Improving Alzheimer's Disease Classification in Brain MRI Images Using a Neural Network Model Enhanced with PCA and SWLDA.

The examination of Alzheimer's disease (AD) using adaptive machine learning algorithms has unveiled promising findings. However, achieving substantial credibility in medical contexts necessitates a combination of notable accuracy, minimal processing time, and universality across diverse populations. Therefore, we have formulated a hybrid methodology in this study to classify AD by employing a brain MRI image dataset. We incorporated an averaging filter during preprocessing in the initial stage to reduce extraneous details. Subsequently, a combined strategy was utilized, involving principal component analysis (PCA) in conjunction with stepwise linear discriminant analysis (SWLDA), followed by an artificial neural network (ANN). SWLDA employs a combination of forward and backward recursion methods to choose a restricted set of features. The forward recursion identifies the most interconnected features based on partial Z-test values. Conversely, the backward recursion method eliminates the least correlated features from the same feature space. After the extraction and selection of features, an optimized artificial neural network (ANN) was utilized to differentiate the various classes of AD. To demonstrate the significance of this hybrid approach, we utilized publicly available brain MRI datasets using a 10-fold cross-validation strategy. The proposed method excelled over existing state-of-the-art systems, attaining weighted average recognition rates of 99.35% and 96.66%, respectively, across all the datasets.

On the evaluation of edgeless diode detectors for patient-specific QA in high-dose stereotactic radiosurgery.

PURPOSE: In this work, the potential of an innovative "edgeless" silicon diode was evaluated as a response to the still unmet need of a reliable tool for plan dosimetry verification of very high dose, non-coplanar, patient-specific radiosurgery treatments. In order to prove the effectiveness of the proposed technology, we focused on radiosurgical treatments for functional disease like tremor or pain. METHODS: The edgeless diodes response has been validated with respect to clinical practice standard detectors by reproducing the reference dosimetry data adopted for the Treatment Planning System. In order to evaluate the potential for radiosurgery patient-specific treatment plan verification, the anthropomorphic phantom Alderson RANDO has been adopted along with three edgeless sensors, one placed in the centre of the Planning Target Volume, one superiorly and one inferiorly. RESULTS: The reference dosimetry data obtained from the edgeless detectors are within 2.6% for output factor, off-axis ratio and well within 2% for tissue phantom ratio when compared to PTW 60,018 diode. The edgeless detectors measure a dose discrepancy of approximately 3.6% from the mean value calculated by the TPS. Larger discrepancies are obtained in very steep gradient dose regions when the sensors are placed outside the PTV. CONCLUSIONS: The angular independent edgeless diode is proposed as an innovative dosimeter for patient quality assurance of brain functional disorders and other radiosurgery treatments. The comparison of the diode measurements with TPS calculations confirms that edgeless diodes are suitable candidates for patient-specific dosimetric verification in very high dose ranges delivered by non-isocentric stereotactic radiosurgery modalities.

Evaluation of the PTW microDiamond in edge-on orientation for dosimetry in small fields.

PURPOSE: The PTW microDiamond has an enhanced spatial resolution when operated in an edge-on orientation but is not typically utilized in this orientation due to the specifications of the IAEA TRS-483 code of practice for small field dosimetry. In this work the suitability of an edge-on orientation and advantages over the recommended face-on orientation will be presented. METHODS: The PTW microDiamond in both orientations was compared on a Varian TrueBeam linac for: machine output factor (OF), percentage depth dose (PDD), and beam profile measurements from 10 × 10 cm2 to a 0.5 × 0.5 cm2 field size for 6X and 6FFF beam energies in a water tank. A quantification of the stem effect was performed in edge-on orientation along with tissue to phantom ratio (TPR) measurements. An extensive angular dependence study for the two orientations was also undertaken within two custom PMMA plastic cylindrical phantoms. RESULTS: The OF of the PTW microDiamond in both orientations agrees within 1% down to the 2 × 2 cm2 field size. The edge-on orientation overresponds in the build-up region but provides improved penumbra and has a maximum observed stem effect of 1%. In the edge-on orientation there is an angular independent response with a maximum of 2% variation down to a 2 × 2 cm2 field. The PTW microDiamond in edge-on orientation for TPR measurements agreed to the CC01 ionization chamber within 1% for all field sizes. CONCLUSIONS: The microDiamond was shown to be suitable for small field dosimetry when operated in edge-on orientation. When edge-on, a significantly reduced angular dependence is observed with no significant stem effect, making it a more versatile QA instrument for rotational delivery techniques.

Quality assurance of Cyberknife robotic stereotactic radiosurgery using an angularly independent silicon detector.

PURPOSE: The aim of this work was to evaluate the use of an angularly independent silicon detector (edgeless diodes) developed for dosimetry in megavoltage radiotherapy for Cyberknife in a phantom and for patient quality assurance (QA). METHOD: The characterization of the edgeless diodes has been performed on Cyberknife with fixed and IRIS collimators. The edgeless diode probes were tested in terms of basic QA parameters such as measurements of tissue-phantom ratio (TPR), output factor and off-axis ratio. The measurements were performed in both water and water-equivalent phantoms. In addition, three patient-specific plans have been delivered to a lung phantom with and without motion and dose measurements have been performed to verify the ability of the diodes to work as patient-specific QA devices. The data obtained by the edgeless diodes have been compared to PTW 60016, SN edge, PinPoint ionization chamber, Gafchromic EBT3 film, and treatment planning system (TPS). RESULTS: The TPR measurement performed by the edgeless diodes show agreement within 2.2% with data obtained with PTW 60016 diode for all the field sizes. Output factor agrees within 2.6% with that measured by SN EDGE diodes corrected for their field size dependence. The beam profiles' measurements of edgeless diodes match SN EDGE diodes with a measured full width half maximum (FWHM) within 2.3% and penumbra widths within 0.148 mm. Patient-specific QA measurements demonstrate an agreement within 4.72% in comparison with TPS. CONCLUSION: The edgeless diodes have been proved to be an excellent candidate for machine and patient QA for Cyberknife reproducing commercial dosimetry device measurements without need of angular dependence corrections. However, further investigation is required to evaluate the effect of their dose rate dependence on complex brain cancer dose verification.