Is radiomics a useful addition to magnetic resonance imaging in the preoperative classification of PitNETs?

BACKGROUND

The WHO 2021 introduced the term pituitary neuroendocrine tumours (PitNETs) for pituitary adenomas and incorporated transcription factors for subtyping, prompting the need for fresh diagnostic methods. Current biomarkers struggle to distinguish between high- and low-risk non-functioning PitNETs. We explored if radiomics can enhance preoperative decision-making.

METHODS

Pre-treatment magnetic resonance (MR) images of patients who underwent surgery between 2015 and 2019 with available WHO 2021 classification were used. The tumours were manually segmented on the T1w, T1-contrast enhanced, and T2w images using 3D Slicer. One hundred Pyradiomic features were extracted from each MR sequence. Models were built to classify (1) somatotroph and gonadotroph PitNETs and (2) high- and low-risk subtypes of non-functioning PitNETs. Feature were selected independently from the MR sequences and multi-sequence (combining data from more than one MR sequence) using Boruta and Pearson correlation. Support vector machine (SVM), logistic regression (LR), random forest (RF), and multi-layer perceptron (MLP) were the classifiers used. Data imbalance was addressed using the Synthetic Minority Oversampling TEchnique (SMOTE). Performance of the models were evaluated using area under the receiver operating curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

A total of 222 PitNET patients (train, n = 149; test, n = 73) were enrolled in this retrospective study. Multi-sequence-based LR model discriminated best between somatotroph and gonadotroph PitNETs, with a test AUC of 0.84, accuracy of 0.74, specificity of 0.81, and sensitivity of 0.70. Multi-sequence-based MLP model perfomed best for the high- and low-risk non-functioning PitNETs, achieving a test AUC of 0.76, accuracy of 0.67, specificity of 0.72, and sensitivity of 0.66.

CONCLUSIONS

Utilizing pre-treatment MRI and radiomics holds promise for distinguishing high-risk from low-risk non-functioning PitNETs based on the latest WHO classification. This could assist neurosurgeons in making critical decisions regarding surgery or alternative management strategies for PitNETs after further clinical validation.

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.

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

Context:

Cancer Radiomics is an emerging field in medical imaging and refers to the process of converting routine radiological images that are typically qualitatively interpreted to quantifiable descriptions of the tumor phenotypes and when combined with statistical analytics can improve the accuracy of clinical outcome prediction models. However, to understand the radiomic features and their correlation to molecular changes in the tumor, first, there is a need for the development of robust image analysis methods, software tools and statistical prediction models which is often limited in low- and middle-income countries (LMIC).

Aims:

The aim is to build a framework for machine learning of radiomic features of planning computed tomography (CT) and positron emission tomography (PET) using open source radiomics and data analytics platforms to make it widely accessible to clinical groups. The framework is tested in a small cohort to predict local disease failure following radiation treatment for head-and-neck cancer (HNC). The predictors were also compared with the existing Aerts HNC radiomics signature.

Settings and Design:

Retrospective analysis of patients with locally advanced HNC between 2017 and 2018 and 31 patients with both pre- and post-radiation CT and evaluation PET were selected.

Subjects and Methods:

Tumor volumes were delineated on baseline PET using the semi-automatic adaptive-threshold algorithm and propagated to CT; PyRadiomics features (total of 110 under shape/intensity/texture classes) were extracted. Two feature-selection methods were tested for model stability. Models were built based on least absolute shrinkage and selection operator-logistic and Ridge regression of the top pretreatment radiomic features and compared to Aerts' HNC-signature. Average model performance across all internal validation test folds was summarized by the area under the receiver operator curve (ROC).

Results:

Both feature selection methods selected CT features MCC (GLCM), SumEntropy (GLCM) and Sphericity (Shape) that could predict the binary failure status in the cross-validated group and achieved an AUC >0.7. However, models using Aerts' signature features (Energy, Compactness, GLRLM-GrayLevelNonUniformity and GrayLevelNonUniformity-HLH wavelet) could not achieve a clear separation between outcomes (AUC = 0.51–0.54).

Conclusions:

Radiomics pipeline included open-source workflows which makes it adoptable in LMIC countries. Additional independent validation of data is crucial for the implementation of radiomic models for clinical risk stratification.

