Pump, Heather K.

Introduction: Glutamic acid decarboxylase 65 (GAD65) antibody-associated temporal lobe epilepsy (GAD65-TLE) is a rare form of autoimmune-associated epilepsy characterized by medically refractory seizures and cognitive decline. Diagnosis typically requires antibody testing and clinical correlation, and treatment options include immunotherapy and antiseizure medications (ASMs). However, many patients experience persistent or worsening symptoms despite ongoing treatment. Case Report: A 20-year-old woman presented with mild cognitive impairment and focal aware seizures that gradually progressed in frequency and severity. A diagnostic workup revealed GAD65-TLE, and the patient began treatment with intravenous methylprednisolone infusions and antiseizure medications within 6 months of her presentation. After 20 months of treatment, the patient was on stable doses of levetiracetam and lamotrigine and finished tapering immunosuppressive therapy with methylprednisolone. The frequency of her focal aware seizures significantly decreased, whereas the focal impaired aware and focal bilateral tonic-clonic seizures resolved. The patient was able to return to all of her previous daily activities. Conclusions: In patients presenting with new-onset seizures characterized by unusual semiology and frequent focal aware seizures, it is crucial to consider GAD65-TLE in the list of potential diagnoses. Delayed diagnosis may lead to resistance to both ASMs and immunotherapy. This case report emphasizes how prompt identification and early initiation of immunotherapy can significantly impact the course of the disease.

Abstract Clinical management of IDH wildtype glioblastoma (GBM) and tumefactive multiple sclerosis (tMS) is drastically different. GBM requires maximal safe resection followed by chemoradiation, while tMS outcome is worsened by surgery and radiotherapy. Noninvasive methods are needed to help with accurate diagnosis of tumor and non-tumor etiologies. To develop an MRI-based classification model, tMS subjects diagnosed prior to January 1, 2020, were matched to tMS by age at diagnosis, sex, index MRI date, and 2D/3D acquisition. Inclusion criteria included one cm minimal lesion size and pre-operative post-contrast T1 and T2 images available for analysis. A 3D-DenseNet121 was used to develop a classification model using prespecified parameters: 650 epochs, batch size 16, learning rate 10-3, cross-entropy loss, and AdamW optimizer. The stopping rule was defined as three sequential differences in epoch cross-entropy loss <0.02. Models were developed using both T1gd and T2, as well as from only T1gd and only T2. Training included 220 subjects (110 GBM, 110 tMS). A 2-stage validation design was used, which included both retrospective and prospective cohorts. Stage 1 consisted of 272 retrospective GBM (diagnosed prior to January 1, 2020). Stage 2 consisted of 69 and 34 prospective (diagnosed after January 1, 2020) GBM and tMS, respectively. External validation on the 272 retrospective GBM demonstrated accuracy of 91%, 84%, and 78% for T1gd+T2, T1gd only, and T2 only, respectively. External validation on the 69 prospective GBM demonstrated an accuracy of 87%, 64%, and 67% for T1gd+T2, T1gd only, and T2 only, respectively. The 34 prospective tMS demonstrated accuracy of 76%, 76%, and 82% for T1gd+T2, T1gd only, and T2 only, respectively. This shows the feasibility of deep learning to aid in differential diagnosis of brain lesions. Future work entails the integration of germline variants into the classification model, including variants associated with the risk of glioma or MS.