Data at different stages of AIVE processing. (A–C) 3D depictions of 2D data shown in Figs. 1 and 2, showing the 3D surfaces generated using (A) raw predictions, (B) blurred predictions, or (C) AIVE with one of six different trained models (RF, J48, MLP, DT, JRip, and PART). (D) Raw distance measurements between the 3D probes (shown in Fig. 2 H) and membrane surfaces under every condition shown in A–C. (E–G) Raw AIVE data from mitochondrion #33 (set 1) displayed as a sum projection from (E) the front and (F) above (also see Video 6), with (G) an orthoslice montage of EM and AIVE data through the mitochondrial nanotunnel (position shown by box in F). Scale bars; A–C, 200 nm; E and F, 500 nm. MLP, multilayer perceptron; DT, decision table; PART, projective adaptive resonance theory.
Figure S2.

Data at different stages of AIVE processing. (A–C) 3D depictions of 2D data shown in Figs. 1 and 2, showing the 3D surfaces generated using (A) raw predictions, (B) blurred predictions, or (C) AIVE with one of six different trained models (RF, J48, MLP, DT, JRip, and PART). (D) Raw distance measurements between the 3D probes (shown in Fig. 2 H) and membrane surfaces under every condition shown in A–C. (E–G) Raw AIVE data from mitochondrion #33 (set 1) displayed as a sum projection from (E) the front and (F) above (also see Video 6), with (G) an orthoslice montage of EM and AIVE data through the mitochondrial nanotunnel (position shown by box in F). Scale bars; A–C, 200 nm; E and F, 500 nm. MLP, multilayer perceptron; DT, decision table; PART, projective adaptive resonance theory.

This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal