MTMichael C. Tjong

Michael C. Tjong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Michael C. Tjong has a total of 57 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Stepwise Transfer Learning for Expert-level Pediatric Brain Tumor MRI Segmentation in a Limited Data Scenario

    by Aidan Boyd, Zezhong Ye, Sanjay P. Prabhu, Michael C. Tjong, Yining Zha, Anna Zapaishchykova, Sridhar Vajapeyam, Paul J. Catalano, Hasaan Hayat, Rishi Chopra, et al.

    "Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning (DL) pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001-December 2015) from a national brain tumor consortium (n = 184; median age, 7 years (range: 1-23 years); 94 male) and a pediatric cancer center (n = 100; median age, 8 years (range: 1-19 years); 47 male) to develop and evaluate DL neural networks for pediatric low-grade glioma segmentation using a novel stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally-tested on an independent test set and subjected to randomized, blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain, stepwise transfer learning (median DSC: 0.88 [IQR 0.72-0.91] versus 0.812 [0.56-0.89] for baseline model; P = .049). On external testing, AI model yielded excellent accuracy using reference standards from three clinical experts (Expert-1: 0.83 [0.75-0.90]; Expert-2: 0.81 [0.70-0.89]; Expert-3: 0.81 [0.68-0.88]; mean accuracy: 0.82)). On clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score: median 9 [IQR 7-9]) versus 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% versus 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. ©RSNA, 2024.


  • Open Access

    Province-Wide Analysis of Patient-Reported Outcomes for Stage IV Non-Small Cell Lung Cancer

    by Michael C. Tjong, Mark Doherty, Hendrick Tan, Wing C. Chan, Haoyu Zhao, Julie Hallet, Gail Darling, Biniam Kidane, Frances C. Wright, Alyson Mahar, et al.

    Background: In Ontario, Canada, patient-reported outcome (PRO) evaluation through the Edmonton Symptom Assessment System (ESAS) has been integrated into clinical workflow since 2007. As stage IV non-small cell lung cancer (NSCLC) is associated with substantial disease and treatment-related morbidity, this province-wide study investigated moderate to severe symptom burden in this population. Materials and Methods: ESAS collected from patients with stage IV NSCLC diagnosed between 2007 and 2018 linked to the Ontario provincial health care system database were studied. ESAS acquired within 12 months following diagnosis were analyzed and the proportion reporting moderate to severe scores (ESAS ≥4) in each domain was calculated. Predictors of moderate to severe scores were identified using multivariable Poisson regression models with robust error variance. Results: Of 22,799 patients, 13,289 (58.3%) completed ESAS (84,373 assessments) in the year following diagnosis. Patients with older age, with high comorbidity, and not receiving active cancer therapy had lower ESAS completion. The majority (94.4%) reported at least one moderate to severe symptom. The most prevalent were tiredness (84.1%), low well-being (80.7%), low appetite (71.7%), and shortness of breath (67.8%). Most symptoms peaked at diagnosis and, while declining, remained high in the following year. On multivariable analyses, comorbidity, low income, nonimmigrants, and urban residency were associated with moderate to severe symptoms. Moderate to severe scores in all ESAS domains aside from anxiety were associated with radiotherapy within 2 weeks prior, whereas drowsiness, low appetite and well-being, nausea, and tiredness were associated with systemic therapy within 2 weeks prior. Conclusion: This province-wide PRO analysis showed moderate to severe symptoms were prevalent and persistent among patients with metastatic NSCLC, underscoring the need to address supportive measures in this population especially around treatments. Implications for Practice: In this largest study of lung cancer patient-reported outcomes (PROs), stage IV non-small cell lung cancer patients had worse moderate-to-severe symptoms than other metastatic malignancies such as breast or gastrointestinal cancers when assessed with similar methodology. Prevalence of moderate-to-severe symptoms peaked early and remained high during the first year of follow-up. Symptom burden was associated with recent radiation and systemic treatments. Early and sustained PRO collection is important to detect actionable symptom progression, especially around treatments. Vulnerable patients (e.g., older, high comorbidity) who face barriers in attending in-person clinic visits had lower PRO completion. Virtual PRO collection may improve completion.


  • Impact of neoadjuvant chemotherapy on bladder recurrences in patients managed with trimodal therapy (TMT) for muscle-invasive bladder cancer

    by K. Ajib, M. Tjong, I. Lunsky, G.H. Tan, G. Nason, A. Erlich, M. Manjula, S. Sridhar, N. Fleshner, A. Zlotta, et al.