Abstract 3256
Background
Melanoma patients have shown sarcoid-like lesions as an immune-related adverse event to anti-PD-1 immunotherapy. Proper discrimination is essential for accurate treatment decision. Aim of the study is to distinguish granulomatous disease (GD) from pulmonary metastases (MET) and enlarged intrapulmonary lymph nodes (LN) in melanoma patients treated with immune checkpoint blockade by using deep learning.
Methods
Retrospective (2012-2018) analysis of 165 melanoma patients treated with anti-PD-1 immunotherapy. All patients underwent standardized imaging-based tumor response assessment with contrast enhanced computed tomography (CT) (follow up interval 8-10 weeks) during treatment. Only patients with intrapulmonary lesions were included (n = 132, f = 72, median age 63 (IQR 55-74ys). All lesions were clustered in 4 different classes: (1) MET, (2) LN, (3) GD, and (4) small (2-5 mm) indeterminate calcified granulomas (GC). GD was histologically proven (guided biopsy or operative excision). All LNs and GCs were identified in CT examinations (1-6 years) prior to diagnosis. For all lesions, a labeled region of interest was extracted by an experienced radiologist (11 years). Automatic classification of intrapulmonary lesions was performed by deep learning (VGG-like model).
Results
In total, 4409 lesions were labeled (2746 METs (62.3 %), 1143 LNs (25.9%), 328 GC (7.4%), 192 GD (4.4%)). The model predicted instances of these classes for GD, GC or LN with a significant area under the receiver operating curve (ROC) of 0.66, 0.70 and 0.68, respectively (p-value <0.001). The performance of the algorithm was independent of imaging protocol (e.g. contrast enhancement, slice thickness, and reconstructed imaging kernel (soft versus sharp)) with AUC 0.65 for all.
Conclusions
Deep learning can help to discriminate between intrapulmonary granulomatous disease, indeterminate calcified granulomas and intrapulmonary lymph nodes in anti-PD-1 treated melanoma patients. Further model development is needed to overcome the imbalanced “real clinical scenario” data to classify granulomatous disease in melanoma patients treated with anti-PD-1 immune checkpoint inhibitor blockade for implementation in the clinical workflow.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
5520 - Patient’s Usability Test results of a CINV Diary Application For Smartphones
Presenter: Paz Fernandez
Session: Poster Display session 3
Resources:
Abstract
2323 - Colorectal Telephone Assessment Pathway (CTAP) - A viable means of shortening time to a definitive diagnosis of Colorectal Cancer (CRC)
Presenter: Harriet Watson
Session: Poster Display session 3
Resources:
Abstract
6119 - Cancer Nursing and Social Media: Capturing the Zeitgeist
Presenter: Mark Foulkes
Session: Poster Display session 3
Resources:
Abstract
1776 - Examination of mobile applications on breast cancer
Presenter: AYDANUR AYDIN
Session: Poster Display session 3
Resources:
Abstract
4128 - E-health effectiveness to increase patient adherence for immunotherapy; a cost-benefit study.
Presenter: Maria José Dias
Session: Poster Display session 3
Resources:
Abstract
3219 - Experiences of internet-based stepped care among individuals with recently diagnosed cancer and symptoms of anxiety and/or depression
Presenter: Anna Hauffman
Session: Poster Display session 3
Resources:
Abstract
5010 - What do cancer patients know about their immunotherapy treatment?
Presenter: Mónica Arellano
Session: Poster Display session 3
Resources:
Abstract
4503 - Prospective Comparison of Travel Burden, Cost and Time to Obtain Tumor Board Treatment Plan Through In-Person Visits vs. an AI Enabled Health Technology (N=1803)
Presenter: Rajendra Badwe
Session: Poster Display session 3
Resources:
Abstract
4123 - Cancer care through the fire and flames: 3-year experience in the utilisation of electronic consultation and referral system at the Red Zone in Southern Thailand
Presenter: Nanthiya Rattanakhot
Session: Poster Display session 3
Resources:
Abstract
2087 - The effect of e-mobile education on the quality of life in women with breast cancer
Presenter: Derya ÇInar
Session: Poster Display session 3
Resources:
Abstract