Tumor Area Highlighting Using T2WI, ADC Map, and DWI Sequence Fusion on bpMRI Images for Better Prostate Cancer Diagnosis.
Rossy Vlăduț TeicăMircea-Sebastian ȘerbănescuLucian Mihai FlorescuIoana Andreea GheoneaPublished in: Life (Basel, Switzerland) (2023)
Prostate cancer is the second most common cancer in men worldwide. The results obtained in magnetic resonance imaging examinations are used to decide the indication, type, and location of a prostate biopsy and contribute information about the characterization or aggressiveness of detected cancers, including tumor progression over time. This study proposes a method to highlight prostate lesions with a high and very high risk of being malignant by overlaying a T2-weighted image, apparent diffusion coefficient map, and diffusion-weighted image sequences using 204 pairs of slices from 80 examined patients. It was reviewed by two radiologists who segmented suspicious lesions and labeled them according to the prostate imaging-reporting and data system (PI-RADS) score. Both radiologists found the algorithm to be useful as a "first opinion", and they gave an average score on the quality of the highlight of 9.2 and 9.3, with an agreement of 0.96.
Keyphrases
- prostate cancer
- diffusion weighted
- contrast enhanced
- diffusion weighted imaging
- magnetic resonance imaging
- deep learning
- radical prostatectomy
- artificial intelligence
- magnetic resonance
- newly diagnosed
- machine learning
- ejection fraction
- prognostic factors
- papillary thyroid
- high density
- poor prognosis
- adverse drug
- optical coherence tomography
- high resolution
- fine needle aspiration
- photodynamic therapy
- convolutional neural network
- patient reported outcomes
- positron emission tomography
- social media
- pet ct