Advanced Artificial Intelligence Methods for Medical Applications


ผศ.ดร.ฐิติรัตน์ ศิริบวรรัตนกุล


Lecture Notes in Computer Science


Although analyzing high-stakes medical images is challenging, it is what recent deep neural networks quite excel at. Noticing that there are still many concerns regarding the adoption of vision AI-based digital human models in actual medical practices, this paper goes through challenges that occur in each development stage of vision AI in medical applications. Focusing on modeling patients’ internal organisms via medical imaging, we found that most existing vision-based AI systems share similar challenges, ranging from huge computational resources, laborious data annotation, domain shifting, and unexplainability. Data collection in this era of data privacy law is another challenge that is rarely discussed in previous works conducting technical implementations of deep neural networks. In the end, our conclusion is that leading researchers in deep neural networks tend to put more concern into introducing techniques that allow newer, bigger, and more precise networks to be easily trained and evaluated based on some quantitative evaluation metrics. Meanwhile, physicians and data protection laws seem to hold a different concern regarding qualitative issues about how to make these deep networks trustworthy, ethical, and able to explain their decisions as well as underneath logic in a meaningful manner.

(2566). Advanced Artificial Intelligence Methods for Medical Applications. Lecture Notes in Computer Science, 2023(na), na-na.