Domain-specific loss design for unsupervised physical training: A new approach to modeling medical ML solutions

  title={Domain-specific loss design for unsupervised physical training: A new approach to modeling medical ML solutions},
  author={Hendrik Burwinkel and Holger Matz and Stefan Saur and C. Hauger and Ayse Mine Evren and Nino Hirnschall and Oliver Findl and Nassir Navab and Seyed-Ahmad Ahmadi},
Today, cataract surgery is the most frequently performed ophthalmic surgery in the world. The cataract, a developing opacity of the human eye lens, constitutes the world's most frequent cause for blindness. During surgery, the lens is removed and replaced by an artificial intraocular lens (IOL). To prevent patients from needing strong visual aids after surgery, a precise prediction of the optical properties of the inserted IOL is crucial. There has been lots of activity towards developing… 
2 Citations
Application of Deep Learning Method in Automatic Collection and Processing of Video Surveillance Data for Basketball Sports Prediction
A deep learning-based novel video framework is proposed to rebound and build a system to predict which will get it with the player's position data and viability, performance and efficiency prove the proposed framework's reliability.


Intraocular Lens Power Formula Selection Using Support Vector Machines
Experimental results show that for the first group, formula proposing weaker powers win the race for decreased postoperative refraction error while for the second group, formulas leading to stronger powers perform better, which shows that these formulas overestimate and underestimate for marginal cases.
Accuracy of 3 new methods for intraocular lens power selection.
Comparison of intraocular lens computations using a neural network versus the Holladay formula
C constant: New concept for ray tracing–assisted intraocular lens power calculation
An improved universal theoretical formula for intraocular lens power prediction
  • G. Barrett
  • Medicine
    Journal of cataract and refractive surgery
  • 1993
A three‐part system for refining intraocular lens power calculations
Biometry and intraocular lens power calculation
The article reviews recent studies and advances in the field of biometry and intraocular lens power calculations and finds several noncontact optical-based devices compare favorably, if not superiorly, to older ultrasonic biometric and keratometric techniques.
Comparison of the Kane formula with existing formulas for intraocular lens power selection
Using three variables (AL, K, ACD), the Kane formula was a more accurate predictor of actual postoperative refraction than the other formulae under investigation.