If your stack of images are from X-ray CT, magnetic resonance, TEM, or physical slices then Stradview from Cambridge University may help. This software will reconstruct a 3D surface from a set of parallel images. Here is a link: http://mi.eng.cam.ac.uk/Main/StradView

For medical images, e.g., an X-ray CT saved as stack of 2D DICOM files there are many programs available. One is mentioned above. 3D Slicer is another. But, the list relatively long. For confocal microscopy, I think there is some software too. Otherwise, low level options would requiring some programming in Matlab or Octave.

If by a 3D image you mean a volumetric reconstruction and not a stereoscopic image, I'd say that choosing the right method will depend on the file format and the aim of the reconstruction. All the options mentioned earlier can work fine in datasets of reasonable size. However, if, for some reason, you are trying to reconstruct a large size dataset (dozens of GB). A technical note we recently presented about the use of point clouds to reconstruct gigaresolution medical datasets might give you an idea of how to do it:

-DOI: 10.1096/fasebj.2021.35.S1.04298

The question for Muhammad Huzaifa Khurshid is what type of 3D do you want? A volumetric reconstruction mentioned by Roberto Rodriguez Rubio and Tilo Winkler may require a high end graphics card and memory but many software options are available and techniques as mentioned by Roberto. The type of 3D I mentioned is creating a surface from a threshold better known as isosurfaces. Many software options are also available but the key to either isosurfaces or volumetric reconstruction is what type of images (TIFF, JPEG, DICOM) do you have? The type of images may dictate what software will read and create a 3D view.

Hey Reuben Reyes,

Thanks for your response basically i need to reconstruct 2d ultrasound images into 3d and for that i have to use deep learning not with software and also by reconstructing that images i also need to know about the position information how can i estimate position as well.

Thanks & Regards,

Huzaifa Khurshid