Automatic analysis of nuclear features reveals a non-tumoral predictor of tumor grade in bladder cancer.

BACKGROUND & OBJECTIVES: Tumor grade determines prognosis in urothelial carcinoma. The classification of low and high grade is based on nuclear morphological features that include nuclear size, hyperchromasia and pleomorphism. These features are subjectively assessed by the pathologists and are not numerically measured, which leads to high rates of interobserver variability. The purpose of this study is to assess the value of a computer-based image analysis tool for identifying predictors of tumor grade in bladder cancer. METHODS: Four hundred images of urothelial tumors were graded by five pathologists and two expert genitourinary pathologists using a scale of 1 (lowest grade) to 5 (highest grade). A computer algorithm was used to automatically segment the nuclei and to provide morphometric parameters for each nucleus, which were used to establish the grading algorithm. Grading algorithm was compared to pathologists' agreement. RESULTS: Comparison of the grading scores of the five pathologists with the expert genitourinary pathologists score showed agreement rates between 88.5% and 97.5%.The agreement rate between the two expert genitourinary pathologists was 99.5%. The quantified algorithm based conventional parameters that determine the grade (nuclear size, pleomorphism and hyperchromasia) showed > 85% agreement with the expert genitourinary pathologists. Surprisingly, the parameter that was most associated with tumor grade was the 10th percentile of the nuclear area, and high grade was associated with lower 10th percentile nuclei, caused by the presence of more inflammatory cells in the high-grade tumors. CONCLUSION: Quantitative nuclear features could be applied to determine urothelial carcinoma grade and explore new biologically explainable parameters with better correlation to grade than those currently used.

Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images.

Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel deep learning tool for diagnosing DHLs/THLs directly from scanned images of biopsy slides. A total of 57 biopsies, including 32 in a training set (including five DH lymphoma cases) and 25 in a validation set (including 10 DH/TH cases), were included. The DHL-classifier demonstrated a sensitivity of 100%, a specificity of 87% and an AUC of 0.95, with only two false positive cases, compared to FISH. The DHL-classifier showed a 92% predictive value as a screening tool for performing conventional FISH analysis, over-performing currently used criteria. The work presented here provides the proof of concept for the potential use of an AI tool for the identification of DH/TH events. However, more extensive follow-up studies are required to assess the robustness of this tool and achieve high performances in a diverse population.

Short Training Significantly Improves Ganglion Cell Detection Using an Algorithm-Assisted Approach.

CONTEXT.­: Medical education in pathology relies on the accumulation of experience gained through inspection of numerous samples from each entity. Acquiring sufficient teaching material for rare diseases, such as Hirschsprung disease (HSCR), may be difficult, especially in smaller institutes. The current study makes use of a previously developed decision support system using a decision support algorithm meant to aid pathologists in the diagnosis of HSCR. OBJECTIVE.­: To assess the effect of a short training session on algorithm-assisted HSCR diagnosis. DESIGN.­: Five pathologists reviewed a data set of 568 image sets (1704 images in total) selected from 50 cases by the decision support algorithm and were tasked with scoring the images for the presence or absence of ganglion cells. The task was repeated a total of 3 times. Each pathologist had to complete a short educational presentation between the second and third iterations. RESULTS.­: The training resulted in a significantly increased rate of correct diagnoses (true positive/negative) and a decreased need for referrals for expert consultation. No statistically significant changes in the rate of false positives/negatives were detected. CONCLUSIONS.­: A very short (<10 minutes) training session can greatly improve the pathologist's performance in the algorithm-assisted diagnosis of HSCR. The same approach may be feasible in training for the diagnosis of other rare diseases.

Ex vivo organotypic cultures for synergistic therapy prioritization identify patient-specific responses to combined MEK and Src inhibition in colorectal cancer.

