30 January 2025 in The American Journal of Pathology
Tumor cellularity (TC) in lung adenocarcinoma slides submitted for molecular testing is important in identifying actionable mutations, but absent best practice guidelines yields high interobserver variability in TC assessments. An AI-based pipeline developed to assess TC in whole slide H&E images (WSIs) and in tumor areas (TAs) within WSIs includes a new model (CaBeSt-Net) trained to mask cancer cells, benign epithelial cells, and stroma in H&E WSIs using IHC-restained slides, and a model to detect all cell nuclei. High masking accuracy (>91%) by CaBeSt-Net computed using 1024 H&E ROIs and intraclass correlation coefficient (ICC)>0.97 assessing TC assessments reliability by one pathologist and AI in 20 test ROIs supported pipeline's applicability to TC assessment in 50 study H&E WSIs. Utilizing the pipeline, TCs assessed in TAs and WSIs were compared with those by 3 pathologists. Reliabilities of these ratings by the pathologists supported by the pipeline were good (ICC>0.82, p<0.0001). The consistency of sample categorizations as inadequate or adequate (TC≤20% cut-point) for molecular testing among the pathologists assessing TCs without AI support was moderate in TAs (kappa=0.410, p<0.0001) and slight in WSIs (kappa=0.132, ns.). With AI support, the consistency was substantial in both WSIs (kappa=0.602, p<0.0001) and TAs (kappa=0.704, p<0.0001). By visualizing cancer and measuring TC in the sample this novel AI-based pipeline assists pathologists in selecting samples for molecular testing.
1 August 2025 in JCO Precision Oncology
PURPOSE: Tumor molecular profiling is recommended in pancreatic ductal adenocarcinoma (PDAC). However, the predictive and prognostic value of KRAS variants on clinical outcomes including response to standard therapies remains unknown. METHODS: In this retrospective analysis using real-world data from patients with early-stage (I to III) and metastatic PDAC who underwent molecular profiling via referrals to Perthera or the PanCAN Know Your Tumor program, patients included were 18 years and older, received standard chemotherapy in the first- and second-line setting, and had complete records. Main outcomes were overall survival (OS) and progression-free survival (PFS) measured from the date of diagnosis of metastatic/recurrent metastatic disease stratified by the KRAS variants and chemotherapy regimen. OS and PFS on first- or second-line therapies were analyzed using Cox regression. Outcomes from each subgroup were compared with reference cohort G12D/V using a Bonferroni-adjusted significance threshold of α = .00714 (0.05/7). RESULTS: A total of 1359 patients (median [range] age, 64 [28-94] years; 689 [50.7%] male; 707 [52.0%] White) were included. KRAS wild type had significantly longer OS compared with G12D/V (2.1 v 1.4 years; hazard ratio [HR], 0.61 [95% CI, 0.48 to 0.77]; P < .0001). Q61 had shorter OS (1.1 v 1.5 years; HR, 2.28 [95% CI, 1.33 to 3.92]; P = .0027) and PFS (3.13 v 9.03 months; HR, 2.54 [95% CI, 1.43 to 4.52]; P = .0015) on first-line fluorouracil-based therapy compared with G12D/V. G12R had numerically longer OS (1.8 v 1.5 years; HR, 0.69 [95% CI, 0.48 to 0.98]; P = .0366) and PFS (12.17 v 9.03 months; HR, 0.6 [95% CI, 0.41 to 0.88]; P = .0091) on first-line fluorouracil-based therapy compared with G12D/V. CONCLUSION: KRAS variants are associated with survival and may be predictive of response to standard therapies. A molecularly driven, variant-specific approach is recommended to guide PDAC treatment and better inform prognosis.
9 September 2026 in Psycho-Oncology
Background: Demoralization is a maladaptive coping response to stressful situations, characterized by thoughts of hopelessness, helplessness, and loss of meaning and purpose. Demoralization is clinically measurable using the Demoralization Scale 2 (DS‐II). Pancreatic cancer (PC) patients, who carry a notoriously poor prognosis, are hypothesized to be at higher risk of demoralization. Aims: This study uses the DS‐II to gauge the impact of demoralization in PC patients compared to a heterogenous cancer population and establish its relation to depression. Methods: Patients completed the DS‐II, PHQ‐9, and a demographic survey. The mean DS‐II score of PC patients was compared with that of a previously published heterogenous cancer cohort reported by Ignatius et al. using a one‐sample t ‐test. The univariable association between DS‐II scores and PHQ‐9 scores was examined using linear regression models. Results: Of the 206 patients enrolled in the study, 47% were women and the mean age was 67 ± 10 years. The mean DS‐II total score was 4.9 ± 5.2 points, significantly lower than the mean of 10.8 ± 8.0 previously reported by Ignatius and De La Garza II in a psychiatric oncology cohort ( p < 0.001). There was no significant difference in demoralization scores across disease stages ( p = 0.8). DS‐II scores in univariable models were associated with depression ( β = 0.79, p < 0.001), age ( β = −0.09, p = 0.008), and women ( p = 0.002). Conclusion: Demoralization in this cohort of patients with PC was lower than that reported by Ignatius et al., although differences in recruitment settings and patient characteristics limit direct comparisons. Though disease stage did not impact demoralization scores in PC, our study found demoralization was strongly associated with concurrent depression, young age, and women. Understanding the risk factors associated with demoralization in PC can help enhance the quality of psychosocial care in oncology.
27 March 2026 in American Journal of Transplantation
3 July 2026 in American Journal of Transplantation