning methods, by taking peritumor tissues into consideration.Study typeRetrospective.PopulationIn all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing).Field strength/sequence3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence.Assessment3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connected-component labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs.Statistical testsThe malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis.ResultsIn the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the per-lesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%.Data conclusionDeep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes.Level of evidence3 Technical Efficacy: Stage 2.

Project description:This study assessed the diagnostic performance of a deep learning (DL)-based model for differentiating malignant subcentimeter (≤10 mm) solid pulmonary nodules (SSPNs) from benign ones in computed tomography (CT) images compared against radiologists with 10 and 15 years of experience in thoracic imaging (medium-senior seniority). Overall, 200 SSPNs (100 benign and 100 malignant) were retrospectively collected. Malignancy was confirmed by pathology, and benignity was confirmed by follow-up or pathology. CT images were fed into the DL model to obtain the probability of malignancy (range, 0-100%) for each nodule. According to the diagnostic results, enrolled nodules were classified into benign, malignant, or indeterminate. The accuracy and diagnostic composition of the model were compared with those of the radiologists using the McNemar-Bowker test. Enrolled nodules were divided into 3-6-, 6-8-, and 8-10-mm subgroups. For each subgroup, the diagnostic results of the model were compared with those of the radiologists. The accuracy of the DL model, in differentiating malignant and benign SSPNs, was significantly higher than that of the radiologists (71.5% vs. 38.5%, P<0.001). The DL model reported more benign or malignant deterministic results and fewer indeterminate results. In subgroup analysis of nodule size, the DL model also yielded higher performance in comparison with that of the radiologists, providing fewer indeterminate results. The accuracy of the two methods in the 3-6-, 6-8-, and 8-10-mm subgroups was 75.5% vs. 28.3% (P<0.001), 62.0% vs. 28.2% (P<0.001), and 77.6% vs. 55.3% (P=0.001), respectively, and the indeterminate results were 3.8% vs. 66.0%, 8.5% vs. 66.2%, and 2.6% vs. 35.5% (all P<0.001), respectively. The DL-based method yielded higher performance in comparison with that of the radiologists in differentiating malignant and benign SSPNs. This DL model may reduce uncertainty in diagnosis and improve diagnostic accuracy, especially for SSPNs smaller than 8 mm.

Project description:ObjectivesTo investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning.MethodsIn this retrospective analysis of an average risk colorectal cancer screening sample, polyps of all size categories and morphologies were manually segmented on supine and prone CT colonography images and classified as premalignant (adenoma) or benign (hyperplastic polyp or regular mucosa) according to histopathology. Two deep learning models SEG and noSEG were trained on 3D CT colonography image subvolumes to predict polyp class, and model SEG was additionally trained with polyp segmentation masks. Diagnostic performance was validated in an independent external multicentre test sample. Predictions were analysed with the visualisation technique Grad-CAM++.ResultsThe training set consisted of 107 colorectal polyps in 63 patients (mean age: 63 ± 8 years, 40 men) comprising 169 polyp segmentations. The external test set included 77 polyps in 59 patients comprising 118 polyp segmentations. Model SEG achieved a ROC-AUC of 0.83 and 80% sensitivity at 69% specificity for differentiating premalignant from benign polyps. Model noSEG yielded a ROC-AUC of 0.75, 80% sensitivity at 44% specificity, and an average Grad-CAM++ heatmap score of ≥ 0.25 in 90% of polyp tissue.ConclusionsIn this proof-of-concept study, deep learning enabled the differentiation of premalignant from benign colorectal polyps detected with CT colonography and the visualisation of image regions important for predictions. The approach did not require polyp segmentation and thus has the potential to facilitate the identification of high-risk polyps as an automated second reader.Key points• Non-invasive deep learning image analysis may differentiate premalignant from benign colorectal polyps found in CT colonography scans. • Deep learning autonomously learned to focus on polyp tissue for predictions without the need for prior polyp segmentation by experts. • Deep learning potentially improves the diagnostic accuracy of CT colonography in colorectal cancer screening by allowing for a more precise selection of patients who would benefit from endoscopic polypectomy, especially for patients with polyps of 6-9 mm size.

