An integrated radiology-pathology machine learning classifier for outcome prediction following radical prostatectomy: Preliminary findings.

Objectives: To evaluate the added benefit of integrating features from pre-treatment MRI (radiomics) and digitized post-surgical pathology slides (pathomics) in prostate cancer (PCa) patients for prognosticating outcomes post radical-prostatectomy (RP) including a) rising prostate specific antigen (PSA), and b) extraprostatic-extension (EPE). Methods: Multi-institutional data (N = 58) of PCa patients who underwent pre-treatment 3-T MRI prior to RP were included in this retrospective study. Radiomic and pathomic features were extracted from PCa regions on MRI and RP specimens delineated by expert clinicians. On training set (D1, N = 44), Cox Proportional-Hazards models MR, MP and MRaP were trained using radiomics, pathomics, and their combination, respectively, to prognosticate rising PSA (PSA > 0.03 ng/mL). Top features from MRaP were used to train a model to predict EPE on D1 and test on external dataset (D2, N = 14). C-index, Kalplan-Meier curves were used for survival analysis, and area under ROC (AUC) was used for EPE. MRaP was compared with the existing post-treatment risk-calculator, CAPRA (MC). Results: Patients had median follow-up of 34 months. MRaP (c-index = 0.685 ± 0.05) significantly outperformed MR (c-index = 0.646 ± 0.05), MP (c-index = 0.631 ± 0.06) and MC (c-index = 0.601 ± 0.071) (p < 0.0001). Cross-validated Kaplan-Meier curves showed significant separation among risk groups for rising PSA for MRaP (p < 0.005, Hazard Ratio (HR) = 11.36) as compared to MR (p = 0.64, HR = 1.33), MP (p = 0.19, HR = 2.82) and MC (p = 0.10, HR = 3.05). Integrated radio-pathomic model MRaP (AUC = 0.80) outperformed MR (AUC = 0.57) and MP (AUC = 0.76) in predicting EPE on external-data (D2). Conclusions: Results from this preliminary study suggest that a combination of radiomic and pathomic features can better predict post-surgical outcomes (rising PSA and EPE) compared to either of them individually as well as extant prognostic nomogram (CAPRA).

Advancing Fellowship Training in Selective Pathology.

CONTEXT.­: Program requirements for Selective Pathology fellowships in the United States were established by the Accreditation Council for Graduate Medical Education (ACGME) in 2011 to govern fellowships providing advanced training in surgical pathology, focused anatomic pathology, or focused clinical pathology. Selective Pathology entered the ACGME's Next Accreditation System in 2015 with the introduction of the Selective Pathology Milestones 1.0, a set of benchmarks for evaluating fellow progress in each of the 6 ACGME core competencies. In 2019, the ACGME convened a work group for a planned periodic update to these milestones. OBJECTIVE.­: To summarize changes to the Selective Pathology milestones. DESIGN.­: The study design featured expert opinion and survey. RESULTS.­: The Patient Care milestones for anatomic pathology-focused fellowships contain a renewed emphasis on both gross and microscopic examination, whereas for clinical pathology-focused fellowships, the emphasis is on interpretation of laboratory assays. The milestones for the non-Patient Care, non-Medical Knowledge competencies have been updated to a harmonized set of milestones designed to extend across all specialties and subspecialties. New to the milestones program is a supplemental guide that provides examples, suggested assessment tools, and references to aid in implementation. Public comments were supportive of the changes. CONCLUSIONS.­: The Milestones 2.0 are set for implementation in July 2021. Updates in the new milestones are aimed at facilitating training and harmonizing evaluation across subspecialties.

Recurrence of Epidural Spinal Sarcoidosis.

Neurosarcoidosis involving the spine is uncommon. Sarcoidosis of the spine usually presents as an intramedullary lesion and rarely an epidural lesion. To have recurrence of neurosarcoidosis is an even rarer presentation. Here, we present a 37-year-old man with poorly controlled sarcoidosis who initially presented to our medical center in 2015 with thoracic myelopathy from epidural spinal sarcoidosis treated with thoracic decompression and fusion. He presented to the hospital 5 years later with a month history of progressive upper extremity weakness. MRI revealed recurrent stenosis and spinal cord compression in the cervicothoracic junction. Urgent surgical intervention along with medical management resulted in symptomatic and functional improvement. Surgical intervention and compliance with postoperative corticosteroid therapy seem to yield a favorable prognosis for patients with epidural spinal sarcoidosis and to avoid recurrence.

Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study.

Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03-3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40-3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.

Computationally Derived Cribriform Area Index from Prostate Cancer Hematoxylin and Eosin Images Is Associated with Biochemical Recurrence Following Radical Prostatectomy and Is Most Prognostic in Gleason Grade Group 2.

BACKGROUND: The presence of invasive cribriform adenocarcinoma (ICC), an expanse of cells containing punched-out lumina uninterrupted by stroma, in radical prostatectomy (RP) specimens has been associated with biochemical recurrence (BCR). However, ICC identification has only moderate inter-reviewer agreement. OBJECTIVE: To investigate quantitative machine-based assessment of the extent and prognostic utility of ICC, especially within individual Gleason grade groups. DESIGN, SETTING, AND PARTICIPANTS: A machine learning approach was developed for ICC segmentation using 70 RP patients and validated in a cohort of 749 patients from four sites whose median year of surgery was 2007 and with median follow-up of 28 mo. ICC was segmented on one representative hematoxylin and eosin RP slide per patient and the fraction of tumor area composed of ICC, the cribriform area index (CAI), was measured. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The association between CAI and BCR was measured in terms of the concordance index (c index) and hazard ratio (HR). RESULTS AND LIMITATIONS: CAI was correlated with BCR (c index 0.62) in the validation set of 411 patients with ICC morphology, especially those with Gleason grade group 2 cancer (n = 192; c index 0.66), and was less prognostic when patients without ICC were included (c index 0.54). A doubling of CAI in the group with ICC morphology was prognostic after controlling for Gleason grade, surgical margin positivity, preoperative prostate-specific antigen level, pathological T stage, and age (HR 1.19, 95% confidence interval 1.03-1.38; p = 0.018). CONCLUSIONS: Automated image analysis and machine learning could provide an objective, quantitative, reproducible, and high-throughput method of quantifying ICC area. The performance of CAI for grade group 2 cancer suggests that for patients with little Gleason 4 pattern, the ICC fraction has a strong prognostic role. PATIENT SUMMARY: Machine-based measurement of a specific cell pattern (cribriform; sieve-like, with lots of spaces) in images of prostate specimens could improve risk stratification for patients with prostate cancer. In the future, this could help in expanding the criteria for active surveillance.

Benign Metastasizing Leiomyoma in the Heart of a 45-Year-Old Woman.

We report a rare case of benign metastasizing leiomyoma in the heart of a 45-year-old woman 2 years after a uterine leiomyoma had been discovered during hysterectomy. Computed tomograms at presentation showed a large mixed cystic mass in the pelvis and bilateral lung nodules suggestive of metastatic disease. A large cardiac mass, attached to the chordae of the tricuspid valve and later shown to be histopathologically consistent with uterine leiomyoma, was successfully resected through a right atriotomy. This case suggests that benign metastasizing leiomyoma should be considered in the differential diagnosis of right-sided cardiac tumors.

Multidisciplinary approach for repeat musculoskeletal lesion biopsy after nondiagnostic initial sampling: A 10-year single-center experience.

BACKGROUND AND OBJECTIVES: Success rates for initial image-guided biopsy of musculoskeletal (MSK) lesions have been well documented; evidence regarding success rates for repeat biopsy following initially nondiagnostic (ND) image-guided biopsy of MSK lesions is more limited. This study evaluates the outcomes of repeat computerized tomography-guided MSK biopsies following ND biopsies using a multidisciplinary approach. MATERIALS AND METHODS: Electronic medical record search covering a 10-year period identified patients that received two or more biopsies for an MSK tumor or tumor-like process. The decision for initial and repeat image-guided biopsy of each lesion was made following multidisciplinary MSK tumor board review. Lesion location, histopathology results, size of biopsy needle when available, and change in technique between biopsy attempts was documented. RESULTS: Repeat biopsy rate was 1.6%. 23 patients with repeat MSK biopsy were identified. A total of 17 of 23 (74%) repeat biopsy attempts were diagnostic. A total of 22 of 23 (96%) repeat biopsy attempts were clinically useful. Diagnostic repeat biopsies were described as employing one or more of five technical differences compared to the first biopsy attempt, the most common being improved targeting of the lesion itself. CONCLUSIONS: A multidisciplinary approach may yield improved repeat-biopsy rates and clinical utility of repeat MSK biopsies compared to prior reports.

