ZSZaid Ali Siddiqui

Zaid Ali Siddiqui

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zaid Ali Siddiqui has a total of 105 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Blinded, bias‐controlled multi‐rater evaluation of human‐versus‐AI brain metastasis segmentation using a hybrid foundation‐model framework

    by Yiding Han, Enze Zhu, Mhd Hasan Ai Mekdash, Omar Awad, Piyush Pathak, Shixiao Liang, Daniel Allan Hamstra, Xizhe Zhang, Zaid Ali Siddiqui, Baozhou Sun

    Background: Accurate segmentation of brain metastases (BM) is essential for diagnosis, stereotactic radiosurgery planning, and longitudinal assessment. However, manual contouring is time‐intensive, limiting clinical scalability, and exhibits substantial inter‐observer variability. This variability complicates objective assessment of automated segmentation methods and challenges interpretation of model performance. Purpose: To address these limitations, we developed TUM‐SAM, a hybrid foundation‐model framework for fully automated BM segmentation, and introduced a bias‐controlled, blinded multi‐rater evaluation paradigm to determine whether AI‐based BM segmentation has reached expert‐level performance and whether AI‐generated contours are preferred by human experts under unbiased assessment. Methods: TUM‐SAM integrates nnU‐Net‐based lesion detection with a tumor‐adapted Med‐SAM segmentation model to enable prompt‐free, fully automated segmentation. Training used 301 patients (2548 lesions), and external evaluation used an independent cohort of 105 patients (397 lesions). Segmentation accuracy was benchmarked against DeepMedic and nnU‐Net using Dice similarity coefficient (DSC) and 95th‐percentile Hausdorff distance (HD95). Two physicians contoured all external cases, and a third physician contoured a 20‐patient subset for a blinded, tumor‐level, multi‐rater preference study. Pairwise contour preferences were analyzed using a Bradley–Terry probabilistic model to obtain bias‐adjusted estimates of relative contour quality while accounting for rater‐specific tendencies and case difficulty. Results: In the external cohort, TUM‐SAM achieved a lesion‐wise detection sensitivity of 0.94 and outperformed DeepMedic and nnU‐Net across all tumor sizes, with a mean DSC of 0.84 and HD95 of 1.9 mm (nnU‐Net/DeepMedic: DSC < 0.70, HD95 > 3.3 mm). Across voxel‐wise evaluation, TUM‐SAM's geometric performance fell within the range of inter‐observer variability among physicians and was sensitive to reference construction. In contrast, in the blinded rater study, experts preferred TUM‐SAM–generated contours over individual physician contours in 81–87% of raw comparisons; Bradley–Terry analysis yielded conservative, bias‐corrected win probabilities of 55–56%, indicating consistent preference after adjustment for rater and case difficulty. Conclusion: Using a bias‐controlled, blinded multi‐rater evaluation framework, TUM‐SAM demonstrates brain metastasis segmentation quality that is consistently preferred by expert physicians, highlighting the limitations of agreement‐based voxel‐wise metrics under inter‐observer variability. These findings underscore the dependence of conventional evaluation on reference definition and support preference‐based assessment as a complementary approach for evaluating AI segmentation quality in BM MRI.

  • Open Access

    Optimizing and evaluating robustness of AI for brain metastasis detection and segmentation via loss functions and multi-dataset training

    by Yiding Han, Piyush Pathak, Omar Awad, Abdallah S R Mohamed, Vincent Ugarte, Boran Zhou, Daniel Allen Hamstra, Alfredo Enrique Echeverria, Hasan Al Mekdash, Zaid Ali Siddiqui, et al.

