Al momento stai visualizzando RadioPhatomics for biomarkers discovery

RadioPhatomics for biomarkers discovery


Colorectal cancer (CRC) is the third most common cancer worldwide and the second most lethal. Nearly 30% of CRC are in the rectum (RC). The standard treatment of locally advanced rectal cancers (LARC) is preoperative chemo-radiotherapy (CRT) followed by invasive surgery and CAPOX adjuvant chemotherapy. Intensification of the neoadjuvant treatment by anticipating CAPOX in addition to CRT prior to surgery, is well tolerated and associated with a higher pathological complete response (pCR) rate. This approach is known as total neoadjuvant therapy (TNT). Achieving a pCR can translate in a No Operative Management (NOM) of the patient, with full organ function preservation and a vast improvement in quality of life. The feasibility of NOM however depends on defining a response marker with optimal predictive power in each patient.

 Artificial intelligence (AI) applied to radiological images (radiomics) or whole-slide images (WSI, pathomics) is effective in delivering outcomes predictive signatures for many cancer types, including LARC. Tumor molecular profiling also provides valuable prognostic and predictive information guiding treatment choices. Each of these omics has been used in RC but with a single modal approach. We posit that deploying the three techniques concurrently could provide a highly informative snapshot of the tumor response to treatment and deliver an integrated marker with high predictive power for choosing among vastly different treatment options.


The aim of this study is to develop an AI-based multi-omics signatures able to answer the following questions: (i)How can we properly select CRT/TNT-responsive patients eligible for Non-Operative Management? and (ii)Can we predict patients that will develop distant metastases after treatment?


FONDAZIONE AIRC under 5 per mille 2018 – ID 21091 program- PI Alberto Bardelli, GLs Daniele Regge, Silvia Marsoni and Salvatore Siena. 


  1. Defeudis A, Mazzetti S, Panic J, et al. MRI-based radiomics to predict response in locally advanced rectal cancer: comparison of manual and automatic segmentation on external validation in a multicentre
    study. Eur Radiol Exp. 2022;6(1). doi:10.1186/s41747-022-00272-2
  2. Coppola F, Giannini V, Gabelloni M, et al. Radiomics and magnetic resonance imaging of rectal cancer: From engineering to clinical practice. Diagnostics. 2021;11(5). doi:10.3390/diagnostics11050756
  3. Rosati S, Gianfreda CM, Balestra G, Giannini V, Mazzetti S, Regge D. Radiomics to predict response to neoadjuvant chemotherapy in rectal cancer: Influence of simultaneous feature selection and classifier optimization. In: 2018 IEEE Life Sciences Conference, LSC 2018. ; 2018:65-68. doi:10.1109/LSC.2018.8572194
  4. Giannini V, Mazzetti S, Bertotto I, et al. Predicting locally advanced rectal cancer response to neoadjuvant therapy with 18 F-FDG PET and MRI radiomics features. Eur J Nucl Med Mol Imaging. 2019;46(4):878-888. doi:10.1007/s00259-018-4250-6