Virtual Library

Start Your Search

Hedy Lee Kindler



Author of

  • +

    MS13 - Immunotherapy for Mesothelioma (ID 76)

    • Event: WCLC 2019
    • Type: Mini Symposium
    • Track: Mesothelioma
    • Presentations: 1
    • Now Available
    • +

      MS13.02 - Pro - Hedy Kindler Is Right (Immuno Works for Mesothelioma) (Now Available) (ID 3512)

      11:30 - 13:00  |  Presenting Author(s): Hedy Lee Kindler

      • Abstract
      • Presentation
      • Slides

      Abstract not provided

      Only Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login, select "Add to Cart" and proceed to checkout. If you would like to become a member of IASLC, please click here.

      Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.

  • +

    P1.06 - Mesothelioma (ID 169)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Mesothelioma
    • Presentations: 1
    • Now Available
    • Moderators:
    • Coordinates: 9/08/2019, 09:45 - 18:00, Exhibit Hall
    • +

      P1.06-04 - Deep Learning-Based Segmentation of Mesothelioma on CT Scans: Application to Patient Scans Exhibiting Pleural Effusion (Now Available) (ID 1830)

      09:45 - 18:00  |  Author(s): Hedy Lee Kindler

      • Abstract
      • Slides

      Background

      Tumor volume has been a topic of interest in the evaluation of treatment response, staging and prognosis of malignant pleural mesothelioma patients. Many mesothelioma patients present with or develop pleural fluid, the presence of which may complicate tumor segmentation on CT scans. We implemented a method for the automated segmentation of mesothelioma tumor on CT that explicitly excludes pleural effusion, which, if included in the segmentation of tumor, could confound the assessment of tumor volume.

      Method

      Deep convolutional neural networks (CNNs) were trained for the segmentation of mesothelioma tumor in each hemithorax. A database was collected of 180 CT scans of 160 mesothelioma patients who exhibited tumor and pleural effusion. 6026 axial sections containing segmented tumor (1243 sections exhibiting pleural effusion) from 134 chest CT scans were used to train deep CNNs for segmentation of mesothelioma tumor. A radiologist contoured tumor on a test set of 94 axial sections that exhibited both tumor and pleural effusion; these sections were randomly selected from 46 CT scans of 34 patients not included in the training set. Performance was evaluated on the test set by calculating the Dice Similarity Coefficient (DSC) between computer-generated and reference segmentations; DSC is a measure of overlap between a pair of segmentations (a value of 0 indicating no overlap, 1 indicating complete overlap). We compared the performance of the present method to a previously published deep learning-based method for the automated segmentation of mesothelioma tumor on CT scans; differences in DSC values achieved on the test set by the two methods were assessed through a two-tailed paired Wilcoxon signed-rank test.

      Result

      A boxplot of DSC values achieved on the test set by the current method and the previously published method is shown in Fig. 1. The median DSC on the test set achieved by the current method was 0.66 (inter-quartile range 0.20); the median DSC on the test set achieved by the previously published method was 0.51 (inter-quartile range 0.34). The difference in DSC between the two methods was statistically significant (p < 0.0001).

      worldlung2019abstract-dicecomparison_spie2019vsmarch2019.png

      Conclusion

      A deep CNN was implemented for the task of automated segmentation of mesothelioma tumor on CT scans of patients who also exhibit pleural effusion. The present method achieved a statistically higher overlap (p < 0.0001) with radiologist-provided reference contours than a previously published method on a test set of 94 axial CT sections of mesothelioma patients exhibiting both tumor and pleural effusion.

      Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.

  • +

    P2.06 - Mesothelioma (ID 170)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Mesothelioma
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/09/2019, 10:15 - 18:15, Exhibit Hall
    • +

      P2.06-12 - Dysphagia in Patients with Malignant Pleural Mesothelioma (MPM) (ID 2896)

      10:15 - 18:15  |  Author(s): Hedy Lee Kindler

      • Abstract

      Background

      Dysphagia is common with advanced malignancies but is not well characterized in MPM and is under-recognized as a symptom attributable to this disease. The prevalence of dysphagia in MPM is unknown. Available literature is limited to a few case reports. Dysphagia can lead to nutritional compromise, pain and deterioration of quality of life. It can occur as a result of extrinsic compression of the esophagus by mediastinal lymphadenopathy, intrinsic mechanical obstruction or pseudo-achalasia secondary to infiltration of the esophagus. Palliation is an important goal of therapy and recognizing the underlying etiology will guide selection of interventions.

      Method

      We performed a single center, retrospective cohort study of MPM patients who reported dysphagia treated at the University of Chicago between 6/1/2016 and 4/1/2018. 250 consecutive patient records were reviewed for the report of dysphagia and chart extraction was performed. Patient factors collected included patient age at diagnosis, gender and comorbid medical illness. Mesothelioma specific factors included tumor histology, treatment history and overall survival. Dysphagia specific factors including onset of dysphagia relative to diagnosis and patient death, characteristics of dysphagia, findings on imaging and evaluation and interventions performed.

      Result

      Eleven patients (4.4%) reported dysphagia. Median age was 72 (range 55-88). 100% male. 8 had right sided, 3 had left sided disease. Tumor histology: 6 epithelioid, 1 sarcomatoid and 4 biphasic. Of these, one patient had dysphagia unrelated to mesothelioma that resolved with surgical intervention. Of the remaining 10 patients, 9 had mediastinal adenopathy and/or esophageal involvement on CT scans. 1 patient had no CT findings to explain dysphagia and EGD revealed extrinsic compression. 3 patients were stented. 2 of 3 required repeat procedures. 1 required a feeding tube. Median time from diagnosis to onset of dysphagia was 18 months (range 0.7-31.7) One patient developed dysphagia 2 months prior to diagnosis. Median time from development of dysphagia to death was 5.7 months ( range 2-7.7) One patient remains alive. Median overall survival was 19.8 months (range 4.4-159.7).

      Conclusion

      Dysphagia in patients with malignant pleural mesothelioma is most often attributable to the underlying malignancy due to extrinsic compression from mediastinal adenopathy or direct tumor extension. This development is a poor prognostic sign and, in this sample, signaled a median survival just under 6 months. Patients with the shortest interval from diagnosis to onset of dysphagia had the shortest overall survival. A prospective study to further characterize dysphagia in MPM and optimize interventions is ongoing.