Browsing by Author "Mendes, Ana Isabel"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Dermoscopic assisted diagnosis in melanoma: Reviewing results, optimizing methodologies and quantifying empirical guidelinesPublication . Lee, Huei Diana; Mendes, Ana Isabel; Spolaôr, Newton; Oliva, Jefferson Tales; Parmezan, Antonio Rafael Sabino; Wu, Feng Chung; Fonseca-Pinto, RuiEarly diagnosis is still the most important factor to deal with skin cancer, a disease that challenges physicians and researchers. It has benefited from computer-aided diagnosis methods that successfully combine dermoscopy, Digital Image Processing, and Machine Learning techniques. This paper aims to approximate medical professionals working with dermoscopy to these methods, to join the challenge of melanoma early detection. Accordingly, a proposal for extracting, selecting and combining texture and shape features from dermoscopic images is presented. The Feature Selection task is added to the learning process to potentiate the quality of classification models. Three classical Machine Learning algorithms were applied to differentiate melanoma from non-melanoma images. The models are evaluated by standard performance measures and a multi-criteria decision analysis method. This is the first time such method is used in melanoma diagnosis. As a result, we found a decision tree that performs well and allows the explicit representation and analysis of the knowledge learned from the images. In addition, the competitiveness of our decision models in comparison with literature approaches reviewed in this work encourages further applications of Machine Learning and Feature Selection to assist computer-aided diagnosis.
- Fine-tuning pre-trained neural networks for medical image classification in small clinical datasetsPublication . Spolaôr, Newton; Lee, Huei Diana; Mendes, Ana Isabel; Nogueira, Conceição; Parmezan, Antonio Rafael Sabino; Takaki, Weber Shoity Resende; Coy, Claudio Saddy Rodrigues; Wu, Feng Chung; Fonseca-Pinto, RuiConvolutional neural networks have been effective in several applications, arising as a promising supporting tool in a relevant Dermatology problem: skin cancer diagnosis. However, generalizing well can be difficult when little training data is available. The fine-tuning transfer learning strategy has been employed to differentiate properly malignant from non-malignant lesions in dermoscopic images. Fine-tuning a pre-trained network allows one to classify data in the target domain, occasionally with few images, using knowledge acquired in another domain. This work proposes eight fine-tuning settings based on convolutional networks previously trained on ImageNet that can be employed mainly in limited data samples to reduce overfitting risk. They differ on the architecture, the learning rate and the number of unfrozen layer blocks. We evaluated the settings in two public datasets with 104 and 200 dermoscopic images. By finding competitive configurations in small datasets, this paper illustrates that deep learning can be effective if one has only a few dozen malignant and non-malignant lesion images to study and differentiate in Dermatology. The proposal is also flexible and potentially useful for other domains. In fact, it performed satisfactorily in an assessment conducted in a larger dataset with 746 computerized tomographic images associated with the coronavirus disease.
- On the geometric modulation of skin lesion growth: a mathematical model for melanomaPublication . Mendes, Ana Isabel; Nogueira, Conceição; Pereira, Jorge; Fonseca-Pinto, RuiIntroduction: Early detection of suspicious skin lesions is critical to prevent skin malignancies, particularly the melanoma, which is the most dangerous form of human skin cancer. In the last decade, image processing techniques have been an increasingly important tool for early detection and mathematical models play a relevant role in mapping the progression of lesions. Methods: This work presents an algorithm to describe the evolution of the border of the skin lesion based on two main measurable markers: the symmetry and the geometric growth path of the lesion. The proposed methodology involves two dermoscopic images of the same melanocytic lesion obtained at different moments in time. By applying a mathematical model based on planar linear transformations, measurable parameters related to symmetry and growth are extracted. Results: With this information one may compare the actual evolution in the lesion with the outcomes from the geometric model. First, this method was tested on predefined images whose growth was controlled and the symmetry known which were used for validation. Then the methodology was tested in real dermoscopic melanoma images in which the parameters of the mathematical model revealed symmetry and growth rates consistent with a typical melanoma behavior. Conclusions: The method developed proved to show very accurate information about the target growth markers (variation on the growth along the border, the deformation and the symmetry of the lesion trough the time). All the results, validated by the expected phantom outputs, were similar to the ones on the real images.