Dermoscopic dark corner artifacts removal: Friend or foe?

BACKGROUND AND OBJECTIVES

One of the more significant obstacles in classification of skin cancer is the presence of artifacts. This paper investigates the effect of dark corner artifacts, which result from the use of dermoscopes, on the performance of a deep learning binary classification task. Previous research attempted to remove and inpaint dark corner artifacts, with the intention of creating an ideal condition for models. However, such research has been shown to be inconclusive due to a lack of available datasets with corresponding labels for dark corner artifact cases.

METHODS

To address these issues, we label 10,250 skin lesion images from publicly available datasets and introduce a balanced dataset with an equal number of melanoma and non-melanoma cases. The training set comprises 6126 images without artifacts, and the testing set comprises 4124 images with dark corner artifacts. We conduct three experiments to provide new understanding on the effects of dark corner artifacts, including inpainted and synthetically generated examples, on a deep learning method.

RESULTS

Our results suggest that introducing synthetic dark corner artifacts which have been superimposed onto the training set improved model performance, particularly in terms of the true negative rate. This indicates that deep learning learnt to ignore dark corner artifacts, rather than treating it as melanoma, when dark corner artifacts were introduced into the training set. Further, we propose a new approach to quantifying heatmaps indicating network focus using a root mean square measure of the brightness intensity in the different regions of the heatmaps.

CONCLUSIONS

The proposed artifact methods can be used in future experiments to help alleviate possible impacts on model performance. Additionally, the newly proposed heatmap quantification analysis will help to better understand the relationships between heatmap results and other model performance metrics.

S2C-DeLeNet: A parameter transfer based segmentation-classification integration for detecting skin cancer lesions from dermoscopic images

Dermoscopic images ideally depict pigmentation attributes on the skin surface which is highly regarded in the medical community for detection of skin abnormality, disease or even cancer. The identification of such abnormality, however, requires trained eyes and accurate detection necessitates the process being time-intensive. As such, computerized detection schemes have become quite an essential, especially schemes which adopt deep learning tactics. In this paper, a convolutional deep neural network, S2C-DeLeNet, is proposed, which (i) Performs segmentation procedure of lesion based regions with respect to the unaffected skin tissue from dermoscopic images using a segmentation sub-network, (ii) Classifies each image based on its medical condition type utilizing transferred parameters from the inherent segmentation sub-network. The architecture of the segmentation sub-network contains EfficientNet-B4 backbone in place of the encoder and the classification sub-network bears a 'Classification Feature Extraction' system which pulls trained segmentation feature maps towards lesion prediction. Inside the classification architecture, there have been designed, (i) A 'Feature Coalescing Module' in order to trail and mix each dimensional feature from both encoder and decoder, (ii) A '3D-Layer Residuals' block to create a parallel pathway of low-dimensional features with high variance for better classification. After fine-tuning on a publicly accessible dataset, a mean dice-score of 0.9494 during segmentation is procured which beats existing segmentation strategies and a mean accuracy of 0.9103 is obtained for classification which outperforms conventional and noted classifiers. Additionally, the already fine-tuned network demonstrates highly satisfactory results on other skin cancer segmentation datasets while cross-inference. Extensive experimentation is done to prove the efficacy of the network for not only dermoscopic images but also different medical modalities; which can show its potential in being a systematic diagnostic solution in the field of dermatology and possibly more.

Analysis of the ISIC image datasets: Usage, benchmarks and recommendations

The International Skin Imaging Collaboration (ISIC) datasets have become a leading repository for researchers in machine learning for medical image analysis, especially in the field of skin cancer detection and malignancy assessment. They contain tens of thousands of dermoscopic photographs together with gold-standard lesion diagnosis metadata. The associated yearly challenges have resulted in major contributions to the field, with papers reporting measures well in excess of human experts. Skin cancers can be divided into two major groups - melanoma and non-melanoma. Although less prevalent, melanoma is considered to be more serious as it can quickly spread to other organs if not treated at an early stage. In this paper, we summarise the usage of the ISIC dataset images and present an analysis of yearly releases over a period of 2016 - 2020. Our analysis found a significant number of duplicate images, both within and between the datasets. Additionally, we also noted duplicates spread across testing and training sets. Due to these irregularities, we propose a duplicate removal strategy and recommend a curated dataset for researchers to use when working on ISIC datasets. Given that ISIC 2020 focused on melanoma classification, we conduct experiments to provide benchmark results on the ISIC 2020 test set, with additional analysis on the smaller ISIC 2017 test set. Testing was completed following the application of our duplicate removal strategy and an additional data balancing step. As a result of removing 14,310 duplicate images from the training set, our benchmark results show good levels of melanoma prediction with an AUC of 0.80 for the best performing model. As our aim was not to maximise network performance, we did not include additional steps in our experiments. Finally, we provide recommendations for future research by highlighting irregularities that may present research challenges. A list of image files with reference to the original ISIC dataset sources for the recommended curated training set will be shared on our GitHub repository (available at www.github.com/mmu-dermatology-research/isic_duplicate_removal_strategy).

