First of all, the choice of deep learning algorithm depends on your purpose and the problem you are intending to tackle. If your problem is a time series problem, conv-lstm, which is a recurrent neural network, might work better. However, in your case, if I am not mistaken, your objective is to detect whether there is a disease or not in each image (simple classification problem), and in that case deep learning algorithms based on convolutional neural networks or vision transformers might work better.

Convolutional Long Short-Term Memory (Conv-LSTM) networks are a type of recurrent neural network that can be used for image processing tasks. They have the ability to process input sequences with spatial dependencies, making them well-suited for tasks such as image segmentation or prediction.

In general, Conv-LSTM networks can be a good choice for medical image processing tasks, including CT image processing. However, it is important to consider the specific characteristics of your data and the task at hand when selecting an appropriate deep learning algorithm. You may want to consider experimenting with different algorithms and architectures to see which one performs best on your data.

Other deep learning algorithms that may be worth considering for medical image processing tasks include convolutional neural networks (CNNs), fully convolutional networks (FCNs), and U-Net, among others. It may also be useful to consider ensemble methods or hybrid approaches that combine multiple algorithms or architectures.

Ultimately, the choice of algorithm will depend on the specific goals of your project and the resources available to you, and it may be necessary to try out multiple approaches to find the one that works best for your particular dataset and task.