Treatment-related features improve machine learning prediction of prognosis in soft tissue sarcoma patients

The importance of planning CT-based imaging features for machine learning-based prediction of pain response

Patients suffering from painful spinal bone metastases (PSBMs) often undergo palliative radiation therapy (RT), with an efficacy of approximately two thirds of patients. In this exploratory investigation, we assessed the effectiveness of machine learning (ML) models trained on radiomics, semantic and clinical features to estimate complete pain response. Gross tumour volumes (GTV) and clinical target volumes (CTV) of 261 PSBMs were segmented on planning computed tomography (CT) scans. Radiomics, semantic and clinical features were collected for all patients. Random forest (RFC) and support vector machine (SVM) classifiers were compared using repeated nested cross-validation. The best radiomics classifier was trained on CTV with an area under the receiver-operator curve (AUROC) of 0.62 ± 0.01 (RFC; 95% confidence interval). The semantic model achieved a comparable AUROC of 0.63 ± 0.01 (RFC), significantly below the clinical model (SVM, AUROC: 0.80 ± 0.01); and slightly lower than the spinal instability neoplastic score (SINS; LR, AUROC: 0.65 ± 0.01). A combined model did not improve performance (AUROC: 0,74 ± 0,01). We could demonstrate that radiomics and semantic analyses of planning CTs allowed for limited prediction of therapy response to palliative RT. ML predictions based on established clinical parameters achieved the best results.

Applications of machine learning for imaging-driven diagnosis of musculoskeletal malignancies—a scoping review

Abstract

Musculoskeletal malignancies are a rare type of cancer. Consequently, sufficient imaging data for machine learning (ML) applications is difficult to obtain. The main purpose of this review was to investigate whether ML is already having an impact on imaging-driven diagnosis of musculoskeletal malignancies and what the respective reasons for this might be. A scoping review was conducted by a radiologist, an orthopaedic surgeon and a data scientist to identify suitable articles based on the PRISMA statement. Studies meeting the following criteria were included: primary malignant musculoskeletal tumours, machine/deep learning application, imaging data or data retrieved from images, human/preclinical, English language and original research. Initially, 480 articles were found and 38 met the eligibility criteria. Several continuous and discrete parameters related to publication, patient distribution, tumour specificities, ML methods, data and metrics were extracted from the final articles. For the synthesis, diagnosis-oriented studies were further examined by retrieving the number of patients and labels and metric scores. No significant correlations between metrics and mean number of samples were found. Several studies presented that ML could support imaging-driven diagnosis of musculoskeletal malignancies in distinct cases. However, data quality and quantity must be increased to achieve clinically relevant results. Compared to the experience of an expert radiologist, the studies used small datasets and mostly included only one type of data. Key to critical advancement of ML models for rare diseases such as musculoskeletal malignancies is a systematic, structured data collection and the establishment of (inter)national networks to obtain substantial datasets in the future.

Key Points

• Machine learning does not yet significantly impact imaging-driven diagnosis for musculoskeletal malignancies compared to other disciplines such as lung, breast or CNS cancer.

• Research in the area of musculoskeletal tumour imaging and machine learning is still very limited.

• Machine learning in musculoskeletal tumour imaging is impeded by insufficient availability of data and rarity of the disease.

Artificial intelligence applied to musculoskeletal oncology: a systematic review

Developments in artificial intelligence have the potential to improve the care of patients with musculoskeletal tumors. We performed a systematic review of the published scientific literature to identify the current state of the art of artificial intelligence applied to musculoskeletal oncology, including both primary and metastatic tumors, and across the radiology, nuclear medicine, pathology, clinical research, and molecular biology literature. Through this search, we identified 252 primary research articles, of which 58 used deep learning and 194 used other machine learning techniques. Articles involving deep learning have mostly involved bone scintigraphy, histopathology, and radiologic imaging. Articles involving other machine learning techniques have mostly involved transcriptomic analyses, radiomics, and clinical outcome prediction models using medical records. These articles predominantly present proof-of-concept work, other than the automated bone scan index for bone metastasis quantification, which has translated to clinical workflows in some regions. We systematically review and discuss this literature, highlight opportunities for multidisciplinary collaboration, and identify potentially clinically useful topics with a relative paucity of research attention. Musculoskeletal oncology is an inherently multidisciplinary field, and future research will need to integrate and synthesize noisy siloed data from across clinical, imaging, and molecular datasets. Building the data infrastructure for collaboration will help to accelerate progress towards making artificial intelligence truly useful in musculoskeletal oncology.

