Abstract
According to a study performed by John Hopkins Medicine in 2023, misdiagnoses make up approximately 11.1% of total diagnoses in the United States, which result in anything from minor to fatal error for the patient. One of the main contributors to this unfortunate statistic is the heavy reliance on human-read medical scans. As a result, this study investigates the effectiveness of various Machine Learning (ML) models in classifying cancer from histopathological medical images. More specifically, Deep Learning (DL) Convolutional Neural Networks (CNNs) leveraging Transfer Learning (TL) are under analysis. For each experiment, one generic CNN is trained from scratch followed by four prominent pretrained models (i.e., DenseNet, VGG16, ResNet, and InceptionNet). The primary disease used for experimentation was colorectal cancer, while brief research was also done with lung cancer, leukemia, and breast cancer. Each model was trained across various levels of data augmentation and shuffles in data to provide a more verifiable set of findings when compared amongst each other. Results indicate optimal model selections for cancer detection under varying scenarios, such as training constraints (e.g., time and computational resources) along with dataset conditions (e.g., sizes and class balances). Overall, this research provides valuable insights on ideal CNNs for histopathological cancer detection that can be applied to developing future cancer detection software, reducing the heavy reliance on human-interpreted medical imagery diagnosis.