Browsing by Author "Ho, Chang"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy
    (Springer, 2023) Kelly, Brendan; Martinez, Mesha; Do, Huy; Hayden, Joel; Huang, Yuhao; Yedavalli, Vivek; Ho, Chang; Keane, Pearse A.; Killeen, Ronan; Lawlor, Aonghus; Moseley, Michael E.; Yeom, Kristen W.; Lee, Edward H.; Radiology and Imaging Sciences, School of Medicine
    Objectives: Treatment and outcomes of acute stroke have been revolutionised by mechanical thrombectomy. Deep learning has shown great promise in diagnostics but applications in video and interventional radiology lag behind. We aimed to develop a model that takes as input digital subtraction angiography (DSA) videos and classifies the video according to (1) the presence of large vessel occlusion (LVO), (2) the location of the occlusion, and (3) the efficacy of reperfusion. Methods: All patients who underwent DSA for anterior circulation acute ischaemic stroke between 2012 and 2019 were included. Consecutive normal studies were included to balance classes. An external validation (EV) dataset was collected from another institution. The trained model was also used on DSA videos post mechanical thrombectomy to assess thrombectomy efficacy. Results: In total, 1024 videos comprising 287 patients were included (44 for EV). Occlusion identification was achieved with 100% sensitivity and 91.67% specificity (EV 91.30% and 81.82%). Accuracy of location classification was 71% for ICA, 84% for M1, and 78% for M2 occlusions (EV 73, 25, and 50%). For post-thrombectomy DSA (n = 194), the model identified successful reperfusion with 100%, 88%, and 35% for ICA, M1, and M2 occlusion (EV 89, 88, and 60%). The model could also perform classification of post-intervention videos as mTICI < 3 with an AUC of 0.71. Conclusions: Our model can successfully identify normal DSA studies from those with LVO and classify thrombectomy outcome and solve a clinical radiology problem with two temporal elements (dynamic video and pre and post intervention).
  • Thumbnail Image
    Item
    Diagnostic Performance of Ultrafast Brain MRI for Evaluation of Abusive Head Trauma
    (2017-04) Kralik, Stephen; Yasrebi, Mona; Supakul, Nucharin; Lin, Chen; Netter, Lynn; Hicks, Ralph; Hibbard, Roberta; Ackerman, Laurie; Harris, Mandy; Ho, Chang; Radiology and Imaging Sciences, School of Medicine
    BACKGROUND AND PURPOSE: MR imaging with sedation is commonly used to detect intracranial traumatic pathology in the pediatric population. Our purpose was to compare nonsedated ultrafast MR imaging, noncontrast head CT, and standard MR imaging for the detection of intracranial trauma in patients with potential abusive head trauma. MATERIALS AND METHODS: A prospective study was performed in 24 pediatric patients who were evaluated for potential abusive head trauma. All patients received noncontrast head CT, ultrafast brain MR imaging without sedation, and standard MR imaging with general anesthesia or an immobilizer, sequentially. Two pediatric neuroradiologists independently reviewed each technique blinded to other modalities for intracranial trauma. We performed interreader agreement and consensus interpretation for standard MR imaging as the criterion standard. Diagnostic accuracy was calculated for ultrafast MR imaging, noncontrast head CT, and combined ultrafast MR imaging and noncontrast head CT. RESULTS: Interreader agreement was moderate for ultrafast MR imaging (κ = 0.42), substantial for noncontrast head CT (κ = 0.63), and nearly perfect for standard MR imaging (κ = 0.86). Forty-two percent of patients had discrepancies between ultrafast MR imaging and standard MR imaging, which included detection of subarachnoid hemorrhage and subdural hemorrhage. Sensitivity, specificity, and positive and negative predictive values were obtained for any traumatic pathology for each examination: ultrafast MR imaging (50%, 100%, 100%, 31%), noncontrast head CT (25%, 100%, 100%, 21%), and a combination of ultrafast MR imaging and noncontrast head CT (60%, 100%, 100%, 33%). Ultrafast MR imaging was more sensitive than noncontrast head CT for the detection of intraparenchymal hemorrhage (P = .03), and the combination of ultrafast MR imaging and noncontrast head CT was more sensitive than noncontrast head CT alone for intracranial trauma (P = .02). CONCLUSIONS: In abusive head trauma, ultrafast MR imaging, even combined with noncontrast head CT, demonstrated low sensitivity compared with standard MR imaging for intracranial traumatic pathology, which may limit its utility in this patient population.
  • Thumbnail Image
    Item
    Magnetic resonance imaging enhancement of spinal nerve roots in a boy with X-linked adrenoleukodystrophy before diagnosis of chronic inflammatory demyelinating polyneuropathy
    (Elsevier, 2023-11-18) Miller, Derryl; Walsh, Laurence; Smith, Lisa; Supakul, Nucharin; Ho, Chang; Onishi, Toshihiro; Neurology, School of Medicine
    We present a boy with X-linked adrenoleukodystrophy (X-ALD) who was found to have lumbar nerve root enhancement on a screening MRI of the spine. The MRI was performed for lower extremity predominant symptoms. Several weeks after this MRI, he developed leg pain and was averse to walking long distances. He was diagnosed with Chronic Inflammatory Demyelinating Polyneuropathy (CIDP) with electromyography, nerve conduction studies, and serial imaging. His case is consistent with CIDP in association with X-ALD based on improvement with intravenous immunoglobulin (IVIG) with continued contrast enhancement and lower extremity symptoms 8 weeks after his initial scans. Contrast enhancement of nerve roots has not been previously described in X-ALD. Nerve root enhancement has been seen in other leukodystrophies such as globoid cell leukodystrophy and metachromatic leukodystrophy. This case also demonstrates comorbid X-ALD with CIDP and highlights possible mechanisms from the literature for this association. We also review the broad differential of cauda equina nerve root enhancement.
