Browsing by Author "Pugh, Stephanie L."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Molecular classification to refine surgical and radiotherapeutic decision-making in meningioma
    (Springer Nature, 2024) Wang, Justin Z.; Patil, Vikas; Landry, Alexander P.; Gui, Chloe; Ajisebutu, Andrew; Liu, Jeff; Saarela, Olli; Pugh, Stephanie L.; Won, Minhee; Patel, Zeel; Yakubov, Rebeca; Kaloti, Ramneet; Wilson, Christopher; Cohen-Gadol, Aaron; Zaazoue, Mohamed A.; Tabatabai, Ghazaleh; Tatagiba, Marcos; Behling, Felix; Almiron Bonnin, Damian A.; Holland, Eric C.; Kruser, Tim J.; Barnholtz-Sloan, Jill S.; Sloan, Andrew E.; Horbinski, Craig; Chotai, Silky; Chambless, Lola B.; Gao, Andrew; Rebchuk, Alexander D.; Makarenko, Serge; Yip, Stephen; Sahm, Felix; Maas, Sybren L. N.; Tsang, Derek S.; International Consortium on Meningiomas (ICOM); Rogers, C. Leland; Aldape, Kenneth; Nassiri, Farshad; Zadeh, Gelareh; Neurological Surgery, School of Medicine
    Treatment of the tumor and dural margin with surgery and sometimes radiation are cornerstones of therapy for meningioma. Molecular classifications have provided insights into the biology of disease; however, response to treatment remains heterogeneous. In this study, we used retrospective data on 2,824 meningiomas, including molecular data on 1,686 tumors and 100 prospective meningiomas, from the RTOG-0539 phase 2 trial to define molecular biomarkers of treatment response. Using propensity score matching, we found that gross tumor resection was associated with longer progression-free survival (PFS) across all molecular groups and longer overall survival in proliferative meningiomas. Dural margin treatment (Simpson grade 1/2) prolonged PFS compared to no treatment (Simpson grade 3). Molecular group classification predicted response to radiotherapy, including in the RTOG-0539 cohort. We subsequently developed a molecular model to predict response to radiotherapy that discriminates outcome better than standard-of-care classification. This study highlights the potential for molecular profiling to refine surgical and radiotherapy decision-making.
  • Thumbnail Image
    Item
    Stress testing deep learning models for prostate cancer detection on biopsies and surgical specimens
    (Wiley, 2025) Flannery, Brennan T.; Sandler, Howard M.; Lal, Priti; Feldman, Michael D.; Santa-Rosario, Juan C.; Pathak, Tilak; Mirtti, Tuomas; Farre, Xavier; Correa, Rohann; Chafe, Susan; Shah, Amit; Efstathiou, Jason A.; Hoffman, Karen; Hallman, Mark A.; Straza, Michael; Jordan, Richard; Pugh, Stephanie L.; Feng, Felix; Madabhushi, Anant; Pathology and Laboratory Medicine, School of Medicine
    The presence, location, and extent of prostate cancer is assessed by pathologists using H&E-stained tissue slides. Machine learning approaches can accomplish these tasks for both biopsies and radical prostatectomies. Deep learning approaches using convolutional neural networks (CNNs) have been shown to identify cancer in pathologic slides, some securing regulatory approval for clinical use. However, differences in sample processing can subtly alter the morphology between sample types, making it unclear whether deep learning algorithms will consistently work on both types of slide images. Our goal was to investigate whether morphological differences between sample types affected the performance of biopsy-trained cancer detection CNN models when applied to radical prostatectomies and vice versa using multiple cohorts (N = 1,000). Radical prostatectomies (N = 100) and biopsies (N = 50) were acquired from The University of Pennsylvania to train (80%) and validate (20%) a DenseNet CNN for biopsies (MB), radical prostatectomies (MR), and a combined dataset (MB+R). On a tile level, MB and MR achieved F1 scores greater than 0.88 when applied to their own sample type but less than 0.65 when applied across sample types. On a whole-slide level, models achieved significantly better performance on their own sample type compared to the alternative model (p < 0.05) for all metrics. This was confirmed by external validation using digitized biopsy slide images from a clinical trial [NRG Radiation Therapy Oncology Group (RTOG)] (NRG/RTOG 0521, N = 750) via both qualitative and quantitative analyses (p < 0.05). A comprehensive review of model outputs revealed morphologically driven decision making that adversely affected model performance. MB appeared to be challenged with the analysis of open gland structures, whereas MR appeared to be challenged with closed gland structures, indicating potential morphological variation between the training sets. These findings suggest that differences in morphology and heterogeneity necessitate the need for more tailored, sample-specific (i.e. biopsy and surgical) machine learning models.