Michael Dally

Data Mining with Combined Use of Optimization Techniques and Self-Organizing Maps for Improving Risk Grouping Rules: Application to Prostate Cancer Patients

Data mining techniques provide a popular and powerful tool set to generate various data-driven classification systems. In this paper, we investigate the combined use of self-organizing maps (SOM) and nonsmooth nonconvex optimization techniques in order to produce a working case of a data-driven risk classification system. The optimization approach strengthens the validity of SOM results, and the improved classification system increases both the quality of prediction and the homogeneity within the risk groups. Accurate classification of prostate cancer patients into risk groups is important to assist in the identification of appropriate treatment paths. We start with the existing rules and aim to improve classification accuracy by identifying inconsistencies utilizing self-organizing maps as a data visualization tool. Then, we progress to the study of assigning prostate cancer patients into homogenous groups with the aim to support future clinical treatment decisions. Using the case of prostate cancer patients grouping, we demonstrate strong potential of data-driven risk classification schemes for addressing the risk grouping issues in more general organizational settings.

Recommendations for implementation of high dose rate 192Ir brachytherapy in developing countries by the Advisory Group of International Atomic Energy Agency

PURPOSE To provide recommendations for the implementation of high dose rate (HDR) 192Ir brachytherapy technology in developing countries. METHODS An Advisory Group Meeting of the International Atomic Energy Agency (IAEA) met to address the implementation of HDR 192Ir brachytherapy technology in developing countries. These recommendations reflect only the personal opinions of the authors and do not necessarily represent the opinion of the IAEA. RESULTS An HDR treatment system should be purchased as a complete unit that includes the 192Ir radioactive source, source loading unit, applicators, treatment planning system, and control console. Infrastructure support may require additional or improved buildings and procurement of or access to new imaging facilities. A supportive budget is needed for quarterly source replacement and the annual maintenance necessary to keep the system operational. The radiation oncologist, medical physicist, and technologist should be specially trained before HDR can be introduced. Training for the oncologist and medical physicist is an ongoing process as new techniques or sites of treatment are introduced. Procedures for quality assurance (QA) of patient treatment, and the planning system must be introduced. Emergency procedures with adequate training of all associated personnel must be in place. CONCLUSIONS The decision to select HDR in preference to alternate methods of brachytherapy is influenced by the ability of the machine to treat a wide variety of clinical sites. In departments with personnel and budgetary resources to support this equipment appropriately, economic advantage becomes evident only if large numbers of patients are treated. Intangible benefits of source safety, personnel safety, and easy adaptation to fluctuating demand for treatments also require consideration when evaluating the need to introduce this treatment system.

What defines intermediate-risk prostate cancer? Variability in published prognostic models

PURPOSE To assess the efficacy of a variety of prognostic models in the definition of intermediate-risk prostate cancer and to compare them to our own empiric model. METHODS AND MATERIALS Two hundred fifty-six consecutive men with prostate adenocarcinoma treated with external beam radiotherapy alone were studied. Biochemical failure (defined as 3 consecutive PSA rises or the initiation of androgen deprivation therapy) was examined using univariate, multivariate, and recursive partitioning analyses. The risk classification model used in our department was then compared to a number of published models to assess the relative performance of each in discriminating risk groups. RESULTS At a median follow-up of 62.4 months, the 5-year Biochemical failure-free survival (bFFS) was 46.8% for the overall group. This relates to 5-year bFFS of 77.8%, 51.1%, and 33.8% based on our institutional criteria for low-, intermediate-, and high-risk features, respectively. All the models examined showed an outcome group with a comparatively similar poor outcome when applied to our data. Large variation was seen in the intermediate-risk groups, with 5-year bFFS ranging from 38.1% to 51.1%. Good risk categories had similar large variations. All published models showed inability to delineate three significantly different outcome groups. Recursive partitioning analysis derived categories based on combinations of PSA (with cutpoints at 42.4, 20, and 10.6 ng/mL) and Gleason score (with cutpoints at 2-6 and 7-10) only. CONCLUSIONS Large variations in the relative performance of a number of prognostic models are shown when applied to our local data. The prognostic efficacy of PSA and biopsy Gleason score is reiterated, although other factors will need to be explored to further improve the performance of prognostic models, particularly in defining the intermediate-risk subset of prostate cancer.