Resilience as a communal concept: Understanding adolescent resilience in the context of the Syrian refugee crisis in Bar Elias, Lebanon

Background

The conflict in Syria has led to the displacement of 1.5 million refugees into the neighboring country of Lebanon, with a majority that have yet to return to their homeland. Syrian adolescents in the town of Bar Elias in the Bekaa Valley, Lebanon have lived and grown in the face of resource-limited environments, restricted movement, and a longing for return. Resilience is manifested in the adaptation to such circumstances through close supportive relationships, social engagement, employment, and religion. There is a communal aspect to resilience that is important to the adolescent refugee experience and to the efforts supporting these communities.

Methods

Fifteen one-to-one interviews and two focus groups, with a total of eighteen Syrian adolescents, were analyzed using an inductive thematic analysis informed by grounded theory principles. Participants were recruited through partnering non-governmental organizations (NGOs) in the area, and ethical approval was granted through UCL and the American University in Beirut (AUB).

Results

Syrian adolescents highlighted supportive relationships, communal activities and spaces, memories of home, employment, and shared environments as integral elements to their personal adaptation. Methods of resilience involved social cohesion and establishing stability for one's family and close community. Adaptation to the present is intertwined with facing the consequences of displacement in this new context and maintaining aspirations for a bright future. Engaging with the environments they share and help create is an important facet of resilience and occurs through group gatherings , hobbies, and online communication. Additionally, inner strength can be derived from religious activities and empowers individual processing.

Conclusion

This study illuminates the elements and mechanisms embodied in these adolescents' communities and relationships that allow for adaptation to life in Bar Elias. These factors strengthen their approach to overcome social barriers and practice resilience. These communal aspects of the adolescents' lives also connect to their memories of home, current environment, and future aspirations.

Migration, adolescents and health

In low- and middle-income countries, migration for work is common but the health consequences on adolescents is poorly understood. Particularly in low-resource settings, when children enter their adolescent years, their lives change dramatically as they take on adult roles. Young girls may get married and forced to move to their husband's home where they conduct domestic work and are exposed to high levels of air pollution from cooking. They are also more likely to become parents themselves. Many girls and boys drop out of school to work near their home or migrate within the country or abroad. They face risks throughout the journey and often work in precarious forms of labour. Among them, the unaccompanied adolescents face even greater risks than those who move with their parents. When parents migrate, despite increases in wealth from remittances, child and adolescent mental and physical health tends to worsen. With evidence mostly from the South Asian context, Dr Devakumar will explain detrimental impact of parental migration on left-adolescents and raise the importance of policy makers and health-care professionals on taking action to improve the health planning targeting of these young people.

Accuracy of the freehand (fennell) technique using a uniform entry point and sagittal trajectory for insertion of thoracic pedicle screws: A computed tomography-based virtual simulation study

Background

Thoracic spine has complex pedicle anatomy with a narrow canal diameter which makes pedicle screw insertion challenging. Fennell et al. have described a simple freehand technique of thoracic pedicle screw placement. We have tested the accuracy of Fennell technique using computed tomography-based (CT-based) simulation model with pedicle screw simulator (PSS).

Methods

Normal CT thoracic spine obtained from CT thorax data of five patients were used in the 3D slicer environment using PSS for simulation. Entry points and axial trajectory as described by Fennell et al. and a sagittal trajectory parallel to the superior endplate were used for simulating the freehand technique using EA (entry angle) mode in the PSS. An ideal trajectory through the midsection of the pedicle from the same entry point and a sagittal trajectory parallel to the superior endplate were simulated using the ET (Entry Target) mode. Angle predicted by the software for an ideal axial trajectory was compared with the Fennell technique and this angle difference was noted at all the levels. Presence of pedicle breach was noted while simulating the Fennell technique.

Results

A total of 240 thoracic pedicle screw insertions were simulated, 120 screws by each technique. A sagittal trajectory parallel to the superior endplate caused no pedicle breach in the cranial-caudal direction at any level. No medial or lateral breach was noted while using an axial trajectory of 30° at T1-T2 and 20° from T3-T10. A 20° axial trajectory at T11 and T12 resulted in a breach of the medial cortex and the ideal mean axial angles at T11 and T12 were 2.8° and 6.5°, respectively.