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics

BACKGROUND

In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS).

METHODS

Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS.

RESULTS

ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification.

CONCLUSIONS

T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.

Image-Guided Radiooncology: The Potential of Radiomics in Clinical Application

Medical imaging plays an imminent role in today's radiation oncology workflow. Predominantly based on semantic image analysis, malignant tumors are diagnosed, staged, and therapy decisions are made. The field of "radiomics" promises to extract complementary, objective information from medical images. In radiomics, predefined quantitative features including intensity statistics, texture, shape, or filtering techniques are combined into statistical or machine learning models to predict clinical or biological outcomes. Alternatively, deep neural networks can directly analyze medical images and provide predictions. A large number of research studies could demonstrate that radiomics prediction models may provide significant benefits in the radiation oncology workflow including diagnostics, tumor characterization, target volume segmentation, prognostic stratification, and prediction of therapy response or treatment-related toxicities. This chapter provides an overview of techniques within the radiomics toolbox, potential clinical application, and current limitations. A literature overview of four selected malignant entities including non-small cell lung cancer, head and neck squamous cell carcinomas, soft tissue sarcomas, and gliomas is given.

Impact of preoperative treatment on the CINSARC prognostic signature: translational research results from a phase 1 trial of the German Interdisciplinary Sarcoma Group (GISG 03)

PURPOSE

CINSARC (Complexity INdex in SARComas) is a prognostic signature for soft tissue sarcoma that determines the risk for recurrence and may serve to guide the decision for adjuvant chemotherapy. The aim of this study was to compare the CINSARC signature of pre- and posttreatment biopsies of sarcoma patients treated within a phase I trial evaluating preoperative sunitinib and irradiation.

METHODS

We retrieved 14 pairs of formalin-fixed paraffin-embedded blocks from pretreatment biopsies and posttreatment resection specimens and performed expression profiling of the 67 CINSARC signature genes.

RESULTS

In 5/14 patients, both probes were unsuitable for expression analysis because there was no (vital) tissue left in biopsies or resection specimens. Comparing the CINSARC risk classification before and after treatment in the remaining patients, 2/9 shifted from a high- to a low-risk classification for metastatic disease after preoperative treatment with radiation therapy plus sunitinib and 7/9 pairs of pre- and posttreatment biopsies revealed identical results.

CONCLUSION

Concurrent radiation therapy and sunitinib leads to diverging results of prognostic gene array testing in a relevant proportion of sarcoma patients. These changes may reflect tumor heterogeneity, local treatment effects, or prognostic changes of the disease. Caution is advised in the selection of samples and interpretation of test results.

Tumor grading of soft tissue sarcomas using MRI-based radiomics

Background

Treatment decisions for multimodal therapy in soft tissue sarcoma (STS) patients greatly depend on the differentiation between low-grade and high-grade tumors. We developed MRI-based radiomics grading models for the differentiation between low-grade (G1) and high-grade (G2/G3) STS.

Methods

The study was registered at ClinicalTrials.gov (number NCT03798795). Contrast-enhanced T1-weighted fat saturated (T1FSGd), fat-saturated T2-weighted (T2FS) MRI sequences, and tumor grading following the French Federation of Cancer Centers Sarcoma Group obtained from pre-therapeutic biopsies were gathered from two independent retrospective patient cohorts. Volumes of interest were manually segmented. After preprocessing, 1394 radiomics features were extracted from each sequence. Features unstable in 21 independent multiple-segmentations were excluded. Least absolute shrinkage and selection operator models were developed using nested cross-validation on a training patient cohort (122 patients). The influence of ComBatHarmonization was assessed for correction of batch effects.

