Confidence Aware Neural Networks for Skin Cancer Detection

Khaledyan, Donya; Tajally, AmirReza; Sarkhosh, Ali; Shamsi, Afshar; Asgharnezhad, Hamzeh; Khosravi, Abbas; Nahavandi, Saeid

doi:10.48550/arxiv.2107.09118

Cited by 6 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the comparison, studies used different methods with different and the same datasets. For the HAM10000 dataset, Ali et al [39] achieved 91.9% using CNN, and Khaledyan et al [40] achieved 83.6% using Ensemble Bayesian Networks for the precision measure. In addition to these references, Alsaade et al [38] produced a model using CNN based on the PH2 dataset, which contains 40 melanomas, 80 normal nevi, and 80 abnormal nevi, as in Table 8.…”

Section: Discussionmentioning

confidence: 99%

Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique

Elshahawy,

Elnemr,

Oproescu

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Skin cancer, specifically melanoma, is a serious health issue that arises from the melanocytes, the cells that produce melanin, the pigment responsible for skin color. With skin cancer on the rise, the timely identification of skin lesions is crucial for effective treatment. However, the similarity between some skin lesions can result in misclassification, which is a significant problem. It is important to note that benign skin lesions are more prevalent than malignant ones, which can lead to overly cautious algorithms and incorrect results. As a solution, researchers are developing computer-assisted diagnostic tools to detect malignant tumors early. First, a new model based on the combination of “you only look once” (YOLOv5) and “ResNet50” is proposed for melanoma detection with its degree using humans against a machine with 10,000 training images (HAM10000). Second, feature maps integrate gradient change, which allows rapid inference, boosts precision, and reduces the number of hyperparameters in the model, making it smaller. Finally, the current YOLOv5 model is changed to obtain the desired outcomes by adding new classes for dermatoscopic images of typical lesions with pigmented skin. The proposed approach improves melanoma detection with a real-time speed of 0.4 MS of non-maximum suppression (NMS) per image. The performance metrics average is 99.0%, 98.6%, 98.8%, 99.5, 98.3%, and 98.7% for the precision, recall, dice similarity coefficient (DSC), accuracy, mean average precision (MAP) from 0.0 to 0.5, and MAP from 0.5 to 0.95, respectively. Compared to current melanoma detection approaches, the provided approach is more efficient in using deep features.

show abstract

Section: Discussionmentioning

confidence: 99%

Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique

Elshahawy,

Elnemr,

Oproescu

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The randomness resulted by dropout can help us to approximate the posterior distribution with minimum statistical difficulties. The predictive mean (µ pred ) of the model for a specific input can be estimated as follows [50]:…”

Section: Mc-dropoutmentioning

confidence: 99%

An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions

Shamsi¹,

Asgharnezhad²,

Tajally³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte Carlo dropout (MC-Dropout) is one of the most wellknown techniques to quantify uncertainty in deep learning methods. In this study, we propose two new loss functions by combining cross entropy with Expected Calibration Error (ECE) and Predictive Entropy (PE). The obtained results clearly show that the new proposed loss functions lead to having a calibrated MC-Dropout method. Our results confirmed the great impact of the new hybrid loss functions for minimising the overlap between the distributions of uncertainty estimates for correct and incorrect predictions without sacrificing the model's overall performance.

show abstract

“…In the case of segmentation, these algorithms can be trained on large datasets to find boundaries by recognizing their features, such as shape, texture, and color. The DL models can also learn to accurately distinguish the region of interest from the background and other structures in the image [16,17]. In addition to improving the accuracy of detection and diagnosis, DL algorithms can also help reduce the time and cost associated with traditional methods of diagnosis.…”

Section: Introductionmentioning

confidence: 99%

WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound

Khaledyan,

Marini,

O’Connell

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Objective.Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonographers, which hinders its widespread use. Approach. Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images. Combined with deep learning, like convolutional neural networks (CNNs), it can potentially transform breast cancer diagnosis, enhancing accuracy, saving time and costs, and improving patient outcomes. The widely used UNet architecture, known for medical image segmentation, has limitations, such as vanishing gradients and a lack of multi-scale feature extraction and selective region attention. In this study, we present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet). In this model, we incorporate wavelet gates (WGs) and attention gates (AGs) between the encoder and decoder instead of a simple connection to overcome the limitations mentioned, thereby improving model performance.Main results.Two datasets are utilized for the analysis. The public "Breast Ultrasound Images" (BUSI) dataset of 780 images and a VSI dataset of 3818 images. Both datasets contained segmented lesions categorized into three types: no mass, benign mass, and malignant mass. Our segmentation results show superior performance compared to other deep networks. The proposed algorithm attained a Dice coefficient of 0.94 and an F1 score of 0.94 on the VSI dataset and scored 0.93 and 0.94 on the public dataset, respectively. Significance. The experimental findings demonstrate that the proposed WATUNet model achieves precise segmentation of breast lesions in both standard-of-care and VSI images, surpassing state-of-the-art models. Hence, the model holds considerable promise for assisting in lesion identification, an essential step in the clinical diagnosis of breast lesions.

show abstract

Confidence Aware Neural Networks for Skin Cancer Detection

Cited by 6 publications

References 20 publications

Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique

Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique

An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions

WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound

Contact Info

Product

Resources

About