T1 and T2 MR fingerprinting measurements of prostate cancer and prostatitis correlate with deep learning-derived estimates of epithelium, lumen, and stromal composition on corresponding whole mount histopathology.

OBJECTIVES: To explore the associations between T1 and T2 magnetic resonance fingerprinting (MRF) measurements and corresponding tissue compartment ratios (TCRs) on whole mount histopathology of prostate cancer (PCa) and prostatitis. MATERIALS AND METHODS: A retrospective, IRB-approved, HIPAA-compliant cohort consisting of 14 PCa patients who underwent 3 T multiparametric MRI along with T1 and T2 MRF maps prior to radical prostatectomy was used. Correspondences between whole mount specimens and MRI and MRF were manually established. Prostatitis, PCa, and normal peripheral zone (PZ) regions of interest (ROIs) on pathology were segmented for TCRs of epithelium, lumen, and stroma using two U-net deep learning models. Corresponding ROIs were mapped to T2-weighted MRI (T2w), apparent diffusion coefficient (ADC), and T1 and T2 MRF maps. Their correlations with TCRs were computed using Pearson's correlation coefficient (R). Statistically significant differences in means were assessed using one-way ANOVA. RESULTS: Statistically significant differences (p < 0.01) in means of TCRs and T1 and T2 MRF were observed between PCa, prostatitis, and normal PZ. A negative correlation was observed between T1 and T2 MRF and epithelium (R = - 0.38, - 0.44, p < 0.05) of PCa. T1 MRF was correlated in opposite directions with stroma of PCa and prostatitis (R = 0.35, - 0.44, p < 0.05). T2 MRF was positively correlated with lumen of PCa and prostatitis (R = 0.57, 0.46, p < 0.01). Mean T2 MRF showed significant differences (p < 0.01) between PCa and prostatitis across both transition zone (TZ) and PZ, while mean T1 MRF was significant (p = 0.02) in TZ. CONCLUSION: Significant associations between MRF (T1 in the TZ and T2 in the PZ) and tissue compartments on corresponding histopathology were observed. KEY POINTS: • Mean T2 MRF measurements and ADC within cancerous regions of interest dropped with increasing ISUP prognostic groups (IPG). • Mean T1 and T2 MRF measurements were significantly different (p < 0.001) across IPGs, prostatitis, and normal peripheral zone (NPZ). • T2 MRF showed stronger correlations in the peripheral zone, while T1 MRF showed stronger correlations in the transition zone with histopathology for prostate cancer.

Molecular Profiling of Pediatric and Adult Glioblastoma.

OBJECTIVES: Although glioblastoma (GBM) is rare in the pediatric population, it is the most common cause of death among children with central nervous system neoplasms. Recent molecular profiling of these neoplasms has demonstrated distinct differences in comparison to their adult counterparts. Moreover, many pediatric GBMs occur within the context of cancer predisposition syndromes, such as constitutional mismatch repair deficiency syndrome (CMMRD). Children with CMMRD who develop GBM exhibit a high tumor mutational burden and may benefit from treatment with immune checkpoint inhibitors. METHODS: We performed next-generation sequencing and immunohistochemistry for mismatch repair proteins in our cohort of pediatric and adult GBMs to further characterize the molecular profiles of these groups. RESULTS: We examined a total of 11 pediatric and 11 adult GBMs. Pediatric patients had a higher number of alterations compared to their adult counterparts. They also had a higher frequency of alterations in the mismatch repair genes, which can be detected by immunohistochemistry (IHC). We also identified one pediatric patient with CMMRD syndrome. CONCLUSIONS: Our study highlighted the distinct molecular differences between pediatric and adult GBM. We also demonstrated that pediatric patients have a higher frequency of alterations in the mismatch repair genes, which may render them susceptible to treatment with immune checkpoint inhibitors. These alterations can be detected using routine IHC and should be performed on all pediatric GBM.

Hyaline fibromatosis syndrome: A rare case of multifocal intra-articular involvement.

Hyaline fibromatosis syndrome (HFS) is a rare, progressive, autosomal recessive disorder that presents with connective tissue deposition of amorphous hyaline material within the musculocutaneous tissue and/or visceral organs. HFS presents clinically in infancy or early childhood and can result in severe disability and life threatening complications. Given the rarity of the disorder, the imaging characteristics of HFS are seldom described in the literature. We describe a case of a 25-year-old patient presenting with bilateral knee pain, limited range of motion in her extremities, and lower extremity weakness with detailed MR imaging demonstrating the first case of multifocal intra-articular deposition of hyaline material within several joints.

Computer Extracted Features from Initial H&E Tissue Biopsies Predict Disease Progression for Prostate Cancer Patients on Active Surveillance.

In this work, we assessed the ability of computerized features of nuclear morphology from diagnostic biopsy images to predict prostate cancer (CaP) progression in active surveillance (AS) patients. Improved risk characterization of AS patients could reduce over-testing of low-risk patients while directing high-risk patients to therapy. A total of 191 (125 progressors, 66 non-progressors) AS patients from a single site were identified using The Johns Hopkins University's (JHU) AS-eligibility criteria. Progression was determined by pathologists at JHU. 30 progressors and 30 non-progressors were randomly selected to create the training cohort D1 (n = 60). The remaining patients comprised the validation cohort D2 (n = 131). Digitized Hematoxylin & Eosin (H&E) biopsies were annotated by a pathologist for CaP regions. Nuclei within the cancer regions were segmented using a watershed method and 216 nuclear features describing position, shape, orientation, and clustering were extracted. Six features associated with disease progression were identified using D1 and then used to train a machine learning classifier. The classifier was validated on D2. The classifier was further compared on a subset of D2 (n = 47) against pro-PSA, an isoform of prostate specific antigen (PSA) more linked with CaP, in predicting progression. Performance was evaluated with area under the curve (AUC). A combination of nuclear spatial arrangement, shape, and disorder features were associated with progression. The classifier using these features yielded an AUC of 0.75 in D2. On the 47 patient subset with pro-PSA measurements, the classifier yielded an AUC of 0.79 compared to an AUC of 0.42 for pro-PSA. Nuclear morphometric features from digitized H&E biopsies predicted progression in AS patients. This may be useful for identifying AS-eligible patients who could benefit from immediate curative therapy. However, additional multi-site validation is needed.

The crucial p53-dependent oncogenic role of JAB1 in osteosarcoma in vivo.

Osteosarcoma (OS) is the most common primary bone cancer and ranks amongst the leading causes of cancer mortality in young adults. Jun activation domain-binding protein 1 (JAB1) is overexpressed in many cancers and has recently emerged as a novel target for cancer treatment. However, the role of JAB1 in osteosarcoma was virtually unknown. In this study, we demonstrate that JAB1-knockdown in malignant osteosarcoma cell lines significantly reduced their oncogenic properties, including proliferation, colony formation, and motility. We also performed RNA-sequencing analysis in JAB1-knockdown OS cells and identified 4110 genes that are significantly differentially expressed. This demonstrated for the first time that JAB1 regulates a large and specific transcriptome in cancer. We also found that JAB1 is overexpressed in human OS and correlates with a poor prognosis. Moreover, we generated a novel mouse model that overexpresses Jab1 specifically in osteoblasts upon a TP53 heterozygous sensitizing background. Interestingly, by 13 months of age, a significant proportion of these mice spontaneously developed conventional OS. Finally, we demonstrate that a novel, highly specific small molecule inhibitor of JAB1, CSN5i-3, reduces osteosarcoma cell viability, and has specific effects on the ubiquitin-proteasome system in OS. Thus, we show for the first time that the overexpression of JAB1 in vivo can result in accelerated spontaneous tumor formation in a p53-dependent manner. In summary, JAB1 might be a unique target for the treatment of osteosarcoma and other cancers.

Extraprostatic extension in prostate cancer: primer for radiologists.

The presence of extraprostatic extension (EPE) on multiparametric MRI (mpMRI) is an important factor in determining the management of prostate cancer. EPE is an established risk factor for biochemical recurrence of prostate cancer after radical prostatectomy (RP) and patients with EPE may be considered for wider resection margins, non-nerve-sparing surgery, adjuvant radiation therapy (RT), or androgen deprivation therapy (ADT). Several statistical nomograms and scoring systems have been developed to predict pathological stage at time of RP but with varying accuracies. Using the current PI-RADS v2 mpMRI staging guidelines results in high specificity but lacks in sensitivity. These findings reveal the need for more standardization and further refinement of existing MRI protocols and prostate cancer prediction tools. Current studies have looked into indirect additional imaging criteria such as index tumor volume, length of capsular contact, and apparent diffusion coefficient. Measuring for these features can improve the robustness of mpMRI in staging prostate cancer, as they have been shown to be independent predictors of EPE. MRI/ultrasound fusion-guided targeted biopsy can detect EPE not found on standard biopsy. Collectively, these measurements and imaging techniques can augment the detection of EPE and subsequent risk stratification.

Computationally Derived Image Signature of Stromal Morphology Is Prognostic of Prostate Cancer Recurrence Following Prostatectomy in African American Patients.

PURPOSE: Between 30%-40% of patients with prostate cancer experience disease recurrence following radical prostatectomy. Existing clinical models for recurrence risk prediction do not account for population-based variation in the tumor phenotype, despite recent evidence suggesting the presence of a unique, more aggressive prostate cancer phenotype in African American (AA) patients. We investigated the capacity of digitally measured, population-specific phenotypes of the intratumoral stroma to create improved models for prediction of recurrence following radical prostatectomy. EXPERIMENTAL DESIGN: This study included 334 radical prostatectomy patients subdivided into training (VT, n = 127), validation 1 (V1, n = 62), and validation 2 (V2, n = 145). Hematoxylin and eosin-stained slides from resected prostates were digitized, and 242 quantitative descriptors of the intratumoral stroma were calculated using a computational algorithm. Machine learning and elastic net Cox regression models were constructed using VT to predict biochemical recurrence-free survival based on these features. Performance of these models was assessed using V1 and V2, both overall and in population-specific cohorts. RESULTS: An AA-specific, automated stromal signature, AAstro, was prognostic of recurrence risk in both independent validation datasets [V1,AA: AUC = 0.87, HR = 4.71 (95% confidence interval (CI), 1.65-13.4), P = 0.003; V2,AA: AUC = 0.77, HR = 5.7 (95% CI, 1.48-21.90), P = 0.01]. AAstro outperformed clinical standard Kattan and CAPRA-S nomograms, and the underlying stromal descriptors were strongly associated with IHC measurements of specific tumor biomarker expression levels. CONCLUSIONS: Our results suggest that considering population-specific information and stromal morphology has the potential to substantially improve accuracy of prognosis and risk stratification in AA patients with prostate cancer.

Primary cardiac epithelioid angiosarcoma with frond-like features: a rare and ominous radiological mimicker of benign cardiac tumors.

Most primary cardiac tumors are benign neoplasms, which generally can be differentiated from malignant neoplasms via certain radiological features. We present briefly a case of a 26-year-old man undergoing resection of a right atrial mass that based on preceding radiologic findings represent a myxoma. After pathologic examination, the lesion was determined to be an epithelioid angiosarcoma with unique frond-like architecture and multiple pedicular attachments to the atrial wall.

Drug Repurposing: The Anthelmintics Niclosamide and Nitazoxanide Are Potent TMEM16A Antagonists That Fully Bronchodilate Airways.

There is an unmet need in severe asthma where approximately 40% of patients exhibit poor ß-agonist responsiveness, suffer daily symptoms and show frequent exacerbations. Antagonists of the Ca2+-activated Cl- channel, TMEM16A, offers a new mechanism to bronchodilate airways and block the multiple contractiles operating in severe disease. To identify TMEM16A antagonists we screened a library of ∼580,000 compounds. The anthelmintics niclosamide, nitazoxanide, and related compounds were identified as potent TMEM16A antagonists that blocked airway smooth muscle depolarization and contraction. To evaluate whether TMEM16A antagonists resist use- and inflammatory-desensitization pathways limiting ß-agonist action, we tested their efficacy under harsh conditions using maximally contracted airways or airways pretreated with a cytokine cocktail. Stunningly, TMEM16A antagonists fully bronchodilated airways, while the ß-agonist isoproterenol showed only partial effects. Thus, antagonists of TMEM16A and repositioning of niclosamide and nitazoxanide represent an important additional treatment for patients with severe asthma and COPD that is poorly controlled with existing therapies. It is of note that drug repurposing has also attracted wide interest in niclosamide and nitazoxanide as a new treatment for cancer and infectious disease. For the first time we identify TMEM16A as a molecular target for these drugs and thus provide fresh insights into their mechanism for the treatment of these disorders in addition to respiratory disease.

Subtypes of Barrett's oesophagus and oesophageal adenocarcinoma based on genome-wide methylation analysis.