Translating preclinical studies to effective treatment protocols and identifying specific therapeutic responses in individuals with cancer is challenging. This may arise due to the complex genetic makeup of tumor cells and the impact of their multifaceted tumor microenvironment on drug response. To find new clinically relevant drug combinations for colorectal cancer (CRC), we prioritized the top five synergistic combinations from a large in vitro screen for ex vivo testing on 29 freshly resected human CRC tumors and found that only the combination of mitogen-activated protein kinase kinase (MEK) and proto-oncogene tyrosine-protein kinase Src (Src) inhibition was effective when tested ex vivo. Pretreatment phosphorylated Src (pSrc) was identified as a predictive biomarker for MEK and Src inhibition only in the absence of KRASG12 mutations. Overall, we demonstrate the potential of using ex vivo platforms to identify drug combinations and discover MEK and Src dual inhibition as an effective drug combination in a predefined subset of individuals with CRC.

Protective Desmoplasia in Pancreatic Adenocarcinoma: High Vitamin D Receptor Expression and Collagen Content.

BACKGROUND/AIM: Vitamin D receptor (VDR) has been shown to suppress desmoplasia in pancreatic ductal adenocarcinoma (PDAC). Our aim was to assess the clinical effects of VDR expression and its correlation with collagen content in the desmoplasia of PDAC patients. PATIENTS AND METHODS: This is a retrospective analysis of 127 patients with peritumoral desmoplasia resected for PDAC. VDR expression and collagen content were assessed by immunohistochemistry and correlated with clinical outcome. RESULTS: Patients were classified into those with high and those with low VDR expression. High VDR expression was associated with improved overall survival (OS) in localized disease (N0) (median= 33; 95%CI=26.4-39.6 vs. 18; 15.5-20.5 months, p=0.01). Patients with high vs. low collagen content had improved OS [34, (range=22.3-45.6 months) vs. 17, (range=14.4-19.6 months), p<0.001]. The number of VDR+ cells was the same for patients with either high or low collagen content. CONCLUSION: Protective desmoplasia is associated with increased VDR expression and collagen content.

Mutant KRAS Circulating Tumor DNA Is an Accurate Tool for Pancreatic Cancer Monitoring.

BACKGROUND: Many new pancreatic cancer treatment combinations have been discovered in recent years, yet the prognosis of pancreatic ductal adenocarcinoma (PDAC) remains grim. The advent of new treatments highlights the need for better monitoring tools for treatment response, to allow a timely switch between different therapeutic regimens. Circulating tumor DNA (ctDNA) is a tool for cancer detection and characterization with growing clinical use. However, currently, ctDNA is not used for monitoring treatment response. The high prevalence of KRAS hotspot mutations in PDAC suggests that mutant KRAS can be an efficient ctDNA marker for PDAC monitoring. SUBJECTS, MATERIALS, AND METHODS: Seventeen metastatic PDAC patients were recruited and serial plasma samples were collected. CtDNA was extracted from the plasma, and KRAS mutation analysis was performed using next-generation sequencing and correlated with serum CA19-9 levels, imaging, and survival. RESULTS: Plasma KRAS mutations were detected in 5/17 (29.4%) patients. KRAS ctDNA detection was associated with shorter survival (8 vs. 37.5 months). Our results show that, in ctDNA positive patients, ctDNA is at least comparable to CA19-9 as a marker for monitoring treatment response. Furthermore, the rate of ctDNA change was inversely correlated with survival. CONCLUSION: Our results confirm that mutant KRAS ctDNA detection in metastatic PDAC patients is a poor prognostic marker. Additionally, we were able to show that mutant KRAS ctDNA analysis can be used to monitor treatment response in PDAC patients and that ctDNA dynamics is associated with survival. We suggest that ctDNA analysis in metastatic PDAC patients is a readily available tool for disease monitoring. IMPLICATIONS FOR PRACTICE: Avoiding futile chemotherapy in metastatic pancreatic ductal adenocarcinoma (PDAC) patients by monitoring response to treatment is of utmost importance. A novel biomarker for monitoring treatment response in PDAC, using mutant KRAS circulating tumor DNA (ctDNA), is proposed. Results, although limited by small sample numbers, suggest that ctDNA can be an effective marker for disease monitoring and that ctDNA level over time is a better predictor of survival than the dynamics of the commonly used biomarker CA19-9. Therefore, ctDNA analysis can be a useful tool for monitoring PDAC treatment response. These results should be further validated in larger sample numbers.