Automated Segmentation of Ablated Lesions Using Deep Convolutional Neural Networks: A Basis for Response Assessment Following Laser Interstitial Thermal Therapy

Aden P Haskell-Mendoza; Ellery Hepburn Reason; Ariel T Gonzalez; Joshua D Jackson; Eric W Sankey; Ethan S Srinivasan; James E Herndon 2nd; Peter E Fecci; Evan Calabrese

doi:10.1093/neuonc/noad261

Automated Segmentation of Ablated Lesions Using Deep Convolutional Neural Networks: A Basis for Response Assessment Following Laser Interstitial Thermal Therapy

Neuro Oncol. 2024 Jan 3:noad261. doi: 10.1093/neuonc/noad261. Online ahead of print.

Authors

Aden P Haskell-Mendoza¹, Ellery Hepburn Reason¹, Ariel T Gonzalez¹, Joshua D Jackson², Eric W Sankey³, Ethan S Srinivasan⁴, James E Herndon 2nd⁵, Peter E Fecci⁶, Evan Calabrese⁷

Affiliations

¹ Duke University School of Medicine, Durham, NC, USA.
² Department of Neurosurgery, Duke University Medical Center, Durham, NC, USA.
³ Department of Neurosurgery, Piedmont Athens Regional Medical Center, Athens, GA, USA.
⁴ Department of Neurosurgery, Johns Hopkins Hospital, Baltimore, MD, USA.
⁵ Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA.
⁶ The Preston Robert Tisch Brain Tumor Center, Department of Neurosurgery, Duke University Medical Center, Durham, NC, USA.
⁷ Department of Radiology, Division of Neuroradiology, Duke University Medical Center, Durham, NC, USA.

PMID: 38170451
DOI: 10.1093/neuonc/noad261

Abstract

Background: Laser interstitial thermal therapy (LITT) of intracranial tumors or radiation necrosis enables tissue diagnosis, cytoreduction, and rapid return to systemic therapies. Ablated tissue remains in situ, resulting in characteristic post-LITT edema associated with transient clinical worsening and complicating post-LITT response assessment.

Methods: All patients receiving LITT at a single center for tumors or radiation necrosis from 2015 - 2023 with ≥ 9 months of MRI follow-up were included. An nnU-Net segmentation model was trained to automatically segment Contrast-enhancing Lesion Volume (CeLV) of LITT-treated lesions on T1-weighted images. Response assessment was performed using volumetric measurements.

Results: 384 unique MRI exams of 61 LITT-treated lesions and 6 control cases of medically-managed radiation necrosis were analyzed. Automated segmentation was accurate in 367/384 (95.6%) images. CeLV increased to a median of 68.3% (IQR 35.1 - 109.2%) from baseline at 1 - 3 months from LITT (P = 0.0012) and returned to baseline thereafter. Overall survival (OS) for LITT-treated patients was 39.1 (9.2 - 93.4) months. Lesion expansion above 40% from volumetric nadir or baseline was considered volumetric progression. Twenty-one of 56 (37.5%) patients experienced progression for a volumetric progression-free survival of 21.4 (6.0 - 93.4) months. Patients with volumetric progression had worse OS (17.3 vs 62.1 months, P = 0.0015).

Conclusions: Post-LITT CeLV expansion is quantifiable and resolves within 6 months of LITT. Development of response assessment criteria for LITT-treated lesions is feasible and should be considered for clinical trials. Automated lesion segmentation could speed adoption of volumetric response criteria in clinical practice.

Keywords: Laser interstitial thermal therapy; automated segmentation; progression-free survival; response assessment; surrogate endpoints.