The use of chemotherapy in patients with gliomas : Patterns of care in Victoria from 1998-2000

Chemotherapy has an increasing role in the management of gliomas. In particular, chemotherapy provides survival and quality of life benefits in the setting of recurrent high-grade gliomas and in patients with newly diagnosed glioblastoma multiforme. We have previously reported details on patterns of care regarding 828 patients diagnosed with a glioma in the state of Victoria for the period 1998-2000. We observed that 250 patients (30%) received chemotherapy at some stage of their illness, including neo-adjuvant, adjuvant and recurrent clinical settings. There was significant variation in the agents used and their scheduling. Chemotherapy was given at any time in only 15% of patients aged over 60 years. Eight percent of patients were enrolled on a chemotherapy clinical trial. As chemotherapy for gliomas becomes entrenched as the standard of care, this survey will provide an insight into changing patterns of care for the future and points to areas of need in management of these tumours.

Improving risk grouping rules for prostate cancer patients with optimization

Data mining techniques provide a popular and powerful toolset to address both clinical and management issues in the area of health care. This paper describes the study of assigning prostate cancer patients into homogenous groups with the aim to support future clinical treatment decisions. The cluster analysis based model is suggested and an application of non-smooth non-convex optimization techniques to solve this model is discussed. It is demonstrated that using the optimization based approach to data mining of a prostate cancer patients database can lead to generation of a significant amount of new knowledge that can be effectively utilized to enhance clinical decision making.

Hypofractionated stereotactic radiotherapy for benign intracranial tumours of the cavernous sinus.

We present our experience with hypofractionated stereotactic radiotherapy (HSRT) using 15 fractions to treat benign conditions of the cavernous sinus (CS) and emphasise the outcome in terms of cranial nerve (CN) function and toxicity for long term safety and efficacy. We performed a retrospective review of prospectively collected data on 112 patients with benign tumours of the CS treated with HSRT between 1 January 1998 and 31 December 2009. While all tumours involved the CS, a separate analysis was undertaken for meningiomas and pituitary adenomas. The median follow-up was 77 months (range: 2.3-177). Fifty-seven patients (51%) had a diagnosis of meningioma and 55 (49%) had pituitary adenomas. Prior to HSRT, 82 patients (73%) underwent microsurgery. The median tumour volume was 6.6 cm(3) for meningiomas and 3.4 cm(3) for pituitary adenomas (interquartile range: 2.8-7.9), and the mean prescribed dose was 38 Gy (range: 37.5-40.0) to the tumour margin, delivered in 15 fractions. After HSRT, 57% of all preexisting cranial neuropathies either resolved or improved and 38% remained stable, whereas 5% deteriorated. The diagnosis of meningioma was the only variable associated with recovery of cranial neuropathy (p<0.001). Permanent CN complications occurred in three patients (3%). The 5 and 10 year actuarial freedom from progression for patients with meningiomas was 98% and 93%, respectively, and for patients with pituitary adenomas this was 96% and 96%, respectively. We demonstrate low rates of CN morbidity after HSRT and the possibility of resolution or improvement in CN function for common histologies involving the CS.

Role of hypofractionated stereotactic radiotherapy in treatment of skull base meningiomas.

The objective of this paper is to examine the efficacy and safety of hypofractionated stereotactic radiotherapy (SRT) in the treatment of skull base meningiomas. Thirty-eight patients were treated with a median prescribed dose of 37.5 Gy in 15 fractions to the 80% isodose. Median follow-up was 47 months. Ten males and 28 females of median age 55.5 years were followed. SRT was the primary treatment in 15 patients, adjuvant in 10 and given for recurrence in 14 patients. On clinical follow-up 27 patients are unchanged and in six their symptoms have resolved. One patient had symptomatic deterioration and four patients have developed new symptoms. No patients have radiological evidence of progression. Our data suggest that conventional hypofractionated radiotherapy schemes for benign CNS disease may be useful in conjunction with stereotactic techniques. Such schemes are attractive in terms of resource allocation and where tumour size or cranial nerve tolerance is of concern.

