Framework for Machine Learning of CT and PET Radiomics to Predict Local Failure after Radiotherapy in Locally Advanced Head and Neck Cancers

Preoperative high-precision three-dimensional reconstruction in laparoscopic splenectomy for supramassive splenomegaly: a case report and literature review

Background

Massive splenomegaly is considered to pose a high risk for laparoscopic splenectomy (LS). We report a case of supramassive splenomegaly wherein the patient successfully underwent LS guided by preoperative three-dimensional (3D) reconstruction.

Case presentation

A 35-year-old female had a history of autoimmune hepatitis spanning 4 years, accompanied by progressive splenomegaly. Her spleen had grown to a size of 27.3 cm in diameter, and a consistent decline in her blood cell counts had been noted over the same period. Considering the significant enlargement of the spleen and the technical challenges associated with LS in such instances, a preoperative 3D reconstruction was performed. This 3D model accurately delineated the splenic artery and depicted the positional relationships between the enlarged spleen and nearby organs, thus supporting detailed preoperative planning. Following the surgical route determined in the preoperative planning, 3D assistance enabled the safe ligation of the splenic artery and meticulous separation of the spleen from adjacent tissues. The patient's postoperative recovery was smooth and free from complications.

Conclusion

Meticulous preoperative 3D planning may help overcome technical difficulties and enable successful LS even in patients with supramassive splenomegaly.

Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization

Background and purpose

Radiomics models trained with limited single institution data are often not reproducible and generalisable. We developed radiomics models that predict loco-regional recurrence within two years of radiotherapy with private and public datasets and their combinations, to simulate small and multi-institutional studies and study the responsiveness of the models to feature selection, machine learning algorithms, centre-effect harmonization and increased dataset sizes.

Materials and methods

562 patients histologically confirmed and treated for locally advanced head-and-neck cancer (LA-HNC) from two public and two private datasets; one private dataset exclusively reserved for validation. Clinical contours of primary tumours were not recontoured and were used for Pyradiomics based feature extraction. ComBat harmonization was applied, and LASSO-Logistic Regression (LR) and Support Vector Machine (SVM) models were built. 95% confidence interval (CI) of 1000 bootstrapped area-under-the-Receiver-operating-curves (AUC) provided predictive performance. Responsiveness of the models' performance to the choice of feature selection methods, ComBat harmonization, machine learning classifier, single and pooled data was evaluated.

Results

LASSO and SelectKBest selected 14 and 16 features, respectively; three were overlapping. Without ComBat, the LR and SVM models for three institutional data showed AUCs (CI) of 0.513 (0.481-0.559) and 0.632 (0.586-0.665), respectively. Performances following ComBat revealed AUCs of 0.559 (0.536-0.590) and 0.662 (0.606-0.690), respectively. Compared to single cohort AUCs (0.562-0.629), SVM models from pooled data performed significantly better at AUC = 0.680.

Conclusions

Multi-institutional retrospective data accentuates the existing variabilities that affect radiomics. Carefully designed prospective, multi-institutional studies and data sharing are necessary for clinically relevant head-and-neck cancer prognostication models.

Data-centric artificial intelligence in oncology: a systematic review assessing data quality in machine learning models for head and neck cancer

Machine learning models have been increasingly considered to model head and neck cancer outcomes for improved screening, diagnosis, treatment, and prognostication of the disease. As the concept of data-centric artificial intelligence is still incipient in healthcare systems, little is known about the data quality of the models proposed for clinical utility. This is important as it supports the generalizability of the models and data standardization. Therefore, this study overviews the quality of structured and unstructured data used for machine learning model construction in head and neck cancer. Relevant studies reporting on the use of machine learning models based on structured and unstructured custom datasets between January 2016 and June 2022 were sourced from PubMed, EMBASE, Scopus, and Web of Science electronic databases. Prediction model Risk of Bias Assessment (PROBAST) tool was used to assess the quality of individual studies before comprehensive data quality parameters were assessed according to the type of dataset used for model construction. A total of 159 studies were included in the review; 106 utilized structured datasets while 53 utilized unstructured datasets. Data quality assessments were deliberately performed for 14.2% of structured datasets and 11.3% of unstructured datasets before model construction. Class imbalance and data fairness were the most common limitations in data quality for both types of datasets while outlier detection and lack of representative outcome classes were common in structured and unstructured datasets respectively. Furthermore, this review found that class imbalance reduced the discriminatory performance for models based on structured datasets while higher image resolution and good class overlap resulted in better model performance using unstructured datasets during internal validation. Overall, data quality was infrequently assessed before the construction of ML models in head and neck cancer irrespective of the use of structured or unstructured datasets. To improve model generalizability, the assessments discussed in this study should be introduced during model construction to achieve data-centric intelligent systems for head and neck cancer management.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