Conclusions

Fennell technique was effectively simulated using PSS. A uniform entry point and sagittal trajectory parallel to the superior endplate serves as a useful guide for freehand insertion of thoracic pedicle screws. At T11 and 12, ideal axial trajectories are less than 10°.

Hybrid positron emission tomography segmentation of heterogeneous lung tumors using 3D Slicer: improved GrowCut algorithm with threshold initialization

This paper presents an improved GrowCut (IGC), a positron emission tomography-based segmentation algorithm, and tests its clinical applicability. Contrary to the traditional method that requires the user to provide the initial seeds, the IGC algorithm starts with a threshold-based estimate of the tumor and a three-dimensional morphologically grown shell around the tumor as the foreground and background seeds, respectively. The repeatability of IGC from the same observer at multiple time points was compared with the traditional GrowCut algorithm. The algorithm was tested in 11 nonsmall cell lung cancer lesions and validated against the clinician-defined manual contour and compared against the clinically used 25% of the maximum standardized uptake value [SUV-(max)], 40% [Formula: see text], and adaptive threshold methods. The time to edit IGC-defined functional volume to arrive at the gross tumor volume (GTV) was compared with that of manual contouring. The repeatability of the IGC algorithm was very high compared with the traditional GrowCut ([Formula: see text]) and demonstrated higher agreement with the manual contour with respect to threshold-based methods. Compared with manual contouring, editing the IGC achieved the GTV in significantly less time ([Formula: see text]). The IGC algorithm offers a highly repeatable functional volume and serves as an effective initial guess that can well minimize the time spent on labor-intensive manual contouring.

Patterns of domestic exposure to carbon monoxide and particulate matter in households using biomass fuel in Janakpur, Nepal

Household Air Pollution (HAP) from biomass cooking fuels is a major cause of morbidity and mortality in low-income settings worldwide. In Nepal the use of open stoves with solid biomass fuels is the primary method of domestic cooking. To assess patterns of domestic air pollution we performed continuous measurement of carbon monoxide (CO) and particulate Matter (PM2.5) in 12 biomass fuel households in Janakpur, Nepal. We measured kitchen PM2.5 and CO concentrations at one-minute intervals for an approximately 48-h period using the TSI DustTrak II 8530/SidePak AM510 (TSI Inc, St. Paul MN, USA) or EL-USB-CO data logger (Lascar Electronics, Erie PA, USA) respectively. We also obtained information regarding fuel, stove and kitchen characteristics and cooking activity patterns. Household cooking was performed in two daily sessions (median total duration 4 h) with diurnal variability in pollutant concentrations reflecting morning and evening cooking sessions and peak concentrations associated with fire-lighting. We observed a strong linear relationship between PM2.5 measurements obtained by co-located photometric and gravimetric monitoring devices, providing local calibration factors of 4.9 (DustTrak) and 2.7 (SidePak). Overall 48-h average CO and PM2.5 concentrations were 5.4 (SD 4.3) ppm (12 households) and 417.6 (SD 686.4) μg/m3 (8 households), respectively, with higher average concentrations associated with cooking and heating activities. Overall average PM2.5 concentrations and peak 1-h CO concentrations exceeded WHO Indoor Air Quality Guidelines. Average hourly PM2.5 and CO concentrations were moderately correlated (r = 0.52), suggesting that CO has limited utility as a proxy measure for PM2.5 exposure assessment in this setting. Domestic indoor air quality levels associated with biomass fuel combustion in this region exceed WHO Indoor Air Quality standards and are in the hazardous range for human health.

Association between Birth Interval and Cardiovascular Outcomes at 30 Years of Age: A Prospective Cohort Study from Brazil

Background

Birth interval is an important and potentially modifiable factor that is associated with child health. Whether an association exists with longer-term outcomes in adults is less well known.

Methods

Using the 1982 Pelotas (Brazil) Birth Cohort Study, the association of birth interval with markers of cardiovascular health at 30 years of age was examined. Multivariable linear regression was used with birth interval as a continuous variable and categorical variable, and effect modification by gender was explored.

