A deep learning framework for lesion-level treatment response prediction in hodgkin lymphoma using PET/CT tensor radiomics
Mahdie Jajroudi, Hossein Jamalirad, Milad Enferadi, Vahid Roshanravan, Farshad Emami, Parham Geramifar, Saeid Eslami · 2026
Read A deep learning framework for lesion-level treatment response prediction in hodgkin lymphoma using PET/CT tensor radiomics by Mahdie Jajroudi, Hossein Jamalirad, Milad Enferadi, Vahid Roshanravan, Farshad Emami, Parham Geramifar, Saeid Eslami (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/PMC13269603.txt.
Description
Mahdie Jajroudi and co-authors published a journal article in 2026 predicting how Hodgkin lymphoma tumors respond to treatment, lesion by lesion. Their method mines medical scans for thousands of measured features, varied across many settings. A deep learning network then selects features and makes the prediction.
Scans from 70 patients yielded 420 lesions and 13,790 features each. The new network scored 0.8470 on a standard accuracy curve, finding 82.2 percent of responding lesions and clearing 78.2 percent of others. It beat three standard machine learning models, including a boosting method at 0.8160. An explanation tool showed which features drove each prediction. The authors aim at more personal therapy choices.
Catalog record
| CREATOR | Mahdie Jajroudi, Hossein Jamalirad, Milad Enferadi, Vahid Roshanravan, Farshad Emami, Parham Geramifar, Saeid Eslami |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63108 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |