Lin, Chi H.

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.

584 Background: Standard therapy for stage II/III rectal cancer includes surgery, radiation, and chemotherapy. Multiple trials demonstrated neoadjuvant chemoradiation (CRT) provides better local control and decreased morbidity compared to adjuvant CRT, though differences in overall survival and long-term QoL have not been demonstrated. We examined impact of treatment (pre-op CRT/post-op CRT/no CRT) on long-term QoL. Methods: CanCORS patients with survey/medical record data diagnosed in 2003-2005 with stage II/III rectal (non-rectosigmoid) cancer had resection and survived > 7 years were included. QoL (SF-36, EQ-5D) measures and defecation problems were derived from surveys at 14 months and 7 years post-diagnosis. Mean scores were adjusted for the following when significant: age, gender, stage, sphincter preservation, comorbidities, and baseline self-reported health status and QoL scores. Results: Of 119 patients, 53% received pre-op CRT, 23% post-op CRT, and 24% no CRT. Of 114 patients with 14-month follow-up, Pre-op CRT and No CRT groups had better EQ-5D adjusted mean scores but worse defecation scale (DS) scores compared to the Post-op CRT group. Of 49 disease-free survivors with 7 years follow-up, there were no differences among groups in QoL scores, but the No CRT group had better DS scores than other groups. Conclusions: No major differences were detected in long-term QoL based on treatment aside from the DS, though sample sizes became small. Regardless of treatment, long term (7y) mental health and vitality were generally comparable to U.S. norms, while physical health and overall health status (EQ-5D) were somewhat lower. [Table: see text]

Neoadjuvant treatment may result in better quality of life and functional status 1 year after diagnosis.