Results

Birth interval and cardiovascular data were present for 2,239 individuals. With birth interval as a continuous variable, no association was found but stratification by gender tended to show stronger associations for girls. When compared to birth intervals of <18 months, as binary variable, longer intervals were associated with increases in height (1.6 cm; 95% CI: 0.5, 2.8) and lean mass (1.7 kg; 95% CI: 0.2, 3.2). No difference was seen with other cardiovascular outcomes.

Conclusions

An association was generally not found between birth interval and cardiovascular outcomes at 30 years of age, though some evidence existed for differences between males and females and for an association with height and lean mass for birth intervals of 18 months and longer.

Can positron emission tomography be more than a diagnostic tool? A survey on clinical practice among radiation oncologists in India

AIM

The purpose of the survey was to understand the role of positron emission tomography (PET) in clinical radiotherapy practice among the radiation oncologists' in India.

SETTINGS AND DESIGN

An online questionnaire was developed to survey the oncologists on their use of PET, viewing protocols, contouring techniques practiced, the barriers on the use of PET and the need for training in use of PET in radiotherapy. The questionnaire was sent to about 500 oncologists and 76 completed responses were received.

RESULTS

The survey shows that radiation oncologists use PET largely to assess treatment response and staging but limitedly use it for radiotherapy treatment planning. Only manual contouring and fixed threshold based delineation techniques (e.g. 40% maximum standard uptake value [SUV max ] or SUV 2.5) are used. Cost is the major barrier in the wider use of PET, followed by limited availability of FDG radionuclide tracer. Limited or no training was available for the use of PET.

CONCLUSIONS

Our survey revealed the vast difference between literature suggestions and actual clinical practice on the use of PET in radiotherapy. Additional training and standardization of protocols for use of PET in radiotherapy is essential for fully utilizing the capability of PET.

Biomass fuel use and the exposure of children to particulate air pollution in southern Nepal

The exposure of children to air pollution in low resource settings is believed to be high because of the common use of biomass fuels for cooking. We used microenvironment sampling to estimate the respirable fraction of air pollution (particles with median diameter less than 4 μm) to which 7-9 year old children in southern Nepal were exposed. Sampling was conducted for a total 2649 h in 55 households, 8 schools and 8 outdoor locations of rural Dhanusha. We conducted gravimetric and photometric sampling in a subsample of the children in our study in the locations in which they usually resided (bedroom/living room, kitchen, veranda, in school and outdoors), repeated three times over one year. Using time activity information, a 24-hour time weighted average was modeled for all the children in the study. Approximately two-thirds of homes used biomass fuels, with the remainder mostly using gas. The exposure of children to air pollution was very high. The 24-hour time weighted average over the whole year was 168 μg/m(3). The non-kitchen related samples tended to show approximately double the concentration in winter than spring/autumn, and four times that of the monsoon season. There was no difference between the exposure of boys and girls. Air pollution in rural households was much higher than the World Health Organization and the National Ambient Air Quality Standards for Nepal recommendations for particulate exposure.

Targeting apoptosis for optical imaging of infection

PURPOSE

Infection is ubiquitous and a major cause of morbidity and mortality. The most reliable method for localizing infection requires radiolabeling autologous white blood cells ex vivo. A compound that can be injected directly into a patient and can selectively image infectious foci will eliminate the drawbacks. The resolution of infection is associated with neutrophil apoptosis and necrosis presenting phosphatidylserine (PS) on the neutrophil outer leaflet. Targeting PS with intravenous administration of a PS-specific, near-infrared (NIR) fluorophore will permit localization of infectious foci by optical imaging.

METHODS

Bacterial infection and sterile inflammation were induced in separate groups (n = 5) of mice. PS was targeted with a NIR fluorophore, PSVue(®)794 (2.7 pmol). Imaging was performed (ex = 730 nm, em = 830 nm) using Kodak Multispectral FX-Pro system. The contralateral normal thigh served as an individualized control. Confocal microscopy of normal and apoptotic neutrophils and bacteria confirmed PS specificity.