OBJECTIVE: To identify and characterise DNA methylation subtypes in oesophageal adenocarcinoma (EAC) and its precursor Barrett's oesophagus (BE). DESIGN: We performed genome-wide DNA methylation profiling on samples of non-dysplastic BE from cancer-free patients (n=59), EAC (n=23), normal squamous oesophagus (n=33) and normal fundus (n=9), and identified methylation subtypes using a recursively partitioned mixture model. We assessed genomic alterations for 9 BE and 22 EAC samples with massively parallel sequencing of 243 EAC-associated genes, and we conducted integrative analyses with transcriptome data to identify epigenetically repressed genes. We also carried out in vitro experiments treating EAC cell lines with 5-Aza-2'-Deoxycytidine (5-Aza-dC), short hairpin RNA knockdown and anticancer therapies. RESULTS: We identified and validated four methylation subtypes of EAC and BE. The high methylator subtype (HM) of EAC had the greatest number of activating events in ERBB2 (p<0.05, Student's t-test) and the highest global mutation load (p<0.05, Fisher's exact test). PTPN13 was silenced by aberrant methylation in the HM subtype preferentially and in 57% of EACs overall. In EAC cell lines, 5-Aza-dC treatment restored PTPN13 expression and significantly decreased its promoter methylation in HM cell lines (p<0.05, Welch's t-test). Inhibition of PTPN13 expression in the SK-GT-4 EAC cell line promoted proliferation, colony formation and migration, and increased phosphorylation in ERBB2/EGFR/Src kinase pathways. Finally, EAC cell lines showed subtype-specific responses to topotecan, SN-38 and palbociclib treatment. CONCLUSIONS: We identified and characterised methylator subtypes in BE and EAC. We further demonstrated the biological and clinical relevance of EAC methylator subtypes, which may ultimately help guide clinical management of patients with EAC.

Teaching Genomic Pathology: Translating Team-Based Learning to a Virtual Environment Using Computer-Based Simulation.

CONTEXT.­: Developing skills related to use of computer-based tools is critical for practicing genomic pathology. However, given the relative novelty of genomics education, residency programs may lack faculty members with adequate expertise and/or time to implement training. A virtual team-based learning (TBL) environment would make genomic pathology education available to more trainees. OBJECTIVE.­: To translate an extensively implemented in-person TBL genomic pathology workshop into a virtual environment and to evaluate both knowledge and skill acquisition. DESIGN.­: Using a novel interactive simulation approach, online modules were developed translating aspects of the TBL experience into the virtual environment with a goal of acquisition of necessary computer-related skills. The modules were evaluated at 10 postgraduate pathology training programs using a pre-post test design with participants deidentified. A postmodule anonymous survey obtained participant feedback on module quality and efficacy. RESULTS.­: There were 147 trainees who received an email request to voluntarily participate in the study. Of these, 43 trainees completed the pretest and 15 (35%) subsequently completed the posttest. Mean overall scores were 45% on the pretest compared with 70% on the posttest ( P < .001; effect size = 1.4). Posttest improvement of results was similar for questions testing acquisition of knowledge versus skills. Regarding the 19 participants who took the survey, 18 (95%) would recommend the modules to others and believed they met the stated objectives. CONCLUSIONS.­: A simulation-based approach allows motivated pathology trainees to acquire computer-related skills for practicing genomic pathology. Future work can explore efficacy in a nonvoluntary setting and adaptation to different specialties, learners, and computer tools.

Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study.

Site variation in fixation, staining, and scanning can confound automated tissue based image classifiers for disease characterization. In this study we incorporated stability into four feature selection methods for identifying the most robust and discriminating features for two prostate histopathology classification tasks. We evaluated 242 morphology features from N = 212 prostatectomy specimens from four sites for automated cancer detection and grading. We quantified instability as the rate of significant cross-site feature differences. We mapped feature stability and discriminability using 188 non-cancerous and 210 cancerous regions via 3-fold cross validation, then held one site out, creating independent training and testing sets. In training, one feature set was selected only for discriminability, another for discriminability and stability. We trained a classifier with each feature set, testing on the hold out site. Experiments were repeated with 117 Gleason grade 3 and 112 grade 4 regions. Stability was calculated across non-cancerous regions. Gland shape features yielded the best stability and area under the receiver operating curve (AUC) trade-off while co-occurrence texture features were generally unstable. Our stability-informed method produced a cancer detection AUC of 0.98 ± 0.05 and increased average Gleason grading AUC by 4.38%. Color normalization of the images tended to exacerbate feature instability.