A multidimensional scaling and sample clustering to obtain a representative subset of training data for transfer learning-based rosacea lesion identification

Binol, Hamidullah; Niazi, M. Khalid Khan; Plotner, Alisha N.; Sopkovich, Jennifer; Kaffenberger, Benjamin H.; Gürcan, Metin N.

doi:10.1117/12.2549392

Cited by 8 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This network was trained and validated with 50,000 images to classify 1000 object categories, learning-rich feature representations, with 825 layers. We did not retrain the whole network because it was highly likely to result in overfitting [ 37 , 38 ]. Instead, we opted to freeze the first 818 layers, a number that was decided empirically to limit the number of parameters required to learn the features in the network.…”

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results

Çamalan

Mahmood

Binol

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

Oral cancer/oral squamous cell carcinoma is among the top ten most common cancers globally, with over 500,000 new cases and 350,000 associated deaths every year worldwide. There is a critical need for objective, novel technologies that facilitate early, accurate diagnosis. For this purpose, we have developed a method to classify images as “suspicious” and “normal” by performing transfer learning on Inception-ResNet-V2 and generated automated heat maps to highlight the region of the images most likely to be involved in decision making. We have tested the developed method’s feasibility on two independent datasets of clinical photographic images of 30 and 24 patients from the UK and Brazil, respectively. Both 10-fold cross-validation and leave-one-patient-out validation methods were performed to test the system, achieving accuracies of 73.6% (±19%) and 90.9% (±12%), F1-scores of 97.9% and 87.2%, and precision values of 95.4% and 99.3% at recall values of 100.0% and 81.1% on these two respective cohorts. This study presents several novel findings and approaches, namely the development and validation of our methods on two datasets collected in different countries showing that using patches instead of the whole lesion image leads to better performance and analyzing which regions of the images are predictive of the classes using class activation map analysis.

show abstract

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results

Çamalan

Mahmood

Binol

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…We took advantage of 16GB NVIDIA Tesla P100 PCI-E GPU. We used the Deep Learning Toolbox of MATLAB R2018b to implement the U-Net architecture, and Dice coefficient [26, 27] to evaluate the performance of the segmentation.…”

Section: The Proposed Methodologymentioning

confidence: 99%

SelectStitch: Automated Frame Segmentation and Stitching to Create Composite Images from Otoscope Video Clips

Binol

Moberly

Niazi

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background and Objective: The aim of this study is to develop and validate an automated image segmentation-based frame selection and stitching framework to create enhanced composite images from otoscope videos. The proposed framework, called SelectStitch, is useful for classifying eardrum abnormalities using a single composite image instead of the entire raw otoscope video dataset. Methods: SelectStitch consists of a convolutional neural network (CNN) based semantic segmentation approach to detect the eardrum in each frame of the otoscope video, and a stitching engine to generate a high-quality composite image from the detected eardrum regions. In this study, we utilize two separate datasets: the first one has 36 otoscope videos that were used to train a semantic segmentation model, and the second one, containing 100 videos, which was used to test the proposed method. Cases from both adult and pediatric patients were used in this study. A configuration of 4-levels depth U-Net architecture was trained to automatically find eardrum regions in each otoscope video frame from the first dataset. After the segmentation, we automatically selected meaningful frames from otoscope videos by using a pre-defined threshold, i.e., it should contain at least an eardrum region of 20% of a frame size. We have generated 100 composite images from the test dataset. Three ear, nose, and throat (ENT) specialists (ENT-I, ENT-II, ENT-III) compared in two rounds the composite images produced by SelectStitch against the composite images that were generated by the base processes, i.e., stitching all the frames from the same video data, in terms of their diagnostic capabilities. Results: In the first round of the study, ENT-I, ENT-II, ENT-III graded improvement for 58, 57, and 71 composite images out of 100, respectively, for SelectStitch over the base composite, reflecting greater diagnostic capabilities. In the repeat assessment, these numbers were 56, 56, and 64, respectively. We observed that only 6%, 3%, and 3% of the cases received a lesser score than the base composite images, respectively, for ENT-I, ENT-II, and ENT-III in Round-1, and 4%, 0%, and 2% of the cases in Round-2. Conclusions: Frame selection improves the diagnostic quality of composite images from otoscope video clips.

show abstract

“…In addition, even though there are some studies, they usually include other skin lesions (Table 1), as mentioned above, rather than targeting rosacea alone, which can cause poor performance in terms of accuracy [26]. Recently, Binol et al developed a new deep learning model, Ros-NET, to detect rosacea lesions by combining information from varying image scales and resolutions [14,30]. They estimated the Dice coefficient and false positive rate as a global measure using Ros-Net, whose results were compared with two well-known pre-trained deep learning models: Inception-ResNet-v2 and ResNet-101.…”

Section: Related Workmentioning

confidence: 99%

FACES: A Deep-Learning-Based Parametric Model to Improve Rosacea Diagnoses

et al. 2023

View full text Add to dashboard Cite

Rosacea is a chronic inflammatory skin disorder that causes visible blood vessels and redness on the nose, chin, cheeks, and forehead. However, visual assessment, the current standard method used to identify rosacea, is often subjective among clinicians and results in high variation. Recent advances in artificial intelligence have allowed for the effective detection of various skin diseases with high accuracy and consistency. In this study, we develop a new methodology, coined “five accurate CNNs-based evaluation system (FACES)”, to identify and classify rosacea more efficiently. First, 19 CNN-based models that have been widely used for image classification were trained and tested via training and validation data sets. Next, the five best performing models were selected based on accuracy, which served as a weight value for FACES. At the same time, we also applied a majority rule to five selected models to detect rosacea. The results exhibited that the performance of FACES was superior to that of the five individual CNN-based models and the majority rule in terms of accuracy, sensitivity, specificity, and precision. In particular, the accuracy and sensitivity of FACES were the highest, and the specificity and precision were higher than most of the individual models. To improve the performance of our system, future studies must consider patient details, such as age, gender, and race, and perform comparison tests between our model system and clinicians.

show abstract

A multidimensional scaling and sample clustering to obtain a representative subset of training data for transfer learning-based rosacea lesion identification

Cited by 8 publications

References 0 publications

Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results

Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results

SelectStitch: Automated Frame Segmentation and Stitching to Create Composite Images from Otoscope Video Clips

FACES: A Deep-Learning-Based Parametric Model to Improve Rosacea Diagnoses

Contact Info

Product

Resources

About