Predictive and discriminative localization of pathology using high resolution class activation maps with CNNs

PURPOSE

Existing class activation mapping (CAM) techniques extract the feature maps only from a single layer of the convolutional neural net (CNN), generally from the final layer and then interpolate to upsample to the original image resolution to locate the discriminative regions. Consequently these provide a coarse localization that may not be able to capture subtle abnormalities in medical images. To alleviate this, our work proposes a technique called high resolution class activation mapping (HR-CAMs) that can provide enhanced visual explainability to the CNN models.

METHODS

HR-CAMs fuse feature maps by training a network using the input from multiple layers of a trained CNN, thus gaining information from every layer that can localize abnormalities with greater details in original image resolution. The technique is validated qualitatively and quantitatively on a simulated dataset of 8,000 images followed by applications on multiple image analysis tasks that include (1) skin lesion classification (ISIC open dataset-25,331 cases) and (2) predicting bone fractures (MURA open dataset-40,561 images) (3) predicting Parkinson's disease (PD) from neuromelanin sensitive MRI (small cohort-80 subjects).

RESULTS

We demonstrate that our model creates clinically interpretable subject specific high resolution discriminative localizations when compared to widely used CAMs and Gradient-CAMs.

CONCLUSION

HR-CAMs provide finer delineation of abnormalities thus facilitating superior explainability to CNNs as has been demonstrated from its rigorous validation.

Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification

BACKGROUND AND OBJECTIVE

Computer automated diagnosis of various skin lesions through medical dermoscopy images remains a challenging task.

METHODS

In this work, we propose an integrated diagnostic framework that combines a skin lesion boundary segmentation stage and a multiple skin lesions classification stage. Firstly, we segment the skin lesion boundaries from the entire dermoscopy images using deep learning full resolution convolutional network (FrCN). Then, a convolutional neural network classifier (i.e., Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201) is applied on the segmented skin lesions for classification. The former stage is a critical prerequisite step for skin lesion diagnosis since it extracts prominent features of various types of skin lesions. A promising classifier is selected by testing well-established classification convolutional neural networks. The proposed integrated deep learning model has been evaluated using three independent datasets (i.e., International Skin Imaging Collaboration (ISIC) 2016, 2017, and 2018, which contain two, three, and seven types of skin lesions, respectively) with proper balancing, segmentation, and augmentation.

RESULTS

In the integrated diagnostic system, segmented lesions improve the classification performance of Inception-ResNet-v2 by 2.72% and 4.71% in terms of the F1-score for benign and malignant cases of the ISIC 2016 test dataset, respectively. The classifiers of Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201 exhibit their capability with overall weighted prediction accuracies of 77.04%, 79.95%, 81.79%, and 81.27% for two classes of ISIC 2016, 81.29%, 81.57%, 81.34%, and 73.44% for three classes of ISIC 2017, and 88.05%, 89.28%, 87.74%, and 88.70% for seven classes of ISIC 2018, respectively, demonstrating the superior performance of ResNet-50.

CONCLUSIONS

The proposed integrated diagnostic networks could be used to support and aid dermatologists for further improvement in skin cancer diagnosis.

Compensation for Asbestos-Related Diseases in Japan: Utilization of Standard Classifications of Industry and Occupations

Background:

Asbestos-related diseases (ARD) are occupational hazards with high mortality rates. To identify asbestos exposure by previous occupation is the main issue for ARD compensation for workers. This study aimed to identify risk groups by applying standard classifications of industries and occupations to a national database of compensated ARD victims in Japan.

Methods:

We identified occupations that carry a risk of asbestos exposure according to the International Standard Industrial Classification of All Economic Activities (ISIC). ARD compensation data from Japan between 2006 and 2013 were retrieved. Each compensated worker was classified by job section and group according to the ISIC code. Risk ratios for compensation were calculated according to the percentage of workers compensated because of ARD in each ISIC category.

Results:

In total, there were 6,916 workers with ARD who received compensation in Japan between 2008 and 2013. ISIC classification section F (construction) had the highest compensated risk ratio of 6.3. Section C (manufacturing) and section F (construction) had the largest number of compensated workers (2,868 and 3,463, respectively). In the manufacturing section C, 9 out of 13 divisions had a risk ratio of more than 1. For ISIC divisions in the construction section, construction of buildings (division 41) had the highest number of workers registering claims (2,504).

Conclusion:

ISIC classification of occupations that are at risk of developing ARD can be used to identify the actual risk of workers’ compensation at the national level.