Table 4.

Overall accuracies of variant_LeNet architecture at classifying ovarian spectra.

Dataset	# classes	CNN from scratch	Transfer learning	Cumulative learning
Human ovary 1	2	0.78 ± 0.02	0.98 ± 0.00 (25%a)	–
Human ovary 2	2	0.80 ± 0.00	0.83 ± 0.02 (03%a)	0.99 ± 0.00 (23%a 19%b)

The best result for each task (accuracy ± standard variation over 10 independent iterations) is indicated in boldface.

^aThe improvement is expressed as a percentage relative to learning from scratch.

^bThe improvement is expressed as a percentage relative to transfer learning.