Findings

Three radiomic models based on T2FS, T1FSGd and a combined model achieved predictive performances with an area under the receiver operator characteristic curve (AUC) of 0.78, 0.69, and 0.76 on the independent validation set (103 patients), respectively. The T2FS-based model showed the best reproducibility. The radiomics model involving T1FSGd-based features achieved significant patient stratification. Combining the T2FS radiomic model into a nomogram with clinical staging improved prognostic performance and the clinical net benefit above clinical staging alone.

Interpretation

MRI-based radiomics tumor grading models effectively classify low-grade and high-grade soft tissue sarcomas.

Fund

The authors received support by the medical faculty of the Technical University of Munich and the German Cancer Consortium.

Using Image-guided Intensity-modulated Radiotherapy on Patients With Head and Neck Soft-tissue Sarcoma

BACKGROUND

Image-guided intensity-modulated radiotherapy (IG-IMRT) is increasingly being used to treat patients with soft-tissue sarcoma (STS) of the head and neck. Although there is no comparison between IMRT and conventional radiation therapy (CRT) concerning their efficacy. In this analysis, we compared CRT and IMRT outcomes for head and neck STS.

PATIENTS AND METHODS

Sixty-seven patients who underwent radiotherapy between 1994 and 2017 were identified.

RESULTS

The median follow-up was 31 months. Of the 67 patients, 34% were treated with CRT technique and 66% with IG-IMRT. The locoregional relapse rate following IMRT was 21% versus 70% with CRT (p<0.001) and the 5-year locoregional control was 69% versus 28%, respectively (p=0.01). IG-IMRT was associated with non-significant, less acute, and chronic adverse events. In the multivariate analysis, a significant influence of radiation technique on locoregional control was confirmed (p=0.04).

CONCLUSION

IG-IMRT seems to be associated both with higher locoregional control as well as lower acute and chronic toxicities.

Combining multimodal imaging and treatment features improves machine learning-based prognostic assessment in patients with glioblastoma multiforme

Background

For Glioblastoma (GBM), various prognostic nomograms have been proposed. This study aims to evaluate machine learning models to predict patients' overall survival (OS) and progression‐free survival (PFS) on the basis of clinical, pathological, semantic MRI‐based, and FET‐PET/CT‐derived information. Finally, the value of adding treatment features was evaluated.

Methods

One hundred and eighty‐nine patients were retrospectively analyzed. We assessed clinical, pathological, and treatment information. The VASARI set of semantic imaging features was determined on MRIs. Metabolic information was retained from preoperative FET‐PET/CT images. We generated multiple random survival forest prediction models on a patient training set and performed internal validation. Single feature class models were created including "clinical," "pathological," "MRI‐based," and "FET‐PET/CT‐based" models, as well as combinations. Treatment features were combined with all other features.

Results

Of all single feature class models, the MRI‐based model had the highest prediction performance on the validation set for OS (C‐index: 0.61 [95% confidence interval: 0.51‐0.72]) and PFS (C‐index: 0.61 [0.50‐0.72]). The combination of all features did increase performance above all single feature class models up to C‐indices of 0.70 (0.59‐0.84) and 0.68 (0.57‐0.78) for OS and PFS, respectively. Adding treatment information further increased prognostic performance up to C‐indices of 0.73 (0.62‐0.84) and 0.71 (0.60‐0.81) on the validation set for OS and PFS, respectively, allowing significant stratification of patient groups for OS.

Conclusions

MRI‐based features were the most relevant feature class for prognostic assessment. Combining clinical, pathological, and imaging information increased predictive power for OS and PFS. A further increase was achieved by adding treatment features.