    Purpose . Accurate detection and segmentation of brain metastases (BM) from MRI are critical for the appropriate management of cancer patients. This study investigates strategies to enhance the robustness of artificial intelligence (AI)-based BM detection and segmentation models. Method . A DeepMedic-based network with a loss function, tunable with a sensitivity/specificity tradeoff weighting factor α - was trained on T1 post-contrast MRI datasets from two institutions (514 patients, 4520 lesions). Robustness was evaluated on an external dataset from a third institution dataset (91 patients, 397 lesions), featuring ground truth annotations from two physicians. We investigated the impact of loss function weighting factor, α and training dataset combinations. Detection performance (sensitivity, precision, F1 score) and segmentation accuracy (Dice similarity, and 95% Hausdorff distance (HD95)) were evaluated using one physician’s contours as the reference standard. The optimal AI model was then directly compared to the performance of the second physician. Results . Varying α demonstrated a trade-off between sensitivity (higher α ) and precision (lower α ), with α = 0.5 yielding the best F1 score (0.80 versus 0.78 for α = 0.95 and 0.72 for α = 0.99) on the external dataset. The optimally trained model achieved detection performance comparable to the physician (F1: AI = 0.83, Physician = 0.83), but slightly underperformed in segmentation (Dice: 0.81 versus AI = 0.69; HD95: 3.0 mm versus AI = 4.94 mm, p < 0.05). Conclusion . The derived optimal model achieves detection and segmentation performance comparable to an expert physician in a parallel comparison.


  • Open Access

    Optimizing and Evaluating Robustness of AI for Brain Metastasis Detection and Segmentation via Loss Functions and Multi-dataset Training

    by Yiding Han, Piyush Pathak, Omar Award, Abdallah S. R Mohamed, Vincent Ugarte, Boran Zhou, Daniel Allen Hamstra, Alfredo Enrique Echeverria, Hasan Al Mekdash, Zaid Ali Siddiqui, et al.

    Purpose: Accurate detection and segmentation of brain metastases (BM) from MRI are critical for the appropriate management of cancer patients. This study investigates strategies to enhance the robustness of artificial intelligence (AI)-based BM detection and segmentation models. Method: A DeepMedic-based network with a loss function, tunable with a sensitivity/specificity tradeoff weighting factor α- was trained on T1 post-contrast MRI datasets from two institutions (514 patients, 4520 lesions). Robustness was evaluated on an external dataset from a third institution dataset (91 patients, 397 lesions), featuring ground truth annotations from two physicians. We investigated the impact of loss function weighting factor, α and training dataset combinations. Detection performance (sensitivity, precision, F1 score) and segmentation accuracy (Dice similarity, and 95% Hausdorff distance (HD95)) were evaluated using one physician’s contours as the reference standard. The optimal AI model was then directly compared to the performance of the second physician. Results: Varying α demonstrated a trade-off between sensitivity (higher α) and precision (lower α), with α=0.5 yielding the best F1 score (0.80 ± 0.04 vs. 0.78 ± 0.04 for α=0.95 and 0.72 ± 0.03 for α=0.99) on the external dataset. The optimally trained model achieved detection performance comparable to the physician (F1: AI=0.83 ± 0.04, Physician=0.83 ± 0.04), but slightly underperformed in segmentation (Dice: 0.79 ± 0.04 vs. AI=0.74 ± 0.03; HD95: 2.8 ± 0.14 mm vs. AI=3.18 ± 0.16 mm, p<0.05). Conclusion: The derived optimal model achieves detection and segmentation performance comparable to an expert physician in a parallel comparison.

  • Trigeminal Neuralgia

    by Zaid A. Siddiqui, Peter Y. Chen

  • Deep learning for contour quality assurance for RTOG 0933: In-silico evaluation

    by Evan M. Porter, Charles Vu, Ina M. Sala, Thomas Guerrero, Zaid A. Siddiqui


  • Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning

    by Evan Michael Porter, Nicholas K Myziuk, Thomas J Quinn, Daniela Lozano, Avery B Peterson, Duyen M Quach, Zaid A Siddiqui, Thomas M Guerrero

