Amin Javaria, Azhar Marium, Arshad Habiba, Zafar Amad, Kim Seong-Han
Rawalpindi Woman University, Rawalpindi, Pakistan.
Department of Computer Science, University of Wah, Wah Cantt, Pakistan.
Front Med (Lausanne). 2025 Mar 10;12:1524146. doi: 10.3389/fmed.2025.1524146. eCollection 2025.
Skin cancer is one of the most prevalent cancers worldwide. In the clinical domain, skin lesions such as melanoma detection are still a challenge due to occlusions, poor contrast, poor image quality, and similarities between skin lesions. Deep-/machine-learning methods are used for the early, accurate, and efficient detection of skin lesions. Therefore, we propose a boundary-aware segmentation network (BASNet) model comprising prediction and residual refinement modules.
The prediction module works like a U-Net and is densely supervised by an encoder and decoder. A hybrid loss function is used, which has the potential to help in the clinical domain of dermatology. BASNet handles these challenges by providing robust outcomes, even in suboptimal imaging environments. This leads to accurate early diagnosis, improved treatment outcomes, and efficient clinical workflows. We further propose a compact convolutional transformer model (CCTM) based on convolution and transformers for classification. This was designed on a selected number of layers and hyperparameters having two convolutions, two transformers, 64 projection dimensions, tokenizer, position embedding, sequence pooling, MLP, 64 batch size, two heads, 0.1 stochastic depth, 0.001 learning rate, 0.0001 weight decay, and 100 epochs.
The CCTM model was evaluated on six skin-lesion datasets, namely MED-NODE, PH2, ISIC-2019, ISIC-2020, HAM10000, and DermNet datasets, achieving over 98% accuracy.
The proposed model holds significant potential in the clinical domain. Its ability to combine local feature extraction and global context understanding makes it ideal for tasks like medical image analysis and disease diagnosis.
皮肤癌是全球最常见的癌症之一。在临床领域，由于遮挡、对比度差、图像质量不佳以及皮肤病变之间的相似性，诸如黑色素瘤检测等皮肤病变的识别仍然是一项挑战。深度/机器学习方法被用于皮肤病变的早期、准确和高效检测。因此，我们提出了一种包含预测和残差细化模块的边界感知分割网络（BASNet）模型。
预测模块的工作方式类似于U-Net，并由编码器和解码器进行密集监督。使用了一种混合损失函数，这在皮肤病学临床领域可能会有所帮助。BASNet通过提供稳健的结果来应对这些挑战，即使在次优成像环境中也是如此。这有助于实现准确的早期诊断、改善治疗效果以及高效的临床工作流程。我们还基于卷积和变压器提出了一种用于分类的紧凑型卷积变压器模型（CCTM）。该模型是根据选定的层数和超参数设计的，具有两个卷积层、两个变压器层、64个投影维度、分词器、位置嵌入、序列池化、多层感知器、64的批量大小、两个头、0.1的随机深度、0.001的学习率、0.0001的权重衰减以及100个轮次。
CCTM模型在六个皮肤病变数据集上进行了评估，即MED-NODE、PH2、ISIC-2019、ISIC-2020、HAM10000和DermNet数据集，准确率超过98%。
所提出的模型在临床领域具有巨大潜力。它结合局部特征提取和全局上下文理解的能力使其非常适合医学图像分析和疾病诊断等任务。