CT-based radiomics signature analysis for evaluation of response to induction chemotherapy and progression-free survival in locally advanced hypopharyngeal carcinoma

OBJECTIVES

To establish and validate a CT radiomics model for prediction of induction chemotherapy (IC) response and progression-free survival (PFS) among patients with locally advanced hypopharyngeal carcinoma (LAHC).

METHODS

One hundred twelve patients with LAHC (78 in training cohort and 34 in validation cohort) who underwent contrast-enhanced CT (CECT) scans prior to IC were enrolled. Least absolute shrinkage and selection operator (LASSO) was used to select the crucial radiomic features in the training cohort. Radiomics signature and clinical data were used to build a radiomics nomogram to predict individual response to IC. Kaplan-Meier analysis and log-rank test were used to evaluate ability of radiomics signature in progression-free survival risk stratification.

RESULTS

The radiomics signature consisted of 6 selected features from the arterial and venous phases of CECT images and demonstrated good performance in predicting the IC response in both two cohorts. The radiomics nomogram showed good discriminative performance, and the C-index of nomogram was 0.899 (95% confidence interval (CI), 0.831-0.967) and 0.775 (95% CI, 0.591-0.959) in the training and validation cohorts, respectively. Survival analysis indicated that low-risk and high-risk groups defined by the value of radiomics signature had significant difference in PFS (3-year PFS 66.4% vs 29.7%, p < 0.001).

CONCLUSIONS

Multiparametric CT-based radiomics model could be useful for predicting treatment response and PFS in patients with LAHC who underwent IC.

KEY POINTS

• CT radiomics can predict IC response and progression-free survival in hypopharyngeal carcinoma. • We combined significant radiomics signature with clinical predictors to establish a nomogram to predict individual response to IC. • Radiomics signature could divide patients into the high-risk and low-risk groups based on the PFS.

Evaluation of Therapeutic Effects of Computed Tomography Imaging Classification Algorithm-Based Transcatheter Arterial Chemoembolization on Primary Hepatocellular Carcinoma

To investigate the evaluation of therapeutic effects of computerized tomography (CT) imaging machine learning classification algorithm-based transcatheter arterial chemoembolization (TACE) on primary hepatocellular carcinoma (PHC), machine learning algorithm was optimized to propose the feature extraction of soft margin, analyze CT images, and acquire relevant texture features to assess if it can predict the multistage features of PHC for the application of the therapeutic effects of TACE on PHC. Besides, PHC patients receiving surgical excision were retrospectively collected, and then 483 patients with hepatocellular carcinoma (HCC) were determined from cases. After that, a total of 162 cases meeting the standards were selected. Besides, the features of images were classified and analyzed by machine learning algorithm, and volume of interest (VOI) images of patients in each group were acquired by image segmentation layer by layer. In addition, the texture features of images were extracted. The results showed that 5 CT image-based texture features, including 2 histogram features and 3 matrix-based features, all described the specificity and heterogeneity of tumors. The analysis of the diagnostic effectiveness of the evaluation of response group by each texture parameter demonstrated that its sensitivity, specificity, and area under curve (AUC) were 83.63%, 90.91%, and 0.08%, respectively. Based on CT prediction, machine learning algorithm was fused to realize excellent classification effects on multistage and multiphase features and offer imaging support to the clinical selection of reasonable therapeutic plans. In addition, multiphase and multifeature-based medical tumor classification method was put forward.