    Purpose: To develop and evaluate the performance of a deep learning model to generate synthetic pulmonary perfusion images from clinical 4DCT images for patients undergoing radiotherapy for lung cancer. Methods: A clinical data set of 58 pre- and post-radiotherapy 99mTc-labelled MAA-SPECT perfusion studies (32 patients) each with contemporaneous 4DCT studies was collected. Using the inhale and exhale phases of the 4DCT, a 3D-Residual Network was trained to create synthetic perfusion images utilizing the MAA-SPECT as ground truth. The training process was repeated for a 50-imaging study, five-fold validation with twenty model instances trained per fold. The highest performing model instance from each fold was selected for inference upon the eight-study test set. A manual lung segmentation was used to compute correlation metrics constrained to the voxels within the lungs. From the pre-treatment test cases (N=5), 50th-percentile contours of well-perfused lung were generated from both the clinical and synthetic perfusion images and the agreement was quantified. Results: Across the hold-out test set, our deep learning model predicted perfusion with a Spearman correlation coefficient of 0.70 (IQR: 0.61 – 0.76) and a Pearson correlation coefficient of 0.66 (IQR: 0.49 – 0.73). The agreement of the functional avoidance contour pairs was Dice of 0.803 (IQR: 0.750 – 0.810) and average surface distance of 5.92mm (IQR: 5.68 – 7.55). Conclusion: We demonstrate that from 4DCT alone, a deep learning model can generate synthetic perfusion images with potential application in functional avoidance treatment planning.


  • Higher biologically effective dose is associated with improved survival in patients with squamous cell carcinoma of the lung treated with stereotactic body radiation therapy

    by Jacob S. Parzen, Muayad F. Almahariq, Thomas J. Quinn, Zaid A. Siddiqui, Andrew B. Thompson, Thomas Guerrero, Kuei Lee, Craig Stevens, Inga S. Grills


  • The Role of Postoperative Radiation Therapy for pN2 Non–small-cell Lung Cancer

    by Nikhil P. Mankuzhy, Muayad F. Almahariq, Zaid A. Siddiqui, Andrew B. Thompson, Inga S. Grills, Thomas M. Guerrero, Kuei C. Lee, Craig W. Stevens, Thomas J. Quinn


  • Predictors of radiation necrosis in long-term survivors after Gamma Knife stereotactic radiosurgery for brain metastases

    by Zaid A Siddiqui, Bryan S Squires, Matt D Johnson, Andrew M Baschnagel, Peter Y Chen, Daniel J Krauss, Ricky E Olson, Kurt D Meyer, Inga S Grills

    Background: The long-term risk of necrosis after radiosurgery for brain metastases is uncertain. We aimed to investigate incidence and predictors of radiation necrosis for individuals with more than 1 year of survival after radiosurgery for brain metastases. Methods: Patients who had a diagnosis of brain metastases treated between December 2006 and December 2014, who had at least 1 year of survival after first radiosurgery were retrospectively reviewed. Survival was analyzed using the Kaplan-Meier estimator, and the incidence of radiation necrosis was estimated with death or surgical resection as competing risks. Patient and treatment factors associated with radiation necrosis were also analyzed. Results: A total of 198 patients with 732 lesions were analyzed. Thirty-four lesions required salvage radiosurgery and 10 required salvage surgical resection. Median follow-up was 24 months. The estimated median survival for this population was 25.4 months. The estimated per-lesion incidence of radiation necrosis at 4 years was 6.8%. Medical or surgical therapy was required for 60% of necrosis events. Tumor volume and male sex were significant factors associated with radiation necrosis. The per-lesions incidence of necrosis for patients undergoing repeat radiosurgery was 33.3% at 4 years. Conclusions: In this large series of patients undergoing radiosurgery for brain metastases, patients continued to be at risk for radiation necrosis throughout their first 4 years of survival. Repeat radiosurgery of recurrent lesions greatly exacerbates the risk of radiation necrosis, whereas treatment of larger target volumes increases the risk modestly.