Effects of objects and image quality on melanoma classification using deep neural networks

Gazioglu, Bilge S. Akkoca; Kamasak, Mustafa E.

doi:10.1016/j.bspc.2021.102530

Cited by 18 publications

(4 citation statements)

References 31 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we propose -and have provided empirical justification -that image quality threshold should be treated as a tunable hyperparameter. There is ample demonstration of the detrimental effect of synthetic image degradation on the performance of DL models trained on 'clean' datasets [1,9,15,7,20,4]. In line with this, natural sources of image degradation have also been shown to reduce the performance of a DL model trained exclusively on high-quality retinal images [22].…”

Section: Discussionmentioning

confidence: 85%

Rethinking Retinal Image Quality: Treating Quality Threshold as a Tunable Hyperparameter

Yii

Dutt

MacGillivray

et al. 2022

Ophthalmic Medical Image Analysis

View full text Add to dashboard Cite

Assuming the robustness of a deep learning model to suboptimal images is a key consideration, we asked if there was any value in including training images of poor quality. In particular, should we treat the (quality) threshold at which a training image is either included or excluded as a tunable hyperparameter? To that end, we systematically examined the effect of including training images of varying quality on the test performance of a DL model in classifying the severity of diabetic retinopathy. We found that there was a unique combination of (categorical) quality labels or a Goldilocks (continuous) quality score that gave rise to optimal test performance on either high-quality or suboptimal images. The model trained exclusively on high-quality images yielded worse performance in all test scenarios than that trained on the optimally tuned training set which included images with some level of degradation.

show abstract

Section: Discussionmentioning

confidence: 85%

Rethinking Retinal Image Quality: Treating Quality Threshold as a Tunable Hyperparameter

Yii

Dutt

MacGillivray

et al. 2022

Ophthalmic Medical Image Analysis

View full text Add to dashboard Cite

show abstract

“…Here, accuracy defines the system performance examination based on the correct estimation values relevant to the total estimation number. Specificity defines the As mentioned before, the suggested melanoma diagnosis system has been implemented on SIIM-ISIC Melanoma dataset and its achievements were put in comparison with several newest techniques that are Deep neural network (DNN), 37 morphology, 38 Roi-based, 39 oversampling, 40 gray level co-occurrence matrix (GLCM), 41 color and texture features, 42 and superpixels. 43 Table 3 indicates the comparison analysis of the suggested technique with the other state-of--of-the--the-art methods.…”

Section: Simulation Resultsmentioning

confidence: 99%

An optimal diagnosis system for melanoma dermoscopy images based on enhanced design of horse herd optimizer

Ding

Razmjooy

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Skin cells grow in an orderly and controlled manner, in which old cells are pushed to the skin surface by healthy new cells, wherein they finally perish.However, when several cells damage DNA, new ones may start growing disorderly and can finally create cancer cells mass. Different types of skin cancer have been observed by experts. Although, melanoma, as one of the rarely happened cancers, is the most threatening type. Therefore, early detection of this type of cancer can be so useful for avoiding melanoma dangers and even helps to treat this type of cancer. The present paper proposes a new hierarchical procedure for the optimum diagnosis of melanoma cancer from dermoscopy images. Here, after image preprocessing, image segmentation is applied for the segmentation of the ROI. Then, the selection of features from the segmented images is performed and injected to a radial basis function-based classifier to provide the final diagnosis of cancer. To deliver efficient results, the feature selection and the classifier have been optimized by a new design of Horse herd optimization algorithm (HHOA). The method is then implemented on the Society for Imaging Informatics in Medicine-The International Skin Imaging Collaboration (SIIM-ISIC) Melanoma dataset to validate its effectiveness and its achievements and also put in comparison with several different latest techniques. The results show that the proposed method with 95.46% precision provides the maximum performance among the others.

show abstract

“…Specifically, evaluation of the performance of the proposed hybrid strategy with a larger number of subjects may ultimately lead to the development of an algorithm for automated cancer identification and screening with the use of deep learning and machine learning methods. Regarding our future plans, further development of the method is warranted including application of an AI approach for the development of automated tissue classification methods which can later be applied to the assessment of tumor margins based on the hyperspectral imaging concept presented here [20, 32, 44–49]. One way to improve our screening performance is to separately obtain the scattering coefficient from the absorption coefficient by utilizing the approach described in ref.…”

Section: Discussionmentioning

confidence: 99%

Single probe light reflectance spectroscopy and parameter spectrum feature extraction in experimental skin cancer detection and classification

Abookasis

Shemesh

Litwin

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Skin cancer, an anomalous development of skin cells in the epidermis, is among the most common types of cancer worldwide. Because of its clinical importance and to improve early diagnosis and patient management, there is an urgent need to develop noninvasive, accurate medical diagnostic tools. To this aim, light reflectance spectroscopy over the visible and near-infrared spectral range (400-1000 nm) based on a single-fiber six-around-one optical probe was applied to extract nine features used for diagnostics. These features include skewness, entropy, energy, kurtosis, scattering amplitude, and others, and are spread over each of four different spectral signatures, namely, light reflectance, absorbance, scattering profile approximation, and absorption/scattering ratio. Our preliminary studies focused on 11 adult patients with diagnoses of malignant melanoma (n = 4), basal cell carcinoma (n = 5), and squamous cell carcinoma (n = 2) in a variety of locations on the body. Measurements were taken first in vivo before surgery, at the site of the lesion and from healthy skin of the same patient, and ex vivo after surgical excision, where the lesion was rinsed in saline solution and measurements of the reflected light from the "inside" facing plane of the tissue were taken in the same manner. Overall, experimental results demonstrate that by examining a variety of wavebands, features, and statistical metrics, we can detect and distinguish cancer from normal tissue and different cancer subtypes. Nevertheless, discrepancies in results between in vivo and ex vivo tissue were observed and explanations for these discrepancies are discussed.

show abstract

Effects of objects and image quality on melanoma classification using deep neural networks

Cited by 18 publications

References 31 publications

Rethinking Retinal Image Quality: Treating Quality Threshold as a Tunable Hyperparameter

Rethinking Retinal Image Quality: Treating Quality Threshold as a Tunable Hyperparameter

An optimal diagnosis system for melanoma dermoscopy images based on enhanced design of horse herd optimizer

Single probe light reflectance spectroscopy and parameter spectrum feature extraction in experimental skin cancer detection and classification

Contact Info

Product

Resources

About