  • Thumbnail Image
    Item
    Magnetic resonance imaging enhancement of spinal nerve roots in a boy with X-linked adrenoleukodystrophy before diagnosis of chronic inflammatory demyelinating polyneuropathy
    (Elsevier, 2024-01) Miller, Derryl; Walsh, Laurence; Smith, Lisa; Supakul , Nucharin; Ho, Chang; Onishi , Toshihiro; Neurology, School of Medicine
    We present a boy with X-linked adrenoleukodystrophy (X-ALD) who was found to have lumbar nerve root enhancement on a screening MRI of the spine. The MRI was performed for lower extremity predominant symptoms. Several weeks after this MRI, he developed leg pain and was averse to walking long distances. He was diagnosed with Chronic Inflammatory Demyelinating Polyneuropathy (CIDP) with electromyography, nerve conduction studies, and serial imaging. His case is consistent with CIDP in association with X-ALD based on improvement with intravenous immunoglobulin (IVIG) with continued contrast enhancement and lower extremity symptoms 8 weeks after his initial scans. Contrast enhancement of nerve roots has not been previously described in X-ALD. Nerve root enhancement has been seen in other leukodystrophies such as globoid cell leukodystrophy and metachromatic leukodystrophy. This case also demonstrates comorbid X-ALD with CIDP and highlights possible mechanisms from the literature for this association. We also review the broad differential of cauda equina nerve root enhancement.
  • Thumbnail Image
    Item
    Statistical multiscale mapping of IDH1, MGMT, and microvascular proliferation in human brain tumors from multiparametric MR and spatially-registered core biopsy
    (Nature Research, 2019-11-19) Parker, Jason G.; Diller, Emily E.; Cao, Sha; Nelson, Jeremy T.; Yeom, Kristen; Ho, Chang; Lober, Robert; Radiology and Imaging Sciences, School of Medicine
    We propose a statistical multiscale mapping approach to identify microscopic and molecular heterogeneity across a tumor microenvironment using multiparametric MR (mp-MR). Twenty-nine patients underwent pre-surgical mp-MR followed by MR-guided stereotactic core biopsy. The locations of the biopsy cores were identified in the pre-surgical images using stereotactic bitmaps acquired during surgery. Feature matrices mapped the multiparametric voxel values in the vicinity of the biopsy cores to the pathologic outcome variables for each patient and logistic regression tested the individual and collective predictive power of the MR contrasts. A non-parametric weighted k-nearest neighbor classifier evaluated the feature matrices in a leave-one-out cross validation design across patients. Resulting class membership probabilities were converted to chi-square statistics to develop full-brain parametric maps, implementing Gaussian random field theory to estimate inter-voxel dependencies. Corrections for family-wise error rates were performed using Benjamini-Hochberg and random field theory, and the resulting accuracies were compared. The combination of all five image contrasts correlated with outcome (P < 10−4) for all four microscopic variables. The probabilistic mapping method using Benjamini-Hochberg generated statistically significant results (α ≤ 0.05) for three of the four dependent variables: (1) IDH1, (2) MGMT, and (3) microvascular proliferation, with an average classification accuracy of 0.984 ± 0.02 and an average classification sensitivity of 1.567% ± 0.967. The images corrected by random field theory demonstrated improved classification accuracy (0.989 ± 0.008) and classification sensitivity (5.967% ± 2.857) compared with Benjamini-Hochberg. Microscopic and molecular tumor properties can be assessed with statistical confidence across the brain from minimally-invasive, mp-MR.
  • Thumbnail Image
    Item
    Targeting intra-tumoral heterogeneity of human brain tumors with in vivo imaging: A roadmap for imaging genomics from multiparametric MR signals
    (AAPM, 2023-04) Parker, Jason G.; Servati, Mahsa; Diller, Emily E.; Cao, Sha; Ho, Chang; Lober, Robert; Cohen-Gadol, Aaron; Biostatistics and Health Data Science, School of Medicine
    Resistance of high grade tumors to treatment involves cancer stem cell features, deregulated cell division, acceleration of genomic errors, and emergence of cellular variants that rely upon diverse signaling pathways. This heterogeneous tumor landscape limits the utility of the focal sampling provided by invasive biopsy when designing strategies for targeted therapies. In this roadmap review paper, we propose and develop methods for enabling mapping of cellular and molecular features in vivo to inform and optimize cancer treatment strategies in the brain. This approach leverages (1) the spatial and temporal advantages of in vivo imaging compared with surgical biopsy, (2) the rapid expansion of meaningful anatomical and functional magnetic resonance signals, (3) widespread access to cellular and molecular information enabled by next-generation sequencing, and (4) the enhanced accuracy and computational efficiency of deep learning techniques. As multiple cellular variants may be present within volumes below the resolution of imaging, we describe a mapping process to decode micro- and even nano-scale properties from the macro-scale data by simultaneously utilizing complimentary multiparametric image signals acquired in routine clinical practice. We outline design protocols for future research efforts that marry revolutionary bioinformation technologies, growing access to increased computational capability, and powerful statistical classification techniques to guide rational treatment selection.