Cancerous skin lesions are one of the most common malignancies detected in humans, and if not detected at an early stage, they can lead to death. Therefore, it is crucial to have access to accurate results early on to optimize the chances of survival. Unfortunately, accurate results are typically obtained by highly trained dermatologists, who may not be accessible to many people, particularly in low-income and middle-income countries. Artificial Intelligence (AI) appears to be a potential solution to this problem, as it has proven to provide equal or even better diagnoses than healthcare professionals. This project aims to address the issue by collecting state-of-the-art techniques for image classification from various fields and implementing them. Some of these techniques include mixup, presizing, and test-time augmentation, among others. Three architectures were used for the implementation: DenseNet121, VGG16 with batch normalization, and ResNet50. The models were designed with two main purposes. First, to classify images into seven categories, including melanocytic nevus, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses and intraepithelial carcinoma, vascular lesions, and dermatofibroma. Second, to classify images into benign or malignant. The models were trained using a dataset of 8012 images, and their performance was evaluated using 2003 images. It's worth noting that this model is trained end-to-end, directly from the image to the labels, without the need for handcrafted feature extraction.

翻译：癌性皮肤病变是人类最常见的恶性肿瘤之一，若未能在早期阶段发现，可能导致死亡。因此，尽早获取准确结果对优化患者生存几率至关重要。然而，准确诊断通常需要由受过高度专业训练的皮肤科医生完成，而许多人群（尤其是中低收入国家）可能无法接触到这类医生。人工智能（AI）似乎为这一问题提供了潜在解决方案，因其已被证明能够提供与医疗专业人员相当甚至更优的诊断结果。本研究旨在通过收集各领域的先进图像分类技术并加以实现来解决问题，其中涉及的技术包括mixup、presizing和测试时增强等。实施过程中使用了三种架构：DenseNet121、带批归一化的VGG16和ResNet50。模型设计有两个主要目标：其一，将图像分为七类——黑色素细胞痣、黑色素瘤、良性角化病样病变、基底细胞癌、光化性角化病与上皮内癌、血管病变和皮肤纤维瘤；其二，将图像区分为良性与恶性。模型使用8012张图像的数据集进行训练，并通过2003张图像评估性能。值得强调的是，该模型采用端到端训练方式，直接从图像映射至标签，无需手工特征提取。