Brain stem gliomas: patterns of care in Victoria from 1998-2000.

This study describes the management of and outcomes for adult and paediatric patients with newly diagnosed brain stem gliomas during 1998-2000 in Victoria. Adult patients were identified in a retrospective cohort study conducted by surveying doctors involved in managing incident brainstem glioma cases identified from the population-based Victorian Cancer Registry. Paediatric cases were identified from a retrospective analysis of the Victorian Paediatric Brain tumour database for the same period. Ten adult and 14 paediatric patients were considered eligible for this study. Nine (38%) did not have a histologic diagnosis but were diagnosed on the basis of radiological appearance. Complete macroscopic resection was performed in two patients (8%). A variety of tumour types and grades were observed with surgery and radiotherapy the mainstays of therapy. No adult patients and only eight (57%) paediatric patients received chemotherapy. The median survivals for adult patients, paediatric patients with pontine lesions and paediatric patients with non-pontine lesions were: 57, 10 and 60+ months respectively.

A double exposed portal image comparison between electronic portal imaging hard copies and port films in radiation therapy treatment setup confirmation to determine its clinical application in a radiotherapy center

PURPOSE At the William Buckland Radiotherapy Center (WBRC), field-only electronic portal image (EPI) hard copies are used for radiation treatment field verification for whole brain, breast, chest, spine, and large pelvic fields, as determined by a previous study. A subsequent research project, addressing the quality of double exposed EPI hard copies for sites where field only EPI was not considered adequate to determine field placement, has been undertaken. The double exposed EPI hard copies were compared to conventional double exposed port films for small pelvic, partial brain, and head and neck fields and for a miscellaneous group. METHODS AND MATERIALS All double exposed EPIs were captured during routine clinical procedures using liquid ion chamber cassettes. EPI hard copies were generated using a Visiplex multi-format camera. In sites where port film remained the preferred verification format, the port films were generated as per department protocol. In addition EPIs were collected specifically for this project. Four radiation oncologists performed the evaluation of EPI and port film images independently with a questionnaire completed at each stage of the evaluation process to assess the following: Adequacy of information in the image to assess field placement. Adequacy of information for determining field placement correction. Clinicians preferred choice of imaging for field placement assessment RESULTS The results indicate that double exposed EPI hard copies generally do containsufficient information to permit evaluation of field placement and can replace conventionaldouble exposed port films in a significant number of sites. These include the following:pelvis fields < 12 X 12 cm, partial brain fields, and a miscellaneous group. However forradical head and neck fields, the preferred verification image format remained port film dueto the image hard copy size and improved contrast for this media. Thus in this departmenthard copy EPI is the preferred modality of field verification for all sites except radical headand neck treatments. This should result in an increase in efficiency of workloadmanagement and patient care.

Management of glioblastoma in Victoria, Australia (2006-2008).

We describe the management of patients with newly diagnosed glioblastoma multiforme (GBM) in a population-based cohort and compare this to a previously studied cohort. We performed a retrospective cohort study of patients diagnosed with GBM from 2006-2008 in Victoria, Australia. Patients were identified from the population-based Victorian Cancer Registry and their treating doctors surveyed by questionnaire. Outcomes were then compared to a study of GBM patients who were diagnosed between 1998 and 2000 using an identical methodology. We reviewed 351 eligible patients. There were slightly more males (62%) and a minority had multifocal disease (13%). Total macroscopic resection, partial resection or biopsy only was performed in 32%, 37% and 24% of patients, respectively. The majority of patients were referred to a radiation oncologist and medical oncologist postoperatively. A total of 56% of patients were treated with postoperative radiotherapy with concurrent and sequential temozolomide and had a median survival of 14.4 months. This was significantly better than patients treated with postoperative radiotherapy alone in the current or earlier cohorts (2006-2008: median survival 6.2 months, p<0.0001 versus 1998-2000: 8.9 months, p<0.0001). This study demonstrates that postoperative chemoradiation has become the standard of care in this Victorian population with an associated improvement in median survival.