31 Genetic optimization of low-compute techniques for peritoneal lesion detection during staging laparoscopy
Isaac Gendelman, Janil Liu, Liping Thomas · 2026
Read 31 Genetic optimization of low-compute techniques for peritoneal lesion detection during staging laparoscopy by Isaac Gendelman, Janil Liu, Liping Thomas (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13173057.txt.
Description
Spotting cancer spread on the belly's inner wall during keyhole surgery is a task where even skilled surgeons miss marks. Isaac Gendelman, Janil Liu, and Liping Thomas tune a light image pipeline to help in a 2026 conference report. The pool holds 1,414 images with 5,943 marked lesions from 163 patients whose gut cancers were being staged.
Five filters, three by colour and two by edge and texture, each make a mask of the image. The masks merge, are smoothed, and are cut to a final call. Sixteen settings govern the blend, too many to tune by hand. A genetic search, which breeds good settings and keeps the best, tunes them to catch the most lesions while flagging the least healthy tissue. Early data are the base for the tune.
Catalog record
| CREATOR | Isaac Gendelman, Janil Liu, Liping Thomas |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |