Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer

Ye, Zezhong; Saraf, Anurag; Ravipati, Yashwanth; Hoebers, Frank; Catalano, Paul J.; Zha, Yining; Zapaishchykova, Anna; Likitlersuang, Jirapat; Guthier, Christian V.; Tishler, Roy B.; Schoenfeld, Jonathan D.; Margalit, Danielle N.; Haddad, Robert I.; Mak, Raymond H.; Naser, Mohamed A.; Wahid, Kareem A.; Sahlsten, Jaakko; Jaskari, Joel; Kaski, Kimmo; Mäkitie, Antti; Fuller, Clifton D.; Aerts, Hugo J.W.L.; Kann, Benjamin H.

doi:10.1001/jamanetworkopen.2023.28280

Cited by 14 publications

(3 citation statements)

References 52 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, Ye et al [50] recently developed an image-based deep learning platform for SMI calculation to evaluate associations with survival and treatment toxicity outcomes and used separate thresholds for males and females. However, they used literature-based cutoffs [19] established on a mixed population of 250 patients with different types of cancer (mostly colon, rectum and other gastrointestinal or respiratory tract sites,).…”

Section: Discussionmentioning

confidence: 99%

Untailored vs. Gender- and Body-Mass-Index-Tailored Skeletal Muscle Mass Index (SMI) to Assess Sarcopenia in Advanced Head and Neck Squamous Cell Carcinoma (HNSCC)

Morelli,

Formica,

Bossi

et al. 2023

Cancers

View full text Add to dashboard Cite

(1) Background: Sarcopenia lasting >1 year might be considered a chronic condition in many HNSCC patients. CT-scan-derived Skeletal Muscle Mass Index (SMI) is an established surrogate of sarcopenia; yet, the cut-off reported in the literature (literature-based, lb-SMI < 43.2) is mainly based on the risk of chemoradiotherapy-induced toxicity, and the optimal value to discriminate OS is under-investigated. (2) Methods: The effect on OS of the lb-SMI cutoff was compared with an untailored OS-oriented SMI cutoff obtained in a cohort of consecutive advanced HNSCC patients treated with primary chemoradiotherapy, bio-chemotherapy or chemo-immunotherapy (cohort-specific, cs-SMI cutoff). Gender- and BMI-tailored (gt-SMI and bt-SMI) cut-offs were also evaluated. Cutoff values were identified by using the maximally selected rank statistics for OS. (3) Results: In 115 HNSCC patients, the cs-SMI cutoff was 31.50, which was lower compared to the lb-SMI reported cut-off. The optimal cut-off separately determined in females, males, overweight and non-overweight patients were 46.02, 34.37, 27.32 and 34.73, respectively. gt-SMI categorization had the highest effect on survival (p < 0.0001); its prognostic value was independent of the treatment setting or the primary location and was retained in a multivariate cox-regression analysis for OS including other HNSCC-specific prognostic factors (p = 0.0004). (4) Conclusions: A tailored SMI assessment would improve clinical management of sarcopenia in chemoradiotherapy-, bio-chemotherapy- or chemo-immunotherapy-treated HNSCC patients. Gender-based SMI could be used for prognostication in HNSCC patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Untailored vs. Gender- and Body-Mass-Index-Tailored Skeletal Muscle Mass Index (SMI) to Assess Sarcopenia in Advanced Head and Neck Squamous Cell Carcinoma (HNSCC)

Morelli,

Formica,

Bossi

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…As they occur most often (in two-thirds of cases) subclinical, imaging of the spine is the only way to have a full VF history [ 103 ]. Vertebral Fractures Assessment (VFA) has been shown to enhance fracture prediction beyond aBMD [ 104 ] and beyond FRAX [ 105 ], indicating that vulnerability to having a VF is likely a consequence of combined structural and density traits that make a up an individual's bone phenotype. Opportunistic identification of VFs from CT scans performed for other medical reasons is one of the emerging developments for assessing fracture risk and is a promising means to identify definite cases of bone fragility in the population [ 106 ].…”

Section: Clinical Implications Of Skeletal Phenotypesmentioning

confidence: 99%

Characterizing Bone Phenotypes Related to Skeletal Fragility Using Advanced Medical Imaging

Whittier,

Bevers,

Geusens

et al. 2023

Curr Osteoporos Rep

View full text Add to dashboard Cite

Purpose of Review Summarize the recent literature that investigates how advanced medical imaging has contributed to our understanding of skeletal phenotypes and fracture risk across the lifespan. Recent Findings Characterization of bone phenotypes on the macro-scale using advanced imaging has shown that while wide bones are generally stronger than narrow bones, they may be more susceptible to age-related declines in bone strength. On the micro-scale, HR-pQCT has been used to identify bone microarchitecture phenotypes that improve stratification of fracture risk based on phenotype-specific risk factors. Adolescence is a key phase for bone development, with distinct sex-specific growth patterns and significant within-sex bone property variability. However, longitudinal studies are needed to evaluate how early skeletal growth impacts adult bone phenotypes and fracture risk. Metabolic and rare bone diseases amplify fracture risk, but the interplay between bone phenotypes and disease remains unclear. Although bone phenotyping is a promising approach to improve fracture risk assessment, the clinical availability of advanced imaging is still limited. Consequently, alternative strategies for assessing and managing fracture risk include vertebral fracture assessment from clinically available medical imaging modalities/techniques or from fracture risk assessment tools based on clinical risk factors. Summary Bone fragility is not solely determined by its density but by a combination of bone geometry, distribution of bone mass, microarchitecture, and the intrinsic material properties of bone tissue. As such, different individuals can exhibit distinct bone phenotypes, which may predispose them to be more vulnerable or resilient to certain perturbations that influence bone strength.

show abstract

“…Therefore, non-invasive imaging-based tumor molecular subtyping, if accurate and reliable, could enable proper selection of patients for BRAF-targeted therapies and clinical trials. In recent years, deep learning (DL) has emerged as the forefront technology for analyzing medical images (6,7), and has demonstrated numerous successful applications, encompassing tumor segmentation (8–10), outcome prediction (11,12), tumor and molecular classification (13,14). However, DL performance degrades dramatically in limited data scenarios, due to instability, overfitting, and shortcut learning (15), and a key barrier to applying DL to pLGG imaging, is the lack of training data available for these rare tumor cases.…”

Section: Introductionmentioning

confidence: 99%

Noninvasive molecular subtyping of pediatric low-grade glioma with self-supervised transfer learning

Tak

Zapaishchykova

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

PurposeTo develop and externally validate a scan-to-prediction deep-learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pLGG.Materials and MethodsWe conducted a retrospective study of two pLGG datasets with linked genomic and diagnostic T2-weighted MRI of patients: Boston Children’s Hospital (development dataset, N=214), and Child Brain Tumor Network (CBTN) (external validation, N=112). We developed a deep learning pipeline to classify BRAF mutational status (V600E vs. fusion vs. wild-type) from whole-scan input via a two-stage process: 1) 3D tumor segmentation and extraction of axial tumor images, and 2) slice-wise, deep learning-based classification of mutational status. We investigated knowledge-transfer approaches to prevent model overfitting with a primary endpoint of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, we developed a novel metric, COMDist that quantifies the accuracy of model attention with respect to the tumor.ResultsA combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest AUC, taken as a weighted average across the three mutational classes, (0.82 [95% CI: 0.70-0.90], Accuracy: 77%) on internal validation and (0.73 [95% CI 0.68-0.88], Accuracy: 75%) on external validation. Training with TransferX also led to an AUC improvement of 17.7% and a COMDist Improvement of 6.42% over training from scratch on the development dataset.ConclusionTransfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pLGG mutational status prediction in a limited data scenario.Summary StatementThe authors developed and externally validated an automated, scan-to-prediction deep learning pipeline that classifies BRAF Mutational status in pediatric low-grade gliomas directly from T2-Weighted MRI scans.Key ResultsAn innovative training approach combining self-supervision and transfer learning (“TransferX”) is developed to boost model performance in low data settings;TransferX enables the development of a scan-to-prediction pipeline for pediatric LGG mutational status (BRAF V600E, fusion, or wildtype) with high accuracy and mild performance degradation on external validation;An evaluation metric “COMDist” is proposed to increase interpretability and quantify the accuracy of the model’s attention around the tumor.

show abstract

Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer

Cited by 14 publications

References 52 publications

Untailored vs. Gender- and Body-Mass-Index-Tailored Skeletal Muscle Mass Index (SMI) to Assess Sarcopenia in Advanced Head and Neck Squamous Cell Carcinoma (HNSCC)

Untailored vs. Gender- and Body-Mass-Index-Tailored Skeletal Muscle Mass Index (SMI) to Assess Sarcopenia in Advanced Head and Neck Squamous Cell Carcinoma (HNSCC)

Characterizing Bone Phenotypes Related to Skeletal Fragility Using Advanced Medical Imaging

Noninvasive molecular subtyping of pediatric low-grade glioma with self-supervised transfer learning

Contact Info

Product

Resources

About