RESULTS

Lesions, with a 10-s image acquisition, were unequivocally visible at 5 min post-injection. At 3 h post-injection, the lesion to background intensity ratios in the foci of infection (6.6 ± 0.2) were greater than those in inflammation (3.2 ± 0.5). Image fusions confirmed anatomical locations of the lesions. Confocal microscopy determined the fluorophore specificity for PS.

CONCLUSIONS

Targeting PS presented on the outer leaflet of apoptotic or necrotic neutrophils as well as gram-positive microorganism with PS-specific NIR fluorophore provides a sensitive means of imaging infection. Literature indicates that NIR fluorophores can be detected 7-14 cm deep in tissue. This observation together with the excellent results and the continued development of versatile imaging devices could make optical imaging a simple, specific, and rapid modality for imaging infection.

Apoptotic abscess imaging with 99mTc-HYNIC-rh-Annexin-V

Abscess formation causes systemic and localized up-regulation of neutrophil [polymorphonuclear leukocytes (PMNs)] signaling pathways. In the abscess, following bacterial ingestion or PMN activation by inflammatory mediators, PMN apoptosis is elevated and leads to the externalization of phosphatidylserine. Annexin-V (AnxV) has been shown to have high affinity to externalized phosphatidylserine. We hypothesized that (99m)Tc-AnxV will target high densities of apoptotic PMNs and image abscesses. AnxV, conjugated with hydrazinenicaotinamide (HYNIC), was labeled with reduced (99m)TcO(4)(-) and its purity was determined by instant thin-layer chromatography. Apoptosis was induced in isolated human PMNs by incubation in 2% saline for 17 and 22 h at 37 degrees C. PMNs were then incubated with (99m)Tc-HYNIC-AnxV and associated (99m)Tc was determined. Abscesses were induced in mice by intramuscular injection of bacteria or turpentine. Following intravenous administration of (99m)Tc-HYNIC-AnxV, mice were imaged and tissue distribution studied at 4 and 24 h. Radiochemical purity of (99m)Tc-HYNIC-AnxV was 84.9+/-8.11%. At 17 h, (99m)Tc-HYNIC-AnxV bound to apoptotic PMNs was 71.6+/-0.01% and 48.6+/-0.01% for experimental and control cells, respectively (P=.002). At 22 h, experimental cells retained 74.9+/-0.02% and control cells retained 47.2+/-0.02% (P=.005). (99m)Tc-HYNIC-AnxV associated with bacterial abscesses was 1.25+/-0.09 and 3.75+/-0.83 percent injected dose per gram (%ID/g) at 4 and 24 h compared to turpentine abscesses which was 1.02+/-0.16 and 0.72+/-0.17 %ID/g at 4 (P<or=.05) and 24 h (P<or=.01). (99m)Tc-HYNIC-AnxV represents a minimally invasive and promising agent to image and potentially distinguish between infectious and inflammatory abscesses.

The adaptation of megavoltage cone beam CT for use in standard radiotherapy treatment planning

Potential areas where megavoltage computed tomography (MVCT) could be used are second- and third-phase treatment planning in 3D conformal radiotherapy and IMRT, adaptive radiation therapy, single fraction palliative treatment and for the treatment of patients with metal prostheses. A feasibility study was done on using MV cone beam CT (CBCT) images generated by proprietary 3D reconstruction software based on the FDK algorithm for megavoltage treatment planning. The reconstructed images were converted to a DICOM file set. The pixel values of megavoltage cone beam computed tomography (MV CBCT) were rescaled to those of kV CT for use with a treatment planning system. A calibration phantom was designed and developed for verification of geometric accuracy and CT number calibration. The distance measured between two marker points on the CBCT image and the physical dimension on the phantom were in good agreement. Point dose verification for a 10 cm x 10 cm beam at a gantry angle of 0 degrees and SAD of 100 cm were performed for a 6 MV beam for both kV and MV CBCT images. The point doses were found to vary between +/-6.1% of the dose calculated from the kV CT image. The isodose curves for 6 MV for both kV CT and MV CBCT images were within 2% and 3 mm distance-to-agreement. A plan with three beams was performed on MV CBCT, simulating a treatment plan for cancer of the pituitary. The distribution obtained was compared with those corresponding to that obtained using the kV CT. This study has shown that treatment planning with MV cone beam CT images is feasible.