FaceAge is a deep learning system to estimate biological age from easily obtainable and low-cost face photographs. FaceAge was trained on data from 58 851 presumed healthy individuals aged 60 years or older.

References:

• Dennis Bontempi, Osbert Zalay, Danielle S Bitterman, Nicolai Birkbak, Derek Shyr, Fridolin Haugg, Jack M Qian, Hannah Roberts, Subha Perni, Vasco Prudente, Suraj Pai, Andre Dekker, Benjamin Haibe-Kains, Christian Guthier, Tracy Balboni, Laura Warren, Monica Krishan, Benjamin H Kann, Charles Swanton, Dirk De Ruysscher, Raymond H Mak, Hugo J W L Aerts
  FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study
  The Lancet, 2025, Vol.??, pp.1-13.

• FaceAge Github page
• FaceAge data processing demo

• Module Name: FaceAge (see the modules page for more information)
• Unusual environment variables set
  • FACEAGE_HOME  installation directory
  • FACEAGE_BIN  executable directory
  • FACEAGE_DEMO  demo code directory

Allocate an interactive session and run the program. Sample session:

[user@biowulf]$ sinteractive
[user@cn3144 ~]$ module load FaceAge
[+] Loading singularity  4.2.2  on cn3144
[+] Loading FaceAge  1.0

[user@cn3144 ~]$ $FACEAGE_BIN
python-cpu  python-gpu  shell

[user@cn3144 ~]$ cp $FACEAGE_DEMO/* .
[user@cn3144 ~]$ python-gpu download_data.py

[user@cn3144 ~]$ wget  https://github.com/AIM-Harvard/FaceAge/releases/download/v1/faceage_model.h5

[user@cn3144 ~]$ mkdir outputs
[user@cn3144 ~]$ python-gpu process_data.py

[user@cn3144 ~]$ ls outputs
utk_hi-res_qa_res-ext_data.csv
[user@cn3144 ~]$ cat outputs/utk_hi-res_qa_res-ext_data.csv
subj_id,faceage,age,gender,race
20170104020820934,24.617537,20,1,2
20170117172021611,27.616867,26,0,0
20170112234451680,31.989592,27,1,1
20170117180322086,36.77299,28,1,0
20170117180725353,36.312866,29,0,0
20170113000500356,36.81711,31,1,1
20170119200236372,35.818333,32,0,3
20170117203121712,35.975834,32,1,4
20170117163541966,55.346806,36,0,0
20170117142732651,46.028004,42,0,4
20170117182212741,46.373608,45,0,0
20170119205156254,53.01375,47,0,3
20170119195739498,39.857475,50,0,3
20170104212216588,61.01685,51,1,2
20170120222921386,63.87177,52,0,1
20170104213140733,70.690834,54,0,0
20170110160643391,65.81798,55,1,0
20170120222949154,55.79718,57,0,0
20170117171247961,51.783524,57,0,1
20170110141704735,47.76361,57,1,0
20170111204505433,66.05782,62,0,0
20170111204015410,61.381523,65,0,0
20170117171624306,80.76343,65,0,0
20170111211411216,88.70104,90,0,2
20170110172637082,94.172424,96,1,0
[user@cn3144 ~]$ exit
salloc.exe: Relinquishing job allocation 46116226
[user@biowulf ~]$