Use of Deep Learning to Evaluate Tumor Microenvironmental Features for Prediction of Colon Cancer Recurrence.
Frank A SinicropeGarth D NelsonBahar Saberzadeh-ArdestaniDiana I SegoviaRondell P GrahamChristina WuCatherine E HagenSameer ShivjiPaul SavageDaniel D BuchananMark E JenkinsAmanda I PhippsCarol Jane SwallowLoic Le MarchandSteven J GallingerRobert C GrantReetesh K PaiStephen N SinicropeDongyao YanKandavel ShanmugamJames ConnerDavid P CyrRichard KirschImon BanerjeeSteven R AlbertsQian ShiRish K PaiPublished in: Cancer research communications (2024)
A deep learning algorithm can quantify tumor morphologic features that may reflect underlying mechanisms driving prognosis within MMR groups. TSR was the most robust morphologic feature associated with TTR in p-MMR colon cancers. Extent of inflammatory stroma and N stage were the strongest prognostic features in d-MMR tumors. TIL density was not independently prognostic in either MMR group.