Malaria parasites pose a significant global health burden, causing widespread
suffering and mortality. Detecting malaria infection accurately is crucial for
effective treatment and control. However, existing automated detection
techniques have shown limitations in terms of accuracy and generalizability.
Many studies have focused on specific features without exploring more
comprehensive approaches. In our case, we formulate a deep learning technique
for malaria-infected cell classification using traditional CNNs and transfer
learning models notably VGG19, InceptionV3, and Xception. The models were
trained using NIH datasets and tested using different performance metrics such
as accuracy, precision, recall, and F1-score. The test results showed that deep
CNNs achieved the highest accuracy -- 97%, followed by Xception with an
accuracy of 95%. A machine learning model SVM achieved an accuracy of 83%,
while an Inception-V3 achieved an accuracy of 94%. Furthermore, the system can
be accessed through a web interface, where users can upload blood smear images
for malaria detection.

我们使用传统的 CNN 和迁移学习模型（VGG19、InceptionV3 和 Xception）来构建深度学习技术，用于疟疾感染细胞分类。测试结果显示，深度 CNN 具有最高的准确度（97%），其次是 Xception（95%）。用户可以通过网页界面上传血涂片图像进行疟疾检测。

基于机器学习和深度学习技术的自动化基于网络的疟疾检测系统

Automated Web-Based Malaria Detection System with Machine Learning and  Deep Learning Techniques

Melanoma is the most aggressive form of skin cancer, and early detection can
significantly increase survival rates and prevent cancer spread. However,
developing reliable automated detection techniques is difficult due to the lack
of standardized datasets and evaluation methods. This study introduces a
unified melanoma classification approach that supports 54 combinations of 11
datasets and 24 state-of-the-art deep learning architectures. It enables a fair
comparison of 1,296 experiments and results in a lightweight model deployable
to the web-based MeshNet architecture named Mela-D. This approach can run up to
33x faster by reducing parameters 24x to yield an analogous 88.8\% accuracy
comparable with ResNet50 on previously unseen images. This allows efficient and
accurate melanoma detection in real-world settings that can run on
consumer-level hardware.

通过引入支持 11 个数据集和 24 种先进深度学习架构的统一黑素瘤分类方法，该研究建立了一个可比较 1,296 个实验的公平对比，并生成一个可在 Web 上部署的轻量级模型（称为 Mela-D）以及减少参数 24 倍以提高 33 倍运行速度，并在之前未见过的图像上获得与 ResNet50 相似的 88.8% 的准确率，从而实现在消费级硬件上高效准确地在实际环境中检测黑素瘤。