Project description:BackgroundAccurate preoperative identification of ovarian tumour subtypes is imperative for patients as it enables physicians to custom-tailor precise and individualized management strategies. So, we have developed an ultrasound (US)-based multiclass prediction algorithm for differentiating between benign, borderline, and malignant ovarian tumours.MethodsWe randomised data from 849 patients with ovarian tumours into training and testing sets in a ratio of 8:2. The regions of interest on the US images were segmented and handcrafted radiomics features were extracted and screened. We applied the one-versus-rest method in multiclass classification. We inputted the best features into machine learning (ML) models and constructed a radiomic signature (Rad_Sig). US images of the maximum trimmed ovarian tumour sections were inputted into a pre-trained convolutional neural network (CNN) model. After internal enhancement and complex algorithms, each sample's predicted probability, known as the deep transfer learning signature (DTL_Sig), was generated. Clinical baseline data were analysed. Statistically significant clinical parameters and US semantic features in the training set were used to construct clinical signatures (Clinic_Sig). The prediction results of Rad_Sig, DTL_Sig, and Clinic_Sig for each sample were fused as new feature sets, to build the combined model, namely, the deep learning radiomic signature (DLR_Sig). We used the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) to estimate the performance of the multiclass classification model.ResultsThe training set included 440 benign, 44 borderline, and 196 malignant ovarian tumours. The testing set included 109 benign, 11 borderline, and 49 malignant ovarian tumours. DLR_Sig three-class prediction model had the best overall and class-specific classification performance, with micro- and macro-average AUC of 0.90 and 0.84, respectively, on the testing set. Categories of identification AUC were 0.84, 0.85, and 0.83 for benign, borderline, and malignant ovarian tumours, respectively. In the confusion matrix, the classifier models of Clinic_Sig and Rad_Sig could not recognise borderline ovarian tumours. However, the proportions of borderline and malignant ovarian tumours identified by DLR_Sig were the highest at 54.55% and 63.27%, respectively.ConclusionsThe three-class prediction model of US-based DLR_Sig can discriminate between benign, borderline, and malignant ovarian tumours. Therefore, it may guide clinicians in determining the differential management of patients with ovarian tumours.

Project description:BackgroundConvex probe endobronchial ultrasound images can reflect the morphology, blood flow status and stiffness of the lesions. Endobronchial ultrasound multimodal imaging has great value for the diagnosis of intrathoracic lymph nodes. This study aimed to analyze the application of endobronchial ultrasound multimodal imaging on lung lesions.MethodsPatients undergoing endobronchial ultrasound-guided transbronchial needle aspiration in Shanghai Chest Hospital from July 2018 to December 2019 were retrospectively enrolled. Nine grayscale features (long and short axes, margin, shape, lobulation sign, echogenicity, necrosis, liquefaction, calcification, and air-bronchogram), blood flow volume and elastography five-score method were analyzed to explore the best diagnostic method. The gold standard for diagnosing lesions depends on the histological and cytopathological findings of endobronchial ultrasound-guided transbronchial needle aspiration, transthoracic biopsy, resected sample of lesions, microbiological examination or clinical follow-up of at least 6 months.ResultsEndobronchial ultrasound multimodal imaging of 97 malignant lung lesions and 19 benign lung lesions from 116 patients were analyzed. There were statistically significant differences in distinct margin, presence of lobulation sign, presence of necrosis, and elastography grading score 4-5 between malignant and benign lung lesions, among which presence of lobulation sign and elastography grading score 4-5 were independent predictors. A diagnostic scoring model was then constructed based on the above four features, and when two or more features were present, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy for malignant lung lesions prediction were 92.78%, 57.89%, 91.84%, 61.11% and 87.07%, respectively.ConclusionsThe combination of endobronchial ultrasound grayscale and elastography has potential value for malignant and benign lung lesions differentiation. The diagnostic scoring model established in this study needs further validation to guide the malignant and benign diagnosis of lung lesions.

Dataset Information

Differentiating malignant and benign eyelid lesions using deep learning.

Publications

Differentiating malignant and benign eyelid lesions using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets